Two-wheeled motorcycle reverse detection method, device and system

Abstract

The present invention relates to the field of computer technology, and provides a method, device and system for detecting reverse traffic on a two-wheeled motorcycle. The method performs reverse traffic detection from different angles such as road signs, facial features, vehicle lights and the area of ​​the two sides, and can realize full-scene reverse traffic detection on the entire road, and make the final reverse traffic detection result more accurate and reliable. Moreover, the method does not require the use of GPS signals, and its application scenarios are not limited by unfavorable factors such as GPS signal strength, low accuracy or map data, and can be widely used in various traffic road scenarios.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method, device and system for detecting reverse movement of a two-wheeled electric motorcycle. Background Art

[0002] Traffic going against the flow refers to the behavior of vehicles or pedestrians not moving on the side of the road as required. Traffic going against the flow is extremely harmful to traffic safety, so it is crucial to detect and issue an alarm for traffic going against the flow.

[0003] The existing vehicle reverse driving detection method generally utilizes the Global Positioning System (GPS) to obtain the vehicle's driving trajectory, and compares the driving trajectory with a preset driving trajectory to achieve reverse driving detection.

[0004] Existing vehicle reverse detection methods cannot be applied in scenarios with weak GPS signals, low accuracy, or lack of map data, resulting in limited application scenarios. Summary of the invention

[0005] The present invention provides a two-wheeled electric motorcycle reverse running detection method, device and system, which are used to solve the defects existing in the prior art.

[0006] The present invention provides a method for detecting a two-wheeled electric motorcycle running in the wrong direction, comprising:

[0007] Acquire a front-view video stream when the speed of the two-wheeled motorcycle is greater than 0, and perform road sign detection, facial feature detection, and vehicle light detection on the image in the front-view video stream to obtain a first detection result, a second detection result, and a third detection result, respectively;

[0008] Based on the first detection result, determine the lane area formed by the target lane where the two-wheeled motorcycle is located and the lane in the same direction of the target lane, and calculate the left area area and the right area area of ​​the two-wheeled motorcycle in the lane area;

[0009] Comparing the size relationship between the area of ​​the left region and the area of ​​the right region, and performing a reverse driving detection on the two-wheeled motorcycle based on the first detection result, the second detection result, the third detection result and the comparison result, to obtain a first initial reverse driving result, a second initial reverse driving result, a third initial reverse driving result and a fourth initial reverse driving result;

[0010] Based on the first initial retrograde result, the second initial retrograde result, the third initial retrograde result and the fourth initial retrograde result, a final retrograde detection result of the two-wheeled electric motorcycle is determined.

[0011] According to a two-wheeled motorcycle wrong-way detection method provided by the present invention, the first detection result includes a road driving arrow mark;

[0012] The first initial retrograde result is obtained based on the following steps:

[0013] Determine a target road driving arrow mark in the target lane;

[0014] If there is at least one frame of image within the first preset time length in the front perspective video stream, and the target road driving arrow mark corresponding to the at least one frame of image points to the two-wheeled motorcycle, then it is determined that the first initial reverse driving result is that the two-wheeled motorcycle is driving in reverse.

[0015] According to a two-wheeled motorcycle wrong-way detection method provided by the present invention, the second detection result includes at least one of a facial feature and a back feature of a portrait;

[0016] The second initial retrograde result is obtained based on the following steps:

[0017] If the second detection results of the first preset number of frame images within the second preset time length in the front perspective video stream are all that the number of facial features is greater than the number of portrait back features, then the second initial reverse result is determined to be the reverse movement of the two-wheeled motorcycle.

[0018] According to a two-wheeled motorcycle wrong-way detection method provided by the present invention, the third detection result includes at least one of the presence of headlights, the presence of taillights, and the absence of headlights;

[0019] The third initial retrograde result is obtained based on the following steps:

[0020] If the third detection results of the second preset number of frame images within the third preset time length in the front perspective video stream are all that the number of headlights is greater than the number of taillights, then the third initial wrong-travel result is determined to be that the two-wheeled motorcycle is wrong-travelling.

[0021] According to a two-wheeled motorcycle wrong-way detection method provided by the present invention, the fourth initial wrong-way result is obtained based on the following steps:

[0022] If the comparison results corresponding to each frame image within the fourth preset time length in the front perspective video stream are all that the area of ​​the left region is smaller than the area of ​​the right region, then it is determined that the fourth initial reverse result is that the two-wheeled motorcycle is reversed.

[0023] According to a two-wheeled motorcycle wrong-way detection method provided by the present invention, the final wrong-way detection result of the two-wheeled motorcycle is determined based on the first initial wrong-way result, the second initial wrong-way result, the third initial wrong-way result and the fourth initial wrong-way result, and then comprises:

[0024] The voice prompt indicates that the two-wheeled motorcycle is in the reverse state.

[0025] According to a two-wheeled motorcycle wrong-way detection method provided by the present invention, the final wrong-way detection result of the two-wheeled motorcycle is determined based on the first initial wrong-way result, the second initial wrong-way result, the third initial wrong-way result and the fourth initial wrong-way result, and then comprises:

[0026] The front perspective video stream, the final retrograde detection result and the target user information of the two-wheeled electric motorcycle are sent to the central control device of the two-wheeled electric motorcycle, so that the central control device forwards the front perspective video stream, the final retrograde detection result and the target user information to the cloud server for storage.

[0027] The present invention also provides a two-wheeled electric motorcycle reverse running detection device, comprising:

[0028] The first detection module is used to obtain a front-view video stream when the speed of the two-wheeled motorcycle is greater than 0, and perform road sign detection, face feature detection and vehicle light detection on the image in the front-view video stream to obtain a first detection result, a second detection result and a third detection result respectively;

[0029] a calculation module, for determining, based on the first detection result, a lane area formed by a target lane where the two-wheeled motorcycle is located and a lane in the same direction as the target lane, and calculating a left area area and a right area area of ​​the two-wheeled motorcycle in the lane area;

[0030] a second detection module, for comparing the size relationship between the area of ​​the left region and the area of ​​the right region, and performing a reverse traffic detection on the two-wheeled motorcycle based on the first detection result, the second detection result, the third detection result and the comparison result, to obtain a first initial reverse traffic result, a second initial reverse traffic result, a third initial reverse traffic result and a fourth initial reverse traffic result;

[0031] The third detection module is used to determine the final wrong-travel detection result of the two-wheeled electric motorcycle based on the first initial wrong-travel result, the second initial wrong-travel result, the third initial wrong-travel result and the fourth initial wrong-travel result.

[0032] The present invention also provides a two-wheeled motorcycle reverse detection system, comprising: a camera, a voice alarm, a central control device of the two-wheeled motorcycle, a cloud server and the above-mentioned two-wheeled motorcycle reverse detection device;

[0033] The camera, the two-wheeled motorcycle reverse detection device, the central control device and the cloud server are connected in sequence, and the voice alarm is connected to the central control device;

[0034] The camera is arranged at the front of the two-wheeled motorcycle, and faces the front of the two-wheeled motorcycle. The camera is used to collect the front view video stream when the speed of the two-wheeled motorcycle is greater than 0;

[0035] The voice alarm is arranged on the two-wheeled motorcycle, and the central control device is used for controlling the voice alarm to give a voice prompt that the two-wheeled motorcycle is in a reverse state when the final reverse detection result of the two-wheeled motorcycle is reverse.

[0036] According to a two-wheeled motorcycle reverse detection system provided by the present invention, the central control device is also used for:

[0037] receiving a vehicle use request, wherein the vehicle use request carries target user information;

[0038] The final retrograde detection result corresponding to the target user information is queried in the cloud server, and if the final retrograde detection results for retrograde movement reach a preset number, at least one of the following steps is performed:

[0039] Reject the vehicle request;

[0040] Deducting the credit score corresponding to the target user information;

[0041] There are pending charges.

[0042] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a method for detecting wrong-way movement of a two-wheeled electric motorcycle as described in any one of the above is implemented.

[0043] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-described methods for detecting the wrong-way movement of a two-wheeled electric motorcycle.

[0044] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the method for detecting wrong-way movement of a two-wheeled electric motorcycle as described in any one of the above is implemented.

[0045] The present invention provides a method, device and system for detecting wrong-way traffic of a two-wheeled motorcycle. The method first obtains a front-view video stream when the speed of the two-wheeled motorcycle is greater than 0, and performs road sign detection, facial feature detection and headlight detection on the image in the front-view video stream to obtain a first detection result, a second detection result and a third detection result respectively; then, based on the first detection result, the lane area where the two-wheeled motorcycle is located is determined, and the left area area and the right area area of ​​the two-wheeled motorcycle in the lane area are calculated; then, the size relationship between the left area area and the right area area is compared, and based on the first detection result, the second detection result, the third detection result and the comparison result, the two-wheeled motorcycle is detected for wrong-way traffic, and a first initial wrong-way traffic result, a second initial wrong-way traffic result, a third initial wrong-way traffic result and a fourth initial wrong-way traffic result are obtained; finally, the first initial wrong-way traffic result, the second initial wrong-way traffic result, the third initial wrong-way traffic result and the fourth initial wrong-way traffic result are combined to determine the final wrong-way traffic detection result of the two-wheeled motorcycle. This method detects reverse traffic from different angles such as road signs, facial features, vehicle lights, and the area on both sides, which can achieve full-scene reverse traffic detection on the entire road and make the final reverse traffic detection result more accurate and reliable. Moreover, this method does not require the use of GPS signals, and its application scenarios are not limited by unfavorable factors such as GPS signal strength, low accuracy, or map data, and can be widely used in various traffic road scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on the drawings in the following description without paying any creative work.

[0047] Figure 1 It is a schematic flow chart of a two-wheeled motorcycle reverse running detection method provided by the present invention;

[0048] Figure 2 It is a schematic diagram of the flow chart of the two-wheeled motorcycle reverse running detection device provided by the present invention;

[0049] Figure 3 It is a structural schematic diagram of a two-wheeled electric motorcycle reverse running detection system provided by the present invention;

[0050] Figure 4 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0052] The existing vehicle reverse detection method cannot be applied in scenarios with weak GPS signals, low accuracy or lack of map data, resulting in limited application scenarios. To this end, an embodiment of the present invention provides a two-wheeled motorcycle reverse detection method that is not limited by application scenarios, thereby improving the accuracy and reliability of two-wheeled motorcycle reverse detection.

[0053] Figure 1 FIG. 1 is a flow chart of a method for detecting a two-wheeled motorcycle traveling in the wrong direction provided in an embodiment of the present invention. Figure 1 As shown, the method includes:

[0054] S1, obtaining a front-view video stream when the speed of the two-wheeled motorcycle is greater than 0, and performing road sign detection, face feature detection and vehicle light detection on the image in the front-view video stream to obtain a first detection result, a second detection result and a third detection result respectively;

[0055] S2, based on the first detection result, determining a lane area formed by a target lane where the two-wheeled motorcycle is located and a lane in the same direction as the target lane, and calculating a left area area and a right area area of ​​the two-wheeled motorcycle in the lane area;

[0056] S3, comparing the size relationship between the area of ​​the left region and the area of ​​the right region, and performing a reverse driving detection on the two-wheeled motorcycle based on the first detection result, the second detection result, the third detection result and the comparison result, to obtain a first initial reverse driving result, a second initial reverse driving result, a third initial reverse driving result and a fourth initial reverse driving result;

[0057] S4, determining a final wrong-travel detection result of the two-wheeled electric motorcycle based on the first initial wrong-travel result, the second initial wrong-travel result, the third initial wrong-travel result and the fourth initial wrong-travel result.

[0058] Specifically, the two-wheeled motorcycle reverse detection method provided in the embodiment of the present invention is implemented by a two-wheeled motorcycle reverse detection device, which can be a two-wheeled motorcycle reverse detection chip, and the device is installed at the front position of the two-wheeled motorcycle, which is not specifically limited here. The two-wheeled motorcycle reverse detection device can carry a camera, which is used to capture the front perspective video stream when the speed of the two-wheeled motorcycle is greater than 0. To facilitate night detection or detection on rainy days, the camera can be an infrared camera. The camera can be set at the front position of the two-wheeled motorcycle, and the camera faces the front of the two-wheeled motorcycle.

[0059] First, step S1 is executed to obtain the front view video stream when the speed of the two-wheeled motorcycle is greater than 0. When the speed is greater than 0, it means that the two-wheeled motorcycle is in the starting state and is moving on the road. Only then is there a need for reverse detection. The front view video stream refers to a collection of images of the front view of the two-wheeled motorcycle taken in real time.

[0060] Thereafter, by performing road sign detection, facial feature detection, and vehicle light detection on the image in the front view video stream, a first detection result, a second detection result, and a third detection result are obtained respectively. Road sign detection, facial feature detection, and vehicle light detection may be performed on each frame of the front view video stream to obtain a first detection result, a second detection result, and a third detection result. The front view video stream may also be sampled respectively, and road sign detection, facial feature detection, and vehicle light detection may be performed on each frame of the sampled video clip to obtain a first detection result, a second detection result, and a third detection result.

[0061] Road sign detection refers to determining road signs in an image, that is, obtaining a first detection result. Road signs may include road driving arrow signs, road center lines, and lane dividing lines, etc. Road sign detection can be achieved through the difference information of each road sign, which is not specifically limited here.

[0062] Facial feature detection refers to determining the facial features in an image, that is, obtaining the second detection result. In one frame of an image, there may be facial features of one or more people, or there may be back features of one or more people, or there may be facial features and back features of different people at the same time, or there may not be any facial features or back features of any person, depending on the actual situation. Facial feature detection can be obtained by extracting facial features from an image using a neural network model, or it can be achieved using other facial feature detection methods.

[0063] Here, the presence of one or more persons' facial features indicates that there are people coming towards you in the adjacent lane or in front, and the presence of one or more persons' back features indicates that there are people going in the adjacent lane or in front in the same direction as the two-wheeled motorcycle.

[0064] Vehicle light detection refers to determining the type of vehicle lights in an image, that is, obtaining the third detection result. Vehicle light types may include headlights and taillights. Usually, headlights are white or white with a yellowish tint, and taillights are red. Therefore, vehicle light detection can be achieved by using different types of vehicle light colors.

[0065] Here, the presence of headlights indicates that there is an oncoming vehicle in the adjacent lane or ahead, and the presence of taillights indicates that there is a vehicle in the adjacent lane or ahead traveling in the same direction as the two-wheeled motorcycle.

[0066] Then, step S2 is executed to determine the target lane where the two-wheeled motorcycle is located and the lane area formed by the same-direction lane in the target lane area according to the first detection result. The lane area refers to the area on the side of the center line of the road surface where the two-wheeled motorcycle is located, which can be determined by the position of the center line of the road surface in the first detection result, or by the road driving arrow mark in the first detection result combined with the lane dividing line.

[0067] Furthermore, combined with the position information of the two-wheeled motorcycle in the lane area, the left area and the right area of ​​the two-wheeled motorcycle in the lane area can be calculated.

[0068] Thereafter, step S3 is executed to compare the size relationship between the area of ​​the left region and the area of ​​the right region, and the comparison result includes that the area of ​​the left region is larger than the area of ​​the right region and the area of ​​the left region is smaller than the area of ​​the right region.

[0069] Furthermore, the reverse driving detection of the two-wheeled motorcycle can be performed based on the first detection result, the second detection result, the third detection result and the comparison result to obtain the first initial reverse driving result, the second initial reverse driving result, the third initial reverse driving result and the fourth initial reverse driving result. For example, if the target road driving arrow mark in the target lane where the two-wheeled motorcycle is located in the first detection result points to the two-wheeled motorcycle, then the first initial reverse driving result can be directly determined as reverse driving; if the target road driving arrow mark is along the front direction of the two-wheeled motorcycle, then the first initial reverse driving result can be directly determined as not reverse driving.

[0070] If the number of facial features in the second detection result is greater than the number of back features of the portrait, the second initial reverse result is determined to be that the two-wheeled motorcycle is reversed; if the number of facial features is less than the number of back features of the portrait, the second initial reverse result is determined to be that the two-wheeled motorcycle is not reversed. Here, the number of facial features represents the number of users facing the target user riding the two-wheeled motorcycle head-on, and the number of back features of the portrait represents the number of users facing the back of the target user riding the two-wheeled motorcycle.

[0071] If the number of headlights in the third detection result is greater than the number of taillights, the third initial reverse traffic result is determined to be that the two-wheeled motorcycle is reversed; if the number of headlights in the third detection result is less than the number of taillights, the third initial reverse traffic result is determined to be that the two-wheeled motorcycle is not reversed.

[0072] If the comparison result is that the area of ​​the left region is larger than the area of ​​the right region, the fourth initial retrograde result can be directly determined as not retrograde; if the comparison result is that the area of ​​the left region is smaller than the area of ​​the right region, the fourth initial retrograde result can be directly determined as retrograde.

[0073] Finally, execute step S4. Finally, execute step S4. Combine the first initial retrograde result, the second initial retrograde result, the third initial retrograde result and the fourth initial retrograde result to determine the final retrograde detection result of the two-wheeled electric motorcycle. For example, if at least one of the first initial retrograde result, the second initial retrograde result, the third initial retrograde result and the fourth initial retrograde result is that the two-wheeled electric motorcycle is traveling in the opposite direction, then determine that the final retrograde detection result is that the two-wheeled electric motorcycle is traveling in the opposite direction.

[0074] The method for detecting wrong-way traffic of a two-wheeled motorcycle provided in an embodiment of the present invention first obtains a front-view video stream when the speed of the two-wheeled motorcycle is greater than 0, and performs road sign detection, facial feature detection and headlight detection on the image in the front-view video stream to obtain a first detection result, a second detection result and a third detection result, respectively; then, based on the first detection result, the lane area where the two-wheeled motorcycle is located is determined, and the left area area and the right area area of ​​the two-wheeled motorcycle in the lane area are calculated; then, the size relationship between the left area area and the right area area is compared, and based on the first detection result, the second detection result, the third detection result and the comparison result, the two-wheeled motorcycle is detected to obtain a first initial wrong-way traffic result, a second initial wrong-way traffic result, a third initial wrong-way traffic result and a fourth initial wrong-way traffic result; finally, the first initial wrong-way traffic result, the second initial wrong-way traffic result, the third initial wrong-way traffic result and the fourth initial wrong-way traffic result are combined to determine the final wrong-way traffic detection result of the two-wheeled motorcycle. This method detects reverse traffic from different angles such as road signs, facial features, vehicle lights, and the area on both sides, which can achieve full-scene reverse traffic detection on the entire road and make the final reverse traffic detection result more accurate and reliable. Moreover, this method does not require the use of GPS signals, and its application scenarios are not limited by unfavorable factors such as GPS signal strength, low accuracy, or map data, and can be widely used in various traffic road scenarios.

[0075] On the basis of the above-mentioned embodiment, in the method for detecting wrong-way driving of a two-wheeled motorcycle provided in the embodiment of the present invention, the first detection result includes a road driving arrow mark;

[0076] The first initial retrograde result is obtained based on the following steps:

[0077] Determine a target road driving arrow mark in the target lane;

[0078] If there is at least one frame of image within the first preset time length in the front perspective video stream, and the target road driving arrow mark corresponding to the at least one frame of image points to the two-wheeled motorcycle, then it is determined that the first initial reverse driving result is that the two-wheeled motorcycle is driving in reverse.

[0079] Specifically, in an embodiment of the present invention, when the first detection result includes a road driving arrow mark, the target road driving arrow mark in the target lane can be determined first. The target road driving arrow mark can point to the two-wheeled motorcycle or be in the same direction as the front of the two-wheeled motorcycle.

[0080] In order to reduce the amount of calculation, a video clip of a first preset duration can be sampled from the front view video stream, and the first initial reverse result is determined within the first preset duration. The first preset duration can be 5s, that is, the judgment is made once every first preset duration. If there is at least one frame of image within the first preset duration, and its corresponding target road driving arrow mark points to the two-wheeled motorcycle, then the first initial reverse result is considered to be the two-wheeled motorcycle is reversed. Otherwise, if the target road driving arrow marks corresponding to each frame of image within the first preset duration do not point to the two-wheeled motorcycle, then the first initial reverse result is considered to be that the two-wheeled motorcycle is not reversed.

[0081] In the embodiment of the present invention, the first preset time length is introduced to reduce the amount of calculation and improve the efficiency of obtaining the first initial retrograde result.

[0082] Based on the above embodiment, in the two-wheeled motorcycle wrong-way detection method provided in the embodiment of the present invention, the second detection result includes at least one of a facial feature and a back feature of a portrait;

[0083] The second initial retrograde result is obtained based on the following steps:

[0084] If the second detection results of the first preset number of frame images within the second preset time length in the front perspective video stream are all that the number of facial features is greater than the number of portrait back features, then the second initial reverse result is determined to be the reverse movement of the two-wheeled motorcycle.

[0085] Specifically, in an embodiment of the present invention, when the second detection result includes at least one of facial features and portrait back features, in order to reduce detection errors and reduce the amount of calculation, a video segment of a second preset length is sampled from the front perspective video stream, and the second initial retrograde result is determined within the second preset length. The second preset length can be 5 minutes, that is, the judgment is made once every second preset length, and the judgment is reset before each judgment to avoid the previous judgment affecting the current judgment.

[0086] If the second detection results of the first preset number of frames of images within the second preset duration are all that the number of facial features is greater than the number of back features of the portrait, then the second initial retrograde result is considered to be a two-wheeled motorcycle retrograde. The first preset number can be set as needed, for example, it can be set to 6, that is, every 5 minutes, 6 frames of image second detection results are selected for judgment. The first preset number of frames of images can be randomly selected, or can be obtained by sampling at equal intervals from a 5-minute video clip, which is not specifically limited here.

[0087] Otherwise, if the second detection results of only some frames of the first preset number of frames within the second preset time period are that the number of facial features is greater than the number of portrait back features, then the second detection result of that the number of facial features is greater than the number of portrait back features is considered to be a case of misidentification or a reverse peak. At this time, the second initial reverse result is that the two-wheeled motorcycle is not reversing.

[0088] In the embodiment of the present invention, the introduction of the second preset duration and the first preset number can avoid the influence of misidentification or reverse peak on the second initial retrograde result, improve the accuracy and reliability of the second initial retrograde result. Moreover, the amount of calculation can be reduced, and the efficiency of obtaining the second initial retrograde result can be improved.

[0089] On the basis of the above-mentioned embodiment, in the two-wheeled motorcycle wrong-way detection method provided in the embodiment of the present invention, the third detection result includes at least one of the presence of headlights, the presence of taillights, and the absence of headlights;

[0090] The third initial retrograde result is obtained based on the following steps:

[0091] If the third detection results of the second preset number of frame images within the third preset time length in the front perspective video stream are all that the number of headlights is greater than the number of taillights, then the third initial wrong-travel result is determined to be that the two-wheeled motorcycle is wrong-travelling.

[0092] Specifically, in an embodiment of the present invention, when the third detection result includes at least one of the presence of headlights, the presence of taillights, and the absence of headlights, in order to reduce detection errors and reduce the amount of calculation, a video segment of a third preset duration is sampled from the front perspective video stream, and the third initial retrograde result is determined within the third preset duration. The third preset duration can be 1 minute, that is, the judgment is made once every third preset duration, and the judgment is reset before each judgment to avoid the previous judgment affecting the current judgment.

[0093] If the third detection results of the second preset number of frames of images within the third preset duration are all that the number of headlights is greater than the number of taillights, then the third initial wrong-way result is considered to be wrong-way driving of a two-wheeled motorcycle. The second preset number can be set as needed, for example, it can be set to 3, that is, every 1 minute, the third detection results of 3 frames of images are selected for judgment. The second preset number of frames of images can be randomly selected, or can be obtained by sampling at equal intervals from a video clip of 1 minute in length, which is not specifically limited here.

[0094] Otherwise, if the third detection result of only some frames of the second preset number of frames within the third preset time length is that the number of headlights is greater than the number of taillights, then it is considered that the third detection result of the number of headlights being greater than the number of taillights is a misidentification or a reverse peak situation. At this time, the third initial reverse result is that the two-wheeled motorcycle is not reversed.

[0095] In the embodiment of the present invention, the third preset duration and the second preset number are introduced to avoid the influence of misidentification or reverse peak on the third initial retrograde result, thereby improving the accuracy and reliability of the third initial retrograde result. Moreover, the amount of calculation can be reduced, thereby improving the efficiency of obtaining the third initial retrograde result.

[0096] On the basis of the above-mentioned embodiment, in the two-wheeled motorcycle wrong-way detection method provided in the embodiment of the present invention, the fourth initial wrong-way result is obtained based on the following steps:

[0097] If the comparison results corresponding to each frame image within the fourth preset time length in the front perspective video stream are all that the area of ​​the left region is smaller than the area of ​​the right region, then it is determined that the fourth initial reverse result is that the two-wheeled motorcycle is reversed.

[0098] Specifically, in an embodiment of the present invention, in order to reduce detection errors and reduce the amount of calculation, a video segment of a fourth preset duration is sampled from the front perspective video stream, and the fourth initial retrograde result is determined within the fourth preset duration. The fourth preset duration can be 5s, that is, the judgment is made once every fourth preset duration.

[0099] If the comparison results corresponding to each frame image within the fourth preset time length are all that the area of ​​the left region is smaller than the area of ​​the right region, it is considered that the fourth initial wrong-way result is that the two-wheeled motorcycle is wrong-way.

[0100] Otherwise, if the comparison results corresponding to only a few frames of images within the fourth preset time length show that the area of ​​the left region is smaller than the area of ​​the right region, it is considered that the comparison result that the area of ​​the left region is smaller than the area of ​​the right region is a misjudgment or a misoperation by the target user. At this time, the fourth initial reverse result is that the two-wheeled electric motorcycle is not reversed.

[0101] In the embodiment of the present invention, the fourth preset time length is introduced to avoid the influence of misjudgment or misoperation of the target user on the fourth initial retrograde result, thereby improving the accuracy and reliability of the fourth initial retrograde result. Moreover, the amount of calculation can be reduced, thereby improving the efficiency of obtaining the fourth initial retrograde result.

[0102] On the basis of the above-mentioned embodiment, the two-wheeled motorcycle wrong-way detection method provided in the embodiment of the present invention, the final wrong-way detection result of the two-wheeled motorcycle is determined based on the first initial wrong-way result, the second initial wrong-way result, the third initial wrong-way result and the fourth initial wrong-way result, and then comprises:

[0103] The voice prompt indicates that the two-wheeled motorcycle is in the reverse state.

[0104] Specifically, in an embodiment of the present invention, after determining the final wrong-travel detection result of a two-wheeled electric motorcycle, a voice prompt can be given that the two-wheeled electric motorcycle is in a wrong-travel state, so that the user can detect and correct it in time, thereby reducing the occurrence of traffic accidents caused by wrong-travel.

[0105] The two-wheeled motorcycle reverse detection device may be equipped with a voice module, and the two-wheeled motorcycle reverse detection device may also send the final reverse detection result to the central control device of the two-wheeled motorcycle when the final reverse detection result is reverse, so that the central control device controls the voice module of the two-wheeled motorcycle to give a voice prompt, which is not specifically limited here. Here, the voice module of the two-wheeled motorcycle may be a vehicle-mounted speaker.

[0106] On the basis of the above-mentioned embodiment, the two-wheeled motorcycle wrong-way detection method provided in the embodiment of the present invention, the final wrong-way detection result of the two-wheeled motorcycle is determined based on the first initial wrong-way result, the second initial wrong-way result, the third initial wrong-way result and the fourth initial wrong-way result, and then comprises:

[0107] The front perspective video stream, the final retrograde detection result and the target user information of the two-wheeled electric motorcycle are sent to the central control device of the two-wheeled electric motorcycle, so that the central control device forwards the front perspective video stream, the final retrograde detection result and the target user information to the cloud server for storage.

[0108] Specifically, in an embodiment of the present invention, after determining the final wrong-traffic detection result of the two-wheeled electric motorcycle, the front-view video stream, the final wrong-traffic detection result and the target user information of the two-wheeled electric motorcycle can also be sent to the central control device of the two-wheeled electric motorcycle. The central control device forwards the front-view video stream, the final wrong-traffic detection result and the target user information to the cloud server for storage, so as to facilitate the subsequent tracking of the target user's riding information, and can restrict the target user from riding the same type of two-wheeled electric motorcycle, deduct a certain credit score or generate a certain fine after the target user's wrong-traffic reaches a certain number of times.

[0109] like Figure 2 As shown, based on the above embodiments, a two-wheeled electric motorcycle reverse running detection device is provided in an embodiment of the present invention, comprising:

[0110] The first detection module 21 is used to obtain a front-view video stream when the speed of the two-wheeled motorcycle is greater than 0, and perform road sign detection, face feature detection and vehicle light detection on the image in the front-view video stream to obtain a first detection result, a second detection result and a third detection result respectively;

[0111] A calculation module 22, for determining a lane area formed by a target lane where the two-wheeled motorcycle is located and a lane in the same direction of the target lane based on the first detection result, and calculating a left area area and a right area area of ​​the two-wheeled motorcycle in the lane area;

[0112] The second detection module 23 is used to compare the size relationship between the area of ​​the left region and the area of ​​the right region, and perform a reverse driving detection on the two-wheeled motorcycle based on the first detection result, the second detection result, the third detection result and the comparison result, to obtain a first initial reverse driving result, a second initial reverse driving result, a third initial reverse driving result and a fourth initial reverse driving result;

[0113] The third detection module 24 is used to determine the final wrong-travel detection result of the two-wheeled electric motorcycle based on the first initial wrong-travel result, the second initial wrong-travel result, the third initial wrong-travel result and the fourth initial wrong-travel result.

[0114] On the basis of the above-mentioned embodiment, in the two-wheeled motorcycle wrong-way detection device provided in the embodiment of the present invention, the first detection result includes a road driving arrow mark;

[0115] The second detection module is specifically used for:

[0116] Determine a target road driving arrow mark in the target lane;

[0117] If there is at least one frame of image within the first preset time length in the front perspective video stream, and the target road driving arrow mark corresponding to the at least one frame of image points to the two-wheeled motorcycle, then it is determined that the first initial reverse driving result is that the two-wheeled motorcycle is driving in reverse.

[0118] Based on the above embodiment, in the two-wheeled motorcycle wrong-way detection device provided in the embodiment of the present invention, the second detection result includes at least one of a facial feature and a back feature of a portrait;

[0119] The second detection module is specifically used for:

[0120] If the second detection results of the first preset number of frame images within the second preset time length in the front perspective video stream are all that the number of facial features is greater than the number of portrait back features, then the second initial reverse result is determined to be the reverse movement of the two-wheeled motorcycle.

[0121] On the basis of the above-mentioned embodiment, in the two-wheeled motorcycle wrong-way detection device provided in the embodiment of the present invention, the third detection result includes at least one of the presence of headlights, the presence of taillights, and the absence of headlights;

[0122] The second detection module is specifically used for:

[0123] If the third detection results of the second preset number of frame images within the third preset time length in the front perspective video stream are all that the number of headlights is greater than the number of taillights, then the third initial wrong-travel result is determined to be that the two-wheeled motorcycle is wrong-travelling.

[0124] On the basis of the above-mentioned embodiments, in the two-wheeled electric motorcycle wrong-way detection device provided in the embodiments of the present invention, the second detection module is specifically used for:

[0125] If the comparison results corresponding to each frame image within the fourth preset time length in the front perspective video stream are all that the area of ​​the left region is smaller than the area of ​​the right region, then it is determined that the fourth initial reverse result is that the two-wheeled motorcycle is reversed.

[0126] On the basis of the above-mentioned embodiment, the two-wheeled motorcycle wrong-way detection device provided in the embodiment of the present invention further includes a voice prompt module for:

[0127] The voice prompt indicates that the two-wheeled motorcycle is in the reverse state.

[0128] On the basis of the above-mentioned embodiment, the two-wheeled electric motorcycle wrong-way detection device provided in the embodiment of the present invention further includes a sending module for:

[0129] The front perspective video stream, the final retrograde detection result and the target user information of the two-wheeled electric motorcycle are sent to the central control device of the two-wheeled electric motorcycle, so that the central control device forwards the front perspective video stream, the final retrograde detection result and the target user information to the cloud server for storage.

[0130] Specifically, the functions of each module in the two-wheeled electric motorcycle wrong-way detection device provided in the embodiment of the present invention correspond one-to-one to the operating procedures of each step in the above-mentioned method embodiment, and the effects achieved are also consistent. Please refer to the above-mentioned embodiment for details, and no further details will be given in the embodiment of the present invention.

[0131] like Figure 3 As shown, based on the above embodiments, a two-wheeled motorcycle wrong-way detection system is provided in an embodiment of the present invention, comprising: a camera 31, a central control device 32 of a two-wheeled motorcycle, a cloud server 33, a two-wheeled motorcycle wrong-way detection device 34 provided in the above embodiments, and a voice alarm 35;

[0132] The camera 31, the two-wheeled motorcycle reverse detection device 34, the central control device 32 and the cloud server 33 are connected in sequence;

[0133] The camera 31 is disposed at the front of the two-wheeled motorcycle, and the camera 31 faces the front of the two-wheeled motorcycle. The camera 31 is used to collect the front view video stream when the speed of the two-wheeled motorcycle is greater than 0;

[0134] The voice alarm 35 is arranged on the two-wheeled motorcycle, and the central control device 32 is used for controlling the voice alarm 35 to give a voice prompt that the two-wheeled motorcycle is in a reverse state when the final reverse detection result of the two-wheeled motorcycle is reverse.

[0135] Specifically, in the embodiment of the present invention, the camera 31 is arranged at the front position of the two-wheeled electric motorcycle, and the camera 31 is facing the front of the two-wheeled electric motorcycle. The camera 31 is used to collect the front perspective video stream when the speed of the two-wheeled electric motorcycle is greater than 0, and send the front perspective video stream to the two-wheeled electric motorcycle reverse detection device 34, so that the two-wheeled electric motorcycle reverse detection device 34 performs reverse detection and obtains the final reverse detection result of the two-wheeled electric motorcycle.

[0136] After that, if the final reverse detection result is reverse, the two-wheeled motorcycle reverse detection device 34 can send the final reverse detection result to the central control device 32, and the central control device 32 controls the voice alarm 35 to voice prompt that the two-wheeled motorcycle is in a reverse state. At the same time, the two-wheeled motorcycle reverse detection device 34 will also forward the front view video stream, the final reverse detection result, and the target user information of the two-wheeled motorcycle to the cloud server 33 through the central control device 32 for storage. Here, the voice alarm 35 can be a vehicle-mounted voice module, for example, a vehicle-mounted speaker.

[0137] On the basis of the above-mentioned embodiment, in the two-wheeled motorcycle reverse running detection system provided in the embodiment of the present invention, the central control device is further used for:

[0138] receiving a vehicle use request, wherein the vehicle use request carries target user information;

[0139] The final retrograde detection result corresponding to the target user information is queried in the cloud server, and if the final retrograde detection results for retrograde movement reach a preset number, at least one of the following steps is performed:

[0140] Reject the vehicle request;

[0141] Deducting the credit score corresponding to the target user information;

[0142] There are pending charges.

[0143] Specifically, in an embodiment of the present invention, the controller of a two-wheeled motorcycle can track the riding information of a target user, and can restrict the target user from riding similar two-wheeled motorcycles, deduct a certain credit score, or generate a certain fine after the target user's reverse driving reaches a certain number of times. That is, after the central control device receives a vehicle use request, it queries the cloud server for the final reverse driving detection result corresponding to the target user information carried in the vehicle use request. If the final reverse driving detection result for reverse driving reaches a preset number, it means that the target user has a credit problem, and the central control device further performs at least one of the following steps:

[0144] Reject the vehicle request;

[0145] Deducting the credit score corresponding to the target user information;

[0146] There are pending charges.

[0147] The preset number can be set as needed, for example, 3 times, 5 times, 10 times, etc. The credit score can be accumulated by whether the target user's riding behavior violates the rules, whether the vehicle is returned on time, whether the vehicle is paid on time, etc. When deducting the credit score, you can choose to deduct part of it or all of it. The fee to be paid is the fine for riding against the flow, which can be set according to the actual situation and is not specifically limited here.

[0148] In an embodiment of the present invention, the central control device can restrict the target user's vehicle use request based on the target user's historical retrograde behavior, thereby restricting his riding, thereby reducing the danger he creates on the road and reducing the harm he causes to other pedestrians on the road.

[0149] Figure 4 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 4 As shown, the electronic device may include: a processor (Processor) 410, a communication interface (Communications Interface) 420, a memory (Memory) 430 and a communication bus 440, wherein the processor 410, the communication interface 420, and the memory 430 communicate with each other through the communication bus 440. The processor 410 can call the logic instructions in the memory 430 to execute the two-wheeled motorcycle reverse detection method provided in the above-mentioned embodiments, the method comprising: obtaining the front perspective video stream when the speed of the two-wheeled motorcycle is greater than 0, and performing road sign detection, facial feature detection and vehicle light detection on the image in the front perspective video stream to obtain a first detection result, a second detection result and a third detection result respectively; based on the first detection result, determining the lane area formed by the target lane where the two-wheeled motorcycle is located and the same-direction lane of the target lane, and calculating the two-wheeled motorcycle in the lane area. The left area area and the right area area of ​​the vehicle; compare the size relationship between the left area area and the right area area, and perform a reverse detection on the two-wheeled motorcycle based on the first detection result, the second detection result, the third detection result and the comparison result, to obtain a first initial reverse result, a second initial reverse result, a third initial reverse result and a fourth initial reverse result; based on the first initial reverse result, the second initial reverse result, the third initial reverse result and the fourth initial reverse result, determine the final reverse detection result of the two-wheeled motorcycle.

[0150] In addition, the logic instructions in the above-mentioned memory 430 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program codes.

[0151] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the two-wheeled motorcycle wrong-way detection method provided in the above-mentioned embodiments, the method comprising: obtaining a front-view video stream when the speed of the two-wheeled motorcycle is greater than 0, and performing road sign detection, facial feature detection and vehicle light detection on the image in the front-view video stream to obtain a first detection result, a second detection result and a third detection result respectively; based on the first detection result, determining whether the target lane where the two-wheeled motorcycle is located is different from the target lane The lane area is composed of lanes in the same direction, and the left area area and the right area area of ​​the two-wheeled motorcycle in the lane area are calculated; the size relationship between the left area area and the right area area is compared, and based on the first detection result, the second detection result, the third detection result and the comparison result, the two-wheeled motorcycle is detected for wrong traffic, and the first initial wrong traffic result, the second initial wrong traffic result, the third initial wrong traffic result and the fourth initial wrong traffic result are obtained; based on the first initial wrong traffic result, the second initial wrong traffic result, the third initial wrong traffic result and the fourth initial wrong traffic result, the final wrong traffic detection result of the two-wheeled motorcycle is determined.

[0152] On the other hand, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the two-wheeled motorcycle wrong-way detection method provided in the above-mentioned embodiments, the method comprising: obtaining a front-view video stream when the speed of the two-wheeled motorcycle is greater than 0, and performing road sign detection, facial feature detection and vehicle light detection on the image in the front-view video stream to obtain a first detection result, a second detection result and a third detection result respectively; based on the first detection result, determining a lane area formed by a target lane where the two-wheeled motorcycle is located and a lane in the same direction of the target lane, and Calculate the left area and the right area of ​​the two-wheeled motorcycle in the lane area; compare the size relationship between the left area area and the right area area, and perform a reverse traffic detection on the two-wheeled motorcycle based on the first detection result, the second detection result, the third detection result and the comparison result, to obtain a first initial reverse traffic result, a second initial reverse traffic result, a third initial reverse traffic result and a fourth initial reverse traffic result; determine a final reverse traffic detection result of the two-wheeled motorcycle based on the first initial reverse traffic result, the second initial reverse traffic result, the third initial reverse traffic result and the fourth initial reverse traffic result.

[0153] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0154] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0155] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for detecting a two-wheeled motorcycle going in the wrong direction, It is characterized in that include: Acquire a front-view video stream when the speed of the two-wheeled motorcycle is greater than 0, and perform road sign detection, facial feature detection, and vehicle light detection on the image in the front-view video stream to obtain a first detection result, a second detection result, and a third detection result, respectively; Based on the first detection result, determine the lane area formed by the target lane where the two-wheeled motorcycle is located and the lane in the same direction of the target lane, and calculate the left area area and the right area area of ​​the two-wheeled motorcycle in the lane area; the lane area refers to the area on the side of the center line of the road surface where the two-wheeled motorcycle is located, which is determined by the position of the center line of the road surface in the first detection result, or by the road driving arrow mark in the first detection result combined with the lane dividing line; Comparing the size relationship between the area of ​​the left region and the area of ​​the right region, and performing a reverse driving detection on the two-wheeled motorcycle based on the first detection result, the second detection result, the third detection result and the comparison result, to obtain a first initial reverse driving result, a second initial reverse driving result, a third initial reverse driving result and a fourth initial reverse driving result; Based on the first initial retrograde result, the second initial retrograde result, the third initial retrograde result and the fourth initial retrograde result, a final retrograde detection result of the two-wheeled electric motorcycle is determined.

2. The method for detecting a two-wheeled motorcycle running in the wrong direction according to claim 1, It is characterized in that The first detection result includes a road driving arrow mark; The first initial retrograde result is obtained based on the following steps: Determine a target road driving arrow mark in the target lane; If there is at least one frame of image within the first preset time length in the front perspective video stream, and the target road driving arrow mark corresponding to the at least one frame of image points to the two-wheeled motorcycle, then it is determined that the first initial reverse driving result is that the two-wheeled motorcycle is driving in reverse.

3. The method for detecting a two-wheeled motorcycle running in the wrong direction according to claim 1, It is characterized in that The second detection result includes at least one of a facial feature and a back feature of a portrait; The second initial retrograde result is obtained based on the following steps: If the second detection results of the first preset number of frame images within the second preset time length in the front perspective video stream are all that the number of facial features is greater than the number of portrait back features, then the second initial reverse result is determined to be the reverse movement of the two-wheeled motorcycle.

4. The method for detecting a two-wheeled motorcycle running in the wrong direction according to claim 1, It is characterized in that The third detection result includes at least one of the following: the presence of headlights, the presence of taillights, and the absence of headlights; The third initial retrograde result is obtained based on the following steps: If the third detection results of the second preset number of frame images within the third preset time length in the front perspective video stream are all that the number of headlights is greater than the number of taillights, then the third initial wrong-travel result is determined to be that the two-wheeled motorcycle is wrong-travelling.

5. The method for detecting wrong-way movement of a two-wheeled electric motorcycle according to claim 1, It is characterized in that The fourth initial retrograde result is obtained based on the following steps: If the comparison results corresponding to each frame image within the fourth preset time length in the front perspective video stream are all that the area of ​​the left region is smaller than the area of ​​the right region, then it is determined that the fourth initial reverse result is that the two-wheeled motorcycle is reversed.

6. The method for detecting a two-wheeled motorcycle running in the wrong direction according to any one of claims 1 to 5, It is characterized in that The method of determining a final retrograde detection result of the two-wheeled motorcycle based on the first initial retrograde result, the second initial retrograde result, the third initial retrograde result and the fourth initial retrograde result, further comprises: The voice prompt indicates that the two-wheeled motorcycle is in the reverse state.

7. The method for detecting a two-wheeled motorcycle running in the wrong direction according to any one of claims 1 to 5, It is characterized in that The method of determining a final retrograde detection result of the two-wheeled motorcycle based on the first initial retrograde result, the second initial retrograde result, the third initial retrograde result and the fourth initial retrograde result, further comprises: The front perspective video stream, the final retrograde detection result and the target user information of the two-wheeled electric motorcycle are sent to the central control device of the two-wheeled electric motorcycle, so that the central control device forwards the front perspective video stream, the final retrograde detection result and the target user information to the cloud server for storage.

8. A two-wheeled motorcycle reverse detection device, It is characterized in that include: The first detection module is used to obtain a front-view video stream when the speed of the two-wheeled motorcycle is greater than 0, and perform road sign detection, face feature detection and vehicle light detection on the image in the front-view video stream to obtain a first detection result, a second detection result and a third detection result respectively; a calculation module, for determining, based on the first detection result, a lane area formed by a target lane where the two-wheeled motorcycle is located and a lane in the same direction as the target lane, and calculating an area of ​​a left area and an area of ​​a right area of ​​the two-wheeled motorcycle within the lane area; the lane area refers to an area on one side of a center line of a road surface where the two-wheeled motorcycle is located, determined by a position of a center line of a road surface in the first detection result, or determined by a road driving arrow mark in the first detection result in combination with a lane dividing line; a second detection module, for comparing the size relationship between the area of ​​the left region and the area of ​​the right region, and performing a reverse traffic detection on the two-wheeled motorcycle based on the first detection result, the second detection result, the third detection result and the comparison result, to obtain a first initial reverse traffic result, a second initial reverse traffic result, a third initial reverse traffic result and a fourth initial reverse traffic result; The third detection module is used to determine the final wrong-travel detection result of the two-wheeled electric motorcycle based on the first initial wrong-travel result, the second initial wrong-travel result, the third initial wrong-travel result and the fourth initial wrong-travel result.

9. A two-wheeled motorcycle reverse detection system, It is characterized in that include: A camera, a voice alarm, a central control device of a two-wheeled motorcycle, a cloud server and a two-wheeled motorcycle reverse detection device as claimed in claim 8; The camera, the two-wheeled motorcycle reverse detection device, the central control device and the cloud server are connected in sequence, and the voice alarm is connected to the central control device; The camera is arranged at the front of the two-wheeled motorcycle, and faces the front of the two-wheeled motorcycle. The camera is used to collect the front view video stream when the speed of the two-wheeled motorcycle is greater than 0; The voice alarm is arranged on the two-wheeled motorcycle, and the central control device is used for controlling the voice alarm to give a voice prompt that the two-wheeled motorcycle is in a reverse state when the final reverse detection result of the two-wheeled motorcycle is reverse.

10. The two-wheeled motorcycle wrong-way detection system according to claim 9, It is characterized in that The central control device is also used for: receiving a vehicle use request, wherein the vehicle use request carries target user information; The final retrograde detection result corresponding to the target user information is queried in the cloud server, and if the final retrograde detection results for retrograde movement reach a preset number, at least one of the following steps is performed: Reject the vehicle request; Deducting the credit score corresponding to the target user information; There are pending charges.

Images