Map updating method and device, electronic equipment and computer readable storage medium

Abstract

The application discloses a map updating method and device, electronic equipment and a computer readable storage medium. The method comprises the following steps: acquiring a road image collected by a roadside camera and detecting the road image to obtain a detection result of a motor vehicle area and an initial detection result of a non-motor vehicle parking area in the road image; determining a corrected detection result of the non-motor vehicle parking area in the road image according to the detection result of the motor vehicle area and the initial detection result of the non-motor vehicle parking area; performing boundary segmentation on the corrected detection result of the non-motor vehicle parking area to obtain an actual non-motor vehicle parking area in the road image; and updating a road map according to the actual non-motor vehicle parking area in the road image. The application updates the accurate area position of the non-motor vehicle parking area to the map based on the detection of the non-motor vehicle parking area by the roadside sensing device, so that the application can be used for navigation of the non-motor vehicle parking area and parking navigation of the automatic driving non-motor vehicle.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of map updating, in particular to a map updating method and device, electronic equipment and a computer readable storage medium. BACKGROUND

[0002] With the popularization of travel concepts such as "green and healthy", "energy saving and environmental protection", non-motor vehicles have gradually become the preferred travel mode for people's short-distance travel, and the provision of non-motor vehicle parking areas can facilitate people to park non-motor vehicles more conveniently when traveling and even provide help for automatic parking of automatic driving non-motor vehicles.

[0003] However, the current road map rarely provides relevant information of non-motor vehicle parking areas, and even if a few maps can provide information of non-motor vehicle parking areas, the information of non-motor vehicle parking areas needs to be collected manually and then synchronized to the map, resulting in low map updating efficiency and high cost. SUMMARY

[0004] The embodiments of the present application provide a map updating method, device, electronic equipment and computer readable storage medium to update the information of non-motor vehicle parking areas to the map, providing a basis for non-motor vehicle travel navigation.

[0005] The embodiments of the present application adopt the following technical solutions:

[0006] In a first aspect, the embodiments of the present application provide a map updating method, and the method comprises:

[0007] obtaining a road image collected by a roadside camera and detecting the road image to obtain a detection result of a motor vehicle area and an initial detection result of a non-motor vehicle parking area in the road image;

[0008] determining a corrected detection result of the non-motor vehicle parking area in the road image according to the detection result of the motor vehicle area and the initial detection result of the non-motor vehicle parking area;

[0009] performing boundary segmentation on the corrected detection result of the non-motor vehicle parking area to obtain an actual non-motor vehicle parking area in the road image;

[0010] updating a road map according to the actual non-motor vehicle parking area in the road image.

[0011] Optionally, the detection of the road image to obtain the detection result of the motor vehicle area and the initial detection result of the non-motor vehicle parking area comprises:

[0012] detecting the motor vehicle in the road image by using a first preset target detection model to obtain a motor vehicle detection result;

[0013] determining a motor vehicle region detection result and a non-motor vehicle region detection result in the road image according to the motor vehicle detection result;

[0014] determining an initial non-motor vehicle parking region detection result according to the non-motor vehicle region detection result.

[0015] Optionally, the determining the initial non-motor vehicle parking region detection result according to the non-motor vehicle region detection result comprises:

[0016] detecting a parking region in the non-motor vehicle region by using a second preset target detection model to obtain the initial non-motor vehicle parking region detection result.

[0017] Optionally, the determining the corrected non-motor vehicle parking region detection result in the road image according to the motor vehicle region detection result and the initial non-motor vehicle parking region detection result comprises:

[0018] determining a road boundary corresponding to the motor vehicle region according to the motor vehicle region detection result;

[0019] correcting the initial non-motor vehicle parking region detection result by using the road boundary corresponding to the motor vehicle region to obtain the corrected non-motor vehicle parking region detection result.

[0020] Optionally, the initial non-motor vehicle parking region detection result comprises an initial non-motor vehicle parking region detection box, the corrected non-motor vehicle parking region detection result comprises a corrected non-motor vehicle parking region detection box, and the correcting the initial non-motor vehicle parking region detection result by using the road boundary corresponding to the motor vehicle region to obtain the corrected non-motor vehicle parking region detection result in the road image comprises:

[0021] determining a part of the initial non-motor vehicle parking region detection box that is beyond the road boundary corresponding to the motor vehicle region based on the road boundary corresponding to the motor vehicle region;

[0022] removing the part of the initial non-motor vehicle parking region detection box that is beyond the road boundary corresponding to the motor vehicle region to obtain the corrected non-motor vehicle parking region detection box.

[0023] Optionally, the updating the road map according to the actual non-motor vehicle parking region in the road image comprises:

[0024] detecting, by using a third preset target detection model, the non-motor vehicle in the actual non-motor vehicle parking area, to obtain a non-motor vehicle detection result;

[0025] tracking, according to the non-motor vehicle detection result, the non-motor vehicle, to obtain a non-motor vehicle tracking result;

[0026] verifying, according to the non-motor vehicle tracking result, the actual non-motor vehicle parking area;

[0027] in a case where the verification is passed, updating, according to the actual non-motor vehicle parking area, the road map.

[0028] Optionally, the updating, according to the actual non-motor vehicle parking area in the road image, of the road map comprises:

[0029] obtaining a transformation relationship between a roadside camera coordinate system and a world coordinate system;

[0030] transforming, according to the transformation relationship between the roadside camera coordinate system and the world coordinate system, the actual non-motor vehicle parking area in the road image to the world coordinate system, to obtain a non-motor vehicle parking area in the world coordinate system;

[0031] updating, by using the non-motor vehicle parking area in the world coordinate system, of the road map.

[0032] In a second aspect, the embodiments of the present application further provide a map updating device, wherein the device comprises:

[0033] a detection unit configured to acquire a road image collected by a roadside camera, and detect the road image to obtain a detection result of a motor vehicle area and an initial detection result of a non-motor vehicle parking area in the road image;

[0034] a determination unit configured to determine a corrected detection result of the non-motor vehicle parking area in the road image according to the detection result of the motor vehicle area and the initial detection result of the non-motor vehicle parking area;

[0035] a segmentation unit configured to perform boundary segmentation on the corrected detection result of the non-motor vehicle parking area to obtain an actual non-motor vehicle parking area in the road image;

[0036] an updating unit configured to update a road map according to the actual non-motor vehicle parking area in the road image.

[0037] In a third aspect, the embodiments of the present application further provide an electronic device, comprising:

[0038] a processor; and

[0039] a memory arranged to store computer-executable instructions that, when executed, cause the processor to perform any of the aforementioned methods.

[0040] In a fourth aspect, the embodiments of the present application further provide a computer-readable storage medium storing one or more programs, which, when executed by an electronic device comprising a plurality of application programs, cause the electronic device to perform any of the aforementioned methods.

[0041] The above at least one technical scheme adopted by the embodiments of the present application can achieve the following beneficial effects: the map updating method of the embodiments of the present application first acquires a road image collected by a roadside camera, and detects the road image to obtain a detection result of a motor vehicle region and an initial detection result of a non-motor vehicle parking region in the road image; then determines a corrected detection result of the non-motor vehicle parking region in the road image according to the detection result of the motor vehicle region and the initial detection result of the non-motor vehicle parking region; thereafter performs boundary segmentation on the corrected detection result of the non-motor vehicle parking region to obtain an actual non-motor vehicle parking region in the road image; and finally updates a road map according to the actual non-motor vehicle parking region in the road image. The map updating method of the embodiments of the present application updates the accurate region position of the non-motor vehicle parking region to the map based on the detection of the non-motor vehicle parking region by the roadside perception device, so as to be used for navigation of the non-motor vehicle parking region and parking navigation of an autonomous non-motor vehicle, etc. BRIEF DESCRIPTION OF DRAWINGS

[0042] The accompanying drawings, which are included to provide a further understanding of the present application, constitute a part of the present application and illustrate illustrative embodiments of the present application and its description, which serve to explain the present application, and do not constitute improper limitations on the present application. In the drawings:

[0043] Figure 1 a flowchart of a map updating method in the embodiments of the present application;

[0044] Figure 2 a structural diagram of a map updating device in the embodiments of the present application;

[0045] Figure 3 a structural diagram of an electronic device in the embodiments of the present application. DETAILED DESCRIPTION

[0046] In order to make the purposes, technical solutions and advantages of the present application clearer, the technical solutions of the present application will be described below in connection with specific embodiments of the present application and corresponding drawings. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0047] The technical solutions provided by the embodiments of the present application will be described in detail below in connection with the drawings.

[0048] The embodiments of the present application provide a map updating method, as shown in the figure, a flowchart of a map updating method in the embodiments of the present application is provided, and the method at least includes the following steps S110 to S140: Figure 1

[0049] Step S110, acquiring a road image collected by a roadside camera and detecting the road image to obtain a detection result of a motor vehicle area and an initial detection result of a non-motor vehicle parking area in the road image.

[0050] The map updating method of the embodiments of the present application is mainly used to provide the related information of the non-motor vehicle parking area for the current map, so as to facilitate the navigation of the non-motor vehicle parking area and the parking navigation of the automatic driving non-motor vehicle, etc.

[0051] The embodiments of the present application need to acquire a road image collected by a roadside camera first, and then detect the road image to obtain a detection result of a motor vehicle area and an initial detection result of a non-motor vehicle parking area in the road image. The detection result of the motor vehicle area here can be understood as the area range of the motor vehicle drivable area. Considering the actual road scene, the non-motor vehicle parking area in the road usually adopts the form of a rectangular frame (closed or open), so the initial detection result of the non-motor vehicle parking area here mainly refers to the position of the initial detection frame of the non-motor vehicle parking area.

[0052] Step S120, determining a correction detection result of the non-motor vehicle parking area in the road image according to the detection result of the motor vehicle area and the initial detection result of the non-motor vehicle parking area.

[0053] Since the detection result of the non-motor vehicle parking area obtained by the foregoing step only provides a general non-motor vehicle parking area range, and the information required to be updated to the road map is the area position information which is accurate enough, the embodiments of the present application can further correct the initial detection result of the non-motor vehicle parking area in combination with the detection result of the motor vehicle area, further accurately the range of the non-motor vehicle parking area, so as to obtain the correction detection result of the non-motor vehicle parking area. ​

[0054] Step S130, boundary segmentation is performed on the corrected detection result of the non-motor vehicle parking area to obtain the actual non-motor vehicle parking area in the road image.

[0055] The corrected detection result of the non-motor vehicle parking area obtained by the above steps is also a detection box obtained by image detection in nature, but due to the shooting angle of the roadside camera and image distortion, the non-motor vehicle parking area in the road image collected by the roadside camera is not a perfect rectangular box, that is, the four boundaries of the detection box of the above corrected result are not necessarily the boundary positions of the actual non-motor vehicle parking area, and therefore the embodiment of the present application needs to further perform boundary segmentation detection on the corrected detection result of the non-motor vehicle parking area to obtain the boundary positions of the actual non-motor vehicle parking area in the road image.

[0056] The boundary segmentation can be obtained based on an existing segmentation detection model, and by performing straight line segmentation detection on the white solid line or the yellow solid line in the actual road scene, the area range surrounded by the segmented straight line is taken as the actual non-motor vehicle parking area.

[0057] Step S140, updating the road map according to the actual non-motor vehicle parking area in the road image.

[0058] After obtaining the boundary positions of the actual non-motor vehicle parking area in the road image, the absolute position information of the actual non-motor vehicle parking area can be updated to the corresponding position of the road map based on the boundary positions of the actual non-motor vehicle parking area in the road image, and the road map here can be a cloud high-definition map, a standard map, etc., so as to facilitate the user or the automatic driving non-motor vehicle to navigate based on the updated map when entering the non-motor vehicle parking area.

[0059] The map updating method of the embodiment of the present application updates the accurate area position of the non-motor vehicle parking area to the map based on the detection of the non-motor vehicle parking area by the roadside perception device, so as to be used for navigation of the non-motor vehicle parking area and parking navigation of the automatic driving non-motor vehicle, etc.

[0060] In some embodiments of the present application, the detection of the road image to obtain the detection result of the motor vehicle area and the initial detection result of the non-motor vehicle parking area in the road image comprises: detecting the motor vehicle in the road image by using a first preset target detection model to obtain a motor vehicle detection result; determining the detection result of the motor vehicle area and the detection result of the non-motor vehicle area in the road image according to the motor vehicle detection result; and determining the initial detection result of the non-motor vehicle parking area according to the detection result of the non-motor vehicle area.

[0061] The embodiment of the present application can first detect motor vehicle targets in the road image by using a first preset target detection model, determine the area covered by the motor vehicle according to the detected motor vehicle, define the area covered by the motor vehicle in the road image as a motor vehicle area, and define other areas in the road image as non-motor vehicle areas. The first preset target detection model can be obtained based on an existing convolutional neural network such as a YOLO series network. How to detect non-motor vehicles is flexible and can be determined by combining the prior art, and is not limited here.

[0062] The non-motor vehicle area may contain a non-motor vehicle driving area or a non-motor vehicle parking area, so the embodiment of the present application can further detect a non-motor vehicle parking area in the non-motor vehicle area to obtain an initial detection result of the non-motor vehicle parking area.

[0063] By the above method of first determining the non-motor vehicle area and then determining the non-motor vehicle parking area in the non-motor vehicle area, the possibility of false detection of the non-motor vehicle parking area can be reduced to some extent. It should be noted that in other embodiments of the present application, the non-motor vehicle parking area in the road image can be directly detected, and in the case of meeting the map accuracy requirements, it can also be used as a basis for map updating.

[0064] In some embodiments of the present application, the initial detection result of the non-motor vehicle parking area is determined according to the detection result of the non-motor vehicle area, which includes: detecting the parking area in the non-motor vehicle area by using a second preset target detection model to obtain the initial detection result of the non-motor vehicle parking area.

[0065] In the embodiment of the present application, the second preset target detection model is used to detect the parking area in the non-motor vehicle area. Since the boundary of the non-motor vehicle parking area in the actual road scene is usually in the form of four lines intersecting or three lines intersecting (i.e. lacking the boundary on the side close to the motor vehicle road), the embodiment of the present application can use a large number of sample images containing the non-motor vehicle parking area in the above form, and mark the rectangular frame position of the non-motor vehicle parking area, so as to train the convolutional neural network and obtain the second preset target detection model.

[0066] Due to the interference of other road signs and obstacles in the road image, the detection result of the second preset target detection model may have some false detection, so the detection result of the non-motor vehicle parking area obtained above can be used as an initial detection result, and the detection result can be further corrected to accurately determine the position of the non-motor vehicle parking area.

[0067] In some embodiments of the present application, the determining the corrected detection result of the non-motor vehicle parking area in the road image according to the detection result of the motor vehicle area and the initial detection result of the non-motor vehicle parking area comprises: determining the road boundary corresponding to the motor vehicle area according to the detection result of the motor vehicle area; and correcting the initial detection result of the non-motor vehicle parking area by using the road boundary corresponding to the motor vehicle area to obtain the corrected detection result of the non-motor vehicle parking area.

[0068] Since the initial detection result of the non-motor vehicle parking area is essentially a minimum enclosing box corresponding to the boundary of the non-motor vehicle parking area, and the road area contained in the minimum enclosing box may have a part falling within the non-motor vehicle area, when the initial detection result of the non-motor vehicle parking area is corrected by using the motor vehicle area, the present application can first determine the road boundary corresponding to the motor vehicle area according to the detection result of the motor vehicle area, and then correct the initial detection result of the non-motor vehicle parking area by using the road boundary corresponding to the motor vehicle area, that is, the boundary position of the non-motor vehicle parking area is further refined by the constraint of the boundary position of the motor vehicle area.

[0069] When determining the road boundary of the motor vehicle area, it can be determined based on the driving coverage range of the motor vehicle, or based on the road identification information in the high-precision map corresponding to the area where the roadside camera is located. The motor vehicle road boundary position in the high-precision map is projected into the image through the transformation relationship between the roadside camera and the high-precision map, so as to determine the road boundary of the motor vehicle area in the road image. Alternatively, since the position of the roadside camera is fixed, the actual road boundary position of the motor vehicle area is also fixed, and therefore the road boundary position of the motor vehicle area in the road image captured by the roadside camera is also fixed, and the road boundary corresponding to the motor vehicle area can be determined by manually drawing a line. Of course, how to determine the road boundary of the motor vehicle area can be flexibly selected by those skilled in the art according to actual needs, which is not limited here.

[0070] In some embodiments of the present application, the initial detection result of the non-motor vehicle parking area comprises an initial detection box of the non-motor vehicle parking area, the corrected detection result of the non-motor vehicle parking area comprises a corrected detection box of the non-motor vehicle parking area, and the correcting the initial detection result of the non-motor vehicle parking area by using the road boundary corresponding to the motor vehicle area to obtain the corrected detection result of the non-motor vehicle parking area in the road image comprises: determining the part of the initial detection box of the non-motor vehicle parking area that is beyond the road boundary corresponding to the motor vehicle area based on the road boundary corresponding to the motor vehicle area; and removing the part of the initial detection box of the non-motor vehicle parking area that is beyond the road boundary corresponding to the motor vehicle area to obtain the corrected detection box of the non-motor vehicle parking area.

[0071] The initial detection result of the non-motor vehicle parking area in the embodiments of the present application includes an initial detection frame of the non-motor vehicle parking area. When the initial detection frame of the non-motor vehicle parking area is corrected, a part of the initial detection frame of the non-motor vehicle parking area falling into the motor vehicle area can be determined based on the road boundary corresponding to the motor vehicle area. This part is obviously not part of the non-motor vehicle parking area, so this part of the image area can be directly removed from the initial detection frame, and the remaining part is used as the corrected detection frame of the non-motor vehicle parking area, that is, the area range of the non-motor vehicle parking area is further refined by the road boundary of the motor vehicle area.

[0072] In some embodiments of the present application, updating the road map according to the actual non-motor vehicle parking area in the road image includes: detecting non-motor vehicles in the actual non-motor vehicle parking area by using a third preset target detection model to obtain a non-motor vehicle detection result; tracking the non-motor vehicles according to the non-motor vehicle detection result to obtain a non-motor vehicle tracking result; verifying the actual non-motor vehicle parking area according to the non-motor vehicle tracking result; and updating the road map according to the actual non-motor vehicle parking area in the case of passing the verification.

[0073] In order to further improve the accuracy of map updating, after determining the actual non-motor vehicle parking area in the road image based on the foregoing embodiments, the embodiments of the present application can further combine the tracking detection result of the non-motor vehicle target in the actual non-motor vehicle parking area to determine whether the actual non-motor vehicle parking area can be updated to the road map.

[0074] Specifically, the non-motor vehicle such as a bicycle target in the actual non-motor vehicle parking area in the continuous multiple frames of road images can be detected by using a third preset target detection model trained in advance to obtain a non-motor vehicle detection result of the continuous multiple frames. The non-motor vehicle detection results of multiple frames are associated to obtain the parking time of the same non-motor vehicle in the actual non-motor vehicle parking area. If the parking time exceeds a certain time threshold, the area is marked as a non-motor vehicle parking area, and then the road map can be updated based on the boundary position information of the non-motor vehicle parking area.

[0075] In some embodiments of the present application, updating the road map according to the actual non-motor vehicle parking area in the road image includes: obtaining a transformation relationship between a roadside camera coordinate system and a world coordinate system; transforming the actual non-motor vehicle parking area in the road image to the world coordinate system according to the transformation relationship between the roadside camera coordinate system and the world coordinate system to obtain a non-motor vehicle parking area in the world coordinate system; and updating the road map by using the non-motor vehicle parking area in the world coordinate system.

[0076] Since the boundary position information of the actual non-motor vehicle parking area in the road image is in the roadside camera coordinate system, and the position information in the road map is absolute position information in the world coordinate system, the embodiment of the present application can convert the boundary position of the actual non-motor vehicle parking area in the road image to the world coordinate system based on the transformation relationship between the roadside camera coordinate system and the world coordinate system, so as to obtain the boundary position of the non-motor vehicle parking area in the world coordinate system, and finally update the boundary position of the non-motor vehicle parking area in the world coordinate system to the corresponding position of the road map.

[0077] The embodiment of the present application provides a map updating device 200, as shown in the structure schematic diagram of the map updating device in the embodiment of the present application, the device 200 comprises a detection unit 210, a determination unit 220, a segmentation unit 230 and an updating unit 240, wherein: Figure 2

[0078] The detection unit 210 is configured to acquire a road image collected by a roadside camera, and detect the road image to obtain a detection result of a motor vehicle area and an initial detection result of a non-motor vehicle parking area in the road image.

[0079] The determination unit 220 is configured to determine a corrected detection result of the non-motor vehicle parking area in the road image according to the detection result of the motor vehicle area and the initial detection result of the non-motor vehicle parking area.

[0080] The segmentation unit 230 is configured to perform boundary segmentation on the corrected detection result of the non-motor vehicle parking area to obtain an actual non-motor vehicle parking area in the road image.

[0081] The updating unit 240 is configured to update a road map according to the actual non-motor vehicle parking area in the road image.

[0082] In some embodiments of the present application, the detection unit 210 is specifically configured to: detect a motor vehicle in the road image by using a first preset target detection model to obtain a motor vehicle detection result; determine a detection result of a motor vehicle area and a detection result of a non-motor vehicle area in the road image according to the motor vehicle detection result; and determine the initial detection result of the non-motor vehicle parking area according to the detection result of the non-motor vehicle area.

[0083] In some embodiments of the present application, the detection unit 210 is specifically configured to: detect a parking area in the non-motor vehicle area by using a second preset target detection model to obtain the initial detection result of the non-motor vehicle parking area.

[0084] ​In some embodiments of the present application, the determining unit 220 is specifically configured to: determine the road boundary corresponding to the motor vehicle area according to the detection result of the motor vehicle area; and correct the initial detection result of the non-motor vehicle parking area by using the road boundary corresponding to the motor vehicle area, to obtain the corrected detection result of the non-motor vehicle parking area.

[0085] In some embodiments of the present application, the initial detection result of the non-motor vehicle parking area includes an initial detection box of the non-motor vehicle parking area, and the corrected detection result of the non-motor vehicle parking area includes a corrected detection box of the non-motor vehicle parking area. The determining unit 220 is specifically configured to: determine the part of the initial detection box of the non-motor vehicle parking area that is beyond the road boundary corresponding to the motor vehicle area based on the road boundary corresponding to the motor vehicle area; and remove the part of the initial detection box of the non-motor vehicle parking area that is beyond the road boundary corresponding to the motor vehicle area, to obtain the corrected detection box of the non-motor vehicle parking area.

[0086] In some embodiments of the present application, the updating unit 240 is specifically configured to: detect non-motor vehicles in the actual non-motor vehicle parking area by using a third preset target detection model, to obtain a non-motor vehicle detection result; track the non-motor vehicles according to the non-motor vehicle detection result, to obtain a non-motor vehicle tracking result; verify the actual non-motor vehicle parking area according to the non-motor vehicle tracking result; and update the road map according to the actual non-motor vehicle parking area in a case where the verification is passed.

[0087] In some embodiments of the present application, the updating unit 240 is specifically configured to: obtain a transformation relationship between a roadside camera coordinate system and a world coordinate system; transform the actual non-motor vehicle parking area in the road image to the world coordinate system according to the transformation relationship between the roadside camera coordinate system and the world coordinate system, to obtain a non-motor vehicle parking area in the world coordinate system; and update the road map by using the non-motor vehicle parking area in the world coordinate system.

[0088] It can be understood that the above map updating apparatus can realize each step of the map updating method provided in the foregoing embodiments, and the related explanations about the map updating method are all applicable to the map updating apparatus, which will not be repeated here.

[0089] Figure 3 is a structural schematic diagram of an electronic device according to an embodiment of the present application. Please refer to Figure 3At the hardware level, the electronic device includes a processor and, optionally, an internal bus, a network interface, and memory. The memory may include internal memory, such as high-speed random-access memory (RAM), or non-volatile memory, such as at least one disk drive. Of course, the electronic device may also include other hardware required for its services.

[0090] The processor, network interface, and memory can be interconnected via an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0091] The memory is used to store programs. Specifically, the program may include program code, which includes computer operating instructions. The memory may include internal memory and non-volatile memory, and provides instructions and data to the processor.

[0092] The processor reads the corresponding computer program from the non-volatile memory into the internal memory and then runs it, forming a map update device at the logical level. The processor executes the program stored in the memory and is specifically used to perform the following operations:

[0093] Acquire a road image captured by a roadside camera, and perform detection on the road image to obtain a detection result of a motor vehicle area and an initial detection result of a non-motor vehicle parking area in the road image;

[0094] determining a revised detection result of the non-motor vehicle parking area in the road image based on the detection result of the motor vehicle area and the initial detection result of the non-motor vehicle parking area;

[0095] performing boundary segmentation on the corrected detection result of the non-motor vehicle parking area to obtain an actual non-motor vehicle parking area in the road image;

[0096] The road map is updated according to the actual non-motor vehicle parking area in the road image.

[0097] The above application Figure 1The method performed by the map updating apparatus disclosed in the embodiments shown can be applied in a processor or implemented by the processor. The processor can be an integrated circuit chip with processing capability. In the implementation process, the steps of the method can be completed by the integrated logic circuit or the instruction of the software form in the processor. The processor mentioned above can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; or can be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The methods, steps and logical block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as a hardware code processor for execution, or a combination of hardware and software modules in the code processor for execution. The software module can be located in a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium in the art. The storage medium is located in the memory, and the processor reads the information in the memory, and combines the hardware to complete the steps of the above method.

[0098] The electronic device can also execute Figure 1 the method performed by the map updating apparatus in the embodiments shown, and implement the functions of the map updating apparatus in Figure 1 the embodiments shown. The embodiments of the present application will not be described here.

[0099] The embodiments of the present application also propose a computer readable storage medium, which stores one or more programs, the one or more programs including instructions, which when executed by an electronic device including a plurality of application programs, can enable the electronic device to execute Figure 1 the method performed by the map updating apparatus in the embodiments shown, and specifically for executing

[0100] obtaining a road image collected by a roadside camera, and detecting the road image to obtain a detection result of a motor vehicle region and an initial detection result of a non-motor vehicle parking region in the road image;

[0101] determining a correction detection result of the non-motor vehicle parking area in the road image according to the detection result of the motor vehicle area and the initial detection result of the non-motor vehicle parking area;

[0102] performing boundary segmentation on the correction detection result of the non-motor vehicle parking area to obtain an actual non-motor vehicle parking area in the road image;

[0103] updating a road map according to the actual non-motor vehicle parking area in the road image.

[0104] Those skilled in the art will understand that embodiments of the present application can be provided as methods, systems, or computer program products. Accordingly, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application can take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage devices, etc.) embodying computer readable program code.

[0105] The present application is described in reference to the flowchart and / or block diagrams of the method, apparatus (system) and computer program product according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing apparatus to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing apparatus produce the functions specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more flows and / or blocks Figure 1 means for performing the function specified in the flow or flows and / or block or blocks.

[0106] These computer program instructions can also be stored in a computer-readable memory that can direct the computer or other programmable data processing apparatus to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including instruction means, which implements the functions specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more flows and / or blocks Figure 1 means for performing the function specified in the flow or flows and / or block or blocks.

[0107] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, so that a series of operation steps are performed on the computer or other programmable data processing apparatus to produce a computer-implemented process, so that the instructions executed on the computer or other programmable data processing apparatus provide the functions specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more flows and / or blocks ​steps of a function specified in one or more blocks.

[0108] In one typical arrangement, the computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0109] The memory can include non-persistent memory and / or volatile memory, such as random access memory (RAM) and / or cache memory, which can store information such as data, metadata, and so on. The memory can also include non-volatile memory, such as read only memory (ROM), electrically programmable read only memory (EPROM), electrically erasable programmable read only memory (EEPROM), flash memory, or non-volatile random access memory (NVRAM) (e.g., read only memory device, readonly light emitting diode (LED) memory device, or the like), which can also store information such as, for example, an operating system, or software modules or segments. The memory can also include a storage medium or device, such as a hard disk drive, a floppy disk drive, a CD-ROM device, a DVD-ROM device, tape drive, or the like, which can store information, such as an operating system, software modules, or segments, or the like.

[0110] Computer readable media includes permanent and non-permanent, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory (ROM), electrically programmable read only memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital versatile disc (DVD), or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible to a computing device. According to the definition herein, computer readable media does not include transitory media, such as modulated data signals and carrier waves.

[0111] It should also be noted that the terms "comprising," "including," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can also include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without limitation, an element preceded by "comprises a... " does not, without more constraints, foreclose the existence of additional identical elements in the process, method, article, or apparatus that comprises the recited element.

[0112] Those skilled in the art will appreciate that embodiments of the present application can be devised for a method, a system, or a computer program product. Accordingly, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application can take the form of a computer program product on one or more computer readable storage media (including, but not limited to, disk storage, CD-ROM, optical storage memory etc.) embodying computer usable program code embodied thereon.

[0113] The above merely provides an example of the present application, but is not intended to limit the present application. Any modification, equivalent replacement, improvement, etc. within the spirit and principle of the present application should be included in the scope of claims of the present application.

Claims

1. A map updating method, wherein: The method comprises: Acquire a road image captured by a roadside camera, and perform detection on the road image to obtain a detection result of a motor vehicle area and an initial detection result of a non-motor vehicle parking area in the road image; determining a revised detection result of the non-motor vehicle parking area in the road image based on the detection result of the motor vehicle area and the initial detection result of the non-motor vehicle parking area; performing boundary segmentation on the corrected detection result of the non-motor vehicle parking area to obtain an actual non-motor vehicle parking area in the road image; The road map is updated according to the actual non-motor vehicle parking area in the road image.

2. The method according to claim 1, wherein: The detecting of the road image to obtain a detection result of the motor vehicle area and an initial detection result of the non-motor vehicle parking area in the road image includes: Detecting motor vehicles in the road image using a first preset object detection model to obtain a motor vehicle detection result; determining a detection result of a motor vehicle area and a detection result of a non-motor vehicle area in the road image according to the motor vehicle detection result; An initial detection result of the non-motor vehicle parking area is determined according to the detection result of the non-motor vehicle area.

3. The method according to claim 2, wherein: Determining the initial detection result of the non-motor vehicle parking area according to the detection result of the non-motor vehicle area includes: The parking area in the non-motor vehicle area is detected using a second preset target detection model to obtain an initial detection result of the non-motor vehicle parking area.

4. The method according to claim 1, wherein: Determining the corrected detection result of the non-motor vehicle parking area in the road image based on the detection result of the motor vehicle area and the initial detection result of the non-motor vehicle parking area includes: determining a road boundary corresponding to the motor vehicle area according to a detection result of the motor vehicle area; An initial detection result of the non-motor vehicle parking area is corrected using the road boundary corresponding to the motor vehicle area to obtain a corrected detection result of the non-motor vehicle parking area.

5. The method according to claim 4, wherein: The initial detection result of the non-motor vehicle parking area includes an initial detection frame of the non-motor vehicle parking area, the revised detection result of the non-motor vehicle parking area includes a revised detection frame of the non-motor vehicle parking area, and the revised detection result of the non-motor vehicle parking area in the road image obtained by correcting the initial detection result of the non-motor vehicle parking area using the road boundary corresponding to the motor vehicle area includes: Based on the road boundary corresponding to the motor vehicle area, determining a portion of the initial detection frame of the non-motor vehicle parking area that exceeds the road boundary corresponding to the motor vehicle area; The portion of the initial detection frame of the non-motor vehicle parking area that exceeds the road boundary corresponding to the motor vehicle area is removed to obtain a revised detection frame of the non-motor vehicle parking area.

6. The method of claim 1, wherein: The updating of the road map according to the actual non-motor vehicle parking area in the road image includes: Detecting non-motor vehicles in the actual non-motor vehicle parking area using a third preset target detection model to obtain a non-motor vehicle detection result; Tracking the non-motor vehicle according to the non-motor vehicle detection result to obtain a non-motor vehicle tracking result; Verifying the actual non-motor vehicle parking area according to the non-motor vehicle tracking result; If the verification is passed, the road map is updated according to the actual non-motor vehicle parking area.

7. The method of claim 1, wherein: The updating of the road map according to the actual non-motor vehicle parking area in the road image includes: Obtain the transformation relationship between the roadside camera coordinate system and the world coordinate system; According to the transformation relationship between the roadside camera coordinate system and the world coordinate system, the actual non-motor vehicle parking area in the road image is transformed into the world coordinate system to obtain the non-motor vehicle parking area in the world coordinate system; The road map is updated using the non-motor vehicle parking area in the world coordinate system.

8. A map updating device, wherein: The device comprises: a detection unit, configured to acquire a road image captured by a roadside camera and perform detection on the road image to obtain a detection result of a motor vehicle area and an initial detection result of a non-motor vehicle parking area in the road image; a determining unit, configured to determine a revised detection result of the non-motor vehicle parking area in the road image based on the detection result of the motor vehicle area and the initial detection result of the non-motor vehicle parking area; a segmentation unit, configured to perform boundary segmentation on the corrected detection result of the non-motor vehicle parking area to obtain an actual non-motor vehicle parking area in the road image; An updating unit is used to update the road map according to the actual non-motor vehicle parking area in the road image.

9. An electronic device comprising: processor; as well as A memory arranged to store computer executable instructions, which when executed cause the processor to perform the method of any one of claims 1 to 7.

10. A computer-readable storage medium storing one or more programs, which, when executed by an electronic device including a plurality of application programs, causes the electronic device to execute the method according to any one of claims 1 to 7.

Images