A method, device and server for generating parking fence

Abstract

The present disclosure provides a method, device and server for generating a parking fence, the method comprising: obtaining driving images captured by a driving recorder; determining a target area for adding a parking fence based on the driving images; obtaining user vehicle return data of shared vehicles parked in the target area within a first statistical period; detecting whether a target event of adding a parking fence for a shared vehicle in the target area occurs based on the user vehicle return data; and generating a parking fence in the target area in the shared vehicle map when the target event occurs.

Description

Technical Field

[0001] The disclosed embodiments relate to the technical field of shared vehicles, and more specifically, to a method, device, and server for generating a parking fence. Background Art

[0002] At present, sharing vehicles has become a new mode of travel in cities, which can effectively meet the travel needs of urban people. Existing shared vehicles include ordinary bicycles with riding power provided by users, as well as electric bicycles with power-assisted motors.

[0003] For shared vehicles, designated parking is currently required, that is, users need to park the shared vehicle in a set parking fence before returning the vehicle.

[0004] In the prior art, the government usually adds parking fences on the sidewalk by drawing white lines or setting up car cages. The white-lined parking fence is a new map element. Because it exists on the sidewalk, the dashcam of vehicles traveling on the motor vehicle lane is limited by the shooting angle, resulting in unclear driving images and a high amount of omissions. The accuracy of directly identifying the newly added parking fences based on the driving images taken by the dashcam is extremely low. Therefore, the white-lined parking fence cannot be directly obtained through the driving images taken by the dashcam like other car map elements. Therefore, for operators of shared vehicles, they need to determine the area of ​​the new parking fence through manual street sweeping and generate the new parking fence in the map of shared vehicles.

[0005] However, manual street sweeping requires people to go on site to collect data on newly added parking fences, which has high requirements for equipment and labor arrangements, and has a long generation cycle. Summary of the invention

[0006] One purpose of the embodiments of the present disclosure is to provide a new technical solution for automatically generating parking fences.

[0007] According to a first aspect of the present disclosure, a method for generating a parking fence is provided, comprising:

[0008] Acquire driving images collected by a driving recorder;

[0009] Determine a target area for adding a parking fence according to the driving image;

[0010] Acquire vehicle return data of users of shared vehicles parked in the target area within a first statistical period;

[0011] According to the user's vehicle return data, detecting whether a target event of adding a parking fence for a shared vehicle in the target area occurs;

[0012] When the target event occurs, a parking fence is generated in the target area in the shared vehicle map.

[0013] Optionally, determining a target area for adding a parking fence according to the driving image includes:

[0014] According to the driving image, identifying whether the roadside contains a preset target object;

[0015] In the case where it is identified that the roadside contains the target object, determining the area where the target object is located as the area to be identified;

[0016] Detecting whether a parking fence is set in the to-be-identified area in the shared vehicle map;

[0017] When no parking fence is set in the to-be-identified area in the shared vehicle map, the to-be-identified area is used as the target area for adding a parking fence.

[0018] Optionally, determining the area where the target object is located as the area to be identified includes:

[0019] According to the driving image, identifying the direction of the road on which the vehicle where the driving recorder is located is traveling;

[0020] The area to be identified is obtained according to the acquisition position of the driving image, the direction of the road, and the position of the target object in the driving image.

[0021] Optionally, obtaining the area to be identified according to a collection position of the driving image, a direction of the road, and a position of the target object in the driving image includes:

[0022] According to a preset segmentation ratio, the driving image is segmented into a set number of image regions;

[0023] Determine an image region to which the target object belongs as a target image region;

[0024] Determine a distance corresponding to the target image area as a target distance;

[0025] The area to be identified is obtained according to the acquisition position of the driving image, the direction of the road and the target distance.

[0026] Optionally, detecting whether a target event of adding a parking fence for a shared vehicle to the target area occurs according to the user's vehicle return data includes:

[0027] Detecting whether an abnormal vehicle return event occurs in the target area according to the vehicle return data of the user;

[0028] According to the detection result of the abnormal vehicle return event, the number of occurrences of each abnormal vehicle return event is obtained,

[0029] Determining a first number of preset scoring items for each abnormal return of the vehicle according to the number of occurrences of each abnormal return of the vehicle event;

[0030] Whether the target event occurs is detected according to the first quantity of each abnormal vehicle return scoring item.

[0031] Optionally, the abnormal vehicle return event includes at least one of the following:

[0032] First, the shared vehicle fails to be returned once;

[0033] The second item is that the shared vehicle is illegally parked;

[0034] The third item is that the review result of the complaint picture containing the target object submitted by the user for illegal parking complaint is passed.

[0035] Optionally, the method further includes:

[0036] Determining a second number of preset driving image scoring items, wherein the second number is the number of driving images collected during a second statistical period and used to determine a newly added parking fence in the target area;

[0037] Furthermore, whether the target event occurs is detected according to the second number of the driving image scoring items.

[0038] Optionally, the detecting whether the target event occurs according to the second number of the driving image scoring items includes:

[0039] Obtaining a first score of each preset vehicle return abnormality scoring item and a second score of the driving image scoring item;

[0040] Obtaining a comprehensive score for the target area according to the first number and the first score of each vehicle return abnormality scoring item, the second number and the second score of the driving image scoring item;

[0041] Whether the target event occurs is detected according to the comprehensive score of the target area.

[0042] According to a second aspect of the present disclosure, a device for generating a parking fence is provided, comprising:

[0043] An image acquisition module is used to acquire driving images collected by a driving recorder;

[0044] An area determination module, used to determine a target area for adding a parking fence according to the driving image;

[0045] A data acquisition module, used to acquire vehicle return data of users of shared vehicles parked in the target area within a first statistical period;

[0046] An event detection module, used to detect whether a target event of adding a parking fence for a shared vehicle in the target area occurs according to the user's vehicle return data;

[0047] A fence generation module is used to generate a parking fence in the target area in the shared vehicle map when the target event occurs.

[0048] According to a third aspect of the present disclosure, a server is provided, comprising the apparatus according to the second aspect of the present disclosure; or,

[0049] The server includes a memory and a processor, the memory is used to store a computer program, and the computer program is used to control the processor to execute the method described in the first aspect of the present disclosure.

[0050] In an embodiment of the present disclosure, a target area for a newly added parking fence is determined based on driving images captured by a driving recorder, and a parking fence is generated in a target area in a shared vehicle map when target data of a parking fence for a newly added shared vehicle in the target area is determined based on the vehicle return data of users of shared vehicles parked in the target area during a first statistical period. This embodiment can more accurately identify the target area for a newly added parking fence by fusing the driving images captured by the driving recorder with the vehicle return data of users, and can improve the user's vehicle return efficiency and vehicle return experience by generating a parking fence in the target area in the shared vehicle map for users to return the vehicle. In addition, this embodiment automatically generates parking fences, which can reduce labor costs and improve the efficiency of generating parking fences.

[0051] Further features and advantages of the present invention will become apparent from the following detailed description of exemplary embodiments of the present invention with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the invention and, together with the description, serve to explain the principles of the invention.

[0053] Figure 1 It is a schematic diagram of the composition structure of a shared vehicle system capable of implementing the method for generating a parking fence according to an embodiment of the present invention;

[0054] Figure 2 is a flow chart of a method for generating a parking fence according to an embodiment;

[0055] Figure 3is a schematic diagram of a segmentation method of a driving image according to an embodiment;

[0056] Figure 4 is a schematic diagram of a road in a driving image according to an embodiment;

[0057] Figure 5 is a block diagram of a device for generating a parking fence according to an embodiment;

[0058] Figure 6 is a block diagram of a server according to one embodiment. DETAILED DESCRIPTION

[0059] Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be noted that the relative arrangement of components and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present invention unless otherwise specifically stated.

[0060] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses.

[0061] Technologies, methods and equipment known to persons of ordinary skill in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods and equipment should be considered part of the specification.

[0062] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0063] It should be noted that like reference numerals and letters refer to similar items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0064] <Hardware Configuration>

[0065] Figure 1 1 is a schematic diagram of the structure of a shared vehicle system 100 that can be used to implement the method for generating a parking fence according to an embodiment of the present disclosure. The shared vehicle system 100 can be applied as a whole to the generation scenario of a parking fence.

[0066] like Figure 1 As shown, the shared vehicle system 100 includes a server 1000 , a user terminal 2000 , and a shared vehicle 3000 .

[0067] The server 1000 provides a business point for processing, database, and communication facilities. The server 1000 can be a monolithic server, a distributed server across multiple computers, a computer data center, a cloud server, or a server cluster deployed in the cloud, etc. The server can be of various types, such as but not limited to, a network server, a news server, a mail server, a message server, an advertising server, a file server, an application server, an interactive server, a database server, or a proxy server. In some embodiments, each server may include hardware, software, or an embedded logic component or a combination of two or more such components for executing the appropriate functions supported or implemented by the server. For example, a server such as a blade server, a cloud server, etc., or a server group consisting of multiple servers, which may include one or more of the above-mentioned types of servers, etc.

[0068] In one embodiment, the server 1000 may be Figure 1 As shown, it includes a processor 1100 , a memory 1200 , an interface device 1300 , a communication device 1400 , a display device 1500 , and an input device 1600 .

[0069] The processor 1100 is used to execute a computer program, which can be written in an instruction set of an architecture such as x86, Arm, RISC, MIPS, SSE, etc. The memory 1200 includes, for example, a ROM (read-only memory), a RAM (random access memory), a non-volatile memory such as a hard disk, etc. The interface device 1300 includes, for example, various bus interfaces, such as a serial bus interface (including a USB interface), a parallel bus interface, etc. The communication device 1400 is capable of wired or wireless communication. The display device 1500 is, for example, a liquid crystal display, an LED display, a touch display, etc. The input device 1600 may include, for example, a touch screen, a keyboard, etc.

[0070] In this embodiment, the memory 1200 of the server 1000 is used to store a computer program, and the computer program is used to control the processor 1100 to operate to perform the method according to the embodiment of the present invention. A technician can design the computer program according to the scheme disclosed in the present invention. How the computer program controls the processor to operate is well known in the art, so it will not be described in detail here.

[0071] Despite Figure 1 , multiple devices of the server 1000 are shown; however, the present invention may only involve some of the devices, for example, the server 1000 only involves the memory 1200 , the processor 1100 and the communication device 1400 .

[0072] In this embodiment, the user terminal 2000 is, for example, a mobile phone, a portable computer, a tablet computer, a PDA, a wearable device, etc.

[0073] The user terminal 2000 is installed with a car-using application client so as to achieve the purpose of using a shared vehicle by operating the car-using application client.

[0074] like Figure 1 As shown, the user terminal 2000 may include a processor 2100, a memory 2200, an interface device 2300, a communication device 2400, a display device 2500, an input device 2600, a speaker 2700, a microphone 2800, and the like.

[0075] The processor 2100 is used to execute a computer program, which can be written in an instruction set of an architecture such as x86, Arm, RISC, MIPS, SSE, etc. The memory 2200 includes, for example, a ROM (read-only memory), a RAM (random access memory), a non-volatile memory such as a hard disk, etc. The interface device 2300 includes, for example, a USB interface, a headphone interface, etc. The communication device 2400 is capable of wired or wireless communication, and the communication device 2400 may include at least one short-range communication module, such as any module for short-range wireless communication based on short-range wireless communication protocols such as Hilink protocol, WiFi (IEEE 802.11 protocol), Mesh, Bluetooth, ZigBee, Thread, Z-Wave, NFC, UWB, LiFi, etc. The communication device 2400 may also include a remote communication module, such as any module for WLAN, GPRS, 2G / 3G / 4G / 5G remote communication. The display device 2500 is, for example, a liquid crystal display, a touch display, etc. The input device 2600 may include, for example, a touch screen, a keyboard, etc. The user terminal 2000 can output audio signals through the speaker 2700 and collect audio signals through the microphone 2800 .

[0076] In this embodiment, the memory 2200 of the user terminal 2000 is used to store a computer program, which is used to control the processor 2100 to operate to execute the method of using a shared vehicle, for example, including: obtaining a unique identifier of the shared vehicle 3000, forming an unlocking request for a specific shared vehicle and sending it to the server; and performing bill settlement according to the fee settlement notice sent by the server, etc. A technician can design a computer program according to the scheme disclosed in the present invention. How a computer program controls a processor to operate is well known in the art, so it will not be described in detail here.

[0077] like Figure 1As shown, the shared vehicle 3000 may include a processor 3100, a memory 3200, an interface device 3300, a communication device 3400, an output device 3500, and an input device 3600, etc. The processor 3100 is used to execute a computer program, which may be written in an instruction set of an architecture such as x86, Arm, RISC, MIPS, SSE, etc. The memory 3200 may include, for example, a ROM (read-only memory), a RAM (random access memory), a non-volatile memory such as a hard disk, etc. The interface device 3300 may include, for example, a USB interface, a headphone interface, etc. The communication device 3400 may include at least one communication module, for example, capable of wired or wireless communication, and for example, capable of short-distance and long-distance communication. The output device 3500 may be, for example, a device for outputting signals, a display device such as an LCD display, a touch display, etc., or a speaker for outputting voice information, etc. The input device 3600 may include, for example, a touch device such as a touch screen, a sound sensing device such as a key, a microphone, a pressure sensing device such as a pressure sensor, etc.

[0078] The shared vehicle 3000 may be any type of vehicle such as a bicycle, an electric bicycle, an electric motorcycle, a tricycle, a four-wheel vehicle, etc., and is not limited here.

[0079] In this embodiment, the shared vehicle 3000 can report its own location information to the server 1000 .

[0080] In this embodiment, the memory 3200 of the shared vehicle 3000 is used to store a computer program, which is used to control the processor 3100 to operate to perform the method according to any embodiment of the present invention. A technician can design the computer program according to the scheme disclosed in the present invention. How the computer program controls the processor to operate is well known in the art, so it will not be described in detail here.

[0081] The network 4000 may be a wireless communication network or a wired communication network, and may be a local area network or a wide area network. Figure 1 In the shared vehicle system 100 shown, the shared vehicle 3000 and the server 1000, and the user terminal 2000 and the server 1000 can communicate via a network 4000. In addition, the network 4000 based on which the shared vehicle 3000 and the server 1000, and the user terminal 2000 and the server 1000 communicate can be the same or different.

[0082] It should be understood that although Figure 1Only one server 1000 , user terminal 2000 , and shared vehicle 3000 are shown, but this does not mean to limit the number of each. The shared vehicle system 100 may include multiple servers 1000 , multiple user terminals 2000 , multiple shared vehicles 3000 , etc.

[0083] Figure 1 The illustrated shared vehicle system 100 is illustrative only and is in no way intended to limit the invention, its application, or uses.

[0084] <Method Example>

[0085] Figure 2 A schematic diagram of a method for generating a parking fence according to an embodiment is shown. The method steps of this embodiment are implemented by a server, for example, Figure 1 The server 1000 is implemented in.

[0086] like Figure 2 As shown, the method for generating a parking fence in this embodiment may include the following steps S2100 to S2500:

[0087] Step S2100, obtaining driving images collected by the driving recorder.

[0088] Drive recorder is an instrument that records relevant information such as images and sounds while a vehicle is traveling. After installing the drive recorder, the video image and sound of the entire driving process can be recorded, as well as the time, vehicle speed and location.

[0089] The driving image in this embodiment may be an image collected by a driving recorder during the driving of the vehicle. The driving image may record the environment in which the vehicle is located when the driving image is collected.

[0090] Step S2200: determining a target area for adding a parking fence based on the driving image.

[0091] In a real environment, parking fences are usually set in the sidewalk and marked by wireframes or cages. Therefore, the area where the newly added wireframes or cages are located can be determined according to the driving image as the target area.

[0092] In one embodiment of the present disclosure, determining the target area for adding a parking fence according to the driving image may include steps S2210 to S2230 as shown below:

[0093] Step S2210, identifying whether the roadside contains a preset target object based on the driving image.

[0094] In this embodiment, since the parking fence is usually marked by a wireframe or a cage, the target object may include a wireframe and a cage. The wireframe may be a solid wireframe or a dotted wireframe, and the color of the wireframe may be white or other colors.

[0095] Since a large number of shared vehicles may be placed in the parking fence in use, causing part of the wireframe to be blocked by the shared vehicles, the target object may also include a large number of neatly parked shared vehicles. In one example, the large number of neatly parked shared vehicles may also include at least part of the wireframe.

[0096] In one embodiment of the present disclosure, a target recognition model may be pre-set, and the target recognition model may be able to recognize the image area to which the object of interest in the image belongs. The object of interest may include the target object, and then, based on the preset target recognition model, it may be possible to identify whether the roadside contains the preset target object according to the driving image. Specifically, the driving image may be input into the target recognition model to obtain the target object recognition result.

[0097] In this embodiment, the image input to the target recognition model may be pre-segmented into a set number of image regions according to a preset segmentation ratio, so that the result output by the target recognition model may include the image region to which the object of interest in the image belongs.

[0098] Among them, the segmentation ratio and the set number can be pre-set according to the application scenario or specific needs. The segmentation ratio can include the segmentation ratio in the width direction of the image and the segmentation ratio in the height direction of the image. The width direction of the image is usually perpendicular to the direction of the road on which the vehicle is traveling, and the height direction of the image is usually parallel to the direction of the road on which the vehicle is traveling. For example, the segmentation ratio in the width direction of the image can be 1:2:1, and the segmentation ratio in the height direction of the image can be 1:1:1. According to the segmentation ratio, the image can be divided into 9 image areas.

[0099] In actual scenarios, since the parking fences of shared vehicles are usually set on both sides of the road where the vehicles are traveling, the middle area in the width direction of the image, that is, the part corresponding to 2 in the segmentation ratio 1:2:1, is the road where the vehicles are traveling. Therefore, the three image areas corresponding to the middle area can be removed, leaving six image areas, that is, the set number of image areas.

[0100] Specifically, the image may be first segmented according to a segmentation ratio of 1:2:1 in the width direction of the image to obtain three parts; then the middle part is removed to obtain the parts corresponding to 1 and 1 in the segmentation ratio of 1:2:1; and then each of the remaining parts is segmented again according to a segmentation ratio of 1:1:1 in the height direction of the image to obtain six image areas.

[0101] In one example, in order to prevent scattered parked shared vehicles from interfering with the recognition result of the target object, the objects of interest that can be recognized by the target recognition model may also include a small number of parked shared vehicles.

[0102] On this basis, the target recognition model can also identify the category of the object of interest in the image. The categories of the object of interest may include: wireframe, car cage, a large number of neatly parked shared vehicles, and a small number of parked shared vehicles. Then, based on the coordinate frame of the object of interest in the driving image identified by the target recognition model and the category of the object of interest, it can be determined whether the roadside contains the preset target object.

[0103] The target recognition model of this embodiment independently detects the shared bicycles scattered on the roadside, which can avoid confusion in the recognition of the type of "a large number of shared bicycles parked neatly".

[0104] In one embodiment of the present disclosure, the method may further include the step of training the target recognition model, specifically including: obtaining training samples, training the initial target recognition model according to the training samples, and obtaining a trained target recognition model.

[0105] The training samples may include sample images and image annotations. The sample images may be images captured by a driving recorder, and the image annotations include the image region where the object of interest is located in the sample image and the type of the object of interest.

[0106] Since the parking fence is generally located at the edge of the driving image, and the size of the target of interest in the driving image is small, the image collected by the driving recorder can be scaled according to the target size to obtain a sample image of the target size. The target size can be set in advance according to the application scenario or specific needs. For example, the target size can be 960*960 pixels.

[0107] In this embodiment, the neck part of the target recognition model adopts the FPN+PAN structure, which can better learn targets of different sizes. The loss supervision function of each level can be expressed as:

[0108] L l =L cls (O cls,l ,GT cls,l )+λL reg (O reg,l ,GT reg,l )

[0109] Among them, l represents the current FPN level, L cls Represents the loss of the classification part, L regrepresents the loss of the coordinate regression part, O cls,l Represents the predicted value of the classification part of the lth layer, GT cls,l Represents the true value of the classification part of the lth layer, O reg,l Represents the predicted value of the l-th layer coordinate regression part, GT reg,l It represents the true value of the coordinate regression part of the lth layer, and λ represents the preset score value.

[0110] The classification part is used to detect whether the image contains the object of interest, and the coordinate regression part is used to detect whether the object of interest is located on both sides of the road.

[0111] Furthermore, in order to better adapt to the driving images collected by different models of driving recorders, in the process of training the target recognition model, the images collected by the driving recorder can be data enhanced to obtain sample images, so as to improve the robustness of the target recognition model trained based on the sample images. Among them, the data enhancement processing methods can include: HSV transformation, random angle rotation, scale change, brightness change, image flipping, mosaic enhancement, etc.

[0112] In an example, the value of FPN level l can be 2-4, the number of epochs can be 300, the accuracy requirement batch-size can be 4, and the initial learning rate can be 0.01.

[0113] According to the target recognition model of this embodiment, it is possible to identify whether the roadside in the driving image contains a target object.

[0114] Step S2220, when it is identified that the roadside contains the target object, the area where the target object is located is determined as the area to be identified.

[0115] In one embodiment of the present disclosure, determining the area where the target object is located as the area to be identified may include steps S2221 to S2222 as shown below:

[0116] Step S2221, identifying the direction of the road on which the vehicle with the driving recorder is traveling based on the driving image.

[0117] In actual scenarios, at non-intersection locations on the road, the direction of the road on which the vehicle is traveling is the direction of the road in the driving image.

[0118] At the intersection of the road, each lane can be provided with a sign corresponding to the driving direction. By identifying the sign of the driving direction in the driving image, the direction of the road where the vehicle where the driving recorder is located can be determined. Figure 4In the road shown, when the vehicle's position is determined to be position 1 based on the driving image, the driving direction of the lane corresponding to position 1 is marked as a right turn, and the direction of the road on which the vehicle is traveling may be as indicated by the arrow direction of road direction 1; when the vehicle's position is determined to be position 2 based on the driving image, the driving direction of the lane corresponding to position 2 is marked as straight ahead, and the direction of the road on which the vehicle is traveling may be as indicated by the arrow direction of road direction 2; when the vehicle's position is determined to be position 3 based on the driving image, the driving direction of the lane corresponding to position 3 is marked as a left turn, and the direction of the road on which the vehicle is traveling may be as indicated by the arrow direction of road direction 3.

[0119] Step S2222, obtaining the area to be identified according to the acquisition position of the driving image, the direction of the road and the position of the target object in the driving image.

[0120] In one embodiment of the present disclosure, obtaining the area to be identified according to the acquisition position of the driving image, the direction of the road, and the position of the target object in the driving image may include the following steps S2222-1 to S2222-4:

[0121] Step S2222-1, dividing the driving image into a set number of image areas according to a preset division ratio.

[0122] The segmentation ratio and the set number can be pre-set according to the application scenario or specific needs. The segmentation ratio can include the segmentation ratio in the width direction of the image and the segmentation ratio in the height direction of the image. The width direction of the image is usually perpendicular to the direction of the road on which the vehicle is traveling, and the height direction of the image is usually parallel to the direction of the road on which the vehicle is traveling. For example, the segmentation ratio in the width direction of the image can be 1:2:1, and the segmentation ratio in the height direction of the image can be 1:1:1. According to the segmentation ratio, the image can be segmented into 9 image regions, such as Figure 3 shown.

[0123] In actual scenarios, since the parking fences of shared vehicles are usually set on both sides of the road where the vehicles are traveling, the middle area in the width direction of the image, that is, the part corresponding to 2 in the segmentation ratio 1:2:1, is the road where the vehicles are traveling. Therefore, the three image areas corresponding to the middle area can be removed, leaving six image areas, that is, the set number of image areas.

[0124] Specifically, the image may be first segmented according to the segmentation ratio of 1:2:1 in the width direction to obtain three parts; then the middle part is removed to obtain the parts corresponding to 1 and 1 in the segmentation ratio of 1:2:1; then each of the remaining parts is segmented again according to the segmentation ratio of 1:1:1 in the height direction to obtain six image regions, such as Figure 3 Image area 1 to image area 6 in .

[0125] Step S2222-2, determine the image area to which the target object belongs as the target image area.

[0126] Specifically, an image region including the target object may be determined as the target image region.

[0127] Step S2222-3, determine the distance corresponding to the target image area as the target distance.

[0128] In this embodiment, the distance corresponding to each image area may be preset. Figure 3 In the driving image shown, the distance between image area 1 and image area 4 can be preset as d1, the distance between image area 2 and image area 5 can be preset as d2, and the distance between image area 3 and image area 6 can be preset as d3. Wherein, d1≥d2≥d3.

[0129] For example, when the target image region to which the target object belongs is image region 4, the target distance may be d1.

[0130] Step S222-4, obtaining the area to be identified according to the acquisition position of the driving image, the direction of the road on which the vehicle is traveling, and the target distance.

[0131] In this embodiment, the target position may be a position whose driving distance from the acquisition position of the driving image is the target distance along the direction of the road on which the vehicle is traveling; and an area of ​​a set size may be determined on the sidewalk corresponding to the target position as the area to be identified. The driving distance between the target position and the acquisition position may be the distance required for the vehicle to travel from the acquisition position to the target position along the direction of the road on which the vehicle is traveling, and is not the straight-line distance between the target position and the acquisition position.

[0132] The set size may be set in advance according to an application scenario or specific requirements. The shape of the area to be identified may be a rectangle, for example.

[0133] Furthermore, it is also possible to determine, based on the target image area, whether the parking fence is located on the left or right side of the road on which the vehicle is traveling, thereby determining the sidewalk corresponding to the target position. Figure 3 In the example shown, if the target image area is one of image areas 1-3, then the sidewalk corresponding to the target position can be determined to be the sidewalk on the left side of the target position, and if the target image area is one of image areas 4-6, then the sidewalk corresponding to the target position can be determined to be the sidewalk on the right side of the target position.

[0134] According to this embodiment, the area to be identified where the target object is located in the image can be identified more accurately, thereby making the position of the generated parking fence more accurate.

[0135] In another embodiment of the present disclosure, determining the area where the target object is located as the area to be identified may also include: determining the pixel coordinates of the target object in the driving image, determining a first distance between the target object and the acquisition position of the driving image, and a first orientation of the target object relative to the acquisition position in the width direction of the driving image; determining a position in the sidewalk of the road where the vehicle is traveling, which is a first distance away from the acquisition position of the driving image in the first orientation relative to the acquisition position of the driving image, as the first position; and determining an area of ​​a set size centered on the first position as the area to be identified.

[0136] Step S2230, detecting whether a parking fence is set in the area to be identified in the shared vehicle map.

[0137] Step S2240: If no parking fence is set in the area to be identified in the shared vehicle map, the area to be identified is used as a target area for adding a parking fence.

[0138] When no parking fence is set in the area to be identified in the shared vehicle map, it indicates that the target object in the area to be identified may be a newly added parking fence. Therefore, the area to be identified may be used as the target area for adding a parking fence.

[0139] According to this embodiment, the target area for adding a parking fence can be determined based on the driving image, and then the result of whether to add a parking fence to the target area can be verified based on the user's vehicle return data, so that the generated parking fence is more accurate.

[0140] Step S2300, obtaining the vehicle return data of users of shared vehicles parked in the target area during the first statistical period.

[0141] The first statistical period may be a period set in advance according to an application scenario or specific requirements. For example, the first statistical period may be the past week.

[0142] The shared vehicles parked in the target area during the first statistical period may be shared vehicles whose return positions were once located in the target area during the first statistical period. When executing step S2300, the actual positions of the shared vehicles whose return positions were once located in the target area during the first statistical period may be any other positions, and are not limited to the target area. The return positions of the shared vehicles may be collected by a positioning device disposed in the shared vehicles when a return event occurs, or may be collected by a user terminal using the shared vehicles.

[0143] In this embodiment, the vehicle return event may include at least one of the following:

[0144] Detecting that a touch device provided on the shared vehicle senses a designated touch action;

[0145] Detecting that a sound sensing device provided on the shared vehicle receives a designated voice issued by a user;

[0146] The shared vehicle’s kickstand senses the designated vehicle return action;

[0147] Detecting that a short-range wireless communication device provided in the shared vehicle can sense the user terminal;

[0148] It is detected that the continuous time length for which the shared vehicle does not sense pressure reaches a first set time length;

[0149] Detecting that the connection between the Bluetooth device of the shared vehicle and the Bluetooth device of the user terminal is disconnected;

[0150] It is detected that the signal strength value of the Bluetooth signal of the user terminal received by the Bluetooth device of the shared vehicle is less than the set value;

[0151] It is detected that the shared vehicle is stationary for a time length reaching a second set time length;

[0152] Receive a lock instruction sent by a server or a user terminal.

[0153] User vehicle return data may be data generated when a user returns a vehicle, and may specifically include the return location and time of the shared vehicle, data indicating a successful or failed return of the shared vehicle, data indicating whether the shared vehicle is illegally parked, and data indicating complaints about illegal parking of the shared vehicle.

[0154] In this embodiment, each time a shared vehicle is returned, a user return data is generated.

[0155] Step S2400: Detect whether a target event of generating a parking fence for a shared vehicle in a target area occurs based on the user's vehicle return data.

[0156] In one embodiment of the present disclosure, based on the user's vehicle return data, detecting whether a target event of generating a parking fence for a shared vehicle in a target area occurs may include the following steps S2410 to S2440:

[0157] Step S2410: Detect whether an abnormal vehicle return event occurs in the target area based on the vehicle return data of the user.

[0158] In this embodiment, it may be determined whether an abnormal vehicle return event occurs in the target area based on the vehicle return data of each user.

[0159] Among them, the abnormal vehicle return event may include at least one of the following:

[0160] The first one is that the shared vehicle failed to be returned once;

[0161] The second item is illegal parking of shared vehicles;

[0162] The third item is that the review result of the complaint picture containing the target object submitted by the user for illegal parking complaint is passed.

[0163] Specifically, when it is determined based on the return data of a user that a shared vehicle has failed to be returned, the first abnormal return event is determined to have occurred; when it is determined based on the return data of a user that a shared vehicle has been illegally parked, the second abnormal return event is determined to have occurred; when it is determined based on the return data of a user that the review result of a complaint picture containing a target object submitted by the user for an illegal parking complaint is passed, the third abnormal return event is determined to have occurred.

[0164] In this embodiment, a failed return means that during one use of the shared vehicle, the return operation fails when the shared vehicle is returned for the first time, that is, at least two return operations need to be performed before the return is successful.

[0165] Step S2420, obtaining the number of occurrences of each abnormal car return event based on the detection results of the abnormal car return events of all users' car return data.

[0166] In this embodiment, when it is determined that the first abnormal car return event occurs based on a user's car return data, the first abnormal car return event is determined to have occurred once; when it is determined that the second abnormal car return event occurs based on a user's car return data, the second abnormal car return event is determined to have occurred once; when it is determined that the third abnormal car return event occurs based on a user's car return data, the third abnormal car return event is determined to have occurred once.

[0167] That is to say, the number of occurrences of each abnormal car return event is the number of user car return data that can be used to determine the occurrence of the corresponding abnormal car return event.

[0168] Step S2430: Determine a first quantity of each preset abnormal car return scoring item according to the number of occurrences of each abnormal car return event.

[0169] In one embodiment, the abnormal scoring items for returning a vehicle may include at least one of the following:

[0170] The first one is that the number of failed returns of shared vehicles has increased dramatically;

[0171] The second is the sudden increase in illegal parking of shared vehicles;

[0172] The third item is illegal parking of shared vehicles;

[0173] The fourth item is that the complaint picture containing the target object submitted by the user for illegal parking complaint is approved.

[0174] In an embodiment where the abnormal return scoring item includes a sudden increase in the number of failed return of a shared vehicle, the first number of the abnormal return scoring item may be the difference between the first number of occurrences and the second number of occurrences. The first number of occurrences may be the number of abnormal return events in which a shared vehicle fails to return once in the target area within a first statistical period, and the second number of occurrences may be the number of abnormal return events in which a shared vehicle fails to return once in the target area within a third statistical period.

[0175] The third statistical period may be a statistical period set in advance according to application scenarios or specific requirements and before the first statistical period, and the duration of the third statistical period may be greater than or equal to the duration of the first statistical period. For example, the third statistical period may be one month before the first statistical period.

[0176] In an embodiment where the abnormal return scoring item includes a sudden increase in illegal parking of shared vehicles, the first number of the abnormal return scoring item may be the difference obtained by subtracting the fourth number of occurrences from the third number of occurrences. The third number of occurrences may be the number of abnormal return events of illegal parking of shared vehicles in the target area within the first statistical period, and the fourth number of occurrences may be the number of abnormal return events of illegal parking of shared vehicles in the target area within the fourth statistical period.

[0177] The fourth statistical period may be a statistical period that is set in advance according to an application scenario or specific needs and is before the first statistical period, and the length of the fourth statistical period may be greater than or equal to the length of the first statistical period. The fourth statistical period may be the same as or different from the third statistical period. For example, the fourth statistical period may be two weeks before the first statistical period.

[0178] In an embodiment where the abnormal return scoring item includes illegal parking of shared vehicles, the first number of the abnormal return scoring item may be the number of abnormal return events of illegal parking of shared vehicles in the target area within the first statistical period.

[0179] In an embodiment where the abnormal car return scoring item includes a complaint picture containing a target object submitted by a user when filing a complaint for illegal parking, and the review result is passed, the first number of the abnormal car return scoring item can be the number of abnormal car return events in which the complaint picture containing the target object submitted by the user when filing a complaint for illegal parking is passed within the first statistical period in the target area.

[0180] Step S2440: Detect whether the target event occurs according to the first quantity of each abnormal vehicle return scoring item.

[0181] In one embodiment of the present disclosure, based on the first quantity of each car return abnormality score item, detecting whether the target event occurs can be performed by determining whether the first quantity of each car return abnormality score item is greater than or equal to the third quantity threshold of the corresponding car return abnormality score item. When the first quantity of each car return abnormality score item is greater than or equal to the third quantity threshold of the corresponding car return abnormality score item, it is determined that the target event occurs; when the first quantity of any car return abnormality score item is less than the third quantity threshold of the corresponding car return abnormality score item, it is determined that the target event does not occur.

[0182] In another embodiment of the present disclosure, detecting whether a target event occurs based on the first number of each abnormal vehicle return scoring item may also include: obtaining a preset score for each abnormal vehicle return scoring item; obtaining a comprehensive score for the target area based on the first number and first score of each abnormal vehicle return scoring item; and detecting whether a target event occurs based on the comprehensive score of the target area.

[0183] Specifically, for each abnormal car return scoring item, the product of the first number and the first score of the abnormal car return scoring item is calculated as the total score of the abnormal car return scoring item; the total scores of all abnormal car return scoring items are summed to obtain the comprehensive score of the target area.

[0184] In this embodiment, the comprehensive score of the target area can reflect the probability of adding a parking fence in the target area. The higher the comprehensive score of the target area, the greater the probability of adding a parking fence in the target area.

[0185] The first score of each abnormal return scoring item can be pre-set according to the application scenario or specific needs. The first scores of different abnormal return scoring items can be the same or different. For example, the first score of the first abnormal return scoring item can be 1.5, the first score of the second abnormal return scoring item can be 5, the first score of the third abnormal return scoring item can be 1, and the first score of the fourth abnormal return scoring item can be 50.

[0186] Furthermore, a maximum score can be set for each abnormal return scoring item in advance according to the application scenario or specific needs. For example, the maximum score of the first abnormal return scoring item can be 100, the maximum score of the second abnormal return scoring item can be 5, the maximum score of the third abnormal return scoring item can be 100, and the maximum score of the fourth abnormal return scoring item can be 200.

[0187] When the product of the first quantity and the first score of a return abnormality scoring item is greater than the corresponding highest score, the highest score is used as the total score of the return abnormality scoring item. For example, when the product of the first quantity and the score of the fourth return abnormality scoring item is greater than the highest score of the fourth return abnormality scoring item, the highest score of the fourth return abnormality scoring item may be used as the total score of the fourth return abnormality scoring item.

[0188] In another embodiment of the present disclosure, the method may further include: determining a second number of preset driving image scoring items, wherein the second number is the number of driving images collected during a second statistical period to determine the newly added parking fences in the target area, and detecting whether the target event occurs based on the second number of driving image scoring items.

[0189] In this embodiment, the driving images collected near the target area during the second statistical period may be obtained, and the number of driving images capable of determining the newly added parking fence in the target area may be determined as the second number of driving image scoring items. The vicinity of the target area may be an area whose distance from the target area is less than or equal to a preset distance.

[0190] In one embodiment, multiple driving images captured by a driving recorder of a vehicle within a set time period may be filtered in advance to retain only one driving image captured by the driving recorder of the vehicle within the set time period. The set time period may be set in advance according to an application scenario or specific needs.

[0191] In this embodiment, detecting whether the target event occurs may also include: obtaining a first score for each preset vehicle return abnormality scoring item and a second score for the driving image scoring item; obtaining a comprehensive score for the target area based on the first number and first score of each vehicle return abnormality scoring item and the second number and second score of the driving image scoring item; and detecting whether the target event occurs based on the comprehensive score of the target area.

[0192] In this embodiment, for each abnormal car return scoring item, the product of the first number and the first score of the abnormal car return scoring item is calculated as the total score of the abnormal car return scoring item; the product of the second number and the second score of the driving image scoring item is calculated as the total score of the driving image scoring item; the total scores of all abnormal car return scoring items and the total score of the driving image scoring items are summed to obtain the comprehensive score of the target area.

[0193] In one embodiment, detecting whether a target event occurs based on the comprehensive score of the target area may include: sorting all target areas within a preset range in descending order based on the comprehensive score to obtain a ranking value for each target area, and determining the occurrence of a target event of adding a parking fence to a target area whose ranking value is greater than or equal to a preset ranking value.

[0194] The preset ranking value may be set in advance according to an application scenario or specific requirements. For example, the preset ranking value may be 300.

[0195] In another embodiment, detecting whether a target event occurs based on the comprehensive score of the target area may include: determining whether the comprehensive score of the target area is greater than or equal to a preset score threshold, and determining that a target event of adding a new parking fence to the target area occurs when the comprehensive score of the target area is greater than or equal to the score threshold.

[0196] The score threshold may be pre-set according to an application scenario or specific requirements. For example, the score threshold may be 75.

[0197] In another embodiment of the present disclosure, detecting whether a target event occurs based on user vehicle return data may include: detecting whether an abnormal vehicle return event occurs in a target area based on the user vehicle return data; and obtaining, based on the detection result of the abnormal vehicle return event, a number of user vehicle return data that can determine the occurrence of any abnormal vehicle return event, and determining that the target event occurs when the number is greater than or equal to a preset first number threshold.

[0198] The first quantity threshold may be pre-set according to an application scenario or specific requirements.

[0199] In another embodiment of the present disclosure, detecting whether a target event occurs based on user vehicle return data may include: detecting whether an abnormal vehicle return event occurs in a target area based on the user vehicle return data; obtaining, based on the detection result of the abnormal vehicle return event, the number of user vehicle return data that can determine the occurrence of each abnormal vehicle return event as the number corresponding to the corresponding abnormal vehicle return event; determining that the target event occurs when the number corresponding to each abnormal vehicle return event is greater than or equal to a preset second number threshold of the corresponding abnormal vehicle return event.

[0200] The second quantity threshold may be pre-set according to an application scenario or specific requirements.

[0201] Step S2500, when a target event occurs, a parking fence is generated in a target area in a shared vehicle map.

[0202] When the target event of adding a parking fence to the target area is determined in step S2400, a parking fence may be generated in the target area in the shared vehicle map.

[0203] In an embodiment of the present disclosure, a target area for a newly added parking fence is determined based on driving images captured by a driving recorder, and a parking fence is generated in a target area in a shared vehicle map when target data of a parking fence for a newly added shared vehicle in the target area is determined based on the vehicle return data of users of shared vehicles parked in the target area during a first statistical period. This embodiment can more accurately identify the target area for a newly added parking fence by fusing the driving images captured by the driving recorder with the vehicle return data of users, and can improve the user's vehicle return efficiency and vehicle return experience by generating a parking fence in the target area in the shared vehicle map for users to return the vehicle. In addition, this embodiment automatically generates parking fences, which can reduce labor costs and improve the efficiency of generating parking fences.

[0204] <Device Example>

[0205] Corresponding to the above method, the present disclosure also provides a parking fence generation device 5000, such as Figure 5 As shown, it includes an image acquisition module 5100, an area determination module 5200, a data acquisition module 5300, an event detection module 5400 and a fence generation module 5500. The image acquisition module 5100 is used to acquire the driving image collected by the driving recorder; the area determination module 5200 is used to determine the target area for adding a parking fence according to the driving image; the data acquisition module 5300 is used to acquire the user return data of the shared vehicle parked in the target area during the first statistical period; the event detection module 5400 is used to detect whether the target event of adding a parking fence for a shared vehicle in the target area occurs according to the user return data; the fence generation module 5500 is used to generate a parking fence in the target area in the shared vehicle map when the target event occurs.

[0206] In one embodiment of the present disclosure, the region determination module 5200 is further configured to:

[0207] According to the driving image, identifying whether the roadside contains a preset target object;

[0208] In the case where it is identified that the roadside contains the target object, determining the area where the target object is located as the area to be identified;

[0209] Detecting whether a parking fence is set in the to-be-identified area in the shared vehicle map;

[0210] When no parking fence is set in the to-be-identified area in the shared vehicle map, the to-be-identified area is used as the target area for adding a parking fence.

[0211] In one embodiment of the present disclosure, determining the area where the target object is located as the area to be identified includes:

[0212] According to the driving image, identifying the direction of the road on which the vehicle where the driving recorder is located is traveling;

[0213] The area to be identified is obtained according to the acquisition position of the driving image, the direction of the road, and the position of the target object in the driving image.

[0214] In one embodiment of the present disclosure, obtaining the area to be identified according to the acquisition position of the driving image, the direction of the road, and the position of the target object in the driving image includes:

[0215] According to a preset segmentation ratio, the driving image is segmented into a set number of image regions;

[0216] Determine an image region to which the target object belongs as a target image region;

[0217] Determine a distance corresponding to the target image area as a target distance;

[0218] The area to be identified is obtained according to the acquisition position of the driving image, the direction of the road and the target distance.

[0219] In one embodiment of the present disclosure, the event detection module 5400 is further configured to:

[0220] Detecting whether an abnormal vehicle return event occurs in the target area according to the vehicle return data of the user;

[0221] According to the detection result of the abnormal vehicle return event, the number of occurrences of each abnormal vehicle return event is obtained,

[0222] Determining a first number of preset scoring items for each abnormal return of the vehicle according to the number of occurrences of each abnormal return of the vehicle event;

[0223] Whether the target event occurs is detected according to the first quantity of each abnormal vehicle return scoring item.

[0224] In one embodiment of the present disclosure, the abnormal vehicle return event includes at least one of the following:

[0225] First, the shared vehicle fails to be returned once;

[0226] The second item is that the shared vehicle is illegally parked;

[0227] The third item is that the review result of the complaint picture containing the target object submitted by the user for illegal parking complaint is passed.

[0228] In one embodiment of the present disclosure, the parking fence generation device 50000 further includes:

[0229] A module for determining a second number of preset driving image scoring items, wherein the second number is the number of driving images collected during a second statistical period to determine a newly added parking fence in the target area;

[0230] A module for detecting whether the target event occurs according to a second number of the driving image scoring items.

[0231] In one embodiment of the present disclosure, the step of detecting whether the target event occurs according to the second number of the driving image scoring items includes:

[0232] Obtaining a first score of each preset vehicle return abnormality scoring item and a second score of the driving image scoring item;

[0233] Obtaining a comprehensive score for the target area according to the first number and the first score of each vehicle return abnormality scoring item, the second number and the second score of the driving image scoring item;

[0234] Whether the target event occurs is detected according to the comprehensive score of the target area.

[0235] Those skilled in the art should understand that the parking fence generation device 5000 can be implemented in various ways. For example, the parking fence generation device 5000 can be implemented by configuring the processor with instructions. For example, the instructions can be stored in a ROM, and when the device is started, the instructions are read from the ROM into a programmable device to implement the parking fence generation device 5000. For example, the parking fence generation device 5000 can be solidified into a dedicated device (such as an ASIC). The parking fence generation device 5000 can be divided into independent units, or they can be combined together for implementation. The parking fence generation device 5000 can be implemented by one of the various implementations described above, or can be implemented by a combination of two or more of the various implementations described above.

[0236] In this embodiment, the parking fence generating device 5000 can have multiple implementation forms. For example, the parking fence generating device 5000 can be a functional module running in any software product or application that provides parking fence generation services, or it can be an external embedded component, plug-in, patch, etc. of these software products or applications, or it can also be these software products or applications themselves.

[0237] <Server Implementation>

[0238] This embodiment provides a server 6000. In one example, the server may include the aforementioned parking fence generation device 5000.

[0239] In another example, Figure 6 As shown, the server 6000 may include a memory 6200 and a processor 6100, the memory 6200 is used to store program instructions, and the processor 6100 is used to control the server 6000 to execute any one of the methods provided in this embodiment when executing the computer program.

[0240] In an embodiment of the present disclosure, a target area for a newly added parking fence is determined based on driving images captured by a driving recorder, and a parking fence is generated in a target area in a shared vehicle map when target data of a parking fence for a newly added shared vehicle in the target area is determined based on the vehicle return data of users of shared vehicles parked in the target area during a first statistical period. This embodiment can more accurately identify the target area for a newly added parking fence by fusing the driving images captured by the driving recorder with the vehicle return data of users, and can improve the user's vehicle return efficiency and vehicle return experience by generating a parking fence in the target area in the shared vehicle map for users to return the vehicle. In addition, this embodiment automatically generates parking fences, which can reduce labor costs and improve the efficiency of generating parking fences.

[0241] The present invention may be a system, a method and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present invention.

[0242] A computer-readable storage medium may be a tangible device that can hold and store instructions used by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples of computer-readable storage media (a non-exhaustive list) include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the foregoing. As used herein, a computer-readable storage medium is not to be interpreted as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.

[0243] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0244] The computer program instructions for performing the operation of the present invention may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. Computer-readable program instructions may be executed entirely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be personalized by utilizing the state information of the computer-readable program instructions, and the electronic circuit may execute the computer-readable program instructions, thereby realizing various aspects of the present invention.

[0245] Various aspects of the present invention are described herein with reference to the flow charts and / or block diagrams of the methods, devices (systems) and computer program products according to embodiments of the present invention. It should be understood that each box of the flow chart and / or block diagram and the combination of each box in the flow chart and / or block diagram can be implemented by computer-readable program instructions.

[0246] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0247] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0248] The flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to multiple embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of an instruction, and a part of the module, program segment or instruction contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or the flowchart, and the combination of the boxes in the block diagram and / or the flowchart can be implemented by a dedicated hardware-based system that performs the specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions. It is well known to those skilled in the art that it is equivalent to implement it by hardware, implement it by software, and implement it by combining software and hardware.

[0249] Embodiments of the present invention have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terms used herein are selected to best explain the principles of the embodiments, practical applications, or technical improvements in the marketplace, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein. The scope of the present invention is defined by the appended claims.

Claims

1. A method for generating a parking fence, comprising: Acquire driving images collected by a driving recorder; Determine a target area for adding a parking fence according to the driving image; Acquire vehicle return data of users of shared vehicles parked in the target area within a first statistical period; According to the user's vehicle return data, detecting whether a target event of adding a parking fence for a shared vehicle in the target area occurs; generating a parking fence in the target area in the shared vehicle map when the target event occurs; The step of detecting whether a target event of adding a parking fence for a shared vehicle to the target area occurs according to the user's vehicle return data includes: Detecting whether an abnormal vehicle return event occurs in the target area according to the vehicle return data of the user; According to the detection result of the abnormal car return event, the number of occurrences of each abnormal car return event is obtained, and according to the number of occurrences of each abnormal car return event, a first number of each preset abnormal car return scoring item is determined; Detecting whether the target event occurs according to the first number of each abnormal vehicle return scoring item; The step of determining the target area for adding a parking fence according to the driving image includes: According to the driving image, identifying whether the roadside contains a preset target object; In the case where it is identified that the roadside contains the target object, determining the area where the target object is located as the area to be identified; Detecting whether a parking fence is set in the to-be-identified area in the shared vehicle map; In the case where no parking fence is set in the to-be-identified area in the shared vehicle map, the to-be-identified area is used as the target area for adding a parking fence.

2. According to the method of claim 1, the step of determining the area where the target object is located as the area to be identified comprises: According to the driving image, identifying the direction of the road on which the vehicle where the driving recorder is located is traveling; The area to be identified is obtained according to the acquisition position of the driving image, the direction of the road, and the position of the target object in the driving image.

3. The method according to claim 2, wherein obtaining the area to be identified according to the acquisition position of the driving image, the direction of the road, and the position of the target object in the driving image comprises: According to a preset segmentation ratio, the driving image is segmented into a set number of image regions; Determine an image region to which the target object belongs as a target image region; Determine a distance corresponding to the target image area as a target distance; The area to be identified is obtained according to the acquisition position of the driving image, the direction of the road and the target distance.

4. According to the method of claim 1, the abnormal vehicle return event includes at least one of the following: First, the shared vehicle fails to be returned once; The second item is that the shared vehicle is illegally parked; The third item is that the review result of the complaint picture containing the target object submitted by the user for illegal parking complaint is passed.

5. The method according to claim 1, further comprising: Determining a second number of preset driving image scoring items, wherein the second number is the number of driving images collected during a second statistical period and used to determine a newly added parking fence in the target area; Furthermore, whether the target event occurs is detected according to the second number of the driving image scoring items.

6. The method according to claim 5, further detecting whether the target event occurs according to the second number of the driving image scoring items, comprises: Obtaining a first score of each preset vehicle return abnormality scoring item and a second score of the driving image scoring item; Obtaining a comprehensive score for the target area according to the first number and the first score of each vehicle return abnormality scoring item, the second number and the second score of the driving image scoring item; Whether the target event occurs is detected according to the comprehensive score of the target area.

7. A parking fence generation device, comprising: An image acquisition module is used to acquire driving images collected by a driving recorder; An area determination module, used to determine a target area for adding a parking fence according to the driving image; A data acquisition module, used to acquire vehicle return data of users of shared vehicles parked in the target area within a first statistical period; An event detection module, used to detect whether a target event of adding a parking fence for a shared vehicle in the target area occurs according to the user's vehicle return data; a fence generation module, configured to generate a parking fence in the target area in the shared vehicle map when the target event occurs; The detecting, based on the user vehicle return data, whether a target event of adding a parking fence for a shared vehicle in the target area occurs includes: Detecting whether an abnormal vehicle return event occurs in the target area according to the vehicle return data of the user; According to the detection result of the abnormal car return event, the number of occurrences of each abnormal car return event is obtained, and according to the number of occurrences of each abnormal car return event, a first number of each preset abnormal car return scoring item is determined; Detecting whether the target event occurs according to the first number of each abnormal vehicle return scoring item; The step of determining a target area for adding a parking fence according to the driving image includes: According to the driving image, identifying whether the roadside contains a preset target object; In the case where it is identified that the roadside contains the target object, determining the area where the target object is located as the area to be identified; Detecting whether a parking fence is set in the to-be-identified area in the shared vehicle map; In the case where no parking fence is set in the to-be-identified area in the shared vehicle map, the to-be-identified area is used as the target area for adding a parking fence.

8. A server, comprising a memory and a processor, wherein the memory is used to store a computer program, and the computer program is used to control the processor to execute the method according to any one of claims 1 to 6.

Images