System for monitoring transport infrastructure and method thereof
专利摘要:
The present invention relates to a system (1) for monitoring a transport infrastructure (I), such as a road, railway tracks and the like, on which moving means (10) can move, comprising: a remote detecting unit (11), associated with said moving means (10), comprising data acquisition means (111), for acquiring operational data, comprising one or more data related to the motion parameters of said moving means (10), and transceiver means (110), connectable to a telematics communication network (12); and a central control unit (13) comprising a processing unit (130) and transceiver means (131), connectable to said telematics communication network (12), wherein said central control unit (13) is configured to transmit, through said transceiver means (131) and through said telematics communication network (12), one or more predetermined reference thresholds of the motion of said moving means (10) to said remote detecting unit (11), and wherein said remote detecting unit (11) is configured to check if said one or more data relating to motion parameters of said moving means (10) are greater than said respective one or more predetermined reference thresholds, so as to determine failures (D) of said transport infrastructure (I). The present invention also relates to a method for monitoring a transport infrastructure (I). 公开号:EP3709670A1 申请号:EP20162155.4 申请日:2020-03-10 公开日:2020-09-16 发明作者:Alba Chiara PARISI 申请人:Aliseatech Srl; IPC主号:H04Q9-00
专利说明:
[0001] The present invention relates to a system for monitoring transport infrastructures and method thereof. Field of the invention [0002] More specifically, the invention relates to a system and method of the type mentioned, studied and realized in particular for carrying out continuous monitoring of transport infrastructures, such as for example roads, railways or the like, but which can be used for any infrastructure, of which is necessary to monitor the condition, allowing to determine the possible failures, and to determine the possible hazard. [0003] In the following, the description will be addressed to the monitoring of transport infrastructures intended for the circulation of vehicles, but it is clear that the same should not be considered limited to this specific use. Prior art [0004] In recent years, there has been a progressive development of devices and systems capable of monitoring the state of transport infrastructures. [0005] In particular, technical solutions are currently spreading that allow to detect deformations or breakages of the road surface, such as road potholes and the like, by sending a stream of data (images, videos, etc.) by each user via mobile devices to a central processing unit. [0006] However, such technical solutions have drawbacks. [0007] A first drawback of such known solutions is the fact that they depend on the number of users who use the system. In fact, the accuracy and precision of these systems directly depends on the number of users who transmit the data collected via mobile devices. [0008] Another drawback of these solutions is due to the need of simultaneously managing data streams from multiple mobile devices of respective users in order to guarantee the correct operation of the monitoring system. [0009] A further drawback of these known solutions consists in the fact that they do not allow continuous monitoring of the state of infrastructures and civil works. [0010] A technical problem with the above-mentioned solutions is that they are increasingly based on so-called "intelligent" computer learning systems, which are capable of detecting any road accidents, e.g. potholes, "recognizing" them from photographic images or captured videos. [0011] Although such systems are becoming more and more reliable, it often happens that, for example, a pothole can be filled with sand, water or present superficially soft objects (an envelope, a paper or the like), which at worst do not allow the known systems to identify the pothole, at best, instead, do not allow an accurate assessment of the depth of the same. [0012] This may imply an underestimation of the dangerousness of the road disasters detected, not allowing a prompt settlement of the most dangerous failures. Just to mention an example, it is known that even a small but deep road pothole can be very dangerous for a motorcyclist. Scope of the invention [0013] In light of the above, it is therefore an object of the present invention overcoming the drawbacks mentioned in the proposed solutions of the prior art, providing a system for monitoring transport infrastructures capable of detecting, for example, any deformation or failures of the road surface, capable of determining with a better degree of certainty, the dangerousness. [0014] Another object of the invention is that of providing a system for monitoring transport infrastructures, which allows acquiring in real time data on possible deformations or failures of the road surface. [0015] A further object of the invention is to provide a system for monitoring transport infrastructures, which allows users to be warned of a possible danger for their safety. [0016] Another object of the invention is to provide a system for monitoring transport infrastructure that is highly reliable, relatively simple to manufacture, and at competitive costs when compared to the prior art. [0017] Still, object of the present invention is to provide the tools necessary for the execution of the method and the apparatuses to perform such method. Object of the invention [0018] It is therefore specific object of the present invention a system for monitoring a transport infrastructure, such as a road, railway tracks and the like, on which moving means can move, comprising: a remote detecting unit, associated with said moving means, comprising data acquisition means, for acquiring operational data, comprising one or more data related to the motion parameters of said moving means, and transceiver means, connectable to a telematics communication network; and a central control unit comprising a processing unit and transceiver means, connectable to said telematics communication network, wherein said central control unit is configured to transmit, through said transceiver means and through said telematics communication network, one or more predetermined reference thresholds of the motion of said moving means to said remote detecting unit, and wherein said remote detecting unit is configured to check if said one or more data relating to motion parameters of said moving means are greater than said respective one or more predetermined reference thresholds, so as to determine failures of said transport infrastructure. [0019] Advantageously according to the invention, said one or more data relating to motion parameters of said moving means may comprise vertical acceleration or deceleration data of said moving means with respect to a vertical axis perpendicular to said transport infrastructure, linear speed data of said moving means with respect to a reference system, and angular velocity data of said moving means, with respect to said reference system, said data acquisition means comprise an accelerometer, configured to detect said vertical acceleration or deceleration data, and said linear speed data, and a gyroscope, configured to detect said angular velocity data, and said one or more reference thresholds comprise a first vertical acceleration or deceleration reference threshold, a second linear speed reference threshold, and a third angular velocity reference threshold. [0020] Preferably according to the invention, said reference system is a Cartesian reference system xyz, wherein the linear speed data of said moving means are detected by said accelerometer with respect to the xy plane of said Cartesian reference system xyz, said xy plane being perpendicular to said axis, and wherein said angular velocity data of said moving means are detected by said gyroscope around the x, y, z axes of said Cartesian reference system xyz. [0021] Still according to the invention, the determination of said failures of said transport infrastructure is detected by said remote detecting unit by comparing a recognition model of said failures defined by said operational data with a objects model recognition of the Open Source type as a TensorFlow model or the like. [0022] Conveniently according to the invention, said system may be disabled when said linear speed of said moving means on said transport infrastructure is less than a further predetermined speed threshold. [0023] Advantageously according to the invention, said operating data may comprise structure data relating to the geometric configuration of said transport infrastructure, wherein said data acquisition means comprise at least one video camera for acquiring said structure data in real time, and/or said structure data relating to the geometric configuration of said transport infrastructure may be processed or post-processed by said processing unit of said central control unit through object recognition algorithms, which use a HOG descriptor, a SIFT descriptor, or the like. [0024] Still according to the invention, said operating data may comprise geolocation data relating to at least one geographical position of said handling means, and wherein said data acquisition means may comprise geolocation means configured to acquire said geolocation data, and/or said operating data may comprise environmental data relating to respective atmospheric conditions with respect to said at least one geographical position of said moving means, and wherein said data acquisition means comprise a plurality of sensors to acquire said environmental data. [0025] Always according to the invention, said remote detecting unit may comprise storage means for storing said operating data. [0026] Advantageously according to the invention, said central control unit may comprise storage means, for storing said data received by said central control unit and to generate at least one model for recognizing said failures of said transport infrastructure. [0027] It is also object of the present invention method for monitoring a transport infrastructure, such as a road, railway tracks and the like, on which a moving means is mobile, by means of the system for monitoring transport infrastructure, wherein a remote detecting unit is associated with said moving means and wherein said method comprises the following steps: acquiring, through said data acquisition means of said remote detecting unit, said operating data comprising said one or more data relating to motion parameters of said moving means; receiving, from said remote detecting unit, through said transceiver means of said central control unit, said operational data; generating, by means of said storage means of said central control unit, said model for the recognition of said failures of said transport infrastructure starting from said operating data; transmitting, by means of said transceiver means of said central control unit, said recognition model and said one or more predetermined reference thresholds of the motion of said moving means to said remote detecting unit; checking, by means of said remote detecting unit, if said one or more data relating to the motion parameters of said moving means are greater than said respective one or more predetermined reference thresholds; transmitting, through said transceiver means of said remote detecting unit, said one or more data relating to motion parameters of said movement means to said central control unit; receiving said data by means of said transceiver means of said central control unit; processing, by means of said processing unit of said central control unit, said data received by said transceiver means, so as to determine failures of said transport infrastructure. [0028] Still according to the invention, said one or more data relating to motion parameters of said moving means comprise vertical acceleration or deceleration data of said moving means with respect to a vertical axis perpendicular to said transport infrastructure, linear speed data of said moving means with respect to a reference system, and angular velocity data of said moving means, with respect to said reference system, said data acquisition means comprise an accelerometer, configured to detect said vertical acceleration or deceleration data, and said linear speed data, and a gyroscope, configured to detect said angular velocity data, and said one or more reference thresholds comprise a first vertical acceleration or deceleration reference threshold, a second linear speed reference threshold, and a third angular velocity reference threshold. [0029] Advantageously according to the invention, said method may comprise, after said verification step, in case of a positive result, the step of comparing said recognition model with a objects recognition model of Open Source type, such as a TensorFlow model or the like, and acquiring, by means of said geolocation means, said geolocation data relating to at least one geographical position of said moving means, and said transmission step further may provide for a transmission to said central control unit of said geolocation data, and of the result of said comparison. [0030] Always according to the invention, said central control unit, in the processing step, generates a further model for recognizing said failures of said transport infrastructure starting from said data received. [0031] Conveniently according to the invention, said method may comprise a further transmission step, wherein said central control unit transmits vehicle data to said storage means, concerning the type of said moving means, and acquisition data, relating to the type of said acquisition means. [0032] Always according to the invention, said method may comprise the step of acquiring, by means of said camera of said data acquisition means of said detection units remote, said structure data relating to the geometric configuration of said transport infrastructure. [0033] Still according to the invention, said method may comprise the step of acquiring, by means of said plurality of sensors of said data acquisition means of said remote detecting unit, said environmental data, relative to respective atmospheric conditions with respect to said at least one geographical position of said moving means. Brief description of the drawings [0034] The present invention will be now described, for illustrative but not limitative purposes, according to its preferred embodiments, with particular reference to the figures of the enclosed drawings, wherein:figure 1 is a block diagram illustrating an embodiment of the system for monitoring transport infrastructures, according to the present invention; figure 2 shows an application to a bus of the system for monitoring transport infrastructures according to figure 1; figure 3 shows a top view of figure 2; figure 4 is a block diagram of an embodiment of data acquisition means of a remote detection unit of the infrastructure monitoring system according to figure 1; and figure 5 is a flowchart showing an embodiment of the method for monitoring infrastructure, according to the present invention. Detailed description [0035] In the various figures, similar parts will be indicated by the same reference numbers. [0036] With reference to the aforementioned figures, it is noted that the system for monitoring a transport infrastructure, indicated as a whole with the reference number 1, comprises a remote detecting unit 11, associated with a respective moving means 10, and a central unit control 13, connected to said remote detecting unit 11 by means of a telematics communication network 12. [0037] Said remote detecting unit 11 is configured to acquire, store and transmit to the central control unit 13 morphological data associated with said transport infrastructure I and data relating to said moving means 10. [0038] As said, the remote detecting unit 11 is installed on said moving means 10, which is mobile on said transport infrastructure I. By way of example, said remote detecting unit 11 can be positioned on a vehicle, a motor vehicle, etc.. [0039] With particular reference to figure 1, in an embodiment of the system 1 according to the present invention, said remote detecting unit 11 comprises: data acquisition means 111, transceiver means 110, and storage means 112, the latter connected both to said data acquisition means 111, and to said transceiver means 110. [0040] In the embodiment at issue, said data acquisition means 111 are configured to acquire operating data. [0041] Said operating data comprise: "structural data" relating to the geometric configuration of said transport infrastructure I; "acceleration data", concerning acceleration or deceleration values of said moving means 10; "linear speed data", concerning linear speed values, or the speed of said moving means 10; "angular velocity data", concerning angular velocity values of said moving means 10; "geolocation data" relating to at least one geographical position of said vehicle 10; and "environmental data" referring to atmospheric conditions with respect to said at least one geographical position of said moving means 10. [0042] The set of said operating data defines a recognition model of at least one failure D of said transport infrastructure I, such as, for example, a deformation of the road surface. [0043] This recognition model, as will be better explained below, together with appropriate predefined reference thresholds, allows identifying, in real time, at least one failure D of the transport infrastructure I, on which the moving means 10 moves. [0044] Furthermore, in the embodiment that is described, said recognition model is an adaptive model, that is, it is capable of updating its data in case of changes in the surrounding environment, for example associated with the transport infrastructure I, compared to previously acquired data. [0045] In particular, said data acquisition means 111 are configured to acquire said data through two operating modes: a continuous mode, in which the data acquisition takes place without interruptions, from a first temporal instant to a second temporal instant (for example, from the switching on time to the switching off time of said acquisition means 111); and an activation or trigger mode, in which the data acquisition is activated by an event (or "trigger" event), which activates the activation of a specific device or sensor. [0046] More in detail, said data acquisition means 111, such as for example a single-board computer of Rasberry Pi type, as can be seen from figure 4, comprise: a video camera 113, an accelerometer 114, geolocation means 115, a plurality of sensors 116, and a gyroscope 117. [0047] Said video camera 113 is configured to acquire, in real time, said structure data, such as, for example, images, video and/or audio sequences, or video and/or audio data of said transport infrastructure I. [0048] In an embodiment of the present invention, the images and the video and/or audio sequences acquired by said video camera 113 during the movement of said moving means 10 are processed or post-processed by, for example, object recognition algorithms using a HOG ("Histogram of Oriented Gradients") descriptor, a "SIFT ("Scale Invariant Feature Transform") descriptor, and so on. [0049] The use of such recognition algorithms typically involves a learning step, in which the collection of data, the selection of one or more features for the recognition, the selection of a classification model, etc. takes place, and a classification step, in which the object is identified on the basis of the data and information previously collected, possibly comparing it with reference objects. [0050] Said accelerometer 114 is capable of acquiring said acceleration or deceleration data of said moving means 10, as well as said linear speed data of said moving means 10. [0051] More in detail, said accelerometer 114 allows measuring the vibrations or the acceleration of said moving means 10 with respect to said transport infrastructure I. In the present embodiment said accelerometer 114 is of the three axial type, that is a device configured to detect the acceleration or deceleration values along the Cartesian axes x, y, and z, as shown in figure 2 and figure 3. [0052] However, the possibility of using further types of accelerometers in the system 1 according to the present invention is not excluded. [0053] Furthermore, as anticipated, said data acquisition means 111 are further configured to detect the speed of the movement, on said transport infrastructure I, of said moving means 10. [0054] In fact, said accelerometer 114 allows to measure the linear speed of said moving means 10, with respect to said transport infrastructure I, with respect to a reference system, such as the xy plane of a Cartesian reference system xyz, as shown in figures 2 and 3. [0055] In particular, as can be seen in figure 2, said xy plane is perpendicular to an axis A, in its turn parallel to the axis z and perpendicular to said transport infrastructure I. [0056] Therefore, the data relating to the motion parameters of said moving means 10 comprise said acceleration or deceleration data, said linear speed data and said angular velocity data of said moving means 10. [0057] The geolocation means 115 of said data acquisition means 111 are configured to acquire at least one geographical position of said moving means 10. In an embodiment of the system 1, such geolocation means 115 comprise a GPS module ("Global Positioning System"). [0058] In an embodiment of the system 1, said plurality of sensors 116 comprises a temperature sensor, for detecting at least one temperature value, a humidity sensor, for acquiring at least one humidity value, and a rain sensor, for detecting the presence of rainfalls. [0059] In particular, the acquisition of these environmental data allows, among other things, the safe execution of maintenance interventions on said transport infrastructure I. [0060] Said gyroscope 117 is capable of measuring the rotational motion of said moving means 10 with respect to a reference system. [0061] In particular, said gyroscope 117 is capable of detecting even minimal variations of the angular velocity of said moving means 10. [0062] In the present embodiment said gyroscope 117 is of the three axial type, i.e. a device configured to detect the angular velocity values with respect to a reference system around the Cartesian axes x, y, and z, as shown in figure 2 and figure 3. [0063] However, the possibility of using further types of gyroscope in system 1 according to the present invention is not excluded. [0064] The transceiver means 110 of the remote detecting unit 11 are configured to transmit data to said central control unit 13. [0065] The storage means 112 of the remote detecting unit 11 comprise, for example, a database and are suitable for storing the data acquired by the data acquisition means 111. In fact, these storage means 112 are preferably connected to said data acquisition means 111. Furthermore, said storage means 112 are connected to said transceiver means 110. [0066] In addition, said acquisition means 111 are further configured to receive from said central control unit 13 a plurality of predefined reference thresholds indicated with the numerical references A1, A2, and A3, vehicle data, concerning the type of said moving means 10, acquisition data, relating to the type of acquisition means 111, as well as the recognition model of at least one failure D of said transport infrastructure I. [0067] In the embodiment described, said predefined reference thresholds A1, A2, and A3 are three. However, in further embodiments, said predefined reference thresholds can be different from three. [0068] In more detail, the first reference threshold A1 is a vertical acceleration threshold, useful for determining the depth of the failure D, such as, for example, the depth of a pothole in the road surface. [0069] The second reference threshold A2 is a linear speed threshold associated with the motion of the moving means 10 in the xy plane. Therefore, this threshold A2 allows to determine the exceeding of a predefined speed for said moving means 10, such as, for example, 50km/h. [0070] The third reference threshold A3, on the other hand, is an angular velocity threshold around the Cartesian axes x, y, and z, useful for determining any rotations of said moving means 10 around at least one of said x, y, z axes. [0071] Therefore, said remote detecting unit 11 is capable of verifying, substantially in real time, whether the acceleration, the linear speed and the angular velocity data acquired by said data acquisition means 111 exceeding or not the respective predefined reference thresholds. [0072] As said, the central control unit 13, such as for example a processor or a computer, a plurality of computers connected to each other in a network, or any other processing device, is in communication with the remote detecting unit 11 via said telematics network communication 12, such as the Internet. [0073] In particular, the central control unit 13 is configured to receive the vertical acceleration or deceleration data transmitted by said remote detecting unit 11 and to process said vertical acceleration or deceleration data to determine the presence of any failures D of said transport infrastructure I. [0074] Said central control unit 13 is further configured to combine the structure data, the linear speed data, the angular velocity data, the geolocation data and the environmental data with said vertical acceleration or deceleration data, in order to confirm the presence of one or more possible failures D of said transport infrastructure I and to carry out subsequent maintenance operations. [0075] Furthermore, said central control unit 13 is configured to update said geolocation data of said moving means 10, or to update the position of said moving means 10 with respect to a location map. [0076] Advantageously, said central control unit 13 is then capable of communicating the presence of one or more possible failures D of said transport infrastructure I to external bodies such as, for example, bodies responsible for the road safety. With particular reference to figure 1, in an embodiment of the system 1, said central control unit 13 comprises: a processing unit 130, transceiver means 131, connected to said processing unit 130, and storage means 132, connected to said processing unit 130. [0077] The processing unit 130 is the functional and main element of the central control unit 13 of the system 1 according to the present invention, and, for this reason, it is connected to, and in communication with the other elements of the central control unit 13 itself. [0078] Conveniently, said processing unit 130 is equipped with calculating and processing means, configured to execute a computer program for the recognition of objects and for processing the data acquired by said remote detecting unit 11, as well as for performing the interface with the other elements of the central control unit 13. Furthermore, said processing unit 130 is also configured to control and coordinate the operation of the elements of the central control unit 13, which it is connected and in communication with. [0079] Said processing unit 130 can be constituted, for example, by a computer or a plurality of computers, possibly cloud connected. [0080] The transceiver means 131 of the central control unit 13 are configured to receive data from said remote detecting unit 11, while the storage means 132, such as for example a database, allow to store the data received by said central unit control 13. [0081] In the embodiment of the present invention, said storage means 132 are included in said central control unit 13. [0082] However, in other embodiments, said storage means 132 can be external to said central control unit 13 and operationally connected to the same. [0083] In particular, said storage means 132 are capable of receiving from said central control unit 13 said vehicle data, said acquisition data, as well as said operational data, acquired by said remote detecting unit 11 in a training step, i.e. a training step of the same remote detecting unit 11. [0084] In an embodiment of the present invention, said storage means 132 comprise further data relating to respective objects such as, for example, road signs, plants, etc., which the system may possibly detect on said transport infrastructure I. [0085] In addition, said storage means 132 are capable of storing at least one further recognition model of at least one failure D of said transport infrastructure I generated by said central control unit 13, said location maps, associated with the movements of said moving means 10, and a set of points and/or images on said location maps and associated with said moving means 10 (called, in jargon, "Knowledge Base"). [0086] Said storage means 132 are capable of transmitting to said central control unit 13 said at least one recognition model of at least one failure D of said transport infrastructure I. [0087] Furthermore, said processing unit 130 is capable of updating, in real time, the data in said storage means 132 and associated with the respective moving means 10. [0088] This allows, also through an operator's intervention, to constantly check and update the presence of any failures D of said transport infrastructure I, which said moving means 10 moves on, thus improving the road safety conditions for users. [0089] The operation of the method 2 for monitoring the transport infrastructure I described above is as follows. [0090] As mentioned above, as can be seen from figures 2 and 3, the moving means 10 is mobile on the transport infrastructure I, such as for example a road. [0091] Initially, with reference to figure 5, in step 200, said remote detecting unit 11 acquires said operating data in continuous mode or trigger mode. [0092] In more detail, said remote detecting unit 11 acquires, by means of said data acquisition means 111, the acceleration or deceleration data, in particular in the vertical direction of said moving means 10, by means of said accelerometer 114, the linear speed data of said moving means 10, by means of said accelerometer 114, and the angular velocity data of said moving means 10, by means of said gyroscope 117. [0093] In particular, the remote detecting unit 11 acquires in continuous mode or in trigger mode, by means of said data acquisition means 111, the acceleration or deceleration data. More in detail, in the vertical direction of said moving means 10, by means of said accelerometer 114. [0094] The accelerometer 114 is configured, among other things, to detect a vertical acceleration or deceleration with respect to the axis A, parallel to the axis z and perpendicular to said transport infrastructure I. [0095] In other words, the accelerometer 114 allows sampling the acceleration data of the accelerometer 114, to obtain an acceleration function over the time along the vertical axis of the means 10, or of the detecting unit 11. [0096] As can be seen from figures 2 and 3, a sudden change in the acceleration or deceleration of the moving means 10 along the z direction (or the direction of the A axis) implies the presence of a deformation of the road surface, such as for example a road pothole or a bump. [0097] In fact, the moving means 10, movable along said transport infrastructure I, changes its vertical acceleration or deceleration typically in the presence of the failure D of said transport infrastructure I. [0098] The acceleration or deceleration variations of the moving means 10 along the x and y directions can contribute providing data and information useful for determining any failures D and for establishing, consequently, the degree of danger of such failures D. [0099] Furthermore, the remote detecting unit 11 acquires, through said data acquisition means 111, said structure data, or video and/or audio data, referred to the geometric or morphological configuration of said transport infrastructure I. By way of example, this acquisition can be carried out by means of one or more video cameras 113, possibly connected to each other. [0100] In addition, the remote detecting unit 11 acquires said geolocation data and said environmental data by means of said geolocation means 115 and said plurality of sensors 116 respectively. [0101] Subsequently, in step 200', said central control unit 13 receives, from said remote detecting unit 11, said operating data through said transceiver means 131. [0102] Therefore, the training step of said remote detecting unit 11 comprises the steps 200 and 200' described above. [0103] Furthermore, again with reference to figure 5, in step 20, said central control unit 13 is in communication with said storage means 132. [0104] In more detail, in step 201, said central control unit 13 transmits said vehicle data to said storage means 132, concerning the type of said moving means 10, and said acquisition data, relating to the type of acquisition means 111, such as, for example, a model of video camera, smartphone, etc.. [0105] Subsequently, in step 202, said central control unit 13 transmits said operating acquired by said remote detecting unit 11 to said storage means 132 in a training step preceding the steps of the method according to the present invention. [0106] In step 203, said storage means 132 store at least one recognition model of at least one failure D of said transport infrastructure I generated by said central control unit 13, said location maps, associated with the movements of said moving means 10, and a set of points and/or images, present on said location maps and associated with said moving means 10 (called, in jargon, "Knowledge Base"). [0107] In step 204, said storage means 132 update said set of points and/or images on the basis of said operating data received from said central control unit 13. [0108] Subsequently, in step 21, said central control unit 13 is in communication with said remote detecting unit 11. [0109] In particular, in step 210, said central control unit 13 is in communication with said remote detecting unit 11. [0110] More in detail, said remote detecting unit 11 receives from said central control unit 13 said vehicle data, referred to said moving means 10, said acquisition data, relating to the type of acquisition means 111, said recognition model of at least one failure D of said transport infrastructure I, and said predetermined reference thresholds A1, A2, and A3. [0111] As said, the first reference threshold A1 is a vertical acceleration threshold, the second reference threshold A2 is a linear speed threshold, associated with the motion of the moving means 10 in the xy plane, and the third reference threshold A3 of is an angular velocity threshold. [0112] In step 211, said remote detecting unit 11 checks whether a predetermined period of time has elapsed (defined by the parameter "var_timer") for updating the data previously received by said central control unit 13. [0113] If said predetermined time period has elapsed, the remote detecting unit 11 repeats step 210. [0114] If, on the other hand, said predetermined period of time has not elapsed, the remote detecting unit 11 executes step 212, i.e. verifies whether said acceleration or deceleration data, said angular velocity data, and said linear speed data of said moving means 10 exceed or not said respective predefined reference thresholds A1, A2, and A3. [0115] More in detail, said remote detecting unit 11 checks, substantially in real time, whether the vertical acceleration or deceleration variation of the respective moving means 10, movable along said transport infrastructure I, exceeds said respective first reference threshold A1, corresponding to a reference vertical acceleration value. [0116] Furthermore, said remote detecting unit 11 checks, in real time, whether the change of the linear speed of the respective moving means 10 exceeds said respective second reference threshold A2, corresponding to a reference linear speed value. [0117] Finally, said remote detecting unit 11 checks, in real time, whether the angular velocity value of the respective moving means 10 exceeds said respective third reference threshold A3, corresponding to a reference angular velocity value. [0118] If the variations of the vertical acceleration or deceleration, the variations of the angular velocity and the linear speed value of said moving means 10 do not exceed said respective reference thresholds A1, A2 and A3, said remote detecting unit 11 repeats step 211. [0119] If, on the other hand, the variations of vertical acceleration or deceleration, the variations of angular velocity, and the linear speed value of said moving means 10 exceed said respective reference thresholds A1, A2, and A3, said remote detecting unit 11 executes the step 213, or activates said video camera 113, said geolocation means 115, and said plurality of sensors 116, to confirm the presence or absence of said failure D of said transport infrastructure I. [0120] Furthermore, said remote detecting unit 11 applies recognition techniques of a further recognition model of the prior art, such as, for example, an objects recognition model of Open Source type (TensorFlow or similar) to said recognition model. [0121] Therefore, said video and/or audio data and said environmental data allow to confirm or not, though, for example, the comparison between the object recognition algorithm used and a further open source recognition algorithm of the prior art, the presence of said failure D of said transport infrastructure I. [0122] In step 214, said remote detecting unit 11 confirms the presence of said failure D of said transport infrastructure I, determining the outcome of the comparison between said recognition model and said further recognition model of the prior art. By way of example, this outcome or feedback can also be defined in percentage terms. [0123] If this failure D is not confirmed, or if such outcome is negative, said remote detecting unit 11 repeats step 211, while, if said failure D is confirmed, or such outcome is positive, said remote detecting unit 11 continues with step 215. [0124] In step 215, said remote detecting unit 11 transmits to said central control unit 13 said acceleration or deceleration data, said angular velocity data, said geolocation data, said linear speed data, said outcome or comparison of said comparison recognition model, and said further recognition model of the prior art, together with the other structural, and environmental data. [0125] By way of example, the transmission of data between said remote detecting unit 11 and said central control unit 13 can take place in real time or periodically at predetermined time intervals. [0126] Finally, in step 22, said central control unit 13 processes the data received by said remote detecting unit 11. [0127] In step 220, the central control unit 13 receives, through said transceiver means 131, said acceleration or vertical deceleration data of said moving means 10, together with the other structure, angular velocity, linear velocity, geolocation and environmental data. [0128] Subsequently, in step 221, said central control unit 13 generates, by means of said processing unit 130, a further recognition model, updates the content of said storage means 132, and updates the position of said moving means 10 with respect to said location map. [0129] In fact, said central control unit 13 processes said vertical acceleration or deceleration data together with the other structure data, angular velocity, linear velocity detected by said data acquisition means 111 and received by said transceiver means 131, to determine any failures D of said transport infrastructure I. [0130] More in detail said central control unit 13 re-processes a further recognition model on the basis of said operating data transmitted by said remote detecting unit 11. [0131] In one embodiment, this regeneration is stimulated by the application of two cascade models, i.e. of a step model and of the prior art for the image recognition. [0132] In one embodiment, the presence of two predetermined thresholds T1 and T2 are assumed to correspond respectively to two reference vertical acceleration values. [0133] In particular, the first threshold T1 corresponds to a failure D of the transport infrastructure I (or first failure D') which is not particularly serious for the safety of the users, such as for example a small road pit compared to a motorcycle tire, and shallow. [0134] The second threshold T2, on the other hand, corresponds to a further failure D of the transport infrastructure I (or second failure D") more serious than the first failure D', such as, for example, a deep and disconnected road pit, therefore dangerous for the users' safety. [0135] If the vertical acceleration or deceleration value of said moving means 10 is lower than said first threshold T1, the system 1 considers the acceleration variation of said moving means 10 in the vertical direction with respect to the axis A as a minimum or standard variation due to normal stresses and/or typical oscillations of the moving means 10 with respect to the transport infrastructure I. [0136] If, on the other hand, the vertical acceleration or deceleration value of said moving means 10 lies between said first threshold T1 and said second threshold T2, the system 1 associates said first failure D' with said vertical acceleration or deceleration value, and therefore a first level of danger of this deformation of the transport infrastructure I. [0137] Finally, if the vertical acceleration or deceleration value of said moving means 10 is higher than said second threshold T2, the system 1 associates said second failure D' with said vertical acceleration or deceleration value, and therefore a second level of danger of this deformation of the transport infrastructure I. [0138] Preferably, said thresholds T1 and T2 are function of the speed of the moving means 10. [0139] For example, below a minimum speed, no detection occurs. In this case, if the moving means 10 is moving below said minimum speed threshold, the monitoring system 1 is not active. [0140] The above allows the system 1 to detect the presence of a failure D, determine the danger of this failure D, and monitor its status over time, or during subsequent acquisitions of said operational data by said remote detecting unit 11. [0141] Furthermore, after determining the presence of a failure D of said transport infrastructure I referred to a respective level of danger, the processing unit 130 of said central control unit 13 is capable of combining the structure and geolocation data received by said remote detecting unit 11 with the vertical acceleration or deceleration value detected by said accelerometer 114, respectively in order to confirm and geolocate said failure D. [0142] In fact, the images or video sequences acquired by said video camera 113 and the geographical position of the moving means 10 detected in the same time instant as the acquisition of the vertical acceleration or deceleration data, can be used, for example, to confirm the presence of any failure D on said transport infrastructure I. [0143] Subsequently, in step 222, said central control unit 13 performs a comparison between said recognition model and said further updated recognition model, in order to verify whether or not to confirm the presence of said failure D previously encountered by said remote detecting unit 11. [0144] Finally, in step 223, said central control unit 13 carries out a periodic check, by means of an operator, of said further recognition model, of the operating data transmission mode, and of the updating of said data. In particular, the intervention of the operator allows to improve the accuracy of the system 1, reducing the presence of errors caused, for example, by an incorrect selection of the reference thresholds. [0145] Furthermore, said central control unit 13 transmits the presence of one or more possible failures D of said transport infrastructure I detected by the system 1, for example, to bodies responsible for road safety. Advantages [0146] An advantage of the system for monitoring transport infrastructures according to the present invention is that it allows to obtain a high degree of scalability. In fact, the elements that make up this system can be modified and updated according to user needs and to different operating conditions. [0147] Another advantage of the present invention is that of acquiring data in real time on possible deformations or failures of the road surface. [0148] A further advantage of the present invention is that of determining the degree of danger of a failure of said transport infrastructure I. [0149] Another advantage of the present invention is that of allowing fast and effective maintenance interventions. [0150] It is also an advantage of the present invention allowing a continuous learning of the system following the reception of the data coming from the sensors previously arranged on transporting means or the like. [0151] The solution according to the present invention also has the advantage of predicting potentially harmful events for users and therefore requiring, for example, precautionary maintenance of the infrastructures concerned. [0152] The present invention has been described for illustrative but not limitative purposes, according to its preferred embodiments, but it is to be understood that modifications and/or changes can be introduced by those skilled in the art without departing from the relevant scope as defined in the enclosed claims.
权利要求:
Claims (16) [0001] System (1) for monitoring a transport infrastructure (I), such as a road, railway tracks and the like, on which moving means (10) can move, comprising: a remote detecting unit (11), associated with said moving means (10), comprising data acquisition means (111), for acquiring operational data, comprising one or more data related to the motion parameters of said moving means (10), and transceiver means (110), connectable to a telematics communication network (12); and a central control unit (13) comprising a processing unit (130) and transceiver means (131), connectable to said telematics communication network (12), wherein said central control unit (13) is configured to transmit, through said transceiver means (131) and through said telematics communication network (12), one or more predetermined reference thresholds of the motion of said moving means (10) to said remote detecting unit (11), and wherein said remote detecting unit (11) is configured to check if said one or more data relating to motion parameters of said moving means (10) are greater than said respective one or more predetermined reference thresholds, so as to determine failures (D) of said transport infrastructure (I). [0002] System (1) according to the preceding claim, characterized in that said one or more data relating to motion parameters of said moving means (10) comprise vertical acceleration or deceleration data of said moving means (10) with respect to a vertical axis (A) perpendicular to said transport infrastructure (I), linear speed data of said moving means (10) with respect to a reference system, and angular velocity data of said moving means (10), with respect to said reference system,in that said data acquisition means (111) comprise an accelerometer (114), configured to detect said vertical acceleration or deceleration data, and said linear speed data, and a gyroscope (117), configured to detect said angular velocity data, andin that said one or more reference thresholds comprise a first vertical acceleration or deceleration reference threshold (A1), a second linear speed reference threshold (A2), and a third angular velocity reference threshold (A3). [0003] System (1) according to the preceding claim, characterized in that said reference system is a Cartesian reference system xyz,wherein the linear speed data of said moving means (10) are detected by said accelerometer (114) with respect to the xy plane of said Cartesian reference system xyz, said xy plane being perpendicular to said axis (A), andwherein said angular velocity data of said moving means (10) are detected by said gyroscope (117) around the x, y, z axes of said Cartesian reference system xyz. [0004] System (1) according to any one of the preceding claims, characterized in that the determination of said failures (D) of said transport infrastructure (I) is detected by said remote detecting unit (11) by comparing a recognition model of said failures (D) defined by said operational data with a objects model recognition of the Open Source type as a TensorFlow model or the like. [0005] System (1) according to any one of the preceding claims, characterized in that said system (1) is disabled when said linear speed of said moving means (10) on said transport infrastructure (I) is less than a further predetermined speed threshold. [0006] System (1) according to any one of the preceding claims, characterized in that said operating data comprise structure data relating to the geometric configuration of said transport infrastructure (I), wherein said data acquisition means (111) comprise at least one video camera (113) for acquiring said structure data in real time, and/orin that said structure data relating to the geometric configuration of said transport infrastructure (I) are processed or post-processed by said processing unit (130) of said central control unit (13) through object recognition algorithms, which use a HOG descriptor, a SIFT descriptor, or the like. [0007] System (1) according to any one of the preceding claims, characterized in that said operating data comprise geolocation data relating to at least one geographical position of said handling means (10), and wherein said data acquisition means (111) comprise geolocation means (115) configured to acquire said geolocation data, and/orin that said operating data comprise environmental data relating to respective atmospheric conditions with respect to said at least one geographical position of said moving means (10), and wherein said data acquisition means (111) comprise a plurality of sensors (116) to acquire said environmental data. [0008] System (1) for monitoring a transport infrastructure (I) according to any one of the preceding claims, characterized in that said remote detecting unit (11) comprises storage means (114) for storing said operating data. [0009] System (1) for monitoring a transport infrastructure (I) according to any one of the preceding claims, characterized in that said central control unit (13) comprises storage means (132), for storing said data received by said central control unit (13) and to generate at least one model for recognizing said failures (D) of said transport infrastructure (I). [0010] Method for monitoring a transport infrastructure (I), such as a road, railway tracks and the like, on which a moving means (10) is mobile, by means of the system (1) according to any one of claims 1- 9, wherein a remote detecting unit (11) is associated with said moving means (10) and wherein said method comprises the following steps: - acquiring (200), through said data acquisition means (111) of said remote detecting unit (11), said operating data comprising said one or more data relating to motion parameters of said moving means (10); - receiving (200'), from said remote detecting unit (11), through said transceiver means (130) of said central control unit (131), said operational data; - generating (203), by means of said storage means (132) of said central control unit (13), said model for the recognition of said failures (D) of said transport infrastructure (I) starting from said operating data; - transmitting (210), by means of said transceiver means (131) of said central control unit (13), said recognition model and said one or more predetermined reference thresholds of the motion of said moving means (10) to said remote detecting unit (11); - checking (212), by means of said remote detecting unit (11), if said one or more data relating to the motion parameters of said moving means (10) are greater than said respective one or more predetermined reference thresholds; - transmitting (215), through said transceiver means (110) of said remote detecting unit (11), said one or more data relating to motion parameters of said movement means (10) to said central control unit (13); - receiving (220) said data by means of said transceiver means (131) of said central control unit (13); - processing (221), by means of said processing unit (130) of said central control unit (13), said data received by said transceiver means (131), so as to determine failures (D) of said transport infrastructure (I). [0011] Method according to claim 10, characterized in that said one or more data relating to motion parameters of said moving means (10) comprise vertical acceleration or deceleration data of said moving means (10) with respect to a vertical axis (A) perpendicular to said transport infrastructure (I), linear speed data of said moving means (10) with respect to a reference system, and angular velocity data of said moving means (10), with respect to said reference system,in that said data acquisition means (111) comprise an accelerometer (114), configured to detect said vertical acceleration or deceleration data, and said linear speed data, and a gyroscope (117), configured to detect said angular velocity data, andin that said one or more reference thresholds comprise a first vertical acceleration or deceleration reference threshold (A1), a second linear speed reference threshold (A2), and a third angular velocity reference threshold (A3). [0012] Method according to any one of claims 10-11, characterized in that, after said verification step (212), in case of a positive result, it includes the step of comparing (213) said recognition model with a objects recognition model of Open Source type, such as a TensorFlow model or the like, and acquiring, by means of said geolocation means (115), said geolocation data relating to at least one geographical position of said moving means (10), andin that said transmission step (215) further provides for a transmission to said central control unit (13) of said geolocation data, and of the result of said comparison. [0013] Method according to any one of claims 10-12, characterized in that said central control unit (13), in the processing step (221), generates a further model for recognizing said failures (D) of said transport infrastructure (I) starting from said received data. [0014] Method according to any one of claims 10-13, characterized in that it comprises a further transmission step (201), wherein said central control unit (13) transmits vehicle data to said storage means (132), concerning the type of said moving means (10), and acquisition data, relating to the type of said acquisition means (111). [0015] Method according to any one of claims 10 -14, when dependent con claim 6, characterized in that it comprises the step of acquiring, by means of said camera (113) of said data acquisition means (111) of said detection units remote (11), said structure data relating to the geometric configuration of said transport infrastructure (I). [0016] Method according to any one of claims 10-15, when dependent on claim 7, characterized in that it comprises the step of acquiring, by means of said plurality of sensors (116) of said data acquisition means (111) of said remote detecting unit (11), said environmental data, relative to respective atmospheric conditions with respect to said at least one geographical position of said moving means (10).
类似技术:
公开号 | 公开日 | 专利标题 Engelbrecht et al.2015|Survey of smartphone-based sensing in vehicles for intelligent transportation system applications JP2019510240A|2019-04-11|System and method for providing vehicle recognition US10768008B2|2020-09-08|Distributed data processing systems for processing remotely captured sensor data US10520904B2|2019-12-31|Event classification and object tracking CN105676251B|2021-04-27|Vehicle occupant identification CN107077794B|2020-04-21|Vehicle-mounted control device, vehicle position and posture determining device, and vehicle-mounted display device US9047721B1|2015-06-02|Driver log generation US10445954B2|2019-10-15|Drive event capturing based on geolocation US10146502B2|2018-12-04|Stream-processing data US20170345232A1|2017-11-30|Emergency event based vehicle data logging AU2013245725B2|2016-10-06|Mobile asset data recorder and transmitter US9663047B2|2017-05-30|Method and system for inferring the behavior or state of the driver of a vehicle, use of the method and computer program for carrying out the method KR100226365B1|1999-10-15|Vehicle driving recorder, vehicle travel analyzer and storage medium US20150153376A1|2015-06-04|Method and apparatus for the alignment of multi-aperture systems US9043041B2|2015-05-26|Monitoring aggressive driving operation of a mobile asset KR101714145B1|2017-03-08|Apparatus for identifying peripheral vehicle and method thereof US20170217434A1|2017-08-03|Tracking Objects Within A Dynamic Environment For Improved Localization US8589015B2|2013-11-19|Vehicle sensor calibration for determining vehicle dynamics US10713955B2|2020-07-14|Method and system for providing artificial intelligence analytic | services for performance prediction CN106485949A|2017-03-08|The sensor fusion of the video camera for vehicle and V2V data US9767622B2|2017-09-19|System and a method for improved car prognosis US9988054B2|2018-06-05|Method and device for ascertaining a minimum value for the friction coefficient of a road segment Yi et al.2015|Toward crowdsourcing-based road pavement monitoring by mobile sensing technologies CN102741900B|2014-12-10|Road condition management system and road condition management method KR20160119119A|2016-10-12|Systems and methods for supervising industrial vehicles via encoded vehicular objects shown on a mobile client device
同族专利:
公开号 | 公开日 IT201900003443A1|2020-09-11|
引用文献:
公开号 | 申请日 | 公开日 | 申请人 | 专利标题
法律状态:
2020-08-14| PUAI| Public reference made under article 153(3) epc to a published international application that has entered the european phase|Free format text: ORIGINAL CODE: 0009012 | 2020-08-14| STAA| Information on the status of an ep patent application or granted ep patent|Free format text: STATUS: THE APPLICATION HAS BEEN PUBLISHED | 2020-09-16| AX| Request for extension of the european patent|Extension state: BA ME | 2020-09-16| AK| Designated contracting states|Kind code of ref document: A1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR | 2021-03-12| STAA| Information on the status of an ep patent application or granted ep patent|Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE | 2021-04-14| 17P| Request for examination filed|Effective date: 20210310 | 2021-04-14| RBV| Designated contracting states (corrected)|Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR | 2021-12-03| STAA| Information on the status of an ep patent application or granted ep patent|Free format text: STATUS: EXAMINATION IS IN PROGRESS | 2022-01-05| 17Q| First examination report despatched|Effective date: 20211207 |
优先权:
[返回顶部]
申请号 | 申请日 | 专利标题 相关专利
Sulfonates, polymers, resist compositions and patterning process
Washing machine
Washing machine
Device for fixture finishing and tension adjusting of membrane
Structure for Equipping Band in a Plane Cathode Ray Tube
Process for preparation of 7 alpha-carboxyl 9, 11-epoxy steroids and intermediates useful therein an
|