Yaw identification method and device of vehicle

Abstract

The invention provides a yaw identification method and device of a vehicle, and relates to the technical field of artificial intelligence, in particular to the technical fields of image processing, map navigation, automatic driving, intelligent traffic and the like. According to the specific implementation scheme, the method comprises the steps of determining a pixel value of a vehicle front image of a target vehicle in response to detection that the target vehicle runs to a preset distance range of a tunnel entrance; based on the pixel values of the plurality of images in front of the vehicle and the image acquisition time, determining the change trend of the pixel values; determining whether the target vehicle is driven into the tunnel based on the change trend of the pixel values; and in response to determining that the target vehicle is driven into the tunnel and the current planned path of the target vehicle does not include the tunnel, determining that the target vehicle is yawed. According to the mode, the timeliness and reliability of vehicle yaw recognition are effectively improved.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, specifically to technical fields such as image processing, map navigation, automatic driving, and intelligent transportation, and more particularly to a vehicle yaw recognition method and device. Background Art

[0002] In tunnels, due to the influence of terrain and tunnel shielding, GPS (Global Positioning System) signals often become weak or even completely fail, causing the GPS-based yaw judgment system to fail to work properly. Summary of the invention

[0003] Embodiments of the present disclosure provide a vehicle deviation identification method, device, equipment, and storage medium.

[0004] In a first aspect, an embodiment of the present disclosure provides a vehicle deviation identification method, the method comprising: in response to detecting that a target vehicle travels within a preset distance range of a tunnel entrance, determining a pixel value of a vehicle front image of the target vehicle; based on the pixel values ​​of multiple vehicle front images and image acquisition time, determining a changing trend of the pixel values; based on the changing trend of the pixel values, determining whether the target vehicle enters a tunnel; in response to determining that the target vehicle enters a tunnel and the tunnel is not included in the currently planned path of the target vehicle, determining that the target vehicle is yawed.

[0005] In a second aspect, an embodiment of the present disclosure provides a vehicle deviation identification device, which includes: a pixel determination module, a trend determination module, a tunnel determination module and a yaw determination module, wherein the pixel determination module is configured to determine the pixel value of the vehicle front image of the target vehicle in response to detecting that the target vehicle travels to a preset distance range of a tunnel entrance; the trend determination module is configured to determine the changing trend of the pixel value based on the pixel values ​​of multiple vehicle front images and the image acquisition time; the tunnel determination module is configured to determine whether the target vehicle enters a tunnel based on the changing trend of the pixel value; the yaw determination module is configured to determine the yaw of the target vehicle in response to determining that the target vehicle enters a tunnel and the tunnel is not included in the current planned path of the target vehicle.

[0006] In a third aspect, an embodiment of the present disclosure provides an electronic device, comprising one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by the one or more processors, the one or more processors implement a vehicle yaw recognition method as in any embodiment of the first aspect.

[0007] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable medium having a computer program stored thereon, which, when executed by a processor, implements a vehicle yaw identification method as in any embodiment of the first aspect.

[0008] In a fifth aspect, an embodiment of the present disclosure provides a computer program product, including a computer program, which, when executed by a processor, implements a vehicle yaw identification method as in any embodiment of the first aspect.

[0009] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 is an exemplary system architecture diagram in which the present disclosure may be applied;

[0011] Figure 2 is a flow chart of an embodiment of a vehicle deviation identification method according to the present disclosure;

[0012] Figure 3 is a flow chart of another embodiment of a vehicle deviation identification method according to the present disclosure;

[0013] Figure 4a is a schematic diagram of an application scenario of the vehicle yaw identification method according to the present disclosure;

[0014] Figure 4b is a schematic diagram of another application scenario of the vehicle yaw identification method according to the present disclosure;

[0015] Figure 5 is a schematic diagram of an embodiment of a vehicle deviation identification device according to the present disclosure;

[0016] Figure 6 It is a schematic diagram of the structure of a computer system suitable for implementing the electronic device of the embodiment of the present disclosure. DETAILED DESCRIPTION

[0017] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0018] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present disclosure may be combined with each other. The present disclosure will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0019] Figure 1 An exemplary system architecture 100 is shown to which an embodiment of the vehicle deviation identification method of the present disclosure may be applied.

[0020] like Figure 1 As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0021] Users can use terminal devices 101 , 102 , 103 to interact with server 105 via network 104 to receive or send messages, etc.

[0022] The terminal devices 101, 102, 103 may be hardware or software. When the terminal devices 101, 102, 103 are software, they may be installed in the electronic devices listed above. They may be implemented as multiple software or software modules, or as a single software or software module. No specific limitation is made here.

[0023] The server 105 may be a server that provides various services, for example, in response to detecting that the target vehicle is traveling within a preset distance range of a tunnel entrance, determining a pixel value of a vehicle front image of the target vehicle; determining a changing trend of the pixel values ​​based on the pixel values ​​of a plurality of vehicle front images and the image acquisition time; determining whether the target vehicle has entered a tunnel based on the changing trend of the pixel values; and determining that the target vehicle is yawed in response to determining that the target vehicle has entered a tunnel and the tunnel is not included in the currently planned path of the target vehicle.

[0024] It should be noted that the server 105 can be hardware or software. When the server 105 is hardware, it can be implemented as a distributed server cluster consisting of multiple servers, or it can be implemented as a single server. When the server is software, it can be implemented as multiple software or software modules (for example, used to provide vehicle deviation identification services), or it can be implemented as a single software or software module. No specific limitation is made here.

[0025] It should be noted that the vehicle deviation identification method provided in the embodiments of the present disclosure can be executed by the server 105, or by the terminal devices 101, 102, 103, or by the server 105 and the terminal devices 101, 102, 103 cooperating with each other. Accordingly, the various parts (such as various units, sub-units, modules, sub-modules) included in the vehicle deviation identification device can be all set in the server 105, or all set in the terminal devices 101, 102, 103, or respectively set in the server 105 and the terminal devices 101, 102, 103.

[0026] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to the implementation requirements.

[0027] Figure 2 The process 200 of an embodiment of a vehicle deviation identification method is shown. The vehicle deviation identification method may specifically include the following steps:

[0028] Step 201 , in response to detecting that a target vehicle is traveling within a preset distance range of a tunnel entrance, determining a pixel value of a vehicle front image of the target vehicle.

[0029] In this embodiment, the execution subject (for example, Figure 1 The server 105 or the terminal devices 101, 102, 103) can obtain the current position of the target vehicle in real time or periodically via sensor devices, such as GPS, GNSS (Global Navigation Satellite System), etc.

[0030] Furthermore, the execution entity may determine the road network structure of the area where the current location is located in a pre-stored map according to the current location.

[0031] The road network structure may include a plurality of road sections and connection relationships between the road sections, and each road section may be a tunnel section or a non-tunnel section.

[0032] Furthermore, the execution entity may determine whether the target vehicle has traveled to within a preset distance range of the tunnel entrance according to the current position and the road network structure.

[0033] Among them, the preset distance can be 100 meters, 200 meters, etc., and this application does not limit this.

[0034] If the target vehicle travels within a preset distance range of the tunnel entrance, the execution entity can obtain the front image of the target vehicle through an image acquisition device installed on the target vehicle, such as a front-view camera, a driving recorder, etc., and determine the pixel value of the front image of the vehicle.

[0035] Among them, the pixel value of the image in front of the vehicle can be the pixel value of all pixels in the image, or it can be the pixel value of a specified area of ​​the image in front of the vehicle (for example, the pixel points in the upper left area, the pixel points in the upper right area, etc.), and this application does not limit this.

[0036] Specifically, the pixel value of the image in front of the vehicle can be represented by the average value of the pixel values ​​of all pixels in the image.

[0037] Step 202 : determining a change trend of pixel values ​​based on the pixel values ​​of a plurality of vehicle front images and the image acquisition time.

[0038] In this embodiment, the execution entity may arrange the pixel values ​​of the plurality of vehicle front images according to the image acquisition time corresponding to each vehicle front image, and determine the change trend of the pixel values ​​over time based on the arranged pixel values.

[0039] Here, the plurality of vehicle front images may be obtained according to an image sequence captured by an image capture device, and the time interval between adjacent images in the plurality of vehicle front images arranged according to the image capture time is generally greater than or equal to the time interval between adjacent images in the image sequence.

[0040] Among them, the pixel value can be a color value or a brightness value determined based on the color value, and the changing trend of the pixel value can be the changing trend of the color value or the changing trend of the brightness value, which is not limited in this application.

[0041] Step 203: Determine whether the target vehicle enters a tunnel based on the change trend of the pixel value.

[0042] In this embodiment, the execution entity may match the changing trend of the pixel value with the preset pixel value changing rule. If the two match, it can be determined that the target vehicle has entered the tunnel. If the two do not match, it can be determined that the target vehicle has not entered the tunnel.

[0043] The preset pixel value change rule may be generally associated with the acquisition environment information, the acquisition quantity and acquisition quality of the images in front of the vehicle, etc.

[0044] Specifically, the pixel value is a brightness value, and the preset pixel value change rule can be that the change trend of the brightness value is increasing, and the total increase value is greater than or equal to a first preset value; it can also be that the change trend of the brightness value is decreasing, and the total decrease value is greater than or equal to a second preset value. This application does not limit this.

[0045] Step 204 : In response to determining that the target vehicle enters a tunnel and the current planned path of the target vehicle does not include the tunnel, determining that the target vehicle is yawed.

[0046] In this embodiment, after determining that the target vehicle has entered a tunnel, the execution subject may further determine whether the current planned path of the target vehicle includes the tunnel. If not, it may be determined that the target vehicle has deviated.

[0047] In some optional implementations of this embodiment, after determining that the target vehicle is yawed, the execution entity may output yaw warning information.

[0048] Among them, the output methods of the alarm information may include multiple methods, such as sound warning, visual warning, vibration warning, etc.

[0049] The vehicle deviation identification method provided by the embodiment of the present disclosure first determines the pixel value of the vehicle front image of the target vehicle in response to detecting that the target vehicle is within a preset distance range of the tunnel entrance, and then determines the change trend of the pixel value based on the pixel value of multiple vehicle front images and the image acquisition time, and determines whether the target vehicle enters the tunnel based on the change trend of the pixel value. If it is determined that the target vehicle enters the tunnel and the tunnel is not included in the current planned path of the target vehicle, the target vehicle is determined to be yawed. Under the condition of weak GPS signal strength, it is realized to directly identify whether the vehicle is yawed based on the vehicle front image collected by the vehicle-mounted image device, thereby improving the timeliness and reliability of vehicle deviation identification.

[0050] In some optional embodiments, the method also includes: determining a lane group detection result based on multiple vehicle front images; determining a first result of whether the target vehicle enters the tunnel based on the lane group detection result and the map lane information of the tunnel; and determining whether the target vehicle enters the tunnel based on a changing trend of pixel values, including: determining a second result of whether the target vehicle enters the tunnel based on a changing trend of pixel values; determining whether the target vehicle enters the tunnel based on the first result and the second result.

[0051] In this implementation, the execution entity may use lane line detection algorithms in existing technologies or future development technologies, such as edge detection, image segmentation, etc., to detect lane lines in images in front of multiple vehicles and determine lane group detection results.

[0052] Furthermore, the execution entity may match the lane group detection result with the map lane information of the tunnel. If the two match (for example, the lane group detection result and the map lane information are both three lanes), the first result of whether the target vehicle enters the tunnel is entering the tunnel; if the two do not match (for example, the lane group detection result is two lanes, and the map lane information is a single lane), the first result of whether the target vehicle enters the tunnel is not entering the tunnel.

[0053] Furthermore, the execution entity may match the changing trend of the pixel value with a preset pixel value changing rule. If the two match, the second result of whether the target vehicle enters the tunnel is entering the tunnel; if the two do not match, the second result of whether the target vehicle enters the tunnel is not entering the tunnel.

[0054] Furthermore, the execution entity may determine whether the target vehicle enters a tunnel according to the first result and the second result.

[0055] Specifically, if the first result and the second result are both entering a tunnel, it can be determined that the target vehicle has entered a tunnel; if the first result and the second result are both not entering a tunnel, it can be determined that the target vehicle has not entered a tunnel; if the first result and the second result are different, such as the first result is entering a tunnel and the second result is not entering a tunnel, then it can be determined whether the target vehicle has entered a tunnel based on the first result, the second result, the first confidence level corresponding to the first result, and the second confidence level corresponding to the second result.

[0056] The first confidence level and the second confidence level may be determined based on current environmental information, such as weather information, road condition information, and the like.

[0057] This implementation method determines the lane group detection result based on multiple vehicle front images; determines the first result of whether the target vehicle enters the tunnel based on the lane group detection result and the map lane information of the tunnel; determines the second result of whether the target vehicle enters the tunnel based on the change trend of the pixel value; determines whether the target vehicle enters the tunnel based on the first result and the second result, thereby realizing the use of the lane group detection result to assist in judging whether the target vehicle enters the tunnel, thereby further improving the accuracy of the recognition result.

[0058] In some optional embodiments, the method further includes: determining the current driving path of the target vehicle based on the positioning information of the target vehicle and the inertial measurement information of the target vehicle; determining a third result of whether the target vehicle enters a tunnel based on the current driving path; determining whether the target vehicle enters a tunnel based on the first result and the second result, including: determining whether the target vehicle enters the tunnel based on the first result, the second result and the third result.

[0059] In this implementation, the execution entity can determine the positioning information and inertial measurement information of the target vehicle through sensor equipment, such as GPS, GNSS, IMU (Inertial measurement unit), etc., and determine the current driving path of the target vehicle based on the positioning information and inertial measurement information of the target vehicle.

[0060] Furthermore, the execution entity may determine a third result of whether the target vehicle enters a tunnel according to the current driving path.

[0061] Furthermore, the execution entity may determine whether the target vehicle enters a tunnel according to the first result, the second result, and the third result.

[0062] Specifically, if the first result, the second result and the third result are all entering a tunnel, it can be determined that the target vehicle has entered a tunnel; if the first result, the second result and the third result are all not entering a tunnel, it can be determined that the target vehicle has not entered a tunnel; if the first result, the second result and the third result are not exactly the same, such as the first result and the third result are entering a tunnel, and the second result is not entering a tunnel, then it can be determined whether the target vehicle has entered a tunnel based on the first result, the second result, the third result, the first confidence level corresponding to the first result, the second confidence level corresponding to the second result, and the third confidence level corresponding to the third result.

[0063] Among them, the first confidence level, the second confidence level, and the third confidence level can be determined according to current environmental information, such as weather information, road condition information, and the external environment of the tunnel.

[0064] This implementation method determines the current driving path of the target vehicle based on the positioning information of the target vehicle and the inertial measurement information of the target vehicle; determines the third result of whether the target vehicle enters a tunnel based on the current driving path; determines whether the target vehicle enters a tunnel based on the first result, the second result and the third result, thereby realizing the use of lane group detection results, positioning information and inertial measurement information to assist in judging whether the target vehicle enters a tunnel, thereby further improving the accuracy of the recognition results.

[0065] In some optional embodiments, the method also includes: determining a fourth result of whether the target vehicle enters a tunnel based on changes in signal strength of the global positioning system; determining whether the target vehicle enters a tunnel based on the first result, the second result, and the third result, including: determining whether the target vehicle enters a tunnel based on the first result, the second result, the third result, and the fourth result.

[0066] In this implementation, the execution entity may determine the fourth result of whether the target vehicle enters a tunnel according to a change in the signal strength of the global positioning system.

[0067] Specifically, if the signal strength weakens and the weakening amplitude is greater than a preset amplitude value, the fourth result can be determined as entering a tunnel; if the signal strength does not change or the weakening amplitude is less than or equal to the preset amplitude value, the fourth result can be determined as not entering a tunnel.

[0068] Furthermore, the execution entity may determine whether the target vehicle enters the tunnel according to the first result, the second result, the third result and the fourth result.

[0069] Specifically, if the first result, the second result, the third result and the fourth result are all entering a tunnel, it can be determined that the target vehicle has entered a tunnel; if the first result, the second result, the third result and the fourth result are all not entering a tunnel, it can be determined that the target vehicle has not entered a tunnel; if the first result, the second result, the third result and the fourth result are not exactly the same, such as the first result and the third result are entering a tunnel, and the second result and the fourth result are not entering a tunnel, then it can be determined whether the target vehicle has entered a tunnel based on the first result, the second result, the third result, the fourth result and the first confidence level corresponding to the first result, the second confidence level corresponding to the second result, the third confidence level corresponding to the third result and the fourth confidence level corresponding to the fourth result.

[0070] Among them, the first confidence level, the second confidence level, the third confidence level, and the fourth confidence level can be determined based on current environmental information, such as weather information, road condition information, and the external environment of the tunnel.

[0071] This implementation method determines the fourth result of whether the target vehicle enters the tunnel based on the signal strength change of the global positioning system; determines whether the target vehicle enters the tunnel based on the first result, the second result, the third result and the fourth result, thereby realizing the use of the signal strength change of the global positioning system, the lane group detection result, the positioning information and the inertial measurement information to assist in judging whether the target vehicle enters the tunnel, thereby further improving the accuracy of the recognition result.

[0072] In some optional methods, the target vehicle is detected to be within a preset distance range of the tunnel entrance by: determining the connection relationship between the current position and the road section ahead of the current position based on the current position of the target vehicle, the driving direction, and the road network structure of the area where the current position is located; determining the probability value of the target vehicle entering each road section ahead based on the lane information and connection relationship corresponding to the previous position; in response to determining that the road section ahead with a probability value greater than or equal to a preset threshold is a tunnel section, determining that the target vehicle is within a preset distance range of the tunnel entrance.

[0073] In this implementation, the execution entity can determine the current position and driving direction of the target vehicle based on GPS, GNSS, etc., and determine the road network structure of the area where the current position is located in the pre-stored map based on the current position.

[0074] Furthermore, the execution entity may determine the connection relationship between the current position and the road section ahead of the current position according to the current position, the driving direction, and the road network structure of the area where the current position is located.

[0075] Furthermore, the execution entity may input the lane information and connection relationship corresponding to the current position into a preset prediction model to determine the probability value of the target vehicle entering each forward road section.

[0076] Among them, the prediction model can be trained based on the historical driving path samples of the target vehicle on the same road section.

[0077] Furthermore, the execution subject may determine whether the road section ahead with a probability value greater than or equal to a preset threshold is a tunnel section. If so, it may be determined that the target vehicle is within a preset distance range from the tunnel entrance.

[0078] This implementation method determines the connection relationship between the current position and the road section ahead of the current position according to the current position of the target vehicle, the driving direction and the road network structure of the area where the current position is located; determines the probability value of the target vehicle entering each road section ahead according to the lane information and the connection relationship corresponding to the previous position; in response to determining that the road section ahead with a probability value greater than or equal to a preset threshold is a tunnel section, determines that the target vehicle travels to within a preset distance range of the tunnel entrance, thereby realizing the determination of whether the vehicle enters the preset distance range of the tunnel entrance based on the predicted driving-in probability, which helps to timely collect the image in front of the vehicle and identify whether the vehicle has deviated based on the image in front of the vehicle in the scenario where the fork is close to the tunnel, thereby improving the timeliness and effectiveness of deviation identification.

[0079] In some optional embodiments, determining the pixel value of the vehicle front image of the target vehicle includes: determining the pixel value of the vehicle front image of the target vehicle collected by a driving recorder.

[0080] In this implementation, the execution entity may collect the image in front of the vehicle via a driving recorder installed on the target vehicle, and determine the pixel value of the image in front of the vehicle.

[0081] Among them, a driving recorder is a device installed on a car (usually installed at the top center of the front windshield or on the right side near the rearview mirror) to record video and audio during the vehicle's driving process to record various situations during driving. The image in front of the vehicle captured by the driving recorder can be a color image or a grayscale image.

[0082] This implementation method collects the image in front of the vehicle through a driving recorder and determines the pixel value of the image in front of the vehicle. It takes advantage of the fact that the driving recorder is installed at a high position and is usually installed in front of the vehicle. It can capture the image in front of the vehicle in time and then determine the trend of pixel value changes, effectively improving the timeliness of deviation identification.

[0083] In some optional embodiments, the method further includes: in response to determining that the target vehicle is yawed, modifying the current planned path according to a tunnel identifier of the tunnel and a destination of the target vehicle to generate a new planned path.

[0084] In this implementation, after determining that the target vehicle has deviated, the execution subject may modify the current planned path according to the tunnel identification of the tunnel and the destination of the target vehicle in the planned path to generate a new planned path.

[0085] This implementation method corrects the current planned path in response to determining the deviation of the target vehicle and generates a new planned path according to the tunnel identification of the tunnel and the destination of the target vehicle, which helps to correct the planned path in time.

[0086] Further references Figure 3 , which shows Figure 2 The process 300 of another embodiment of the vehicle deviation identification method is shown. In this embodiment, the process 300 of the vehicle deviation identification method may include the following steps:

[0087] Step 301 , in response to detecting that a target vehicle has traveled within a preset distance range of a tunnel entrance, determining pixel values ​​of a designated area of ​​a vehicle front image of the target vehicle.

[0088] In this embodiment, the execution entity can determine whether the target vehicle has traveled to within a preset distance range of the tunnel entrance according to the current position and the road network structure.

[0089] If so, the execution entity may obtain the vehicle front image of the target vehicle via an image acquisition device, such as a front-view camera, a driving recorder, etc., and determine the pixel value of a specified area of ​​the vehicle front image.

[0090] The designated area may include multiple rows, for example, 3 rows, 5 rows, etc., of pixels adjacent to the upper edge of the image.

[0091] Here, the pixel value of the specified area can be represented by the pixel value of all the pixels in the specified area, or by the average of the pixel values ​​of all the pixels in the specified area, which is not limited in the present application.

[0092] Step 302 : determining a change trend of pixel values ​​based on the pixel values ​​of a plurality of vehicle front images and the image acquisition time.

[0093] In this embodiment, the implementation details and technical effects of step 302 can refer to the description of step 202 and will not be repeated here.

[0094] Step 303: Determine whether the target vehicle enters a tunnel based on the change trend of the pixel value.

[0095] In this embodiment, the implementation details and technical effects of step 303 can refer to the description of step 203, which will not be repeated here.

[0096] Step 304 : In response to determining that the target vehicle enters a tunnel and the current planned path of the target vehicle does not include the tunnel, determining that the target vehicle is yawed.

[0097] In this embodiment, the implementation details and technical effects of step 304 may refer to the description of step 204 and will not be repeated here.

[0098] The above-mentioned embodiments of the present disclosure highlight that in response to detecting that the target vehicle is traveling within a preset distance range of the tunnel entrance, the pixel value of a specified area of ​​the vehicle front image of the target vehicle is determined, and based on the changing trend of the pixel value of the specified area, it is determined whether the target vehicle has entered the tunnel, thereby effectively reducing the amount of calculation for identifying the changing trends of pixel values ​​of multiple images, thereby effectively improving the efficiency of generating deviation recognition results.

[0099] In some optional embodiments, the designated area includes a row of pixels closest to an upper edge of the image.

[0100] In this implementation, after determining that the target vehicle is within a preset distance range from the tunnel entrance, the execution entity can obtain the image in front of the vehicle and determine the pixel value of the image in front of the vehicle based on the pixel value of a row of pixel points in the image in front of the vehicle that is closest to the upper edge of the image.

[0101] Here, the pixel values ​​of the image in front of the vehicle can be represented by the pixel values ​​of a row of pixels closest to the upper edge of the image, or by the average of the pixel values ​​of a row of pixels closest to the upper edge of the image, and this application does not limit this.

[0102] This implementation method sets the designated area to include a row of pixel points closest to the upper edge of the image, making full use of the fact that the pixel value changes of a row of pixel points closest to the upper edge of the image are most obvious, effectively reducing the amount of calculation for identifying the changing trends of pixel values ​​of multiple images, thereby effectively improving the efficiency of generating yaw recognition results.

[0103] In some optional methods, determining whether a target vehicle enters a tunnel is based on a changing trend of pixel values, including: determining acquisition environment information of an image in front of the vehicle; in response to determining the changing trend of pixel values, matching a pixel value change rule corresponding to the acquisition environment information to determine that the target vehicle enters a tunnel.

[0104] In this implementation, the execution subject can use vehicle-mounted sensors, pre-loaded map information, etc. to determine the collection environment information of the image in front of the vehicle.

[0105] Among them, the collection environment information may include: the movement state of the image acquisition device (for example, 20km / h, 30km / h, etc.), the collection time period (for example, morning, afternoon, noon, evening, etc.), the external environment of the tunnel (for example, the mountain it is attached to, tunnel signs, etc.), etc.

[0106] Furthermore, the execution subject may match the changing trend of the pixel value with the pixel value changing rule corresponding to the collected environment information. If the two match, it can be determined that the target vehicle enters the tunnel.

[0107] This implementation method determines the acquisition environment information of the image in front of the vehicle; in response to determining the change trend of the pixel value, it matches the pixel value change rule corresponding to the acquisition environment information to determine that the target vehicle has entered the tunnel, thereby realizing the judgment of whether the target vehicle has entered the tunnel under different acquisition environments, fully considering the impact of different acquisition environment information on the recognition result, and further improving the accuracy of the recognition result.

[0108] In some optional embodiments, the pixel value change rule may include a pixel value brightness change rule and / or a pixel value color change rule.

[0109] In this implementation, depending on the configuration of the image acquisition device, the acquired image in front of the vehicle may be a grayscale image or a color image.

[0110] For a grayscale image, a pixel value represents a brightness value (grayscale value). In this case, the pixel value variation rule may include the pixel value brightness variation rule.

[0111] For a color image, a pixel value may represent both a brightness value and a color value. In this case, the pixel value variation rule includes one or more of a brightness variation rule and a color variation rule.

[0112] This implementation method can recognize and judge the pixel value change trend of the vehicle front image captured by various types of image acquisition devices by setting the pixel value change rule including the pixel value brightness change rule and / or the pixel value color change rule, thereby improving the application scope of deviation recognition.

[0113] In some optional ways, the collected environmental information may include one or more of the collection time period, weather information and the external environment of the tunnel.

[0114] In this implementation, the execution entity may first determine the acquisition time period of the image in front of the vehicle, weather information, and one or more items of the external environment of the tunnel, and then determine the change trend of the pixel value and match it with the pixel value change rules corresponding to the above-mentioned acquisition time period, weather information, and one or more items of the external environment of the tunnel. If the two match, it can be determined that the target vehicle has entered the tunnel.

[0115] Among them, the collection time period may include morning, afternoon, noon, evening, etc., the weather information may include sunny days, rainy days, etc., and the external environment of the tunnel may include the mountain structure to which the tunnel is attached, the mountain color, the mountain vegetation color, the mountain vegetation coverage, etc.

[0116] Specifically, for example, the collected environmental information includes weather information and a collection time period, such as, on a sunny day, at noon, the pixel value is a brightness value, and the pixel value change rule corresponding to the weather information and the collection time period is that the change trend of the brightness value is decreasing, and the total decrease value is greater than or equal to a second preset value, such as 45. If the change trend of the pixel values ​​of multiple vehicle front images is decreasing, and the total decrease value is 50, that is, the total decrease value is greater than the second preset value, then the two match, and the target vehicle enters the tunnel.

[0117] For another example, the collected environmental information includes the external environment of the tunnel. For example, the color of the mountain is brown, the pixel value is the color value, and the pixel value change rule corresponding to the external environment of the tunnel is brown-black. If the change trend of the pixel values ​​of multiple images is brown-black, the two match, and the target vehicle enters the tunnel.

[0118] Here, it should be pointed out that, under the condition that the collected environmental information includes the external environment of the tunnel, and the pixel values ​​of the image in front of the vehicle are the pixel values ​​of the specified area, that is, the pixel values ​​of multiple rows of pixels adjacent to the upper edge of the image, the pixel value change rules corresponding to the collected environmental information can be determined based on the color of the mountain to which the tunnel is attached (for example, green, gray, etc.), the color of the tunnel edge (for example, cyan, yellow, etc.), and the color inside the tunnel (for example, black, gray, etc.).

[0119] Furthermore, under the condition that the collected environmental information includes the external environment of the tunnel, weather information and the collection time period, and the pixel values ​​of the image in front of the vehicle are the pixel values ​​of multiple rows of pixel points adjacent to the upper edge of the image, the pixel value change rules corresponding to the external environment of the tunnel can be determined based on the change trends of the sky color (for example, blue, light blue, white, etc.), the color of the mountain to which the tunnel is attached (for example, green, gray, etc.), the color of the tunnel edge (for example, cyan, yellow, etc.), and the color inside the tunnel (for example, black, gray, etc.).

[0120] Specifically, the collected environmental information includes the external environment of the tunnel, weather information and the collection time period. The pixel value of the image in front of the vehicle is represented by the mean value of the pixel value of the designated area (such as the three rows of pixels adjacent to the upper edge of the image). If the pixel value change trend of the designated area of ​​the three images over time is white-green-yellow, and the pixel value change rule corresponding to the collected environmental information is white-green-yellow, then the two match, and the target vehicle enters the tunnel; if the pixel value change trend of the designated area of ​​the three images over time is white-white-white, and the pixel value change rule corresponding to the collected environmental information is white-green-yellow, then the two do not match, and the target vehicle does not enter the tunnel.

[0121] This implementation method fully considers the impact of the collection time period, weather information and the external environment of the tunnel on the recognition results, effectively improving the accuracy of the recognition results.

[0122] Continue to see Figure 4a , Figure 4b ,in, Figure 4a , 4b It is a schematic diagram of an application scenario of the vehicle deviation identification method according to this embodiment.

[0123] The execution subject can determine the current position and driving direction of the target vehicle 401 according to GPS, GNSS, etc., and determine the road network structure of the area where the current position is located in the pre-stored map according to the current position. Further, according to the current position, the driving direction and the road network structure of the area where the current position is located, determine the connection relationship between the current position and the road section ahead of the current position (for example, road section A402 and road section B403). Further, the execution subject can determine the probability value of the target vehicle entering each road section ahead according to the lane information and connection relationship corresponding to the current position, and determine whether the road section ahead with a probability value greater than or equal to a preset threshold is a tunnel section. If so, it can be determined that the target vehicle is within a preset distance range from the tunnel entrance.

[0124] When the target vehicle 401 is detected to be within a preset distance range of the tunnel entrance 404, wherein the tunnel entrance 404 is embedded in the mountain 405, the execution subject can collect multiple images in front of the vehicle through an image acquisition device installed on the target vehicle 401, such as a driving recorder, and determine the pixel value of the image in front of the vehicle, such as determining the average of the pixel values ​​of a row of pixels closest to the upper edge of the image as the pixel value of the image in front of the vehicle. Further, the pixel values ​​of the multiple images in front of the vehicle are sorted according to the acquisition time of each image in front of the vehicle, and the change trend of the pixel value is determined according to the sorting result. For example, the pixel value is a color value, and the change trend of the pixel value is white-green-yellow-black.

[0125] Furthermore, the execution entity may match the changing trend of the pixel value with the pixel value changing rule corresponding to the collected environment information, wherein the collected environment information may include weather information, collection time period and the external environment of the tunnel (e.g., on a sunny day, at noon, the mountain to which the tunnel is attached is green, the edge of the tunnel is yellow, and the inside of the tunnel is black), and the pixel value changing rule corresponding to the collected environment information is white (sky color) - green (mountain color) - yellow (tunnel edge color) - black (tunnel color). If the two match, it can be determined that the target vehicle has entered the tunnel.

[0126] Here, the execution entity may also directly input the sorting results into the offline big data iteration model to identify whether to enter the tunnel and obtain the identification results.

[0127] Further, if the current planned path of the target vehicle does not include a tunnel, it may be determined that the target vehicle is yawed.

[0128] Furthermore, the execution entity may modify the planned path according to the tunnel identification and the destination of the target vehicle to generate a new planned path.

[0129] Further references Figure 5 As an implementation of the methods shown in the above figures, the present disclosure provides an embodiment of a vehicle deviation identification device, and the device embodiment is Figure 2 The method embodiments shown correspond.

[0130] like Figure 5 As shown, the vehicle deviation identification device 500 of this embodiment includes: a pixel determination module 501 , a trend determination module 502 , a tunnel determination module 503 and a deviation determination module 504 .

[0131] The pixel determination module 501 may be configured to determine the pixel value of the vehicle front image of the target vehicle in response to detecting that the target vehicle is traveling within a preset distance range of the tunnel entrance.

[0132] The trend determination module 502 may be configured to determine a change trend of pixel values ​​based on the pixel values ​​and image acquisition time of a plurality of vehicle front images.

[0133] The tunnel determination module 503 may be configured to determine whether the target vehicle enters a tunnel based on a change trend of pixel values.

[0134] The yaw determination module 504 may be configured to determine the yaw of the target vehicle in response to determining that the target vehicle enters a tunnel and the current planned path of the target vehicle does not include the tunnel.

[0135] In some optional embodiments of this embodiment, the position evaluation module includes: a first matching unit, a second matching unit and a position evaluation unit, wherein the first matching unit is configured to match the reference lane position with the initial lane position to determine a first matching result; the second matching unit is configured to match the road network lane group with the visual lane group to determine a second matching result; and the position evaluation unit is configured to determine the confidence of the initial lane position based on the first matching result and the second matching result.

[0136] In some optional aspects of this embodiment, the pixel determination module may be further configured to: in response to detecting that the target vehicle travels within a preset distance range of a tunnel entrance, determine the pixel value of a specified area of ​​the vehicle front image of the target vehicle.

[0137] In some optional modes of this embodiment, the designated area includes a row of pixel points closest to the upper edge of the image.

[0138] In some optional embodiments of this embodiment, the tunnel determination module further includes: an environment determination unit, configured to determine the acquisition environment information of the image in front of the vehicle; a rule matching unit, configured to match the pixel value change rule corresponding to the acquisition environment information in response to determining the change trend of the pixel value, to determine that the target vehicle has entered the tunnel.

[0139] In some optional embodiments of this embodiment, the pixel value change rule includes a pixel value brightness change rule and / or a pixel value color change rule.

[0140] In some optional aspects of this embodiment, the collected environmental information includes one or more of the following: collection time period, weather information, and external environment of the tunnel.

[0141] In some optional embodiments of this embodiment, the device also includes a lane determination module, which is configured to determine a lane group detection result based on multiple vehicle front images; determine a first result of whether the target vehicle enters the tunnel based on the lane group detection result and the map lane information of the tunnel; and the tunnel determination module further includes: a first determination unit, which is configured to determine a second result of whether the target vehicle enters the tunnel based on a change trend of pixel values; and a second determination unit, which is configured to determine whether the target vehicle enters the tunnel based on the first result and the second result.

[0142] In some optional embodiments of this embodiment, the device also includes a path determination module, which is configured to determine the current driving path of the target vehicle based on the positioning information of the target vehicle and the inertial measurement information of the target vehicle; determine a third result of whether the target vehicle enters a tunnel based on the current driving path; and the second determination unit is further configured to determine whether the target vehicle enters the tunnel based on the first result, the second result and the third result.

[0143] In some optional embodiments of this embodiment, the device also includes: a signal determination module, configured to determine a fourth result of whether the target vehicle enters the tunnel based on changes in the signal strength of the global positioning system; and the second determination unit is further configured to determine whether the target vehicle enters the tunnel based on the first result, the second result, the third result and the fourth result.

[0144] In some optional modes of this embodiment, the device also includes: a road section relationship determination module, which is configured to determine the connection relationship between the current position and the road section ahead of the current position according to the current position of the target vehicle, the driving direction and the road network structure of the area where the current position is located; a road section probability determination module, which is configured to determine the probability value of the target vehicle entering each road section ahead according to the lane information and connection relationship corresponding to the current position; and a distance range determination module, which is configured to determine that the road section ahead with a probability value greater than or equal to a preset threshold is a tunnel section, and determine that the target vehicle is within a preset distance range from the tunnel entrance.

[0145] In some optional aspects of this embodiment, the pixel determination module is further configured to determine pixel values ​​of the vehicle front image of the target vehicle captured by the driving recorder.

[0146] In some optional aspects of this embodiment, the device further includes: a path planning module configured to, in response to determining that the target vehicle is yawed, modify the current planned path according to the tunnel identification of the tunnel and the destination of the target vehicle to generate a new planned path.

[0147] In the technical solution disclosed herein, the acquisition, storage and application of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0148] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0149] Figure 6A schematic block diagram of an example electronic device 600 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0150] like Figure 6 As shown, the device 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the device 600 can also be stored. The computing unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0151] A number of components in the device 600 are connected to the I / O interface 605, including: an input unit 606, such as a keyboard, a mouse, etc.; an output unit 607, such as various types of displays, speakers, etc.; a storage unit 608, such as a disk, an optical disk, etc.; and a communication unit 609, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0152] The computing unit 601 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 601 performs the various methods and processes described above, such as a method for yaw identification of a vehicle. For example, in some embodiments, the method for yaw identification of a vehicle may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 600 via the ROM 602 and / or the communication unit 609. When the computer program is loaded into the RAM 603 and executed by the computing unit 601, one or more steps of the method for yaw identification of a vehicle described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to execute the method for vehicle deviation identification in any other appropriate manner (for example, by means of firmware).

[0153] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0154] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0155] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0156] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0157] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0158] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and virtual private servers (VPS) services. The server can also be divided into a server of a distributed system, or a server combined with a blockchain.

[0159] According to the technical solution of the embodiment of the present disclosure, the timeliness and reliability of vehicle deviation identification are effectively improved.

[0160] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions provided by this disclosure can be achieved, and this document does not limit this.

[0161] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A vehicle yaw identification method, comprising: In response to detecting that the target vehicle travels within a preset distance range of the tunnel entrance, determining a pixel value of a vehicle front image of the target vehicle; Determining a change trend of the pixel values ​​based on the pixel values ​​of the plurality of images in front of the vehicle and the image acquisition time; Based on the changing trend of the pixel value, determining whether the target vehicle enters the tunnel; In response to determining that the target vehicle enters the tunnel and the tunnel is not included in a currently planned path of the target vehicle, determining that the target vehicle is yawed.

2. The method according to claim 1, wherein: In response to detecting that the target vehicle travels within a preset distance range of the tunnel entrance, determining the pixel value of the vehicle front image of the target vehicle includes: In response to detecting that the target vehicle travels within a preset distance range of the tunnel entrance, pixel values ​​of a specified area of ​​the vehicle front image of the target vehicle are determined, where the specified area includes a plurality of rows of pixel points adjacent to an upper edge of the image.

3. The method according to claim 2, wherein: The designated area includes a row of pixel points closest to the upper edge of the image.

4. The method according to claim 1, wherein: The determining, based on the changing trend of the pixel values, whether the target vehicle enters the tunnel comprises: Determining the acquisition environment information of the image in front of the vehicle; In response to determining the change trend of the pixel value, matching the pixel value change rule corresponding to the collected environment information, it is determined that the target vehicle enters the tunnel.

5. The method according to claim 4, wherein: The collected environment information includes one or more of the following: collection time period, weather information, and tunnel external environment.

6. The method according to claim 4, wherein: The pixel value variation rule includes a pixel value brightness variation rule and / or a pixel value color variation rule.

7. The method according to claim 1, further comprising: Determine a lane group detection result based on a plurality of images in front of the vehicle; Determine a first result of whether the target vehicle enters the tunnel based on the lane group detection result and the map lane information of the tunnel; as well as The determining, based on the changing trend of the pixel values, whether the target vehicle enters the tunnel comprises: Determining a second result of whether the target vehicle enters the tunnel based on a change trend of the pixel value; Based on the first result and the second result, it is determined whether the target vehicle enters the tunnel.

8. The method according to claim 7, further comprising: Determining a current driving path of the target vehicle based on the positioning information of the target vehicle and the inertial measurement information of the target vehicle; Determining, based on the current driving path, a third result of whether the target vehicle enters the tunnel; The determining, based on the first result and the second result, whether the target vehicle enters the tunnel comprises: Based on the first result, the second result and the third result, it is determined whether the target vehicle enters the tunnel.

9. The method according to claim 8, further comprising: A fourth result of determining whether the target vehicle enters the tunnel based on a change in signal strength of a global positioning system; The determining, based on the first result, the second result and the third result, whether the target vehicle enters the tunnel comprises: Based on the first result, the second result, the third result and the fourth result, it is determined whether the target vehicle enters the tunnel.

10. The method according to claim 1, wherein: The target vehicle is detected within the preset distance range of the tunnel entrance by the following methods: Determine the connection relationship between the current position and the road section ahead of the current position according to the current position of the target vehicle, the driving direction and the road network structure of the area where the current position is located; Determining the probability value of the target vehicle entering each road section ahead according to the lane information corresponding to the current position and the connection relationship; In response to determining that the road section ahead with a probability value greater than or equal to a preset threshold is a tunnel section, it is determined that the target vehicle travels within a preset distance range to a tunnel entrance.

11. The method according to claim 1, wherein: The step of determining the pixel value of the vehicle front image of the target vehicle comprises: Determine the pixel value of the vehicle front image of the target vehicle collected by the driving recorder.

12. The method according to any one of claims 1 to 11, further comprising: In response to determining that the target vehicle is yawed, the current planned path is corrected according to a tunnel identifier of the tunnel and a destination of the target vehicle to generate a new planned path.

13. A vehicle deviation identification device, comprising: a pixel determination module configured to determine a pixel value of a vehicle front image of a target vehicle in response to detecting that the target vehicle travels within a preset distance range of a tunnel entrance; A trend determination module is configured to determine a change trend of pixel values ​​based on the pixel values ​​and image acquisition time of the plurality of images in front of the vehicle; a tunnel determination module, configured to determine whether the target vehicle enters the tunnel based on a change trend of the pixel value; The yaw determination module is configured to determine the yaw of the target vehicle in response to determining that the target vehicle enters the tunnel and the tunnel is not included in the current planned path of the target vehicle.

14. The device according to claim 13, wherein: The pixel determination module is further configured to: In response to detecting that the target vehicle travels within a preset distance range of the tunnel entrance, pixel values ​​of a specified area of ​​the vehicle front image of the target vehicle are determined, where the specified area includes a plurality of rows of pixel points adjacent to an upper edge of the image.

15. The device according to claim 14, wherein: The designated area includes a row of pixel points closest to the upper edge of the image.

16. The device according to claim 13, wherein: The tunnel determination module further comprises: An environment determination unit, configured to determine acquisition environment information of the image in front of the vehicle; The rule matching unit is configured to match the pixel value change rule corresponding to the collected environment information in response to determining the change trend of the pixel value, and determine that the target vehicle enters the tunnel.

17. The device according to claim 16, wherein: The collected environment information includes one or more of the following: collection time period, weather information, and tunnel external environment.

18. The device according to claim 16, wherein: The pixel value variation rule includes a pixel value brightness variation rule and / or a pixel value color variation rule.

19. The apparatus according to claim 13, further comprising: A lane determination module, configured to determine a lane group detection result based on a plurality of vehicle front images; Determine a first result of whether the target vehicle enters the tunnel based on the lane group detection result and the map lane information of the tunnel; as well as The tunnel determination module further comprises: A first determining unit is configured to determine a second result of whether the target vehicle enters the tunnel based on a change trend of the pixel value; The second determining unit is configured to determine whether the target vehicle enters the tunnel based on the first result and the second result.

20. The apparatus according to claim 18, further comprising: a path determination module, configured to determine a current driving path of the target vehicle based on the positioning information of the target vehicle and the inertial measurement information of the target vehicle; Determining, based on the current driving path, a third result of whether the target vehicle enters the tunnel; as well as The second determination unit is further configured to determine whether the target vehicle enters the tunnel based on the first result, the second result, and the third result.

21. The device according to claim 20, wherein: The device also includes: a signal determination module configured to determine a fourth result of whether the target vehicle enters the tunnel based on a signal strength change of a global positioning system; and The second determination unit is further configured to determine whether the target vehicle enters the tunnel based on the first result, the second result, the third result, and the fourth result.

22. The apparatus according to claim 13, further comprising: A road segment relationship determination module is configured to determine a connection relationship between the current position and a road segment ahead of the current position according to the current position of the target vehicle, the driving direction, and the road network structure of the area where the current position is located; A road section probability determination module is configured to determine the probability value of the target vehicle entering each road section ahead according to the lane information corresponding to the current position and the connection relationship; The distance range determination module is configured to determine that the target vehicle is within a preset distance range from traveling to a tunnel entrance in response to determining that the road section ahead with a probability value greater than or equal to a preset threshold is a tunnel section.

23. The device according to claim 13, wherein: The pixel determination module is further configured to determine pixel values ​​of the vehicle front image of the target vehicle collected via the driving recorder.

24. The device according to any one of claims 13 to 23, further comprising: The path planning module is configured to, in response to determining that the target vehicle is yawed, modify the current planned path according to the tunnel identifier of the tunnel and the destination of the target vehicle to generate a new planned path.

25. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 12.

26. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 12.

27. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 12.

Images