A road image recognition method, device, electronic device and storage medium

Abstract

The present application relates to a road image recognition method, device, electronic device and storage medium. The method includes obtaining a driving road image of a target vehicle and vehicle information, where the vehicle information includes the wheelbase, wheel width and total weight of the target vehicle; determining the positions and interference levels corresponding to several interference objects based on the driving road image; determining at least two sets of wheel coverage areas from the driving road image based on the wheelbase and wheel width of the target vehicle; determining the bearing capacity corresponding to each of the at least two sets of wheel coverage areas based on the total weight of the target vehicle, the positions and interference levels corresponding to several interference objects, and the at least two sets of wheel coverage areas; and determining a target driving area from the at least two sets of wheel coverage areas, where the target driving area is the wheel coverage area with the strongest bearing capacity. The present application has the effect of improving the safety of vehicle driving at a construction site.

Description

Technical Field

[0001] The present application relates to the field of road recognition, and in particular, to a road image recognition method, device, electronic device, and storage medium. Background Art

[0002] During construction, temporary construction roads will be built to facilitate construction work. The temporary construction roads are used for construction personnel, vehicles, machinery, etc. to enter and exit the construction site during construction. According to the type, the temporary construction roads can be divided into temporary main trunk access roads and temporary branch access roads. The construction party sets the roadbed in the corresponding area according to the construction requirements, and builds the temporary construction road by pouring concrete or laying fine stone on the roadbed. However, there are certain differences between the construction standards of temporary construction roads and formal roads. Therefore, the bearing capacity of temporary construction roads is generally lower than that of formal roads.

[0003] During the construction process, the temporary construction road needs to bear the rolling of heavy construction vehicles, so it is more likely to be damaged. At the same time, when trucks transport building materials at the construction site, it is inevitable that the transported items will fall. If the items fallen on the road surface are not cleaned up in time, when the construction vehicle passes through the uneven road surface, it is more likely to cause safety accidents. Therefore, how to improve the driving safety of vehicles at the construction site is an urgent problem to be solved. Summary of the Invention

[0004] In order to improve the driving safety of vehicles at the construction site, the present application particularly relates to a road image recognition method, device, electronic device, and storage medium.

[0005] In a first aspect, the present application provides a road image recognition method, adopting the following technical solution:

[0006] A road image recognition method includes:

[0007] Obtain the driving road image and vehicle information of the target vehicle, where the vehicle information includes the wheelbase, wheel width, and total weight of the target vehicle;

[0008] Based on the driving road image, determine the positions and interference levels of several interference objects respectively, where the interference objects are the objects that affect the normal driving of the vehicle;

[0009] Based on the wheelbase and wheel width of the target vehicle, determine at least two sets of wheel coverage areas from the driving road image, where the wheel coverage area is the area that the target vehicle will cover when driving on the driving road;

[0010] Determine the bearing capacity corresponding to each of the at least two groups of wheel coverage areas based on the total weight of the target vehicle, the positions and interference levels corresponding to the respective plurality of interference objects, and the at least two groups of wheel coverage areas, where the bearing capacity is used to characterize the safety of the target vehicle when driving within the corresponding wheel coverage area;

[0011] Based on the bearing capacity corresponding to each of the at least two groups of wheel coverage areas, determine a target driving area from the at least two groups of wheel coverage areas, where the target driving area is the wheel coverage area with the strongest bearing capacity.

[0012] By adopting the above technical solution, according to the driving road image, determine a plurality of interference objects that will affect the normal driving of the target vehicle on the temporary construction road, as well as the positions and interference levels of each interference object; according to the wheelbase and wheel width of the target vehicle, determine at least two groups of areas covered by the wheels when the target vehicle is driving in the driving road image; further determine the interference objects corresponding to each group of wheel coverage areas and the total weight of the target vehicle, determine the bearing capacity corresponding to each group of wheel coverage areas, where the bearing capacity is used to characterize the safety of the target vehicle when driving in the corresponding area; further determine the wheel coverage area with the strongest bearing capacity from the at least two groups of wheel coverage areas as the target coverage area. The safety of the target vehicle when driving within the wheel coverage area is relatively high, so the safety of vehicle driving at the construction site can be improved.

[0013] In a possible implementation manner, the determining the positions and interference levels corresponding to the respective plurality of interference objects based on the driving road image includes:

[0014] Determine the road surface area corresponding to the temporary construction road from the driving road image;

[0015] Divide the road surface area into a plurality of sub-region images;

[0016] Determine a standard area from the plurality of sub-region images;

[0017] Based on the standard area and the plurality of sub-regions, determine a plurality of abnormal areas, where the abnormal areas are sub-regions with a similarity lower than a preset similarity to the standard area;

[0018] Based on the plurality of abnormal areas, determine the positions and interference levels corresponding to the respective plurality of interference objects.

[0019] By adopting the above technical solution, the road surface area corresponding to the temporary construction road is determined from the driving road image, and the road surface area is divided into a plurality of sub-region images; a standard region is determined from the plurality of sub-region images; and a plurality of abnormal regions are determined from the plurality of sub-region images according to the standard region; the images of each abnormal region are analyzed and combined to determine a plurality of interfering objects included in the road, as well as the corresponding positions and interference levels of each interfering object, so that the determined interfering objects are more in line with the actual situation of the temporary construction road.

[0020] In a possible implementation manner, the determining a standard region from the plurality of sub-region images includes:

[0021] An initial sub-region and a plurality of adjacent sub-regions corresponding to the initial sub-region are determined from the plurality of sub-region images, and the initial sub-region is a non-edge sub-region image;

[0022] It is determined whether the region similarities corresponding to the initial sub-region and the plurality of adjacent sub-regions are all higher than a preset similarity;

[0023] If so, the initial sub-region is determined as the standard region;

[0024] If not, the initial sub-region is determined as a non-standard region, and the determination of the next initial sub-region is performed until the standard region is determined.

[0025] By adopting the above technical solution, an initial sub-region and a plurality of adjacent sub-regions corresponding to the initial sub-region are determined from the plurality of sub-region images, the initial sub-region is respectively compared with each adjacent sub-region in terms of similarity, and it is determined whether the similarity between the initial sub-region and each adjacent sub-region is higher than the preset similarity; if so, the initial sub-region is determined as the standard region, if not, the initial sub-region is determined as a non-standard region, and a new initial sub-region is determined from the remaining non-edge sub-region images to perform the determination until the standard region is determined. The accuracy of the standard region can be improved and it is more in line with the actual situation of the current temporary construction road.

[0026] In a possible implementation manner, the determining the corresponding positions and interference levels of the plurality of interfering objects based on the plurality of abnormal regions includes:

[0027] Determine the corresponding positions and abnormal types of the plurality of abnormal regions;

[0028] Based on the corresponding positions and abnormal types of the plurality of abnormal regions, the abnormal regions are combined by region to determine the corresponding positions and interference levels of the plurality of interfering objects.

[0029] By adopting the above technical solution, the position and abnormal type corresponding to each abnormal area are determined. For abnormal areas with adjacent positions and the same abnormal type, they are combined to determine at least one abnormal area corresponding to the interference object. For each interference object, based on the positions of at least one abnormal area corresponding to the interference object, the position of the interference object is determined. According to the number and abnormal type of the abnormal areas corresponding to the interference object, the interference level of the interference object is determined, and the position and interference level of the interference object can be determined more accurately.

[0030] In a possible implementation manner, determining the bearing capacity corresponding to each of the at least two wheel coverage areas based on the total weight of the target vehicle, the positions and interference levels respectively corresponding to the several interference objects, and the at least two wheel coverage areas includes:

[0031] Based on the positions and interference levels respectively corresponding to the several interference objects and the at least two wheel coverage areas, determine the road surface flatness corresponding to each of the at least two wheel coverage areas;

[0032] Obtain the material type of the driving road;

[0033] Based on the material type of the driving road, the total weight of the target vehicle, and the road surface flatness corresponding to each of the at least two wheel coverage areas, determine the bearing capacity corresponding to each of the at least two wheel coverage areas.

[0034] By adopting the above technical solution, according to the position and interference level of each interference object, the road surface flatness corresponding to each group of wheel coverage areas is determined. There are differences in the bearing capacity corresponding to different road surface materials. Furthermore, based on the material type of the driving road and the road surface flatness of each wheel coverage area, the bearing capacity of the wheel coverage area under the condition of the total weight of the target vehicle is determined, making the determined bearing capacity more in line with the actual situation of the wheel coverage area.

[0035] In a possible implementation manner, determining the road surface flatness corresponding to any one of the wheel coverage areas based on the positions and interference levels respectively corresponding to the several interference objects and any one of the wheel coverage areas includes:

[0036] Based on the positions respectively corresponding to the several interference objects and any one of the wheel coverage areas, determine the distances respectively corresponding to the several interference objects and any one of the wheel coverage areas;

[0037] Based on the interference levels respectively corresponding to the several interference objects and the distances respectively corresponding to any one of the wheel coverage areas, determine the road surface flatness of any one of the wheel coverage areas.

[0038] By adopting the above technical solution, for any wheel coverage area, the distance between each interference object and the wheel coverage area is determined; in combination with the interference level of each interference object, the influence range of each interference object is determined, and then the degree of influence of the interference object on the road surface in the corresponding distance on the wheel coverage area is determined, and further the road surface flatness of any wheel coverage area is determined, so that the degree of influence of each interference object on the vehicle coverage area can be determined more accurately.

[0039] In a possible implementation manner, a road image recognition method further includes:

[0040] Based on the positions and interference levels respectively corresponding to the several interference objects, maintenance information respectively corresponding to the several interference objects is generated, and the maintenance information is used to prompt relevant maintenance personnel to maintain the temporarily constructed road.

[0041] By adopting the above technical solution, according to the interference levels respectively corresponding to the several interference objects, it is judged whether maintenance is required. If so, the corresponding maintenance information is determined according to the types and positions of the interference objects. The maintenance information can be sent to the terminal devices of the corresponding maintenance personnel to prompt the maintenance personnel to maintain the abnormal conditions on the temporarily constructed road, which can improve the driving safety of the vehicle on the temporarily constructed road.

[0042] In a second aspect, the present application provides a road image recognition device, adopting the following technical solution:

[0043] A road image recognition device includes:

[0044] A target vehicle information acquisition module, configured to acquire the driving road image and vehicle information of the target vehicle, where the vehicle information includes the wheelbase, wheel width, and total weight of the target vehicle;

[0045] An interference object information determination module, configured to determine the positions and interference levels respectively corresponding to several interference objects based on the driving road image, where the interference objects are objects that affect the normal driving of the vehicle;

[0046] A wheel coverage area determination module, configured to determine at least two groups of wheel coverage areas from the driving road image based on the wheelbase and wheel width of the target vehicle, where the wheel coverage area is the area that the target vehicle will cover when driving on the driving road;

[0047] A bearing capacity determination module, configured to determine the bearing capacity respectively corresponding to the at least two groups of wheel coverage areas based on the total weight of the target vehicle, the positions and interference levels respectively corresponding to the several interference objects, and the at least two groups of wheel coverage areas, where the bearing capacity is used to characterize the driving safety of the target vehicle in the corresponding wheel coverage area;

[0048] A target driving area determination module, configured to determine a target driving area from the at least two sets of wheel coverage areas based on the bearing capacities corresponding to the at least two sets of wheel coverage areas, where the target driving area is the wheel coverage area with the strongest bearing capacity.

[0049] By adopting the above technical solution, according to the driving road image, a plurality of interference objects that will affect the normal driving of the target vehicle on the temporary construction road are determined, as well as the positions and interference levels of each interference object; according to the wheelbase and wheel width of the target vehicle, at least two sets of areas covered by the wheels during the driving of the target vehicle in the driving road image are determined; furthermore, the interference objects corresponding to each set of wheel coverage areas and the total weight of the target vehicle are determined, and the bearing capacity corresponding to each set of wheel coverage areas is determined, where the bearing capacity is used to characterize the safety of the target vehicle driving in the corresponding area; furthermore, the one with the strongest bearing capacity is determined as the target coverage area from the at least two sets of wheel coverage areas. The target vehicle has a higher safety when driving in the wheel coverage area, so the driving safety of the vehicle at the construction site can be improved. [[ID=^6]]

[0050] In a possible implementation manner, when the interference object information determination module determines the positions and interference levels corresponding to the plurality of interference objects based on the driving road image, it is specifically configured to:

[0051] Determine the road surface area corresponding to the temporary construction road from the driving road image;

[0052] Divide the road surface area into a plurality of sub-region images;

[0053] Determine a standard area from the plurality of sub-region images;

[0054] Based on the standard area and the plurality of sub-regions, a plurality of abnormal areas are determined, where the abnormal area is a sub-region with a similarity lower than a preset similarity to the standard area;

[0055] Based on the plurality of abnormal areas, determine the positions and interference levels corresponding to the plurality of interference objects.

[0056] In a possible implementation manner, when the interference object information determination module determines a standard area from the plurality of sub-region images, it is specifically configured to:

[0057] Determine an initial sub-region and a plurality of adjacent sub-regions corresponding to the initial sub-region from the plurality of sub-region images, where the initial sub-region is a non-edge sub-region image;

[0058] Determine whether the regional similarities between the initial sub-region and the plurality of adjacent sub-regions are all higher than a preset similarity;

[0059] If so, determine the initial sub-region as the standard region;

[0060] If not, determine the initial sub-region as a non-standard region, and perform the judgment on the next initial sub-region until the standard region is determined.

[0061] In a possible implementation manner, when the interference object information determination module determines the positions and interference levels corresponding to several interference objects based on the several abnormal regions, it is specifically configured to:

[0062] Determine the positions and abnormal types corresponding to the several abnormal regions respectively;

[0063] Based on the positions and abnormal types corresponding to the several abnormal regions respectively, perform region combination on the abnormal regions to determine the positions and interference levels corresponding to several interference objects respectively.

[0064] In a possible implementation manner, when the bearing capacity determination module determines the bearing capacities corresponding to the at least two groups of wheel coverage regions based on the total weight of the target vehicle, the positions and interference levels corresponding to the several interference objects, and the at least two groups of wheel coverage regions, it is specifically configured to:

[0065] Based on the positions and interference levels corresponding to the several interference objects and the at least two groups of wheel coverage regions, determine the road surface flatness corresponding to the at least two groups of wheel coverage regions respectively;

[0066] Obtain the material type of the driving road;

[0067] Based on the material type of the driving road, the total weight of the target vehicle, and the road surface flatness corresponding to the at least two groups of wheel coverage regions respectively, determine the bearing capacities corresponding to the at least two groups of wheel coverage regions respectively.

[0068] In a possible implementation manner, when the bearing capacity determination module determines the road surface flatness corresponding to any one of the wheel coverage regions based on the positions and interference levels corresponding to the several interference objects and any one of the wheel coverage regions, it is specifically configured to:

[0069] Based on the positions corresponding to the several interference objects and any one of the wheel coverage regions, determine the distances corresponding to the several interference objects and any one of the wheel coverage regions respectively;

[0070] Based on the interference levels corresponding to the several interference objects and the distances corresponding to any one of the wheel coverage regions respectively, determine the road surface flatness of any one of the wheel coverage regions.

[0071] In a possible implementation, a road image recognition device further includes:

[0072] A maintenance module, configured to generate maintenance information corresponding to each of the several interference objects based on the position and type of each of the several interference objects, where the maintenance information is used to prompt relevant maintenance personnel to maintain the temporarily constructed road.

[0073] In a third aspect, the present application provides an electronic device, adopting the following technical solution:

[0074] An electronic device, the electronic device includes:

[0075] At least one processor;

[0076] A memory;

[0077] At least one application program, where the at least one application program is stored in the memory and is configured to be executed by the at least one processor, and the at least one application program is configured to: execute the above-mentioned road image recognition method.

[0078] In a fourth aspect, the present application provides a computer-readable storage medium, adopting the following technical solution:

[0079] A computer-readable storage medium, including: a computer program stored that can be loaded and executed by a processor to execute the above-mentioned road image recognition method.

[0080] In summary, the present application includes at least one of the following beneficial technical effects:

[0081] 1. Based on the driving road image, determine several interference objects on the temporarily constructed road that will affect the normal driving of the target vehicle, as well as the position and interference level of each interference object; according to the wheelbase and wheel width of the target vehicle, determine at least two groups of areas covered by the wheels when the target vehicle is driving in the driving road image; further determine the interference objects corresponding to each group of wheel-covered areas and the total weight of the target vehicle, and determine the bearing capacity corresponding to each group of wheel-covered areas, where the bearing capacity is used to characterize the safety of the target vehicle driving in the corresponding area; further determine the group with the strongest bearing capacity as the target covered area from at least two groups of wheel-covered areas. The safety of the target vehicle driving in the wheel-covered area is relatively high, so the driving safety of vehicles at the construction site can be improved.

[0082] 2. Determine the road surface area corresponding to the temporary construction road from the driving lane image, and divide the road surface area into multiple sub-region images; determine the standard region from the multiple sub-region images; and determine several abnormal regions from the multiple sub-region images according to the standard region; analyze and combine the images of each abnormal region to determine several interference objects included in the road, as well as the corresponding positions and interference levels of each interference object, so that the determined interference objects are more in line with the actual situation of the temporary construction road.

[0083] 3. Determine the initial sub-region from the multiple sub-region images, and multiple adjacent sub-regions corresponding to the initial sub-region. Compare the similarity of the initial sub-region with each adjacent sub-region respectively, and determine whether the similarity of the initial sub-region with each adjacent sub-region is higher than the preset similarity; if so, determine that the initial sub-region is the standard region, if not, determine that the initial sub-region is a non-standard region, and determine a new initial sub-region from the remaining non-edge sub-region images to perform the judgment until the standard region is determined. It can improve the accuracy of the standard region and be more in line with the actual situation of the current temporary construction road. Brief Description of the Drawings

[0084] Figure 1 It is a schematic flowchart of a road image recognition method in an embodiment of the present application;

[0085] Figure 2 It is a schematic structural diagram of a road image recognition device in an embodiment of the present application;

[0086] Figure 3 It is a schematic structural diagram of an electronic device in an embodiment of the present application. Detailed Description of the Embodiment

[0087] The following is combined with Figures 1 - 3 to further elaborate on the present application.

[0088] Those skilled in the art can make modifications to this embodiment without creative contributions according to needs after reading this specification, but as long as they are within the scope of the present application, they are protected by the patent law.

[0089] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts fall within the scope of protection of the present application.

[0090] In addition, the term "and / or" in this document is merely a description of the association relationship between associated objects, indicating that there can be three relationships. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this document generally represents an "or" relationship between the front and rear associated objects unless otherwise specified.

[0091] An embodiment of the present application provides a road image recognition method, which is executed by an electronic device. Referring to Figure 1 , the method includes steps S101 to S105, where:

[0092] Step S101, obtain the driving road image and vehicle information of the target vehicle. The vehicle information includes the wheelbase, wheel width, and total weight of the target vehicle.

[0093] For the embodiment of the present application, when the target vehicle needs to drive on a temporarily constructed road, obtain the driving road image of the target vehicle. The driving road image can be an image taken by an image acquisition device installed on the target vehicle for the temporarily constructed road where the target vehicle is currently located; it can also be an image taken by a monitoring device at the construction site for the temporarily constructed road where the target vehicle is located. The embodiment of the present application does not specifically limit the method for obtaining the driving road image of the target vehicle.

[0094] Furthermore, the vehicle information of the target vehicle can be analyzed based on the image taken of the target vehicle to determine the license plate corresponding to the target vehicle, and then obtain information such as the wheelbase, wheel width, vehicle net weight, and vehicle model corresponding to the target vehicle from the database according to the license plate. At the same time, combine the loading situation of the target vehicle in the image taken of the target vehicle with the vehicle model to determine the carrying capacity of the target vehicle; then determine the total weight of the target vehicle according to the vehicle net weight and the carrying capacity. It is also possible to determine the total weight of the target vehicle according to the weight sensors arranged on the temporarily constructed road; determine the distance between each side sensor and the adjacent wheel according to the distance sensors arranged on both sides of the temporarily constructed road, and determine the wheelbase of the target vehicle according to the width of the temporarily constructed road or the distance between the two distance sensors; determine the wheel width of the target vehicle according to the image taken of the target vehicle.

[0095] Step S102, based on the driving road image, determine the positions and interference levels of several interference objects respectively. The interference objects are objects that affect the normal driving of the vehicle.

[0096] For the embodiments of the present application, the driving road image can be grayscaled, local features of the processed grayscale image can be extracted and analyzed to determine several interference objects included in the temporary construction road, as well as the position and interference level of each interference object. The interference object is an object that affects the normal driving of the vehicle, including cracks and scattered sand and gravel on the temporary construction road. The level of the interference object is determined according to the type and area of the interference object. The larger the area of the interference object or the greater the impact of the type of the interference object on vehicle driving, the higher the corresponding interference level of the interference object. The interference levels of the interference objects can be divided into level 1, level 2, …, level 6, where the interference object of level 1 has the least impact on vehicle driving, and the interference object of level 6 has the greatest impact on vehicle driving.

[0097] Further, there are various types of road abnormal images stored in the database, and the target abnormal image corresponding to the road of the same type as the temporary construction road where the target vehicle is located can also be determined from all the road abnormal images. The preset model is trained according to the target abnormal image and its corresponding abnormal type to obtain a trained feature model, and then the driving road image is put into the feature model to determine the positions and interference levels corresponding to several interference objects included therein.

[0098] Step S103: Based on the wheelbase and wheel width of the target vehicle, at least two groups of wheel coverage areas are determined from the driving road image, and the wheel coverage area is the area that the target vehicle will cover when driving on the driving road.

[0099] For the embodiments of the present application, the area corresponding to the temporary construction road is determined from the driving road image, and then, based on the wheelbase of the target vehicle and the wheel width corresponding to the target vehicle, the area that the wheels of the target vehicle will cover when driving on the temporary construction road, that is, the wheel coverage area, is determined. Among them, the width of the temporary construction road is generally greater than the wheelbase, so at least two groups of wheel coverage areas can be determined.

[0100] Step S104: Based on the total weight of the target vehicle, the positions and interference levels corresponding to several interference objects, and at least two groups of wheel coverage areas, the bearing capacity corresponding to each of the at least two groups of wheel coverage areas is determined, and the bearing capacity is used to characterize the safety of the target vehicle when driving in the corresponding wheel coverage area.

[0101] For the embodiments of the present application, several interfering objects included in each group of wheel coverage areas are determined according to the positions corresponding to the respective interfering objects. For each group of wheel coverage areas, according to the interference level of each interfering object included in the wheel coverage area, the load level corresponding to the wheel coverage area is determined, and then the bearing capacity corresponding to each weight range under this load level is determined. Under different load levels, the corresponding relationship between the bearing capacity and the weight range is different. Further, according to the weight range of the total weight of the target vehicle, the bearing capacity corresponding to this group of wheel coverage areas is determined, and the bearing capacity is used to characterize the safety of the target vehicle when driving in this area.

[0102] Further, the load level is determined according to the number and level of each interfering object in the wheel coverage area. For example, the load level is divided into level I and level II. The corresponding relationship between the weight range and the bearing capacity under level I conditions includes: when the total weight of the target vehicle is less than 20T, the bearing capacity is level A; when the total weight of the target vehicle is greater than 20T and less than 50T, the bearing capacity is level B; when the total weight of the target vehicle is greater than 50T, the bearing capacity is level C. The corresponding relationship between the weight range and the bearing capacity under level II conditions includes: when the total weight of the target vehicle is less than 15T, the bearing capacity is level A; when the total weight of the target vehicle is greater than 15T and less than 30T, the bearing capacity is level B; when the total weight of the target vehicle is greater than 30T, the bearing capacity is level C. When the bearing capacity is level A, the safety of the target vehicle driving in the wheel coverage area is the highest, followed by level B, and finally level C.

[0103] Step S105: Based on the bearing capacities corresponding to at least two groups of wheel coverage areas, determine the target driving area from at least two groups of wheel coverage areas. The target driving area is the wheel coverage area with the strongest bearing capacity.

[0104] For the embodiments of the present application, according to the bearing capacity corresponding to each group of wheel coverage areas, the one with the strongest bearing capacity is determined as the target driving area. The road surface flatness corresponding to the target driving area is relatively high. Therefore, the safety of the vehicle when driving in the target driving area is relatively high.

[0105] Based on the driving road image, several interference objects that will affect the normal driving of the target vehicle on the temporary construction road are determined, as well as the position and interference level of each interference object; according to the wheelbase and wheel width of the target vehicle, at least two groups of areas covered by the wheels when the target vehicle is driving are determined in the driving road image; furthermore, the interference objects corresponding to each group of wheel-covered areas and the total weight of the target vehicle are determined, and the bearing capacity corresponding to each group of wheel-covered areas is determined, where the bearing capacity is used to characterize the safety of the target vehicle when driving in the corresponding area; furthermore, the one with the strongest bearing capacity is determined from at least two groups of wheel-covered areas as the target covered area. Since the target vehicle has a higher safety when driving within the wheel-covered area, the driving safety of vehicles at the construction site can be improved.

[0106] Furthermore, based on the driving road image, the positions and interference levels corresponding to several interference objects are determined, including steps S1021 (not shown in the figure) - step S1025 (not shown in the figure), where:

[0107] Step S1021: Determine the road surface area corresponding to the temporary construction road from the driving road image.

[0108] Specifically, the area corresponding to the temporary construction road on which the vehicle is driving, that is, the road surface area, is determined from the driving road image. Among them, if the driving road image is an image captured by an image acquisition device installed on the target vehicle, the road surface area corresponding to the temporary construction road in the driving road image can be determined by identifying the fixed signs on both sides of the road. If the driving road image is an image captured by a monitoring device at the construction site for the temporary construction road where the target vehicle is located, the position of the temporary construction road in the driving road image is relatively fixed, and the road surface area corresponding to the temporary construction road in the driving road image can be determined according to the shooting angle of the monitoring device.

[0109] Step S1022: Divide the road surface area into multiple sub-region images.

[0110] Specifically, due to the different image shooting angles, the manifestation form of the temporary construction road in the driving road image may be different. Therefore, the road surface area corresponding to the temporary construction road can be input into a preset reduction model to determine the restored road surface image, where the restored road surface image is an equal-proportion scaled image of the top view angle of the road surface area corresponding to the temporary construction road. Furthermore, the restored road surface image is divided in the same size and shape to determine several sub-region images, so that the shape and area corresponding to each sub-region image in the actual temporary construction road are the same. Among them, the preset reduction model restores the road surface area by analyzing the shooting angle of the driving road image and combining the extension direction of the road. Step S1023: Determine the standard area from multiple sub-region images.

[0111] Specifically, if the driving road image is an image captured by a monitoring device set at the construction site, the road surface image captured by the monitoring device for the driving road at the initial stage of road use can be obtained. First, the road surface image at the initial stage of road use is divided into several flat sub-region images in the same way as the sub-regions. The similarity between the sub-region images and the flat sub-region images at the same position is compared. The sub-region image with the highest similarity to the road surface image is determined as the standard region from multiple sub-region images, where the flatness of the road surface is relatively high at the initial stage of the driving road being put into use.

[0112] Further, if the driving road image is an image captured by an image acquisition device set on the target vehicle, the type of the driving road in the driving road image can be analyzed first, and then the flat road surface image corresponding to this type of road can be obtained from the image database corresponding to the target vehicle. The image database stores multiple types of flat road surface images captured by the image acquisition device on the target vehicle. Then, the textures corresponding to the flat road surface image and each sub-region image are determined respectively, and the texture of the flat road surface is compared and analyzed with the texture of each sub-region. The sub-region image with the most similar texture to the flat road surface image is determined as the standard region from multiple sub-region images.

[0113] Step S1024: Based on the standard region and multiple sub-region images, several abnormal regions are determined. The abnormal region is a sub-region image with a similarity lower than the preset similarity to the standard region.

[0114] Specifically, the similarity between the remaining sub-region images and the standard region is compared according to the standard region, and the sub-region images with a similarity lower than the preset similarity to the standard region are determined as abnormal regions.

[0115] Step S1025: Based on several abnormal regions, the positions and interference levels corresponding to several interference objects are determined.

[0116] Specifically, the images of each abnormal region are classified and recognized to determine the abnormal type corresponding to each abnormal region. For any abnormal region, if the abnormal type of the adjacent abnormal region is the same as its abnormal type, the adjacent abnormal regions with the same abnormal type can be combined to determine the abnormal type corresponding to several interference objects and at least one abnormal region. For each interference object, the multiple contour coordinate points of at least one abnormal region corresponding to the interference are determined as the position of the interference object, and the interference level corresponding to the interference is determined according to the abnormal type corresponding to the abnormal region and the number of abnormal regions.

[0117] Determine the road surface area corresponding to the temporary construction road from the driving lane image, and divide the road surface area into multiple sub-region images; determine the standard region from the multiple sub-region images; and determine several abnormal regions from the multiple sub-region images according to the standard region; analyze and combine the images of each abnormal region to determine several interfering objects included in the road, as well as the corresponding positions and interference levels of each interfering object, so that the determined interfering objects are more in line with the actual situation of the temporary construction road.

[0118] Further, determining the standard region from the multiple sub-region images includes steps SA1 (not shown in the figure) - step SA4 (not shown in the figure), where:

[0119] Step SA1: Determine the initial sub-region and multiple adjacent sub-regions corresponding to the initial sub-region from the multiple sub-region images, and the initial sub-region is a non-edge sub-region image.

[0120] Specifically, select any non-edge sub-region image from the multiple sub-region images as the initial sub-region, and then determine multiple adjacent sub-regions corresponding to the initial sub-region. Compare and analyze the initial sub-region with each adjacent sub-region respectively to determine the similarity corresponding to the initial sub-region and each adjacent sub-region. And judge whether the similarities corresponding to the initial sub-region and multiple adjacent sub-regions are all higher than the preset similarity

[0121] Further, the number of adjacent sub-regions is determined according to the division method of the sub-region images. Since the initial sub-region is a non-edge sub-region image, if the shape of the sub-region image is hexagonal, the initial sub-region can correspond to six adjacent sub-regions; if the shape of the sub-region image is rectangular, the initial sub-region can correspond to eight adjacent sub-regions.

[0122] Step SA2: Judge whether the regional similarities corresponding to the initial sub-region and multiple adjacent sub-regions are all higher than the preset similarity;

[0123] Step SA3: If so, determine the initial sub-region as the standard region;

[0124] Step SA4: If not, determine the initial sub-region as a non-standard region, and perform the judgment of the next initial sub-region until the standard region is determined.

[0125] Specifically, when cracks or obstacles appear on the road, it generally corresponds to multiple sub-region images. If the similarity between the initial sub-region and its corresponding multiple adjacent sub-regions is higher than the preset similarity, the initial sub-region is determined as the standard region. If there is an adjacent sub-region with a similarity lower than the preset similarity to the initial sub-region, it is impossible to determine whether the initial sub-region is flat, and then the initial sub-region is determined as a non-standard sub-region. Determine a new initial sub-region from multiple sub-region images for judgment, where the new initial sub-region is not a non-standard sub-region and is not a sub-region image close to the edge, and loop through steps SA1 - SA4 until the standard region is determined.

[0126] Determine the initial sub-region from multiple sub-region images, as well as the multiple adjacent sub-regions corresponding to the initial sub-region. Compare the similarity between the initial sub-region and each adjacent sub-region respectively, and judge whether the similarity between the initial sub-region and each adjacent sub-region is higher than the preset similarity; if so, determine the initial sub-region as the standard region, if not, determine the initial sub-region as a non-standard region, and determine a new initial sub-region from the remaining non-edge sub-region images for judgment until the standard region is determined. It can improve the accuracy of the standard region and better conform to the actual situation of the current temporary construction road.

[0127] Further, based on several abnormal regions, determine the positions and interference levels corresponding to several interference objects, including steps SB1 (not shown in the figure) - SB2 (not shown in the figure), where:

[0128] Step SB1: Determine the positions and abnormal types corresponding to several abnormal regions;

[0129] Step SB2: Based on the positions and abnormal types corresponding to several abnormal regions, perform regional combination on the abnormal regions to determine the positions and interference levels corresponding to several interference objects.

[0130] Specifically, determine the position of the image of each abnormal region in the driving road image. Among them, a coordinate system can be established with the area corresponding to the road in the driving road image, and the coordinates where the center point of the abnormal region is located are determined as the coordinates corresponding to the abnormal region. And perform abnormal recognition on the image of each abnormal region to determine the abnormal type corresponding to the abnormal region. Combine the abnormal regions with adjacent positions and the same abnormal type to determine at least one abnormal region corresponding to the interference object, use the multiple contour coordinate points corresponding to at least one abnormal region as the position of the interference object, and determine the interference level of the interference object according to the number and abnormal type of the abnormal regions.

[0131] Determine the position and abnormal type corresponding to each abnormal area, combine the abnormal areas with adjacent positions and the same abnormal type, and determine at least one abnormal area corresponding to the interference object; for each interference object, determine the position of the interference object according to the positions of at least one abnormal area corresponding to the interference object; determine the interference level of the interference object according to the number and abnormal type of the abnormal areas corresponding to the interference object, which can more accurately determine the position and interference level of the interference object.

[0132] Furthermore, based on the total weight of the target vehicle, the positions and interference types corresponding to several interference objects, and at least two groups of wheel coverage areas, determine the bearing capacity corresponding to each of the at least two groups of wheel coverage areas, including step S1041 (not shown in the figure) - step S1042 (not shown in the figure), where:

[0133] Step S1041: Based on the positions and interference levels corresponding to several interference objects and at least two groups of wheel coverage areas, determine the road surface flatness corresponding to each of the at least two groups of wheel coverage areas.

[0134] Specifically, according to the positions corresponding to several interference objects and at least two groups of wheel coverage areas, determine the several interference objects included in each group of wheel coverage areas. For the several interference objects in any group of wheel coverage areas, determine the road surface flatness corresponding to the any group of wheel coverage areas according to the interference type of each interference object. The road surface flatness is used to characterize the degree of interference generated by the interference corresponding to the vehicle driving within the wheel coverage area.

[0135] Furthermore, the road surface flatness of the wheel coverage area can be divided into level 1, level 2,..., level 10 according to the grade division, where level 10 is the flattest and level 1 is the least flat. The road surface flatness is determined according to the number and interference level of the interference objects within the corresponding wheel coverage area. The more the number of interference objects and the higher the interference level, the lower the road surface flatness of the corresponding wheel coverage area.

[0136] Step S1042: Obtain the material type of the driving road.

[0137] Specifically, there are certain differences in the load-bearing capacities of roads made of different materials. Obtain the material type of the driving road, and the driving road is the temporary construction road on which the current target truck is driving. Step S1042 can be executed before step S1041, can also be executed after step S1041, or can be executed simultaneously with step S1041. In the embodiments of the present application, no specific limitation is made.

[0138] Step S1043: Determine the bearing capacity corresponding to each of the at least two wheel coverage areas based on the material type of the driving road, the total weight of the target vehicle, and the road surface flatness corresponding to each of the at least two wheel coverage areas.

[0139] Specifically, for any group of wheel coverage areas, according to the material type of the driving road of the temporary construction road and the road surface flatness, obtain from the database the corresponding relationship table between the bearing capacity and the load-bearing weight range under the condition of the current road surface flatness of the material type of this driving road, determine the load-bearing weight range corresponding to the total weight of the target vehicle, and further determine the bearing capacity corresponding to this group of wheel coverage areas.

[0140] According to the position and interference level of each interference object, determine the road surface flatness corresponding to each group of wheel coverage areas; there are differences in the bearing capacity corresponding to different road surface materials. Furthermore, based on the material type of the driving road and the road surface flatness of each wheel coverage area, determine the bearing capacity of the wheel coverage area under the condition of the total weight of the target vehicle, so that the determined bearing capacity is more in line with the actual situation of the wheel coverage area.

[0141] Furthermore, based on the positions and interference levels corresponding to several interference objects and any wheel coverage area, determining the road surface flatness corresponding to any wheel coverage area includes steps SC1 (not shown in the figure) - step SC2 (not shown in the figure), where:

[0142] Step SC1: Based on the positions corresponding to several interference objects and any wheel coverage area, determine the distances corresponding to several interference objects and any wheel coverage area respectively;

[0143] Step SC2: Based on the interference levels corresponding to several interference objects and the distances corresponding to any wheel coverage area respectively, determine the road surface flatness of any wheel coverage area.

[0144] Specifically, for any wheel coverage area, determine the distance between each interference object and this wheel coverage area; if the position of the interference object is within the wheel coverage area, the distance between this interference object and the vehicle coverage area is 0. Interference objects with different interference levels have different ranges that they can affect. Furthermore, according to the interference level of each interference object and the distance from the wheel coverage area, determine the road surface flatness of this wheel coverage area.

[0145] For any wheel coverage area, determine the distance between each interfering object and the wheel coverage area; combine the interference levels of each interfering object to determine the influence range of each interfering object, and then determine the degree of influence of the interfering object on the road surface within the corresponding distance, and further determine the road surface flatness of any wheel coverage area, which can more accurately determine the degree of influence of each interfering object on the vehicle coverage area.

[0146] Further, when interfering objects appear on the temporary construction road, to ensure driving safety, the corresponding road surface maintenance personnel can be notified to handle the obstacles or cracks on the road surface to improve the flatness of the temporary construction road surface. Therefore, a road image recognition method further includes step S201 of generating maintenance information corresponding to each of several interfering objects based on the positions and interference levels of the interfering objects, where the maintenance information is used to prompt the relevant maintenance personnel to maintain the temporary construction road.

[0147] For the embodiments of the present application, determine whether maintenance is required according to the interference levels corresponding to several interfering objects. If the interference level of a certain interfering object is greater than the preset level, determine the type of maintenance personnel for maintenance according to the type of the interfering object, and generate maintenance information, which includes the position that needs to be maintained, the type of maintenance, and the required maintenance tools, etc. The maintenance information can be sent to the terminal device of the corresponding maintenance personnel to prompt the maintenance personnel to maintain the abnormal situation on the temporary construction road.

[0148] The above embodiments introduce a road image recognition method from the perspective of the method flow. The following embodiments introduce a road image recognition device from the perspective of virtual modules or virtual units. For details, see the following embodiments.

[0149] The embodiments of the present application provide a road image recognition device, as Figure 2 shown. The road image recognition device may specifically include a target vehicle information acquisition module 201, an interfering object information determination module 202, a wheel coverage area determination module 203, a bearing capacity determination module 204, and a target driving area determination module 205, where:

[0150] The target vehicle information acquisition module 201 is used to acquire the driving road image and vehicle information of the target vehicle, and the vehicle information includes the wheelbase, wheel width, and total weight of the target vehicle;

[0151] The interfering object information determination module 202 is used to determine the positions and interference levels corresponding to several interfering objects based on the driving road image, and the interfering objects are objects that affect the normal driving of the vehicle;

[0152] The wheel coverage area determination module 203 is configured to determine at least two sets of wheel coverage areas from the driving road image based on the wheelbase and wheel width of the target vehicle, where the wheel coverage area is the area that the target vehicle will cover when driving on the driving road;

[0153] The bearing capacity determination module 204 is configured to determine the bearing capacity corresponding to each of at least two sets of wheel coverage areas based on the total weight of the target vehicle, the positions and interference levels corresponding to several interference objects, and at least two sets of wheel coverage areas, where the bearing capacity is used to characterize the safety of the target vehicle when driving within the corresponding wheel coverage area;

[0154] The target driving area determination module 205 is configured to determine the target driving area from at least two sets of wheel coverage areas based on the bearing capacity corresponding to each of at least two sets of wheel coverage areas, where the target driving area is the wheel coverage area with the strongest bearing capacity.

[0155] By adopting the above technical solution, several interference objects that will affect the normal driving of the target vehicle on the temporary construction road, as well as the positions and interference levels of each interference object, are determined according to the driving road image; according to the wheelbase and wheel width of the target vehicle, at least two sets of areas covered by the wheels when the target vehicle is driving are determined from the driving road image; furthermore, the interference objects corresponding to each set of wheel coverage areas and the total weight of the target vehicle are determined, and the bearing capacity corresponding to each set of wheel coverage areas is determined, where the bearing capacity is used to characterize the safety of the target vehicle when driving within the corresponding area; furthermore, the wheel coverage area with the strongest bearing capacity is determined from at least two sets of wheel coverage areas as the target coverage area, and the safety of the target vehicle when driving within the wheel coverage area is relatively high, so the driving safety of vehicles at the construction site can be improved.

[0156] In a possible implementation manner, when the interference object information determination module 202 determines the positions and interference levels corresponding to several interference objects based on the driving road image, it is specifically configured to:

[0157] Determine the road surface area corresponding to the temporary construction road from the driving road image;

[0158] Divide the road surface area into multiple sub-region images;

[0159] Determine the standard area from the multiple sub-region images;

[0160] Based on the standard area and the multiple sub-regions, determine several abnormal areas, where the abnormal area is a sub-region with a similarity lower than the preset similarity to the standard area;

[0161] Based on the several abnormal areas, determine the positions and interference levels corresponding to several interference objects.

[0162] In a possible implementation manner, when the interference object information determination module 202 determines a standard region from multiple sub-region images, it is specifically configured to:

[0163] Determine an initial sub-region and multiple adjacent sub-regions corresponding to the initial sub-region from multiple sub-region images, where the initial sub-region is a non-edge sub-region image;

[0164] Judge whether the region similarity between the initial sub-region and each of the multiple adjacent sub-regions is higher than a preset similarity;

[0165] If so, determine the initial sub-region as the standard region;

[0166] If not, determine the initial sub-region as a non-standard region, and perform the judgment on the next initial sub-region until the standard region is determined.

[0167] In a possible implementation manner, when the interference object information determination module 202 determines the positions and interference levels corresponding to several interference objects based on several abnormal regions, it is specifically configured to:

[0168] Determine the positions and abnormal types corresponding to several abnormal regions respectively;

[0169] Based on the positions and abnormal types corresponding to several abnormal regions respectively, perform region combination on the abnormal regions to determine the positions and interference levels corresponding to several interference objects respectively.

[0170] In a possible implementation manner, when the bearing capacity determination module 204 determines the bearing capacities corresponding to at least two groups of wheel coverage regions based on the total weight of the target vehicle, the positions and interference levels corresponding to several interference objects, and at least two groups of wheel coverage regions, it is specifically configured to:

[0171] Based on the positions and interference levels corresponding to several interference objects and at least two groups of wheel coverage regions, determine the road surface flatness corresponding to at least two groups of wheel coverage regions respectively;

[0172] Obtain the material type of the driving road;

[0173] Based on the material type of the driving road, the total weight of the target vehicle, and the road surface flatness corresponding to at least two groups of wheel coverage regions respectively, determine the bearing capacities corresponding to at least two groups of wheel coverage regions respectively.

[0174] In a possible implementation manner, when the bearing capacity determination module 204 determines the road surface flatness corresponding to any one of the wheel coverage regions based on the positions and interference levels corresponding to several interference objects and any one of the wheel coverage regions, it is specifically configured to:

[0175] Based on the positions corresponding to several interference objects and any wheel coverage area, determine the distances corresponding to the several interference objects and any wheel coverage area respectively;

[0176] Based on the interference levels corresponding to several interference objects and the distances corresponding to any wheel coverage area respectively, determine the road surface flatness of any wheel coverage area.

[0177] In a possible implementation manner, a road image recognition device further includes:

[0178] A maintenance module, configured to generate maintenance information corresponding to several interference objects respectively based on the positions and types corresponding to the several interference objects, where the maintenance information is used to prompt relevant maintenance personnel to maintain a temporarily constructed road.

[0179] In an embodiment of the present application, an electronic device is provided, as Figure 3 shown, Figure 3 The electronic device 300 shown includes a processor 301 and a memory 303. Among them, the processor 301 and the memory 303 are connected, such as connected through a bus 302. Optionally, the electronic device 300 may further include a transceiver 304. It should be noted that in practical applications, the transceiver 304 is not limited to one, and the structure of the electronic device 300 does not constitute a limitation to the embodiment of the present application.

[0180] The processor 301 may be a CPU (Central Processing Unit, central processor), a general-purpose processor, a DSP (Digital Signal Processor, data signal processor), an ASIC (Application Specific Integrated Circuit, application-specific integrated circuit), an FPGA (Field Programmable Gate Array, field programmable gate array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It can implement or execute various exemplary logical blocks, modules and circuits described in combination with the disclosure of the present application. The processor 301 may also be a combination for implementing a computing function, such as a combination including one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0181] The bus 302 may include a path for transmitting information among the above components. The bus 302 can be a PCI (Peripheral Component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, or the like. The bus 302 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 it is only represented by a thick line in Figure 3 , but it does not mean that there is only one bus or one type of bus.

[0182] The memory 303 can be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or it can also be an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory), or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media, or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0183] The memory 303 is used to store the application program code for executing the solution of this application, and is controlled by the processor 301 for execution. The processor 301 is used to execute the application program code stored in the memory 303 to implement the content shown in the foregoing method embodiments.

[0184] Among them, the electronic device includes but is not limited to: mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Tablet Computers), PMPs (Portable Multimedia Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. It can also be a server, etc. Figure 3 The electronic device shown is only an example and should not bring any restrictions to the functions and usage scopes of the embodiments of this application.

[0185] The embodiments of this application provide a computer-readable storage medium on which a computer program is stored. When it runs on a computer, it enables the computer to execute the corresponding content in the foregoing method embodiments.

[0186] It should be understood that although the steps in the flowchart of the accompanying drawings are shown sequentially according to the indication of the arrows, these steps are not necessarily executed sequentially in the order indicated by the arrows. Unless there is a clear indication in this document, there is no strict order restriction for the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or sub-steps or stages of other steps.

[0187] The above are only some embodiments of the present application. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present application, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present application.

Claims

1. A road image recognition method, characterized in that, Including: Obtaining a driving road image of a target vehicle and vehicle information, where the vehicle information includes the wheelbase, wheel width, and total weight of the target vehicle; Based on the driving road image, determining the positions and interference levels corresponding to several interference objects, where the interference objects are objects that affect the normal driving of the vehicle; Based on the wheelbase and wheel width of the target vehicle, determining at least two groups of wheel coverage areas from the driving road image, where the wheel coverage areas are the areas that the target vehicle will cover when driving on the driving road; Based on the total weight of the target vehicle, the positions and interference levels corresponding to the several interference objects, and the at least two groups of wheel coverage areas, determining the bearing capacity corresponding to each of the at least two groups of wheel coverage areas, where the bearing capacity is used to characterize the safety of the target vehicle when driving within the corresponding wheel coverage area; Based on the bearing capacity corresponding to each of the at least two groups of wheel coverage areas, determining a target driving area from the at least two groups of wheel coverage areas, where the target driving area is the wheel coverage area with the strongest bearing capacity.

2. The method for road image recognition according to claim 1, wherein, The determining the positions and interference levels corresponding to several interference objects based on the driving road image includes: Determining the road surface area corresponding to the temporary construction road from the driving road image; Dividing the road surface area into multiple sub-region images; Determining a standard area from the multiple sub-region images; Based on the standard area and the multiple sub-regions, determining several abnormal areas, where the abnormal areas are sub-regions with a similarity lower than a preset similarity to the standard area; Based on the several abnormal areas, determining the positions and interference levels corresponding to several interference objects.

3. The road image recognition method according to claim 2, characterized in that, The determining a standard area from the multiple sub-region images includes: Determining an initial sub-region and multiple adjacent sub-regions corresponding to the initial sub-region from the multiple sub-region images, where the initial sub-region is a non-edge sub-region image; Judging whether the area similarities between the initial sub-region and the multiple adjacent sub-regions are all higher than the preset similarity; If so, determining the initial sub-region as the standard area; If not, determining the initial sub-region as a non-standard area, and performing the judgment of the next initial sub-region until a standard area is determined.

4. The method for road image recognition according to claim 2, wherein, The determining the bearing capacity corresponding to each of the at least two groups of wheel coverage areas based on the total weight of the target vehicle, the positions and interference levels corresponding to the several interference objects, and the at least two groups of wheel coverage areas includes: Determining the positions and abnormal types corresponding to the several abnormal areas; Based on the positions and abnormal types corresponding to the several abnormal areas, performing area combination on the abnormal areas to determine the positions and interference levels corresponding to several interference objects.

5. A road image recognition method according to claim 1, characterized in that: The determining the bearing capacity corresponding to each of the at least two groups of wheel coverage areas based on the total weight of the target vehicle, the positions and interference levels corresponding to the several interference objects, and the at least two groups of wheel coverage areas includes: Based on the positions and interference levels corresponding to the several interference objects and the at least two groups of wheel coverage areas, determining the road surface flatness corresponding to each of the at least two groups of wheel coverage areas; Obtain the material type of the driving road; Based on the material type of the driving road, the total weight of the target vehicle, and the road surface flatness corresponding to each of the at least two groups of wheel coverage areas, determine the bearing capacity corresponding to each of the at least two groups of wheel coverage areas.

6. A road image recognition method according to claim 5, characterized in that, Based on the positions and interference levels corresponding to the several interference objects and any one of the wheel coverage areas, determine the road surface flatness corresponding to any one of the wheel coverage areas, including: Based on the positions corresponding to the several interference objects and any one of the wheel coverage areas, determine the distances corresponding to the several interference objects and any one of the wheel coverage areas; Based on the interference levels corresponding to the several interference objects and the distances corresponding to any one of the wheel coverage areas, determine the road surface flatness of any one of the wheel coverage areas.

7. A method for road image recognition according to claim 1, characterized in that Further include: Based on the positions and types corresponding to the several interference objects, generate maintenance information corresponding to the several interference objects, and the maintenance information is used to prompt relevant maintenance personnel to maintain the temporary construction road.

8. A road image recognition device, characterized in that Include: A target vehicle information acquisition module, configured to acquire an image of the driving road of the target vehicle and vehicle information, where the vehicle information includes the wheelbase, wheel width, and total weight of the target vehicle; An interference object information determination module, configured to determine the positions and interference levels corresponding to several interference objects based on the image of the driving road, where the interference objects are objects that affect the normal driving of the vehicle; A wheel coverage area determination module, configured to determine at least two groups of wheel coverage areas from the image of the driving road based on the wheelbase and wheel width of the target vehicle, where the wheel coverage area is the area that the target vehicle will cover when driving on the driving road; A bearing capacity determination module, configured to determine the bearing capacity corresponding to each of the at least two groups of wheel coverage areas based on the total weight of the target vehicle, the positions and interference levels corresponding to the several interference objects, and the at least two groups of wheel coverage areas, and the bearing capacity is used to characterize the safety of the target vehicle when driving within the corresponding wheel coverage area; A target driving area determination module, configured to determine a target driving area from the at least two groups of wheel coverage areas based on the bearing capacity corresponding to each of the at least two groups of wheel coverage areas, and the target driving area is the wheel coverage area with the strongest bearing capacity.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; A memory; At least one application program, where the at least one application program is stored in the memory and is configured to be executed by at least one processor, and the at least one application program is configured to: execute the road image recognition method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, Include: A computer program stored with the ability to be loaded and executed by a processor to execute the road image recognition method according to any one of claims 1-7.

Images