Detection method and device, storage medium and electronic equipment

Abstract

The invention relates to a detection method and device, a storage medium and electronic equipment, a vehicle can obtain a signal lamp video of a target signal lamp in front of a vehicle driving road and a target broadcast signal broadcasted by a roadside unit RSU, and the target broadcast signal carries first signal lamp data sent by the target signal lamp to the RSU. Performing image recognition on a target image frame in the signal lamp video to obtain second signal lamp data, and detecting the first signal lamp data according to the second signal lamp data; or, sending the target broadcast signal and the second signal lamp data to the server, so that the server detects the first signal lamp data according to the second signal lamp data.

Description

Technical Field

[0001] The present disclosure relates to the field of inspection of roadside equipment, and in particular, to a detection method, device, storage medium and electronic equipment. Background Art

[0002] With the development of Internet of Vehicles business, vehicle-road collaboration is an inevitable way to achieve smart transportation. If vehicle-road collaboration is to be achieved, it is necessary to deploy a variety of roadside equipment on the road to obtain relevant information of traffic participants such as vehicles, pedestrians, and traffic lights on the road. Roadside equipment deployed on the road can include cameras, millimeter-wave radars, signal machines, RSUs (RoadSide Units), and MECs (Mobile Edge Computing).

[0003] In order to meet the current growing demand for roadside infrastructure management, it is necessary to realize intelligent detection of roadside equipment. The efficiency and accuracy of the detection methods provided in the relevant technologies need to be improved. Summary of the invention

[0004] The purpose of the present disclosure is to provide a detection method, device, storage medium and electronic device.

[0005] In a first aspect, the present disclosure provides a detection method applied to a vehicle, the method comprising: Acquire a signal light video of a target signal light ahead of the road on which the vehicle is traveling; Acquire a target broadcast signal of a roadside unit RSU of the driving road, wherein the target broadcast signal carries first signal light data sent by the target signal light to the RSU; Performing image recognition on a target image frame in the traffic light video to obtain second traffic light data; detecting the first signal light data according to the second signal light data; Alternatively, the target broadcast signal and the second signal light data are sent to a server, so that the server detects the first signal light data according to the second signal light data.

[0006] Optionally, the acquiring a target broadcast signal of a roadside unit RSU on the driving road includes: receiving a broadcast signal of the RSU according to a preset frequency, wherein the broadcast signal carries signal light data corresponding to a plurality of groups of signal lights; For each time the broadcast signal is received, the current location information of the vehicle is obtained; the target road where the vehicle is currently located is determined based on the location information, and the broadcast signal is filtered according to the target road to obtain the target broadcast signal of the target signal light corresponding to the target road; and / or, the target lane where the vehicle is currently located is determined based on the location information, and the broadcast signal is filtered according to the target lane to obtain the target broadcast signal of the target signal light corresponding to the target lane, wherein the target road includes at least one target lane.

[0007] Optionally, performing image recognition on a target image frame in the traffic light video to obtain second traffic light data includes: After parsing the target broadcast signal, obtaining a collection timestamp of the first signal light data; Taking the image frame corresponding to the acquisition timestamp in the traffic light video as the target image frame; Image recognition is performed on the target image frame to obtain the second signal light data corresponding to the first signal light data.

[0008] Optionally, detecting the first signal light data according to the second signal light data includes: After parsing the target broadcast signal, acquiring the first signal light data; detecting whether the first signal light data is consistent with the second signal light data corresponding to the first signal light data, and obtaining a first detection result; The method further comprises: An inspection report is generated according to the first detection result, and the inspection report includes detection results corresponding to different collection timestamps.

[0009] Optionally, sending the target broadcast signal and the second signal light data to a server so that the server detects the first signal light data according to the second signal light data includes: sending the target broadcast signal and the second signal light data corresponding to the first signal light data carried in the target broadcast signal to the server in pairs, so that the server parses the target broadcast signal to obtain the first signal light data, and detects whether the first signal light data is consistent with the second signal light data corresponding to the first signal light data, to obtain a second detection result; The method further comprises: The server is enabled to generate an inspection report according to the second detection result, and the inspection report includes the detection results corresponding to different collection timestamps.

[0010] Optionally, sending the target broadcast signal and the second signal light data to a server includes: The target broadcast signal and the second signal light data corresponding to the first signal light data carried in the target broadcast signal are sent to the server in pairs, so that the server receives and stores the target broadcast signal and the second signal light data corresponding to the first signal light data carried in the target broadcast signal in pairs.

[0011] Optionally, acquiring a signal light video of a target signal light ahead of the road on which the vehicle is traveling comprises: Obtaining the current location information of the vehicle; When it is determined that the vehicle currently enters a preset acquisition area according to the position information and the preset map, a signal light video of the target signal light is acquired.

[0012] In a second aspect, a detection device is provided, which is applied to a vehicle, and the device comprises: The first acquisition module is used to acquire a signal light video of a target signal light in front of the road where the vehicle is traveling; A second acquisition module is used to acquire a target broadcast signal of a roadside unit RSU of the driving road, wherein the target broadcast signal carries first signal light data sent by the target signal light to the RSU; An image recognition module, used to perform image recognition on a target image frame in the traffic light video to obtain second traffic light data; A detection module is used to detect the first signal light data according to the second signal light data; or, send the target broadcast signal and the second signal light data to a server, so that the server detects the first signal light data according to the second signal light data.

[0013] In a third aspect, a computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the steps of the method described in the first aspect of the present disclosure are implemented.

[0014] In a fourth aspect, an electronic device is provided, including: a memory having a computer program stored thereon; A processor is used to execute the computer program in the memory to implement the steps of the method described in the first aspect of the present disclosure.

[0015] Through the above technical solution, the signal light video of the target signal light is collected, and the target broadcast signal carrying the first signal light data sent by the target signal light to the RSU is obtained. Then, based on the second signal light data obtained by image recognition of the target image frame in the signal light video, the first signal light data broadcast by the RSU is automatically inspected, thereby avoiding the need for inspectors to manually compare the first signal light data broadcast by the RSU with the actual signal light data with the naked eye, thereby improving the efficiency and accuracy of the inspection and saving labor costs.

[0016] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings are used to provide a further understanding of the present disclosure and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the present disclosure but do not constitute a limitation of the present disclosure. In the accompanying drawings: Figure 1 The figure is a flow chart of a detection method according to an exemplary embodiment.

[0018] Figure 2 is based on Figure 1 The illustrated embodiment shows a flow chart of a detection method.

[0019] Figure 3 is based on Figure 2 The illustrated embodiment shows a flow chart of a detection method.

[0020] Figure 4 It is a block diagram of a detection device according to an exemplary embodiment.

[0021] Figure 5 It is a block diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0022] The specific implementation of the present disclosure is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described herein is only used to illustrate and explain the present disclosure, and is not used to limit the present disclosure.

[0023] The present disclosure is mainly used in the scenario of detecting intelligent roadside equipment, and is particularly suitable for the scenario of inspecting the traffic light data broadcast by the roadside unit RSU. In the related art, the inspector located in the inspection car carries the PAD to inspect on the road. When the OBU (On-Board Unit) of the inspection car receives the traffic light signal sent by the RSU, the signal is displayed on the PAD. The inspector visually compares the information on the PAD with the current light color and countdown displayed by the traffic light to see if they are the same, and records the results.

[0024] However, as the types and numbers of intelligent roadside equipment continue to increase, the management and maintenance workload of the equipment is enormous. The inspection of traffic light data broadcast by RSU through manual visual comparison has low efficiency and accuracy.

[0025] In order to solve the above problems, the present invention provides a detection method, device, storage medium and electronic device. The specific implementation of the present invention is described in detail below with reference to the accompanying drawings.

[0026] Figure 1 FIG. 1 is a flow chart showing a detection method according to an exemplary embodiment. The method can be applied to a vehicle, which includes an inspection vehicle for inspecting roadside equipment. Figure 1 As shown, the method comprises the following steps: In step S101, a signal light video of a target signal light ahead of the road on which the vehicle is traveling is acquired.

[0027] In actual application scenarios, when an inspection vehicle drives to an intersection, it can use an image acquisition device to capture a signal light video of the target signal light deployed at the intersection in front of the vehicle.

[0028] Normally, different traffic lights are deployed in different directions of an intersection. In one possible embodiment, the target traffic light may include a target traffic light corresponding to the driving road (hereinafter referred to as the "target road") in front of the driving road where the inspection vehicle is located. For example, the inspection vehicle travels from south to north to the intersection, and the target traffic light is a group of traffic lights deployed at the north entrance of the intersection (the group of traffic lights includes, for example, a left turn light, a straight-ahead light, and a right turn light). In another possible embodiment, the target traffic light may also include a traffic light corresponding to the lane where the inspection vehicle is currently located (hereinafter referred to as the "target lane"). For example, the inspection vehicle travels from south to north to the intersection, and the vehicle is traveling in the straight lane of the road. The target traffic light is the straight-ahead light corresponding to the straight lane in a group of traffic lights deployed at the north entrance of the intersection.

[0029] In a possible implementation of this step, the inspection vehicle can obtain the current location information of the vehicle, so that when it is determined that the inspection vehicle currently enters the preset collection area based on the location information and the preset map, the signal light video of the target signal light can be obtained. In addition, the signal light video can be continuously shot while the vehicle passes through the preset collection area.

[0030] The preset map is a high-precision map of a city road, based on which the location of the target traffic light can be determined. The preset acquisition area refers to a preset area where the video of the target traffic light can be clearly acquired. For example, the preset acquisition area may be an area corresponding to a location where the distance between the location of the target traffic light and the location is less than a preset distance threshold (e.g., 200 meters).

[0031] In this way, after obtaining the current location information of the vehicle, the position of the target traffic light determined based on the preset map can be used to determine whether the current location of the vehicle enters the preset collection area, and if it is determined that the vehicle enters the preset collection area, the signal light video of the target traffic light can be obtained.

[0032] When the inspection vehicle has not entered the preset collection area, it can also collect real-time video of the environment in front of the vehicle. However, it is understandable that the video collected when the vehicle has not entered the preset collection area may not include the video of the target signal light, or the collected video of the target signal light is not clear enough. Therefore, in the present disclosure, in order to save resources and ensure the clarity of the acquired signal light video, the signal light video of the target signal light can be acquired when it is determined that the vehicle is currently entering the preset collection area.

[0033] In step S102, a target broadcast signal broadcast by a roadside unit RSU of the driving road is obtained, wherein the target broadcast signal carries first signal light data sent by the target signal light to the RSU.

[0034] In actual application scenarios, a traffic light or a controller of a traffic light can send traffic light data to the corresponding RSU in real time. The traffic light data can include the status data of the traffic light, such as the light color and countdown of the traffic light at the current moment. The traffic light data sent to the RSU at the same time can include the status data of multiple groups of traffic lights. For example, when traffic lights are respectively deployed at the four entrances of the A intersection, these four groups of traffic lights can send their respective traffic light data to the RSU located near the A intersection. The first traffic light data can include the traffic light data sent by the target traffic light to the RSU. For example, if the target traffic light is a group of traffic lights deployed at the north entrance of the A intersection, the first traffic light data received by the RSU is the traffic light data sent by a group of traffic lights deployed at the north entrance of the A intersection. In the present disclosure, a group of traffic lights (including straight-ahead lights, left turn lights, right turn lights, etc.) deployed at the same location can be regarded as one traffic light.

[0035] After receiving the traffic light data, the RSU can broadcast the traffic light data to other devices, so that devices (such as patrol vehicles or roadside equipment) within the receivable range of the RSU's broadcast signal (for example, within 500 meters of the RSU) can receive the RSU's broadcast signal.

[0036] In actual application scenarios, the RSU can broadcast signals outward at a preset frequency, so that patrol vehicles can receive the broadcast signals of the RSU at a preset frequency, wherein the preset frequency can be broadcast N times per second, and N is usually a positive integer greater than or equal to 1.

[0037] It should be noted that since the broadcast signal may carry the signal light data of multiple groups of signal lights, for example, when signal lights are deployed at the four entrances of intersection A, the four signal lights can send their own signal light data to the RSU located near intersection A. In this way, the RSU broadcast signal carries the signal light data deployed in the four directions of intersection A. It can be understood that in the process of inspecting the signal light data broadcast by the RSU, it can be done separately for the signal lights in each direction. Therefore, after receiving the broadcast signal, the vehicle can filter the broadcast signal based on the current location information of the vehicle to determine the target broadcast signal corresponding to the target signal light, so as to automatically detect the first signal light data of the target signal light carried in the target broadcast signal based on the signal light video of the target signal light.

[0038] Therefore, in the process of executing this step, the inspection vehicle can receive the broadcast signal of the RSU at a preset frequency, and the broadcast signal carries signal light data corresponding to multiple groups of signal lights; for each received broadcast signal, the current location information of the vehicle is obtained, and after filtering the broadcast signal according to the location information, the target broadcast signal corresponding to the target signal light is obtained.

[0039] In the process of filtering the broadcast signal according to the position information to obtain the target broadcast signal corresponding to the target signal light, one implementation method is to determine the target road where the vehicle is currently located according to the current position information of the patrol vehicle, and then use the signal light corresponding to the target road as the target signal light. In this way, the target broadcast signal corresponding to the target signal light can be filtered out from the broadcast signal.

[0040] For example, assuming that it is determined based on the location information that the target road where the inspection vehicle is currently located is road B at intersection X, and it can be further determined that the traffic light corresponding to road B is the traffic light located at the north entrance of intersection X, then the target traffic light is a group of traffic lights located at the north entrance of intersection X, and then the currently received broadcast signal can be filtered to obtain the target broadcast signal corresponding to the group of traffic lights located at the north entrance of intersection X. The example here is only for illustration and the present disclosure is not limited to this.

[0041] In the process of filtering the broadcast signal according to the location information to obtain the target broadcast signal corresponding to the target signal light, another implementation method is to determine the target lane where the vehicle is currently located according to the location information of the patrol vehicle, and the target lane may include, for example, a straight lane, a left turn lane, or a right turn lane, and then use the signal light corresponding to the target lane as the target signal light, so that the target broadcast signal corresponding to the target signal light can be filtered from the broadcast signal. In addition, the target road in the present disclosure may include one or more target lanes.

[0042] For example, assuming that it is determined based on the position information that the target lane where the inspection vehicle is currently located is the through lane on Road B at the X intersection, and it can be further determined that the traffic light corresponding to the through lane of Road B is the through light in a group of traffic lights located at the north entrance of the X intersection, then the target traffic light is the through light in a group of traffic lights located at the north entrance of the X intersection, and then the currently received broadcast signal can be screened to obtain the target broadcast signal corresponding to the through light in the group of traffic lights located at the north entrance of the X intersection. The example here is only for illustration, and the present disclosure is not limited to this.

[0043] It should also be noted that the vehicle in the present invention can receive the broadcast signal of the RSU at a preset frequency. In this way, for each received broadcast signal, it can be automatically screened to obtain the target broadcast signal, and the first signal light data carried in the target broadcast signal can be automatically detected based on the signal light video of the target signal light. There is no need for manual visual detection, and its detection efficiency and detection accuracy can be greatly improved.

[0044] For example, assuming that the preset frequency is 10 times per second, the patrol vehicle can receive the broadcast signal of the RSU 10 times within 1 second. In this way, the patrol vehicle can screen the broadcast signal received each time to obtain the target broadcast signal, and then automatically detect the first signal light data carried in the target broadcast signal, that is, the patrol vehicle can detect the signal light data of the target signal light broadcast by the RSU 10 times within 1 second. However, it is obviously impossible to achieve such high-precision data comparison based on manual comparison. Therefore, the detection method in the present disclosure can improve the inspection efficiency while also improving the inspection accuracy. The above examples are only illustrative, and the present disclosure does not limit this.

[0045] In step S103, image recognition is performed on the target image frame in the traffic light video to obtain second traffic light data.

[0046] The second signal light data may include the light color and countdown of the target signal light obtained based on image recognition.

[0047] In step S104, the first signal light data is detected according to the second signal light data; or, the target broadcast signal and the second signal light data are sent to a server, so that the server detects the first signal light data according to the second signal light data.

[0048] In the present disclosure, the first signal light data is the signal light data of the target signal light broadcast by the RSU, and the second signal light data is the signal light data of the target signal light obtained by performing image recognition on the target image frame in the signal light video. Under normal circumstances, it can be assumed that the second signal light data obtained based on the signal light video of the target signal light is accurate, so that the second signal light data can be used to detect the first signal light data of the target signal light broadcast by the RSU, and then it can be detected whether the signal light data of the target signal light broadcast by the roadside unit RSU is correct.

[0049] It should be noted that the step of automatically detecting the first signal light data in the present invention can be performed on the vehicle side, that is, the vehicle detects the first signal light data based on the second signal light data, and can also be performed on the server side, that is, the vehicle sends the target broadcast signal and the second signal light data to the server, so that the server can detect the first signal light data based on the second signal light data.

[0050] By adopting the above method, the signal light video of the target signal light is collected, and the target broadcast signal carrying the first signal light data sent by the target signal light to the RSU is obtained. Then, based on the second signal light data obtained by image recognition of the target image frame in the signal light video, the first signal light data broadcast by the RSU is automatically inspected, thereby avoiding the inspector's manual comparison of the first signal light data broadcast by the RSU with the actual signal light data, improving the efficiency and accuracy of the inspection, and saving labor costs.

[0051] As described above, in the present disclosure, the second signal light data is obtained by performing image recognition on the target image frame in the signal light video. Therefore, before performing image recognition, it is necessary to first determine the target image frame to be image recognized from the signal light video.

[0052] It is understandable that before using the second signal light data to detect the first signal light data, it is necessary to ensure that the second signal light data and the first signal light data are data of the same signal light and are signal light data corresponding to the same timestamp, so that the comparison is reasonable. Therefore, when determining the target image frame to be image recognized from the signal light video, it can be determined based on the timestamps of each image frame in the signal light video and the acquisition timestamp of the first signal light data received each time.

[0053] Figure 2 is based on Figure 1 The embodiment shown is a flow chart of a detection method, such as Figure 2 As shown, step S103 includes the following sub-steps: In step S1031, the target broadcast signal is parsed to obtain a collection timestamp of the first signal light data.

[0054] The acquisition timestamp is the acquisition time of the corresponding signal light data. The first signal light data received at different times has different corresponding acquisition timestamps.

[0055] In one implementation, each time the first signal light data sent by the RSU to the inspection vehicle carries the acquisition timestamp of the first signal light data, therefore, in this step, the inspection vehicle can obtain the acquisition timestamp by parsing the target broadcast signal.

[0056] In step S1032, an image frame in the traffic light video corresponding to the acquisition timestamp is used as a target image frame.

[0057] Among them, the traffic light video is a video composed of multiple consecutive image frames, and each image frame corresponds to its own timestamp (which can be understood as the generation time of the corresponding image frame). It can be understood that if the timestamp of an image frame A is the same as the acquisition timestamp of the received first traffic light data, then the traffic light data recorded in the image frame A and the first traffic light data can be regarded as the traffic light data of the target traffic light at the same time. At this time, the second traffic light data obtained by performing image recognition on the image frame A can be used to detect the first traffic light data with the same acquisition timestamp broadcast by the RSU.

[0058] Therefore, in this step, after obtaining the acquisition timestamp of the first signal light data currently received, the image frame with the timestamp of the acquisition timestamp can be selected from the multiple image frames of the signal light video as the target image frame, and the target image frame can be used to detect the first signal light data broadcast by the RSU currently received.

[0059] In step S1033, image recognition is performed on the target image frame to obtain second signal light data corresponding to the first signal light data.

[0060] The image recognition method may be a neural network-based image recognition method or other visual processing methods, and the present disclosure does not specifically limit the image recognition method.

[0061] By performing this step to perform image recognition on the target image frame, the second signal light data used for detecting the currently received first signal light data can be obtained.

[0062] Figure 3 is based on Figure 2 The embodiment shown is a flow chart of a detection method, such as Figure 3 As shown, step S104 includes the following sub-steps: In step S1041, the target broadcast signal is parsed to obtain first signal light data.

[0063] The vehicle may parse the target broadcast signal based on the service broadcast protocol and obtain the first signal light data.

[0064] In step S1042, it is detected whether the first signal light data is consistent with the second signal light data corresponding to the first signal light data, and a first detection result is obtained.

[0065] The first detection result is a detection result obtained after the vehicle executes the detection step, and the first detection result indicates whether the first signal light data is consistent with the second signal light data corresponding to the first signal light data.

[0066] In the present disclosure, for each target broadcast signal received, first signal light data can be parsed from the target broadcast signal, and then the first signal light data corresponding to the first signal light data can be used to detect the first signal light data to determine whether the first signal light data and the second signal light data are consistent.

[0067] For example, assuming that the first signal light data and the second signal light data both include data in two dimensions: the light color of the signal light and the countdown. When determining whether the first signal light data and the second signal light data are consistent, it is necessary to make judgments in these two dimensions separately. That is, when it is determined that the light color in the first signal light data and the light color in the second signal light data are the same, and the countdown in the first signal light data and the countdown in the second signal light data are the same, it is determined that the first signal light data and the second signal light data are consistent. When the data in at least one dimension of the two dimensions are different, it can be regarded that the first signal light data and the second signal light data are inconsistent.

[0068] In addition, as described above, in one implementation, the target signal light is a group of signal lights in front of the vehicle, and the group of signal lights may include signal lights corresponding to multiple different lanes (such as a left turn light, a straight ahead light, and a right turn light as a group of signal lights, or a left turn light and a straight ahead light as a group of signal lights). In this case, image recognition is performed on the target image frame in the signal light video, and the obtained second signal light data may include signal light data corresponding to each signal light in the group of signal lights, and the first signal light data parsed from the target broadcast signal also includes signal light data corresponding to each signal light in the group of signal lights. In this way, in the process of detecting whether the first signal light data is consistent with the second signal light data corresponding to the first signal light data, it is necessary to perform detection on each signal light in the group of signal lights separately (for example, detecting whether the light color is consistent and whether the countdown is consistent). When the comparison results of the status data of each signal light in the group of signal lights are consistent, the first signal light data is deemed to be consistent with the second signal light data corresponding to the first signal light data.

[0069] In another implementation, the target signal light is a signal light corresponding to the target lane where the vehicle is currently located in a group of signal lights in front of the vehicle. For example, the target signal light is a straight-through light. In this case, since the target broadcast signal is a broadcast signal based on the target lane screening, the first signal light data parsed from the target broadcast signal only includes the signal light data of the straight-through light. However, the target image frame in the signal light video may also include image information of a group of signal lights in front of the vehicle. Therefore, the second signal light data obtained by performing image recognition on the target image frame may include signal light data of a group of signal lights in front of the vehicle (including the straight-through light). In order to detect the first signal light data corresponding to the straight-through light using the second signal light data, the target signal light data corresponding to the straight-through light can be determined from the second signal light data, and then the target signal light data and the first signal light data are compared to see if they are consistent to obtain the first detection result.

[0070] In the process of determining the target signal light data corresponding to the straight ahead light from the second signal light data, the second signal light data may include signal light data corresponding to different signal light identifiers, and the signal light identifier may be the position of the signal light (such as the middle, the left, or the right) or the name of the signal light. In this way, the target signal light data corresponding to the straight ahead light may be determined from the second signal light data based on the signal light identifier of the straight ahead light.

[0071] After determining the first detection result, the vehicle may also generate an inspection report according to the first detection result, wherein the inspection report includes the detection results corresponding to different collection timestamps.

[0072] In a possible implementation, the vehicle can record the first detection results corresponding to different collection timestamps in a preset inspection report. For each collection timestamp, the first detection result corresponding to the collection timestamp refers to the result obtained by the vehicle detecting the first signal light data corresponding to the collection timestamp. The first detection result can further include whether the first signal light data is consistent with the corresponding second signal light data. If the two are inconsistent, it can be recorded in the preset inspection report whether the two are different in light color or different in signal light countdown. In this way, the inspection report can be automatically generated based on the first detection result to avoid manual recording of the inspection results.

[0073] The above describes a specific embodiment of detecting the first signal light data broadcast by the RSU on the patrol vehicle side. In another possible implementation of the present disclosure, the patrol vehicle can also send the target broadcast signal and the second signal light data to the server so as to complete the automatic patrol of the first signal light data carried in the target broadcast signal on the server side.

[0074] During the execution of step S104, the inspection vehicle can send the target broadcast signal and the second signal light data corresponding to the first signal light data carried in the target broadcast signal to the server in pairs, so that the server can parse the target broadcast signal to obtain the first signal light data, and detect whether the first signal light data is consistent with the second signal light data corresponding to the first signal light data to obtain a second detection result.

[0075] After the inspection vehicle obtains the broadcast signals of multiple groups of traffic lights broadcast by the RSU, it can filter out the target broadcast signals corresponding to the target traffic lights corresponding to the target road based on the target road where the inspection vehicle is currently located, and then send the target broadcast signals and the second traffic light data obtained based on image recognition to the server in pairs in the form of structured data. The server can obtain the target broadcast signal based on protocol parsing in the cloud, extract the first traffic light data carried in the target broadcast signal, and compare the first traffic light data with the second traffic light data to obtain the second detection result, so as to realize automatic inspection of the traffic light data broadcast by the RSU on the server side.

[0076] In addition, a corresponding inspection report may be automatically generated on the server side, that is, the server may generate an inspection report according to the second detection result, and the inspection report includes detection results corresponding to different collection time stamps.

[0077] Among them, the specific implementation method of the server comparing the first signal light data and the second signal light data, and automatically generating the corresponding inspection report on the server side can refer to the method of automatic inspection and report generation with the inspection vehicle as the executor described in the above embodiment, which will not be repeated here.

[0078] It should also be noted that after the vehicle sends the target broadcast signal and the second signal light data corresponding to the first signal light data carried in the target broadcast signal to the server in pairs, the server can store the target broadcast signal and the second signal light data corresponding to the first signal light data carried in the target broadcast signal in pairs, and different data pairs correspond to different timestamps. In this way, the target broadcast signal and the second signal light data stored in pairs on the server can be used to correct the inspection results.

[0079] In another possible implementation, the inspection vehicle can also send the target image frame in the signal light video of the target signal light to the server, and the server stores the target image frame according to the acquisition timestamp, as well as the first signal light data broadcast by the RSU corresponding to the same timestamp as the target image frame, and is stored in pairs in the order of the acquisition timestamps, that is, different data pairs stored on the server correspond to different acquisition timestamps, and the same data pair includes the target image frame and the first signal light data broadcast by the RSU corresponding to the same timestamp as the target image frame. In this way, the data pair of the original data stored on the server can also be used to correct the inspection results. For example, if the user has objections to the inspection results, the original target image frame uploaded to the server and the first signal light data broadcast by the RSU can be retrieved, the first signal light data broadcast by the RSU can be converted into a signal light state, and then manually compared with the signal light state of the original target image frame. When it is determined that the inspection report record is wrong, the report can be manually corrected.

[0080] By adopting the above method, the automatic image recognition technology and RSU broadcast protocol analysis can be combined and applied to the automatic inspection of roadside equipment. The current complex process of manually filling in the inspection report after manual comparison can be solved, saving labor. From requiring two people, the inspector and the driver, to only one driver. At the same time, the RSU broadcast signal data and the traffic light video can be compared all the time. The RSU broadcast signal data is sent N times per second (such as 10 times per second). This comparison frequency cannot be completed manually, which can significantly improve the detection efficiency and detection accuracy.

[0081] Figure 4 is a block diagram of a detection device according to an exemplary embodiment, which can be applied to a vehicle, such as Figure 4 As shown, the device comprises: The first acquisition module 401 is used to acquire a signal light video of a target signal light in front of the road where the vehicle is traveling; A second acquisition module 402 is used to acquire a target broadcast signal of a roadside unit RSU of the driving road, wherein the target broadcast signal carries first signal light data sent by the target signal light to the RSU; An image recognition module 403 is used to perform image recognition on a target image frame in the traffic light video to obtain second traffic light data; The detection module 404 is used to detect the first signal light data according to the second signal light data; or, to send the target broadcast signal and the second signal light data to a server so that the server detects the first signal light data according to the second signal light data.

[0082] Optionally, the second acquisition module 402 is used to receive the broadcast signal of the RSU at a preset frequency, the broadcast signal carrying signal light data corresponding to multiple groups of signal lights; for each received broadcast signal, obtain the current location information of the vehicle; determine the target road where the vehicle is currently located based on the location information, and filter the broadcast signal according to the target road to obtain the target broadcast signal of the target signal light corresponding to the target road; or determine the target lane where the vehicle is currently located based on the location information, and filter the broadcast signal according to the target lane to obtain the target broadcast signal of the target signal light corresponding to the target lane, wherein the target road includes at least one target lane.

[0083] Optionally, the image recognition module 403 is used to obtain the acquisition timestamp of the first signal light data after parsing the target broadcast signal; use the image frame corresponding to the acquisition timestamp in the signal light video as the target image frame; perform image recognition on the target image frame to obtain the second signal light data corresponding to the first signal light data.

[0084] Optionally, the detection module 404 is used to obtain the first signal light data after parsing the target broadcast signal; detect whether the first signal light data is consistent with the second signal light data corresponding to the first signal light data to obtain a first detection result; generate an inspection report based on the first detection result, and the inspection report includes detection results corresponding to different acquisition timestamps.

[0085] Optionally, the detection module 404 is used to send the target broadcast signal and the second signal light data corresponding to the first signal light data carried in the target broadcast signal to the server in pairs, so that the server parses the target broadcast signal to obtain the first signal light data, and detects whether the first signal light data is consistent with the second signal light data corresponding to the first signal light data, to obtain a second detection result, so that the server generates an inspection report based on the second detection result, and the inspection report includes detection results corresponding to different collection timestamps.

[0086] Optionally, the detection module 404 is used to send the target broadcast signal and the second signal light data corresponding to the first signal light data carried in the target broadcast signal to the server in pairs, so that the server receives and stores the target broadcast signal and the second signal light data corresponding to the first signal light data carried in the target broadcast signal in pairs.

[0087] Optionally, the first acquisition module 401 is used to acquire the current location information of the vehicle; when it is determined that the vehicle currently enters a preset collection area based on the location information and a preset map, acquire the signal light video of the target signal light.

[0088] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0089] Figure 5 FIG. 1 is a block diagram of an electronic device according to an exemplary embodiment. Figure 5 As shown, the electronic device 500 may include: a processor 501 , a memory 502 . The electronic device 500 may also include one or more of a multimedia component 503 , an input / output (I / O) interface 504 , and a communication component 505 .

[0090] The processor 501 is used to control the overall operation of the electronic device 500 to complete all or part of the steps in the above-mentioned detection method. The memory 502 is used to store various types of data to support the operation of the electronic device 500. For example, these data may include instructions for any application or method used to operate on the electronic device 500, and application-related data, such as contact data, sent and received messages, pictures, audio, video, etc. The memory 502 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read-Only Memory, referred to as EPROM), programmable read-only memory (Programmable Read-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, magnetic disk or optical disk. The multimedia component 503 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in the memory 502 or sent through the communication component 505. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 504 provides an interface between the processor 501 and other interface modules, and the above-mentioned other interface modules may be a keyboard, a mouse, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 505 is used for wired or wireless communication between the electronic device 500 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G or 4G, or a combination of one or more of them, so the corresponding communication component 505 may include: Wi-Fi module, Bluetooth module, NFC module.

[0091] In an exemplary embodiment, the electronic device 500 can be implemented by one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), controllers, microcontrollers, microprocessors or other electronic components to perform the above-mentioned detection method.

[0092] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the above-mentioned detection method are implemented. For example, the computer-readable storage medium can be the above-mentioned memory 502 including program instructions, and the above-mentioned program instructions can be executed by the processor 501 of the electronic device 500 to complete the above-mentioned detection method.

[0093] In another exemplary embodiment, a computer program product is further provided. The computer program product includes a computer program executable by a processor. When the computer program is executed by the processor, the steps of the above detection method are implemented.

[0094] The preferred embodiments of the present disclosure are described in detail above in conjunction with the accompanying drawings; however, the present disclosure is not limited to the specific details in the above embodiments. Within the technical concept of the present disclosure, a variety of simple modifications can be made to the technical solution of the present disclosure, and these simple modifications all fall within the protection scope of the present disclosure.

[0095] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the present disclosure will not further describe various possible combinations.

[0096] In addition, various embodiments of the present disclosure may be arbitrarily combined, and as long as they do not violate the concept of the present disclosure, they should also be regarded as the contents disclosed by the present disclosure.

Claims

1. A detection method, characterized in that: Applied to a vehicle, the method comprises: Acquire a signal light video of a target signal light ahead of the road on which the vehicle is traveling; Acquire a target broadcast signal of a roadside unit RSU of the driving road, wherein the target broadcast signal carries first signal light data sent by the target signal light to the RSU; Performing image recognition on a target image frame in the traffic light video to obtain second traffic light data; detecting the first signal light data according to the second signal light data; Alternatively, the target broadcast signal and the second signal light data are sent to a server, so that the server detects the first signal light data according to the second signal light data.

2. The method according to claim 1, characterized in that The step of acquiring the target broadcast signal of the roadside unit RSU of the driving road comprises: receiving a broadcast signal of the RSU according to a preset frequency, wherein the broadcast signal carries signal light data corresponding to a plurality of groups of signal lights; For each received broadcast signal, obtaining the current location information of the vehicle; Determine the target road where the vehicle is currently located according to the location information, and filter the broadcast signal according to the target road to obtain the target broadcast signal of the target signal light corresponding to the target road; and / or, The target lane where the vehicle is currently located is determined according to the position information, and the broadcast signal is filtered according to the target lane to obtain the target broadcast signal of the target signal light corresponding to the target lane, wherein the target road includes at least one target lane.

3. The method according to claim 1, characterized in that: The performing image recognition on the target image frame in the traffic light video to obtain the second traffic light data comprises: After parsing the target broadcast signal, obtaining a collection timestamp of the first signal light data; Taking the image frame corresponding to the acquisition timestamp in the traffic light video as the target image frame; Performing image recognition on the target image frame to obtain the second signal light data corresponding to the first signal light data.

4. The method according to claim 3, characterized in that The detecting the first signal light data according to the second signal light data comprises: After parsing the target broadcast signal, acquiring the first signal light data; detecting whether the first signal light data is consistent with the second signal light data corresponding to the first signal light data, and obtaining a first detection result; The method further comprises: An inspection report is generated according to the first detection result, and the inspection report includes detection results corresponding to different collection timestamps.

5. The method according to claim 3, characterized in that: The sending the target broadcast signal and the second signal light data to the server so that the server detects the first signal light data according to the second signal light data comprises: sending the target broadcast signal and the second signal light data corresponding to the first signal light data carried in the target broadcast signal to the server in pairs, so that the server parses the target broadcast signal to obtain the first signal light data, and detects whether the first signal light data is consistent with the second signal light data corresponding to the first signal light data, to obtain a second detection result; The method further comprises: The server is enabled to generate an inspection report according to the second detection result, and the inspection report includes the detection results corresponding to different collection timestamps.

6. The method according to claim 3, characterized in that The sending the target broadcast signal and the second signal light data to the server comprises: The target broadcast signal and the second signal light data corresponding to the first signal light data carried in the target broadcast signal are sent to the server in pairs, so that the server receives and stores the target broadcast signal and the second signal light data corresponding to the first signal light data carried in the target broadcast signal in pairs.

7. The method according to claim 1, characterized in that The method of obtaining a signal light video of a target signal light ahead of the road on which the vehicle is traveling comprises: Obtaining the current location information of the vehicle; When it is determined that the vehicle currently enters a preset acquisition area according to the position information and the preset map, a signal light video of the target signal light is acquired.

8. A detection device, characterized in that: Applied to a vehicle, the device comprises: The first acquisition module is used to acquire a signal light video of a target signal light in front of the road where the vehicle is traveling; A second acquisition module is used to acquire a target broadcast signal of a roadside unit RSU of the driving road, wherein the target broadcast signal carries first signal light data sent by the target signal light to the RSU; An image recognition module, used for performing image recognition on a target image frame in the traffic light video to obtain second traffic light data; A detection module is used to detect the first signal light data according to the second signal light data; or, send the target broadcast signal and the second signal light data to a server so that the server detects the first signal light data according to the second signal light data.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method described in any one of claims 1 to 7 are implemented.

10. An electronic device, characterized in that: include: a memory having a computer program stored thereon; A processor, configured to execute the computer program in the memory to implement the steps of the method according to any one of claims 1 to 7.

Images