Non-motor vehicle red light running identification method and system

Abstract

The invention discloses a non-motor vehicle red light running identification method and system, the system comprises a positioning label arranged on a non-motor vehicle, a server, and a UWB base station and a video acquisition device arranged in a preset road range, the video acquisition device comprises a monitoring camera and a processor, the positioning label comprises a first positioning channel; the UWB base station sends UWB positioning information obtained by communicating with the first positioning channel of the positioning tag to the server; the monitoring camera is used for collecting a non-motor vehicle driving video of a line crossing area in the preset road section range, and the processor is used for intercepting a video slice of a red light time period from the non-motor vehicle driving video and transmitting the video slice to the server; according to the method and the device, whether the non-motor vehicle runs the red light or not can be accurately identified, and the method and the device are convenient and rapid.

Description

Technical Field

[0001] The present application belongs to the field of target recognition, and in particular, to a method and system for recognizing non-motor vehicles running red lights. Background Art

[0002] Traditional non-motor vehicle red light running monitoring mainly relies on manual law enforcement, with traffic police observing at the intersection, intercepting and punishing vehicles that run red lights, or red light running monitoring technology based on induction coils. Some technologies used for motor vehicle red light running monitoring have been tried to be applied to the non-motor vehicle field, but the results are not satisfactory. Taking induction coil technology as an example, its principle is to detect through the change in inductance caused by the passing of vehicles. However, most non-motor vehicles are made of plastic, rubber and other materials, and metal parts account for a small proportion, which makes it difficult for induction coils to sensitively and accurately sense the traffic conditions of non-motor vehicles. When identifying non-motor vehicles running red lights, there are often misjudgments or even failures to detect.

[0003] Video detection technology also faces challenges in identifying non-motor vehicles running red lights. Although cameras can capture images of non-motor vehicles, there are many types of non-motor vehicles, including bicycles, electric vehicles, tricycles, etc., with large differences in appearance and random riding postures. In addition, the complex intersection environment, such as light changes (direct strong light, backlight, shadows, etc.) and background interference (billboards, trees, etc.), makes it difficult for recognition algorithms based on video images to accurately distinguish non-motor vehicles from complex scenes and accurately determine whether they have run a red light. Moreover, under severe weather conditions, such as heavy rain, heavy fog, sand and dust, the quality of video images is severely impaired, and the recognition of non-motor vehicles running red lights is almost paralyzed.

[0004] Therefore, the current non-motor vehicle red light running recognition technology still has defects. Summary of the invention

[0005] The purpose of the present application is to provide a method for identifying a non-motor vehicle running a red light, so as to solve at least one of the above problems.

[0006] On one hand, the present application discloses a non-motor vehicle red light running identification system, the system comprising a positioning tag arranged on the non-motor vehicle, a server, and a UWB base station and a video acquisition device arranged within a preset road section, the video acquisition device comprising a monitoring camera and a processor, the positioning tag comprising a first positioning channel;

[0007] The UWB base station sends UWB positioning information obtained by communicating with the first positioning channel of the positioning tag to the server;

[0008] The monitoring camera is used to collect the non-motor vehicle driving video in the over-line area within the preset road section range. The processor is used to intercept the video slice during the red light period from the non-motor vehicle driving video and transmit the video slice to the server;

[0009] The server is used to determine the positioning trajectory of the non-motor vehicle based on the UWB positioning information, and judge whether the non-motor vehicle has a red light running behavior based on the positioning trajectory and the video slice.

[0010] Optionally, the positioning tag further includes a second positioning channel;

[0011] The server receives the GNSS positioning information based on the second positioning channel transmitted by an external positioning system;

[0012] The server is further used to determine whether there is an abnormality in the positioning trajectory based on the UWB positioning information and the GNSS positioning information.

[0013] Optionally, the server is further used to determine the positioning trajectory and the driving trajectory of the non-motor vehicle based on the UWB positioning information and the GNSS positioning information respectively, and determine whether there is an abnormality in the positioning trajectory of the non-motor vehicle based on the overlapping part of the areas of the positioning trajectory and the driving trajectory.

[0014] Optionally, the driving road of the non-motor vehicle includes a preset road section range at a traffic signal intersection and a driving area connecting between the preset road section ranges;

[0015] When the first positioning channel is enabled after the non-motor vehicle enters the preset road section range, the second positioning channel is closed. When the first positioning channel is closed after the non-motor vehicle leaves the preset road section range, the second positioning channel is opened.

[0016] Optionally, the server is further used to determine the positioning trajectory and the driving trajectory of the non-motor vehicle based on the UWB positioning information and the GNSS positioning information respectively, and determine whether there is an abnormality in the positioning trajectory of the non-motor vehicle based on the connecting part of the areas of the positioning trajectory and the driving trajectory.

[0017] Optionally, the server is further used to predict the over-line distance of the non-motor vehicle running a red light based on the traffic data of non-motor vehicles running a red light in the preset road section range and a trained range prediction model, and determine the over-line area based on the over-line distance and the red light no-entry line in the preset road section range.

[0018] Optionally, the server is configured to determine an abnormal position in the positioning trajectory of the non-motor vehicle according to the positioning trajectories of other non-motor vehicles and the positioning trajectory of the non-motor vehicle, where the abnormal position is a position where the difference degree between the change rate of the positioning trajectory of the non-motor vehicle and the average change rate of the positioning trajectories of other non-motor vehicles is higher than a set threshold; intercept the time stamp corresponding to the abnormal position, and based on each time stamp, configure an intercept period in combination with the difference degree of the change rate, and the time stamp is within the intercept period; analyze whether the non-motor vehicle trajectory runs a red light according to the video data in each intercept period in the video slice.

[0019] Optionally, for each abnormal position, if the number of other non-motor vehicles in front of the non-motor vehicle is greater than the number of those behind the non-motor vehicle, the server is further configured to shift the intercept period forward by a set duration, and vice versa, shift it backward by a set duration.

[0020] Optionally, the video slice further includes non-motor vehicles without labels; the server is further configured to select multiple frames of images from the video slice, where the multiple frames of images include at least two frame images corresponding to abnormal positions; the actual displacement amount and the image displacement amount of the non-motor vehicle identified from at least two frame images corresponding to abnormal positions; generate a crossing line area according to the actual displacement amount and the image displacement amount, in combination with the distance between the road marking and the non-motor vehicle in one of the frame images; fit and generate the driving trajectories of each non-motor vehicle without a label and the non-motor vehicle according to the multiple frames of images; determine whether each non-motor vehicle without a label runs a red light according to each non-motor vehicle without a label, the crossing line area, and the driving trajectory of the non-motor vehicle.

[0021] This application also discloses a method for identifying non-motor vehicles running red lights, including:

[0022] Receiving UWB positioning information obtained by the first positioning channel communication between the UWB base station and the positioning tag on the non-motor vehicle sent by the UWB base station;

[0023] Receiving a non-motor vehicle driving video of a crossing line area within a preset road section range collected by a monitoring camera, and a video slice of a red light period intercepted from the non-motor vehicle driving video;

[0024] Identifying non-motor vehicles in the video slice, determining the positioning trajectory of the non-motor vehicle based on the UWB positioning information of the non-motor vehicle, and judging whether the non-motor vehicle has the behavior of running a red light based on the positioning trajectory and the video slice.

[0025] The beneficial effects of the embodiments of this application compared with the prior art are:

[0026] The non-motor vehicle red light running recognition system of the present application not only collects the driving videos of non-motor vehicles in the crossing area within the preset road section range through the monitoring cameras of the video acquisition device to assist in determining whether the non-motor vehicle has the behavior of running a red light, but also collects the UWB positioning information of the non-motor vehicle in the preset road section range through the positioning tags set on the non-motor vehicle, and jointly determines whether the non-motor vehicle has the behavior of running a red light by combining the UWB positioning information and video slices, improving the accuracy and efficiency of the determination of the non-motor vehicle red light running behavior, and reducing the influence of non-motor vehicle types and weather conditions on the determination of the non-motor vehicle red light running behavior. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0028] Figure 1 It is an application environment diagram of a non-motor vehicle red light running recognition system provided by the present application;

[0029] Figure 2 It is a schematic flowchart of a non-motor vehicle red light running recognition method provided by the present application;

[0030] Figure 3 It is a schematic structural diagram of a computer device suitable for implementing the method of the embodiments of the present application provided by the embodiments of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0031] In the following description, for the purpose of illustration rather than limitation, specific details such as specific system structures and technologies are put forward in order to thoroughly understand the embodiments of the present application. However, those skilled in the art should clearly understand that the present application can also be implemented in other embodiments without these specific details. In other cases, the detailed descriptions of well-known systems, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present application.

[0032] It should be understood that when used in the specification of the present application and the appended claims, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0033] It should also be understood that the term " / and / " as used in the specification of the present application and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0034] As used in the specification of this application and the appended claims, the term "if" may be construed, depending on the context, as "when", "once", "in response to determining", or "in response to detecting". Similarly, the phrase "if determined" or "if [the described condition or event] is detected" may be construed, depending on the context, as meaning "once determined", "in response to determining", "once [the described condition or event] is detected", or "in response to detecting [the described condition or event]".

[0035] In addition, in the description of the specification of this application and the appended claims, the terms "first", "second", "third", etc. are used only for distinguishing descriptions and cannot be construed as indicating or implying relative importance.

[0036] Reference to "one embodiment" or "some embodiments" or the like described in the specification of this application means that a specific feature, structure, or characteristic described in connection with that embodiment is included in one or more embodiments of this application. Thus, statements such as "in one embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments", etc. that appear in different places in this specification do not necessarily all refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in another way. The terms "comprising", "including", "having" and their variants all mean "including but not limited to", unless otherwise specifically emphasized in another way.

[0037] It should be understood that the magnitudes of the sequence numbers of the steps in this embodiment do not mean the order of execution is prior or posterior. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of this application.

[0038] Figure 1 The implementation scenario schematic diagram of this application is shown, as Figure 1 shown, the arrow direction in the figure is the driving direction of non-motor vehicles. The figure represents an intersection, and the over-line area is set within the road markings. At the intersection in the figure, the preset road section range covers a certain distance (for example, 50 meters) outward extension area of each entrance lane and exit lane of the intersection. A plurality of positioned UWB base stations are reasonably arranged along the periphery of the road section. The UWB base stations can receive in real time the UWB positioning information broadcast by the first positioning channel of the positioning tags configured on non-motor vehicles. Of course, in practical applications, those skilled in the art can determine the range of the preset road section, the range of the over-line area, and the installation positions of the UWB base stations according to actual needs, and this application does not make any limitations in this regard.

[0039] Optionally, the overall range of positioning information that can be received by multiple UWB base stations set needs to cover at least the range of the crossing area so as to obtain the positioning information of all non-motor vehicles within the crossing range. Preferably, the overall range of positioning information that can be received by multiple UWB base stations set covers at least the preset road section range to expand the range of positioning information of non-motor vehicles that can be obtained, and more positioning information of non-motor vehicles is obtained to assist in determining whether a non-motor vehicle runs a red light, so as to improve the accuracy of the determination result.

[0040] It should be noted that in the embodiments of the present application, the monitoring camera is installed at a high place such as a traffic light gantry. At present, some non-motor vehicles use the YOLO5 neural network model to identify non-motor vehicles running red lights through video recognition. However, this kind of red light running recognition needs to calculate and analyze the full amount of video collected by the monitoring camera through the neural network model to determine whether there is a non-motor vehicle running a red light. This kind of determination method requires a large amount of data calculation, has a large amount of calculation and low efficiency. The video recognition is greatly affected by the video quality, and there may be problems of inaccurate recognition. Moreover, this kind of determination needs to obtain all the videos collected by the monitoring camera, and the amount of data transmitted is large. Too many invalid videos occupy network resources.

[0041] It should be understood that the UWB base stations of the present application can obtain the UWB positioning information of non-motor vehicles attached with positioning tags in real time, so as to form a positioning trajectory by continuously obtaining the UWB positioning information of non-motor vehicles. Obtaining a positioning trajectory from positioning information is a conventional technical means in the art, and the present application will not elaborate on this.

[0042] Furthermore, it should be understood that traffic information servers such as red light periods in the embodiments of the present application can be obtained in real time from the corresponding cloud platform. Of course, in practical applications, traffic information can also be obtained by other means, and the present application does not limit this.

[0043] In a first aspect, an embodiment of the present application provides a non-motor vehicle red light running recognition system. The system includes a positioning tag set on the non-motor vehicle, a server, a UWB base station and a video acquisition device set in a preset road section range. The video acquisition device includes a monitoring camera and a processor, and the positioning tag includes a first positioning channel.

[0044] Among them, the UWB base station sends UWB positioning information obtained by communicating with the first positioning channel of the positioning tag to the server.

[0045] The monitoring camera is used to collect the non-motor vehicle driving video in the crossing area within the preset road section range, and the processor is used to intercept the video slice of the red light period from the non-motor vehicle driving video and transmit the video slice to the server.

[0046] The server is used to determine the positioning trajectory of the non-motor vehicle based on the UWB positioning information, and determine whether the non-motor vehicle has a red-light running behavior based on the positioning trajectory and the video slice.

[0047] The non-motor vehicle red-light running recognition system of the present application not only uses the monitoring camera of the video acquisition device to collect the driving video of the non-motor vehicle in the crossing area within the preset road section range to assist in determining whether the non-motor vehicle has a red-light running behavior, but also collects the UWB positioning information of the non-motor vehicle in the preset road section range through the positioning tag set on the non-motor vehicle, and jointly determines whether the non-motor vehicle has a red-light running behavior by combining the UWB positioning information and the video slice, improving the accuracy and efficiency of the determination of the non-motor vehicle red-light running behavior, and reducing the influence of the non-motor vehicle type and weather environment on the determination of the non-motor vehicle red-light running behavior.

[0048] In an alternative embodiment, the positioning tag further includes a second positioning channel. The server receives the GNSS positioning information based on the second positioning channel transmitted by an external positioning system; the server is further used to determine whether there is an abnormality in the positioning trajectory based on the UWB positioning information and the GNSS positioning information.

[0049] Specifically, it can be understood that UWB positioning is mainly based on time measurement and signal strength measurement, including methods such as time of arrival (TOA), time difference of arrival (TDOA), and angle of arrival (AoA). The target position is determined by measuring the time difference or angle of arrival of the signal propagation, for example, measuring the propagation time of the signal from the transmitter to the receiver, and then calculating the distance to achieve positioning. UWB positioning is mainly used in scenarios such as indoor positioning and short-distance wireless communication, and can achieve high-precision positioning from sub-centimeter level to centimeter level. In an indoor environment, even in the presence of interference such as multipath effects, it can maintain a high positioning accuracy and is suitable for scenarios with extremely high precision requirements.

[0050] GNSS positioning mainly relies on satellite signals for positioning. Multiple satellites transmit signals, and after the ground receiving device receives them, it calculates the distance between the receiving point and the satellite, and then combines information such as the orbital position of the satellite to use geometric solution methods to determine the three-dimensional coordinates of the receiving point. In an open outdoor environment, the positioning accuracy of GNSS can generally reach several meters to dozens of meters. However, in areas where signals are easily blocked or reflected, such as in dense urban high-rise areas, indoors, and tunnels, the accuracy will drop significantly.

[0051] Therefore, UWB positioning has high positioning accuracy, but has high requirements for equipment and high costs. GNSS positioning, on the other hand, has general positioning accuracy, but has low equipment requirements and low costs. In this embodiment, in order to achieve the purpose of improving the recognition accuracy of non-motor vehicles running red lights while taking into account efficiency and costs, two positioning methods, namely UWB positioning and GNSS positioning, are integrated. A positioning tag with a first positioning channel and a second positioning channel is set. UWB base stations are set in a preset road section range where traffic lights are installed. The UWB base stations receive UWB positioning information through the first positioning channel and transmit GNSS positioning information to the server through the second positioning channel of the positioning tag, enabling the server to determine whether non-motor vehicles run red lights based on the two positioning information and video slices, improving the determination efficiency and accuracy.

[0052] In a specific example, the server determines the positioning trajectories of all non-motor vehicles within the over-line area during the red-light period based on the UWB positioning information, and determines whether there are non-motor vehicles that may run red lights based on the positioning trajectories and the red-light period. If there are, it is identified through video slices whether the non-motor vehicles that may run red lights actually have the behavior of running red lights.

[0053] During this process, the server only determines the non-motor vehicles that may run red lights to be further determined through video slices based on the received UWB positioning information. If the UWB positioning information is inaccurate, there may be a situation where non-motor vehicles that need to be further determined are missed or non-motor vehicles that do not need to be further determined are not completely excluded. Therefore, in order to improve the accuracy of the determination of non-motor vehicle red-light running behavior, this application receives GNSS positioning information through the second positioning channel of the positioning tag, checks the UWB positioning information through the GNSS positioning information, and determines whether there are abnormalities in the UWB positioning information. If the UWB positioning information passes the verification and there are no obvious abnormal situations, the determination result of the UWB positioning information is normally used.

[0054] In a specific example, the current position of a non-motor vehicle can be calculated through the UWB positioning information obtained by multiple UWB base stations communicating with the non-motor vehicle positioning tag. After continuously collecting the UWB positioning information, all consecutive current positions of the non-motor vehicle are connected to obtain the positioning trajectory of the non-motor vehicle. Then, based on the red-light period of the real-time traffic information and the positioning trajectories of all non-motor vehicles, the positioning trajectories of all non-motor vehicles within the over-line area during all red-light periods can be obtained.

[0055] Among them, when determining the positioning trajectory of a non-motor vehicle, non-motor vehicles whose positioning trajectories completely pass through the over-line area during the red light period can be selected based on requirements as non-motor vehicles, that is, the positioning trajectories extend from one end of the over-line area to the other end along the direction indicated by the red light; non-motor vehicles whose positioning trajectories are partially located in the over-line area during the red light period can also be selected as non-motor vehicles. Those skilled in the art can set according to requirements in actual applications, and this application does not make any limitations in this regard.

[0056] After determining the non-motor vehicles that may have committed the act of running a red light, obtain the GNSS positioning information of the non-motor vehicle obtained by the external positioning system through the second positioning channel, and match the GNSS positioning information of the non-motor vehicle with the UWB positioning information to determine whether the positioning trajectory of the UWB positioning information in the over-line area during the red light period coincides with the GNSS positioning information in this part. If they coincide, it means that the UWB positioning information is consistent with the positioning information of the external positioning system, and the credibility of the UWB positioning information is relatively high, which can be used to determine whether the non-motor vehicle has committed the act of running a red light. If there is an abnormality, the GNSS positioning information is used to determine whether the non-motor vehicle has committed the act of running a red light, and the service personnel are notified to quickly check for faults in the positioning tags of the relevant non-motor vehicles.

[0057] Among them, it should be noted that the determination criterion for determining whether the UWB positioning information coincides with the GNSS positioning information can be determined according to the actual situation, and this application does not make any limitations in this regard. For example, multiple corresponding positions are taken from the UWB positioning information and the GNSS positioning information respectively, and the deviation degrees of time and position are calculated. If the deviation degrees are within the preset threshold range, it is determined that the UWB positioning information and the GNSS positioning information coincide.

[0058] It should be noted that the positioning tags including the first positioning channel and the second positioning channel in this application can be obtained by using existing technologies based on the ultra-wideband (UWB) positioning principle and the global navigation satellite system (GNSS) positioning principle, and this application will not elaborate further here. For example, the first positioning channel can be implemented by setting tags based on the UWB positioning principle, and the second positioning channel can be implemented by setting a receiver.

[0059] In an alternative embodiment, the server is further configured to respectively determine the positioning trajectory and the driving trajectory of the non-motor vehicle based on the UWB positioning information and the GNSS positioning information, and determine whether there is an abnormality in the positioning trajectory of the non-motor vehicle based on the overlapping part of the regions of the positioning trajectory and the driving trajectory.

[0060] In an alternative embodiment, the travel road of the non-motor vehicle includes a preset road section range at a traffic signal intersection and a travel area connecting between the preset road section ranges; when the first positioning channel is enabled after the non-motor vehicle enters the preset road section range, the second positioning channel is closed, and when the first positioning channel is closed after the non-motor vehicle leaves the preset road section range, the second positioning channel is opened.

[0061] Specifically, it can be understood that the display tag provided on the non-motor vehicle includes a first positioning channel and a second positioning channel. During the travel of the non-motor vehicle, if both positioning channels are turned on throughout the process, the energy consumption is relatively high. To reduce the power consumption, in this alternative embodiment, in the travel area where the first positioning channel cannot be used for positioning, the first positioning channel is closed, and the second positioning channel is opened to obtain GNSS positioning information. After entering the preset road section range, the first positioning channel is opened while the second positioning channel is closed to receive UWB positioning information. Thus, in this application, different positioning channels are enabled in different ranges. Since the movement trajectory of the non-motor vehicle is continuous, the GNSS positioning information obtained in this way can also be used to verify the UWB positioning information, reducing the energy consumption and data transmission volume while ensuring the accuracy of red-light running behavior determination.

[0062] In a specific example, for an electric bicycle, when its positioning tag is traveling in an open area away from intersections in daily life, the receiver of the second positioning channel is turned on, and it sends the position coordinates to the server once every 10 seconds with relatively low power consumption. When the vehicle approaches the intersection and enters within 30 meters of the boundary of the preset road section range (entering the over-line area, and the preset road section range is set according to the intersection geographical fence), the low-power Bluetooth module detects the Bluetooth beacon signal set at the intersection and immediately triggers the positioning tag to switch to the first positioning channel of the UWB positioning mode. At this time, the positioning accuracy can be improved to the sub-meter level, and it sends multiple real-time position updates to the nearby base station per second to accurately track the movement trajectory of the non-motor vehicle at the intersection.

[0063] In an alternative embodiment, the server is further configured to respectively determine the positioning trajectory and travel trajectory of the non-motor vehicle based on the UWB positioning information and the GNSS positioning information, and determine whether there is an abnormality in the positioning trajectory of the non-motor vehicle based on the regional connection part between the positioning trajectory and the travel trajectory.

[0064] Specifically, the first positioning channel and the second positioning channel are switched when non-motor vehicles enter and exit the preset road section range. Since the driving trajectories of non-motor vehicles are continuous, GNSS positioning information is received in the driving area, and UWB positioning information is received within the preset road section range. Therefore, the UWB positioning information and the GNSS positioning information should be correspondingly connected at the edge of the preset road section range. Based on this, it is possible to determine whether the UWB positioning information is abnormal based on the deviation at the connection between the UWB positioning information and the GNSS positioning information of non-motor vehicles.

[0065] Among them, in practical applications, the positioning trajectory and driving trajectory of non-motor vehicles can be obtained based on the UWB positioning information and the GNSS positioning information. The criteria for determining whether the UWB positioning information is abnormal based on the positioning trajectory and the driving trajectory can be selected from at least one of the following criteria:

[0066] 1) Determine whether the ends of the positioning trajectory and the driving trajectory can be connected to form a complete driving trajectory;

[0067] 2) Combine whether the ends of the connection between the positioning trajectory and the driving trajectory are at the edge of the preset road section range;

[0068] 3) Determine whether the times corresponding to the ends of the connection between the positioning trajectory and the driving trajectory are consistent.

[0069] It should be noted that in the above criteria, the determination calculation method and the passing criteria can be set according to actual needs, and the present application does not limit this.

[0070] In an alternative embodiment, the server is further configured to predict the over-line distance of non-motor vehicles running a red light based on the traffic data of non-motor vehicles running a red light within the preset road section range and the trained range prediction model, and determine the over-line area based on the over-line distance and the red light no-entry line of the preset road section range. Among them, the traffic data includes the positioning trajectories of non-motor vehicles that have been determined to have the behavior of running a red light in the preset road section range, and the over-line area where non-motor vehicles may have the behavior of running a red light is determined through the traffic data and the trained range prediction model.

[0071] Specifically, it can be understood that the control of non-motor vehicles is usually much looser than that of motor vehicles. Therefore, most non-motor vehicles do not park strictly along the edge of the preset road section range and usually cross the preset road section range. Thus, in order to avoid introducing the problem of large calculation amount and low efficiency caused by the determination of the positioning trajectory of non-motor vehicles that do not run a red light due to irregular parking, a range prediction model is trained based on a neural network model. An over-line area is further delimited within the preset road section range, and the positioning trajectory of non-motor vehicles within the over-line area is determined to reduce the amount of data of the positioning information of non-motor vehicles that need to be analyzed, improve the determination efficiency of whether non-motor vehicles run a red light, reduce the calculation amount, and avoid introducing unnecessary positioning information processing processes.

[0072] In a specific example, the range prediction model can be trained through the following process:

[0073] 11) Determine the training data set, where the training data set includes the positioning trajectories of non-motor vehicles that cross each preset road section range and run a red light during the red light period;

[0074] 12) Input the training data set into a model constructed based on a neural network model for training;

[0075] When the training reaches the preset training end condition, a trained range prediction model is obtained. Thus, according to the trained range prediction model, the redundant area that should not be included in the determination of running a red light behavior can be predicted for each preset road section range, and then the over-line area is obtained by shrinking the redundant area inward from the edge of the preset road section range.

[0076] In an optional implementation manner, it further includes intercepting a video slice of the red light period from the non-motor vehicle driving video. Before transmitting the video slice to the server, the server determines the target non-motor vehicles that may run a red light based on the positioning trajectory of the non-motor vehicle, and sends the target non-motor vehicles to the processor. The processor intercepts the video slice corresponding to all the target non-motor vehicles in the red light period from the non-motor vehicle driving video and sends it to the server so that the server determines whether the target non-motor vehicles run a red light based on the positioning trajectory and the video slice. Thus, the processor only needs to transmit the partial video slices that may run a red light determined by the server through the positioning trajectory to the server without uploading the entire video slice of the red light period, greatly reducing the data transmission amount and improving the determination efficiency.

[0077] In an optional embodiment, in order to determine the time when a non-motor vehicle runs a red light, the server is used to determine an abnormal position in the positioning trajectory of the non-motor vehicle based on the positioning trajectories of other non-motor vehicles and the positioning trajectory of the non-motor vehicle, the abnormal position being a position where the difference between the change rate of the positioning trajectory of the non-motor vehicle and the average change rate of the positioning trajectories of other non-motor vehicles is higher than a set threshold; intercepting the timestamp corresponding to the abnormal position, and configuring an interception period based on each timestamp and the difference in the change rate, wherein the timestamp is within the interception period; analyzing whether the non-motor vehicle trajectory runs a red light based on the video data within each interception period in the video slice.

[0078] In an optional embodiment, for each abnormal position, if the number of other non-motor vehicles located in front of the non-motor vehicle is greater than the number located behind the non-motor vehicle, the processor is also used to move the interception time period forward for a set period of time, otherwise move it backward for a set period of time.

[0079] In an optional embodiment, the video slice also includes unlabeled non-motor vehicles; the server is also used to select multiple frames of images from the video slice of the red light period, and the multiple frames of images include at least two frame images corresponding to abnormal positions; the actual displacement and image displacement of the non-motor vehicle identified from the at least two frame images corresponding to abnormal positions; based on the actual displacement and the image displacement, combined with the distance between the road marking in one frame of the image and the non-motor vehicle in the image, the crossing area is generated; based on the multiple frames of images, each unlabeled non-motor vehicle and the driving trajectory of the non-motor vehicle are fitted and generated; based on each unlabeled non-motor vehicle, the crossing area and the driving trajectory of the non-motor vehicle, it is determined whether each unlabeled non-motor vehicle runs a red light.

[0080] The cross-line area of ​​this embodiment is as follows: Figure 1 As shown, the road marking for running a red light is road marking 1 within a preset road section range, and the crossing line area set in this application is offset inward compared to the road marking.

[0081] It can be seen that the present application directly determines the red light running behavior of non-motor vehicles through the positioning trajectory and video slices in the crossing line area during the red light period and includes the judgment evidence of the video slices. It does not require a large amount of video data support, thus avoiding the network construction and operation and maintenance burden of the road section.

[0082] In an embodiment of the present application, after the server determines the positioning trajectory of the non-motor vehicle based on the UWB positioning information, it can preliminarily determine whether the non-motor vehicle has run a red light based on the positioning trajectory, and then, after determining that the target non-motor vehicle may have run a red light, reversely verify the non-motor vehicle in combination with other non-motor vehicles in the video slice corresponding to the non-motor vehicle.

[0083] It should be noted that in this embodiment, other non-motor vehicles are also equipped with positioning tags. Specifically, the server is used to determine the abnormal positions in the positioning trajectory of the to-be-identified non-motor vehicle according to the positioning trajectories of other non-motor vehicles and the positioning trajectory of the to-be-identified non-motor vehicle. The abnormal position is the position where the difference degree between the change rate of the positioning trajectory of the to-be-identified non-motor vehicle and the average change rate of the positioning trajectories of other non-motor vehicles is higher than a set threshold; intercept the time stamps corresponding to the abnormal positions, and based on each time stamp, configure an interception period in combination with the difference degree of the change rate, and the time stamp is within the interception period; finally determine whether the non-motor vehicle trajectory runs a red light according to the video data of the video slices within each interception period.

[0084] In this embodiment, by comparing the positioning trajectory of the non-motor vehicle with the positioning trajectories of other non-motor vehicles, the abnormal positions of the positioning trajectory of the non-motor vehicle can be determined. Borrowing the underlying principle of the majority principle, the average change rate of the positioning trajectories of all other non-motor vehicles is used as a reference. Since the non-motor vehicles running red lights should be in the minority in terms of proportion, even if there are other non-motor vehicles running red lights, the average change rate still tends to the direction of non-running red lights. Therefore, in this application, the abnormal position is the position where the difference degree between the change rate of the positioning trajectory of the non-motor vehicle and the average change rate of the positioning trajectories of other non-motor vehicles is higher than the set threshold. That is, for the to-be-identified non-motor vehicle, if the change rate of its trajectory is significantly different from the average change rate of most non-motor vehicles, there may be abnormal driving at this time, such as sprinting to run a red light or avoiding during running a red light.

[0085] When all the abnormal positions of the entire positioning trajectory are confirmed, find the time stamps corresponding to the abnormal positions, intercept the video data, and confirm whether there is actually a behavior of running a red light through the intercepted video clips and quickly obtain the instantaneous photos of the non-motor vehicle running a red light. In this way, this application only needs a few seconds of video of some key points to determine that the non-motor vehicle runs a red light, greatly reducing the transmission and processing volume of video data.

[0086] Specifically, this application provides a method for configuring an interception period. In the embodiment of this application, configuring the interception period based on each time stamp in combination with the difference degree of the change rate includes:

[0087] According to a preset function, in combination with the difference degree of the change rate, configure an interception period with the time stamp as the starting point of the period, where the preset function is T = a×e -bD + c, where D is the difference degree of the change rate, T is the length of the interception period, and a, b, c are fitting coefficients.

[0088] In this embodiment, when the difference between the trajectory change rate of a non-motor vehicle and the average change rate of other non-motor vehicles increases, it means that the driving state of the vehicle deviates more and more from the normal mode. For example, at an intersection, non-motor vehicles waiting for a red light normally have a stable speed and consistent direction, and the average change rate approaches zero. If a vehicle to be identified suddenly accelerates towards the opposite intersection, its speed value will soar rapidly. At this time, the length of the intercepted time period will approach zero as the difference in the change rate increases, making the length of the intercepted time period mainly determined by smaller values, and the intercepted time period is greatly shortened. In this way, the greater the difference in the change rate, the more obvious the red-light running feature at this time, and the less video data is required. Only the current key frame of data may be sufficient to identify the red-light running image. This embodiment focuses the video interception on the key few seconds that are most likely to reflect the red-light running behavior, avoiding the processing of a large amount of irrelevant video data, enabling the system to quickly lock in the abnormal moment, and greatly improving the recognition efficiency.

[0089] The embodiment of this application uses this function to greatly reduce the data transmission and storage burden on the server. In the traditional method, if we want to comprehensively analyze the red-light running behavior of non-motor vehicles, we may need to transmit the video of the entire red-light period, and the data volume is huge. Now, only the key time period is intercepted according to the function, and the transmitted data volume is sharply reduced. Taking an intersection with a daily non-motor vehicle flow of thousands of vehicles as an example, before using this function, the daily video data storage requirement was as high as hundreds of GB. After introducing the function optimization, the storage volume can be reduced to several GB, saving a large amount of storage space. At the same time, it reduces the network bandwidth occupancy during data transmission, ensures the smooth operation of the system, and provides feasible support for the large-scale intersection monitoring in the city.

[0090] In addition, this function also lays a foundation for the intelligent upgrade of the system. With the continuous accumulation of traffic data, machine learning algorithms can be used to dynamically optimize the values of a, b, and c, enabling the function to continuously adapt to the development and changes of urban traffic, such as the emergence of new non-motor vehicles and the adjustment of traffic rules.

[0091] In an alternative embodiment, for each abnormal position, if the number of other non-motor vehicles in front of the non-motor vehicle is greater than the number of those behind it, based on each of the timestamps, in combination with the difference in the change rate to configure the intercepted time period, it further includes:

[0092] Shifting the intercepted time period forward by a set duration, and conversely, shifting it backward by a set duration.

[0093] In the embodiments of the present application, when it is found that the number of other non-motor vehicles in front of the non-motor vehicle is greater than the number behind, it is possible that the vehicle to be recognized may be accelerating to overtake the vehicle in front in an attempt to run a red light. At this time, the intercepted time period is shifted forward by a set duration, which can accurately capture the starting moment of behaviors such as vehicle acceleration and lane change. For example, at an intersection with a large traffic flow, if there are multiple vehicles waiting for the red light normally in front of an electric vehicle to be recognized, and it suddenly speeds up, the change rate of its trajectory forms a sharp contrast with the surrounding vehicles. By shifting the intercepted time period forward, the system is no longer limited to the conventional time period judged only based on the difference in change rate, but locks in its preparatory actions for running a red light in advance, making the judgment basis more sufficient, greatly reducing the possibility of misjudgment, and improving the discrimination accuracy of real red-light running behaviors.

[0094] Or, taking a busy intersection with a daily non-motor vehicle traffic volume of tens of thousands as an example, if the intercepted time period is fixed, a large number of images of vehicles waiting normally and starting slowly may be intercepted, while the images truly reflecting the core behavior of running a red light account for a small proportion. After adopting this implementation method, through precise time period shifting, the system focuses on high-suspicion moments, making the video data intercepted every second closely revolve around possible red-light running behaviors, which not only reduces the pressure on subsequent video analysis algorithms, but also improves the overall recognition efficiency, enables the limited data processing resources to exert the greatest effectiveness, and ensures the efficient and stable operation of the large-scale intersection monitoring system. It can be seen from this that compared with intercepting in a fixed time period, the dynamic adjustment in the embodiments of the present application avoids wasting resources on invalid or low-correlation video segments.

[0095] Confirming red-light running for non-motor vehicles without positioning tags:

[0096] In an optional implementation manner, it is also possible to confirm red-light running for non-motor vehicles without positioning tags. It should be noted that for the configuration of positioning tags, in most cases, they may not be widely popularized. Therefore, in the embodiments of the present application, further through the method of local coverage, it only needs one non-motor vehicle with a positioning tag to exist at a section of the intersection to achieve the recognition of red-light running for all non-motor vehicles within the section, and it can be achieved without a large amount of data and processing. Specifically, the core concept of this embodiment is to perform spatial projection on the trajectory recognized by video and the positioning trajectory, and determine the positioning trajectory of the non-motor vehicle through the method of spatial projection, so as to determine whether the non-motor vehicle without a configuration runs a red light.

[0097] Specifically, in this embodiment, the video slices further include unlabeled non-motor vehicles; the server is further configured to select multiple frames of images from the video slices, where the multiple frames of images include at least two frame images corresponding to abnormal positions; identify the actual displacement and the image displacement of the non-motor vehicles identified from at least two frame images corresponding to abnormal positions; generate the crossing line area according to the actual displacement and the image displacement, in combination with the distance between the road markings and the non-motor vehicle in one of the frame images; fit and generate each unlabeled non-motor vehicle and the driving trajectory of the non-motor vehicle according to the multiple frames of images; and determine whether each unlabeled non-motor vehicle runs a red light according to each unlabeled non-motor vehicle, the crossing line area, and the driving trajectory of the non-motor vehicle.

[0098] Specifically, as shown in the figure, in the embodiment of the present application, multiple frames of images are first selected from the video slices. It should be noted that the multiple frames of images can be selected at a preset time interval, such as 10 frames, or randomly selected. Of course, the multiple frames of images in the present application should at least cover the entire time period of the video slices. For example, at least one frame of the first N frames and at least one frame of the last N frames are included. In this way, although multiple frames of images are selected, the movement time of the non-motor vehicles is covered, so that the data is more accurate.

[0099] The embodiment of the present application cleverly borrows the characteristics of the gantry camera configuration. At this time, the shooting angle of the camera is an inclination angle. Therefore, the video data includes height data and depth data. After selecting multiple frames of images, the actual displacement and the image displacement of the non-motor vehicles identified from at least two frame images corresponding to abnormal positions are identified. Specifically, the multiple frames of images in the present application include at least two frame images corresponding to abnormal positions, that is, there is a large displacement between the two frame images of abnormal positions. According to this large displacement, the depth change in the video can be calculated by combining the depth calculation algorithm in the video. Since the video captured in the present application is shot obliquely from top to bottom, the position change in the video is directly reflected in the image. The distance between two images can be measured. At this time, at least two frames with a time difference are selected. Since there is a time difference, the position coordinates at different time points can be found from the positioning trajectory, and the distance difference L1 on the positioning trajectory can be obtained. At the same time, a distance difference is formed on the images of the two video frames, so that the corresponding relationship between the image distance and the actual distance can be obtained. Then, in combination with the road markings in one of the frame images, Figure 1 the road markings 1 in, online generate the crossing line area (for example, the left line of the crossing line area is obtained by shifting the position of the road markings 1 by the length of one vehicle body towards the road markings 2. Similarly, the right line can be obtained by shifting the position of the road markings 2 by the length of one vehicle body towards the road markings 1. The present application will not elaborate on this).

[0100] Afterwards, based on the multiple frames of images, each unlabeled non-motor vehicle and the driving trajectory of the non-motor vehicle are fitted and generated. Specifically, as can be seen from the foregoing, a distance difference is formed on the images of the two video frames. Therefore, for the non-motor vehicle without a positioning tag, its actual displacement distance can be calculated through the two frames of images (based on the correspondence between the image distance and the actual distance). At this time, combined with the crossing line area and the red light period, it can be determined whether the non-motor vehicle without a positioning tag has run a red light.

[0101] Furthermore, the present application also provides a method for identifying a non-motor vehicle without a label running a red light. In this embodiment, the non-planar road surface can be handled. Specifically, the method determines whether each non-motor vehicle without a label runs a red light according to each non-motor vehicle without a label, the crossing area, and the driving trajectory of the non-motor vehicle, including:

[0102] Projecting the driving track of the non-motor vehicle onto the positioning track according to a deflection angle;

[0103] The deflection angle is continuously changed until the overlap between the driving trajectory and the positioning trajectory is higher than a set overlap threshold, and the final deflection angle is output.

[0104] Converting the driving trajectory of each unlabeled non-motor vehicle into a positioning trajectory of the unlabeled non-motor vehicle using the deflection angle finally outputted;

[0105] Based on the crossing line area and the positioning track of each untagged non-motor vehicle, it is determined whether each untagged non-motor vehicle runs a red light.

[0106] In this embodiment, the video data is accompanied by depth information and height information due to the shooting angle. If the road surface is horizontal, the height information can be offset by multiple frames of images. However, if the road surface height is not horizontal, such as uphill or downhill, the error caused by the height information cannot be eliminated by image calibration. Based on this, the present application further removes the height information by deflection, so as to cope with the situation where the road surface is non-planar.

[0107] In the embodiments of the present application, since the driving trajectory (the trajectory determined from video data) and the positioning trajectory (the trajectory identified by the base station) of the non-motor vehicle can both be obtained, and with the help of the current road surface characteristics (the slope of the general road surface is uphill or downhill), the height information can be removed by angle correction. By configuring the deflection angle, the driving trajectory is projected onto the positioning trajectory, and through continuous deflection correction, when the coincidence degree between the two is higher than the set threshold (for example, 95%), the height error can be correspondingly eliminated. Then, the driving trajectory of each unlabeled non-motor vehicle is converted into the positioning trajectory of the unlabeled non-motor vehicle with the finally output deflection angle, so that the positioning trajectory of each unlabeled non-motor vehicle eliminates the error disturbance caused by height information. Using the converted positioning trajectory, it is possible to determine whether the unlabeled non-motor vehicle on the uphill and downhill road surfaces runs a red light.

[0108] Based on the same principle, the present application also provides a method for identifying whether a non-motor vehicle runs a red light. As Figure 2 shown, the method includes:

[0109] S100: Receive the UWB positioning information obtained by the first positioning channel communication between the UWB base station and the positioning tag on the non-motor vehicle sent by the UWB base station.

[0110] S200: Receive the non-motor vehicle driving video in the crossing area within the preset road section range collected by the monitoring camera, and intercept the video slice during the red light time period from the non-motor vehicle driving video.

[0111] S300: Identify the non-motor vehicle in the video slice, determine the positioning trajectory of the non-motor vehicle based on the UWB positioning information of the non-motor vehicle, and judge whether the non-motor vehicle has the behavior of running a red light based on the positioning trajectory and the video slice.

[0112] Since the principle of this method is similar to that of the above system, the implementation of this method can refer to the implementation of the above system and will not be elaborated here.

[0113] The embodiments of the present application also provide a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the above method is implemented.

[0114] The embodiments of the present application also provide a computer-readable medium, which stores a computer program. When the computer program is executed by a processor, the above method is implemented.

[0115] The embodiments of the present application provide a computer program product, which can implement the above various methods when running on a computer.

[0116] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. The systems, devices, modules, or units described in the above embodiments can be specifically implemented by a computer chip or an entity, or by a product with certain functions. A typical implementation device is a computer device. Specifically, the computer device can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0117] In a typical example, the computer device specifically includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements the method executed by the client as described above, or when the processor executes the program, it implements the method executed by the server as described above.

[0118] The following refers to Figure 3 , which shows a schematic structural diagram of a computer device 600 suitable for implementing the embodiments of the present application.

[0119] As Figure 3 shown, the computer device 600 includes a central processing unit (CPU) 601, which can perform various appropriate operations and processes according to the program stored in the read-only memory (ROM) 602 or the program loaded from the storage section 608 into the random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the computer device 600 are also stored. The CPU 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. The input / output (I / O) interface 605 is also connected to the bus 604.

[0120] The following components are connected to the I / O interface 605: an input section 606 including a keyboard, a mouse, etc.; an output section 607 including, for example, a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, a modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed so that the computer program read from it can be installed into the storage section 608 as needed.

[0121] In particular, according to an embodiment of the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, an embodiment of the present application includes a computer program product that includes a computer program tangibly embodied on a machine-readable medium, the computer program including program code for performing the methods shown in the flowcharts. In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 609, and / or installed from the removable medium 611.

[0122] Computer-readable media includes both permanent and non-permanent, removable and non-removable media implemented by any method or technology for storing information. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile discs (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices, or any other non-transitory medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media such as modulated data signals and carrier waves.

[0123] For convenience of description, the above-described apparatus is described by dividing it into various units according to functions. Of course, when implementing the present application, the functions of each unit can be implemented in one or more pieces of software and / or hardware.

[0124] The present application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and combinations of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing device generate means for implementing the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0125] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0126] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0127] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0128] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0129] The present application may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0130] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and for the relevant parts, reference can be made to the corresponding description in the method embodiment.

[0131] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of each embodiment of the present application, and should all be included in the protection scope of the present application.

Claims

1. A non-motor vehicle red light running recognition system, characterized in that: The system includes a positioning tag arranged on the non-motor vehicle, a server, and a UWB base station and a video acquisition device arranged within a preset road section, wherein the video acquisition device includes a monitoring camera and a processor, and the positioning tag includes a first positioning channel; The UWB base station sends UWB positioning information obtained by communicating with the first positioning channel of the positioning tag to the server; The monitoring camera is used to collect the non-motor vehicle driving video in the crossing area within the preset road section range, and the processor is used to intercept the video slices of the red light time period from the non-motor vehicle driving video, and transmit the video slices to the server; The server is used to determine the positioning track of the non-motor vehicle based on the UWB positioning information, and judge whether the non-motor vehicle has run a red light based on the positioning track and the video slice.

2. A non-motor vehicle red light running recognition system as claimed in claim 1, characterized in that: The positioning tag also includes a second positioning channel; The server receives GNSS positioning information based on the second positioning channel transmitted by an external positioning system; The server is further configured to determine whether there is an abnormality in the positioning trajectory based on the UWB positioning information and the GNSS positioning information.

3. A non-motor vehicle red light running recognition system as claimed in claim 2, characterized in that: The server is also used to determine the positioning trajectory and driving trajectory of the non-motor vehicle based on the UWB positioning information and the GNSS positioning information respectively, and determine whether there is an abnormality in the positioning trajectory of the non-motor vehicle based on the overlapping area of ​​the positioning trajectory and the driving trajectory.

4. A non-motor vehicle red light running recognition system as claimed in claim 2, characterized in that: The driving road of the non-motor vehicle includes a preset road section range at a traffic light intersection and a driving area connected between the preset road section range; The positioning tag closes the second positioning channel when the first positioning channel is enabled after the non-motor vehicle enters the preset road section range, and opens the second positioning channel when the first positioning channel is closed after the non-motor vehicle leaves the preset road section range.

5. A non-motor vehicle red light running recognition system as claimed in claim 4, characterized in that: The server is also used to determine the positioning trajectory and driving trajectory of the non-motor vehicle based on the UWB positioning information and the GNSS positioning information respectively, and determine whether there is an abnormality in the positioning trajectory of the non-motor vehicle based on the regional connection part of the positioning trajectory and the driving trajectory.

6. A non-motor vehicle red light running recognition system as claimed in claim 1, characterized in that: The server is also used to predict the crossing distance of non-motor vehicles running red lights based on traffic data of non-motor vehicles running red lights within a preset road section and a trained range prediction model, and determine the crossing area based on the crossing distance and the red light no-entry line within the preset road section.

7. The non-motor vehicle red light running recognition system as claimed in claim 1, characterized in that: The server is used to determine an abnormal position in the positioning trajectory of the non-motor vehicle based on the positioning trajectories of other non-motor vehicles and the positioning trajectory of the non-motor vehicle, wherein the abnormal position is a position where the difference between the change rate of the positioning trajectory of the non-motor vehicle and the average change rate of the positioning trajectories of other non-motor vehicles is higher than a set threshold; intercept the timestamp corresponding to the abnormal position, and configure an interception period based on each timestamp and the difference in the change rate, wherein the timestamp is within the interception period; According to the video data in each intercepted time period in the video slice, it is analyzed whether the non-motor vehicle trajectory runs a red light.

8. A non-motor vehicle red light running recognition system as claimed in claim 7, characterized in that: For each abnormal position, if the number of other non-motor vehicles located in front of the non-motor vehicle is greater than the number located behind the non-motor vehicle, the server is also used to move the interception time period forward by a set time length, otherwise move it backward by a set time length.

9. A non-motor vehicle red light running recognition system as claimed in claim 7 or 8, characterized in that: The video slice also includes an unlabeled non-motor vehicle; the server is further used to select multiple frames of images from the video slice, the multiple frames of images including at least two frame images corresponding to abnormal positions; the actual displacement and image displacement of the non-motor vehicle identified from the at least two frame images corresponding to abnormal positions; the crossing line area is generated according to the actual displacement and the image displacement, combined with the distance between the road marking in one frame of the image and the non-motor vehicle in the image; and each unlabeled non-motor vehicle and the driving trajectory of the non-motor vehicle are fitted and generated according to the multiple frames of images; Whether each unlabeled non-motor vehicle runs a red light is determined according to each unlabeled non-motor vehicle, the crossing area, and the driving track of the non-motor vehicle.

10. A method for identifying a non-motor vehicle running a red light, characterized in that: include: Receiving UWB positioning information sent by the UWB base station and obtained by the first positioning channel communication between the UWB base station and the positioning tag on the non-motor vehicle; Receiving a non-motor vehicle driving video in a cross-line area within a preset road section range collected by a surveillance camera, and extracting a video slice of a red light time period from the non-motor vehicle driving video; The non-motor vehicle in the video slice is identified, a positioning track of the non-motor vehicle is determined based on the UWB positioning information of the non-motor vehicle, and whether the non-motor vehicle has run a red light is determined based on the positioning track and the video slice.

Images