Image acquisition method, acquisition device and system of shared vehicle parking camera

By using controllers and light groups in the shared vehicle parking camera acquisition device, the sample images are automatically collected, which solves the problem of high cost and difficulty of manual acquisition, and efficient and accurate model training is achieved to adapt to the quantitative use of shared vehicles.

CN118945290APending Publication Date: 2024-11-12GUANGDONG STARTHING TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410989161.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-23
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

In the prior art, the sample images required for training of shared vehicle parking camera models require manual collection, which leads to high cost, difficulty, and is not conducive to quantitative use.

Method used

By using a controller in the acquisition device to communicate with the user terminal, combining the camera and light group, sample images are automatically collected, different lighting conditions are simulated, and batch automatic acquisition is achieved.

Benefits of technology

It reduces manual acquisition costs, improves acquisition efficiency and accuracy, adapts to the actual use environment of shared vehicles, and simplifies the model training process.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118945290A_ABST
    Figure CN118945290A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of image processing, and provides an image acquisition method, acquisition device and system for a shared vehicle parking camera, the method is applied to a controller which is in communication connection with a user terminal in the acquisition device, and the acquisition device further comprises a camera, a mounting hole array of the camera and a lamp group arranged around the mounting hole array; the method comprises the following steps: receiving an acquisition task of the user terminal; the acquisition task comprises an illumination condition and a target position of the camera; determining the on-off combination of each light-emitting lamp in the lamp group according to the illumination condition; and driving the camera to a target position according to the acquisition task, and controlling the on / off of each luminescent lamp in the lamp group based on the on / off combination, so that the camera acquires a sample image under the illumination condition. Batch automatic acquisition of the sample images is realized through the acquisition device, and the illumination condition of the shared vehicle in actual use is simulated by using the lamp group, so that the acquisition cost and difficulty of the sample images are reduced, and quantitative use of the sample image acquisition in the shared vehicle is facilitated.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to an image acquisition method, acquisition device and system for a shared vehicle parking camera. Background Art

[0002] With the development and application of shared vehicles, the number of shared vehicles has also increased rapidly, which requires standardized management, and the parking of shared vehicles is a key link in standardized management. At present, electronic fences are commonly used to limit the parking location of shared vehicles. On this basis, combined with road stud parking and image recognition, the parking method of users in the parking area is regulated.

[0003] Among them, the image recognition solution mainly uses the on-board camera to identify the road studs or parking signs on the ground, and judges whether the user has parked accurately based on the position of the parking sign. Therefore, a corresponding recognition model needs to be set to identify the parking sign. In addition, shared vehicles are in public areas, and the on-board cameras are prone to stains and offsets, which makes it impossible for users to return the vehicle accurately. Therefore, the on-board camera needs to set a corresponding self-checking model for self-checking. The self-checking model is used to identify the fixed features corresponding to the shared vehicle part that the camera can capture.

[0004] The camera's self-checking model and the parking sign's image recognition model both need to be trained and set up before the shared vehicle is put into use. However, before the shared vehicle is put into use, sample images need to be manually collected for model training. The labor cost required to collect a large number of sample images is high, and the collection is difficult, which is not conducive to quantitative use in shared vehicles. Summary of the invention

[0005] The present invention provides an image acquisition method, acquisition device and system for a shared vehicle parking camera, which are used to solve the defects of the prior art that sample images need to be manually collected for model training of parking cameras before shared vehicles are put into use, which has high labor costs and great acquisition difficulty, and realizes batch automatic acquisition of sample images required for shared vehicle parking camera training.

[0006] The present invention provides an image acquisition method for a shared vehicle parking camera, which is applied to a controller in an acquisition device, wherein the controller is communicatively connected to a user terminal; the acquisition device further comprises a camera, an array of mounting holes for the camera, and a light group arranged around the array of mounting holes; the sample image acquisition method comprises: receiving a collection task from the user terminal; the collection task including lighting conditions and a target position of the camera in the mounting hole array; Determine the on and off combination of each light-emitting lamp in the light group according to the lighting conditions; The camera is driven to the target position according to the acquisition task, and the on and off of each light in the light group is controlled based on the on and off combination, so that the camera can acquire sample images under the lighting conditions.

[0007] According to the image acquisition method for a parking camera of a shared vehicle provided by the present invention, the target positions include multiple ones, the controller is also connected to the vehicle central control of the shared vehicle, the vehicle central control is connected to a sensor, and the sensor is used to detect the speed of the shared vehicle; the method of driving the camera to the target position according to the acquisition task, and controlling the on and off of each light in the light group based on the on and off combination, so that the camera can acquire sample images under the lighting conditions, includes: Driving the camera to each of the target positions in sequence according to the acquisition task, and obtaining the speed of the shared vehicle when driving the camera to any of the target positions, and determining whether the shared vehicle meets the preset acquisition condition according to the speed of the shared vehicle; When the shared vehicle meets the preset acquisition conditions, control parameters are generated according to the on-off combination, and the control parameters are sent to the light group to control the on-off of each light in the light group so that the camera can collect sample images under the lighting conditions.

[0008] According to the image acquisition method of the shared vehicle parking camera provided by the present invention, the acquisition device also includes a light sensing element, and the on-off combination includes multiple ones; the control parameters are generated according to the on-off combination, and the control parameters are sent to the light group to control the on-off of each light in the light group, so that the camera can acquire sample images under the lighting conditions, including: Generate control parameters according to the target combination in each of the on / off combinations, and send the control parameters to the light group to control the on / off of each light in the light group; receiving a sensing signal from the light sensing element, and determining, according to the sensing signal, whether the lamp group has completed the adjustment of each of the light-emitting lamps based on the control parameter; When it is determined that the lamp group has completed the adjustment of each of the light-emitting lamps, a collection drive signal is sent to the camera; the camera collects sample images according to the collection drive signal under the lighting conditions corresponding to the target combination within the collection time corresponding to the collection drive signal; Return to and execute the step of generating control parameters according to the target combination in each of the on-off combinations until the target combination is the last one in each of the on-off combinations.

[0009] According to the image acquisition method for a shared vehicle parking camera provided by the present invention, after driving the camera to the target position according to the acquisition task and controlling the on and off of each light in the light group based on the on and off combination so that the camera can acquire a sample image under the lighting condition, the method further includes: Generate a first folder according to the acquisition task, and generate a subfolder under the first folder according to the lighting condition and the target location; The collected sample images are classified and saved in each of the subfolders under the first folder according to the lighting conditions and the target positions.

[0010] According to the image acquisition method for a shared vehicle parking camera provided by the present invention, after the acquired sample images are classified and saved in each of the subfolders under the first folder according to the lighting conditions, the method further includes: Sending each of the subfolders to the user terminal; the user terminal saving each of the subfolders into a second folder, where the second folder is generated when the acquisition task is generated; Receiving annotation information of a target image sent by the user terminal; the annotation information is generated by the user terminal according to the user's annotation operation on the target image, the target image is any one of the sample images in the target subfolder, and the target subfolder is any one of the subfolders under the second folder; Each sample image in the target sub-file corresponding to the target image is labeled according to the labeling information to construct a sample data set.

[0011] The present invention also provides a collection device, comprising a controller, a camera, a mounting hole array of the camera, and a light group arranged around the mounting hole array, wherein the controller further comprises: A task receiving module, used to receive a collection task from the user terminal; the collection task includes lighting conditions and a target position of the camera in the mounting hole array; A task analysis module, used to determine the on and off combination of each light in the light group according to the lighting conditions; The acquisition control module is used to drive the camera to the target position according to the acquisition task, and control the on and off of each light in the light group based on the on and off combination, so that the camera can acquire sample images under the lighting conditions.

[0012] The present invention also provides an image acquisition system for a shared vehicle parking camera, comprising an acquisition device and a user terminal, wherein: The acquisition device includes a controller, a camera, a mounting hole array of the camera, and a light group arranged around the mounting hole array; The controller is communicatively connected with the user terminal; The controller further includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps of the image acquisition method for a shared vehicle parking camera as described in any one of the above are implemented.

[0013] According to the image acquisition system of the shared vehicle parking camera provided by the present invention, the acquisition device also includes a camera base and a photosensitive element, and the mounting hole array is arranged on the camera base; the photosensitive element is used to sense the lighting conditions of the light group, and the controller is also connected to the vehicle central control of the shared vehicle, and the vehicle central control is connected to a sensor, and the sensor is used to detect the speed of the shared vehicle.

[0014] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the image acquisition method for a shared vehicle parking camera as described in any one of the above are implemented.

[0015] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the image acquisition method for a shared vehicle parking camera as described in any one of the above.

[0016] The present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the image acquisition method of a shared vehicle parking camera as described in any one of the above.

[0017] The image acquisition method, acquisition device and system of the shared vehicle parking camera provided by the present invention receive the acquisition task of the user terminal, determine the on and off combination of the light group according to the lighting conditions in the acquisition task, and then drive the camera to a specific position, and control the on and off of each light according to the on and off combination of the light group, so that the camera can acquire sample images under specific lighting conditions, and the acquisition of sample images required for the shared vehicle parking camera model training is realized based on the acquisition device. By simulating the lighting conditions when the camera acquires images through the light group, the lighting conditions when the camera acquires images in the actual use environment of the shared vehicle can be simulated, thereby ensuring the validity and accuracy of the acquired sample images, and at the same time, batch automatic acquisition of sample images is realized based on the acquisition device, reducing the manual acquisition cost of sample images required for the shared vehicle parking camera model training, and reducing the difficulty of image acquisition, which is conducive to the quantitative use of image acquisition and model training in shared vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 It is a flow chart of an image acquisition method for a shared vehicle parking camera provided in an embodiment of the present invention.

[0020] Figure 2 It is a schematic diagram of the structure of a collection device provided in an embodiment of the present invention.

[0021] Figure 3 It is a schematic diagram of the structure of a controller provided by an embodiment of the present invention.

[0022] Figure 4 It is a structural schematic diagram of a camera base provided by an embodiment of the present invention.

[0023] Figure 5 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0025] The embodiment of the present invention provides an image acquisition method for a shared vehicle parking camera, which can realize the automatic acquisition of sample images required for model training of the shared vehicle parking camera, and is used for model training of a vehicle-mounted camera set on a shared vehicle. The method is applied to a controller in an acquisition device, the controller of the acquisition device is communicatively connected to a user terminal, and the acquisition device also includes a camera, a mounting hole array of the camera, and a light group arranged around the mounting hole array of the camera.

[0026] Figure 1 FIG. 1 is a flow chart of an image acquisition method for a shared vehicle parking camera provided by an embodiment of the present invention. Figure 1 As shown, the image acquisition method of the shared vehicle parking camera provided by the embodiment of the present invention includes the following steps: Step 100, receiving a collection task from the user terminal; the collection task includes lighting conditions and a target position of the camera in the mounting hole array; Step 200, determining the on and off combination of each light-emitting lamp in the lamp group according to the lighting condition; Step 300, driving the camera to the target position according to the acquisition task, and controlling the on and off of each light in the light group based on the on and off combination, so that the camera can acquire sample images under the lighting conditions.

[0027] Receive a collection task sent by a user terminal, the collection task including the lighting condition and the target position of the camera in the installation hole array. Optionally, the collection task is generated by the user in the user terminal, and the lighting condition and the target position of the camera in the installation hole array can be configured by the user in the user terminal, or can be automatically generated according to a task generation instruction triggered by the user, and there is no specific limitation on this.

[0028] It can be seen that the lighting conditions of the environment in which the shared vehicle is located change over time, and the lighting conditions of the light group can be used to simulate the lighting conditions of the environment in which the shared vehicle is located in different time periods during use.

[0029] Optionally, the lighting condition may include one or more, and the target position of the camera in the mounting hole array may also include one or more. When the target position of the camera in the mounting hole array includes multiple, the multiple target positions may have a sequential relationship. Further, any target position corresponds to a mounting hole in the mounting hole array, and the sequential relationship of the multiple target positions may be determined according to the priority of each mounting hole in the mounting hole array. Exemplarily, in the mounting hole array, the priority of the mounting holes in the same row decreases from left to right, and the priority of the mounting holes in the same column decreases from top to bottom.

[0030] The on / off combination of each light-emitting lamp in the light group is determined according to the lighting condition, wherein the lighting condition includes the lighting intensity and the lighting angle, and further, the lighting condition may also include the light color. For different lighting conditions, at least one of the lighting intensity, the lighting angle and the light color is different, and the on / off combination of each light-emitting lamp in the light group corresponding to the different lighting conditions is different.

[0031] The camera is driven to the target position according to the acquisition task, and the on and off of each light in the light group is controlled based on the on and off combination of the light group, so that the camera can acquire sample images under corresponding lighting conditions.

[0032] Optionally, when the light group includes multiple on and off combinations, after driving the camera to the target position of the installation hole array, the on and off of each light in the light group can be controlled in turn according to each on and off combination, and under each on and off combination, the light is controlled to remain on and off for a certain period of time according to the on and off state indicated in the on and off combination, so that the camera can collect a group of sample images under each on and off combination, thereby obtaining multiple groups of sample images under different on and off combinations.

[0033] Optionally, when the camera includes multiple target positions in the installation hole array, the camera can be driven to each target position in sequence, and when the camera is driven to a target position, the light of each light in the light group is controlled according to the light combination of the light group and maintained for a certain period of time, so that the camera can collect a set of sample images at the current target position. Then the camera is driven to the next target position, thereby completing the image collection of the camera at multiple target positions in sequence.

[0034] Optionally, when the light group includes multiple on-off combinations and the camera includes multiple target positions, the camera can be driven to a target position first according to the acquisition task, and sample images can be acquired under different lighting conditions at the same target position. Specifically, the camera is driven to the current target position, and the on-off of each light is controlled under any on-off combination of the light group and maintained for a certain period of time for the camera to acquire images, so that the camera can acquire a set of sample images under the lighting conditions corresponding to the different on-off combinations at the current target position, and obtain multiple sets of sample images acquired by the camera under different lighting conditions at the same position. Then, the camera is driven to the next target position, and the above-mentioned control operation of the light group is repeated, so as to complete the image acquisition of the camera at different target positions.

[0035] Optionally, when the light group includes multiple on-off combinations and the camera includes multiple target positions, the camera can be driven to each target position in sequence according to the acquisition task, and sample images can be acquired under the same lighting conditions at different target positions. Specifically, the camera is driven to the current target position, and each light is controlled to be on and off for a certain period of time under any on-off combination of the light group, so that the camera can acquire images, and then the camera is driven to the next target position for image acquisition, until the camera completes image acquisition at each target position, and obtains multiple groups of sample images acquired by the camera at different positions under uniform lighting conditions. Then, each light is controlled to be on and off according to the next on-off combination of the light group and maintained for a certain period of time, and the above-mentioned camera driving operation is repeated, thereby completing the image acquisition of the camera under different lighting conditions.

[0036] In this embodiment, by receiving the acquisition task from the user terminal, the on / off combination of the light group is determined according to the lighting conditions in the acquisition task, so that after the camera is driven to a specific position, the on / off combination of each light is controlled according to the on / off combination of the light group, so that the camera can acquire sample images under specific lighting conditions, and the acquisition of sample images required for the onboard camera model training is realized based on the acquisition device. The acquisition device realizes batch automatic acquisition of sample images, and uses the light group to simulate the lighting conditions of the camera for acquiring images when the shared vehicle is actually used, thereby ensuring the validity and accuracy of the acquired sample images, reducing the manual acquisition cost of sample images required for the onboard camera model training of the shared vehicle, and reducing the difficulty of acquiring sample images, which is conducive to the quantitative use of image acquisition and model training in shared vehicles.

[0037] Furthermore, when collecting sample images, users only need to operate on the corresponding user terminal to generate and issue collection tasks, without having to manually collect sample images. This greatly reduces the labor cost required for image collection and simplifies the user operation process, making it simple and convenient.

[0038] In one embodiment, the target location includes multiple locations, and the controller in the acquisition device is connected to the user terminal via a wireless communication module, and the wireless communication module is used to establish a wireless channel between the controller and the user terminal. Figure 2 The controller of the acquisition device is also connected to the vehicle central control of the shared vehicle, and the vehicle central control is connected to the sensor of the shared vehicle, and the sensor is used to detect the speed of the shared vehicle. Based on this, step 300 specifically includes: Step 310, driving the camera to each of the target positions in sequence according to the acquisition task, and when driving the camera to any of the target positions, obtaining the speed of the shared vehicle, and determining whether the shared vehicle meets the preset acquisition condition according to the speed of the shared vehicle; Step 320, when the shared vehicle meets the preset acquisition conditions, a control parameter is generated according to the on-off combination, and the control parameter is sent to the light group to control the on-off of each light in the light group so that the camera can acquire sample images under the lighting conditions.

[0039] Before performing image acquisition, it is also necessary to determine whether the shared vehicle meets the acquisition conditions. Specifically, first, the camera is driven to each target position in sequence according to the acquisition task, and when the camera is driven to any target position, based on the vehicle central control connected to the controller, the speed of the shared vehicle detected by the sensor is obtained, that is, the speed of the shared vehicle, and based on the speed, it is determined whether the shared vehicle meets the preset acquisition conditions.

[0040] Optionally, when the speed of the shared vehicle is less than a preset speed, the shared vehicle meets the collection condition. When the shared vehicle meets the preset collection condition, a control parameter is generated according to the on / off combination of the light group, and the control parameter is sent to the light group to control the on / off of each light in the light group, so that the camera can collect sample images under corresponding lighting conditions.

[0041] Optionally, the control parameters sent to the light group include luminous parameters of each light in the light group, and the luminous parameters are used to indicate the on or off state of the light. For a light whose on or off state is on, the luminous parameters further include the light intensity, lighting angle and light color of the light.

[0042] In one embodiment, the acquisition device further includes a photosensitive element, which is used to sense the actual lighting conditions of the light group. The light group includes multiple on-off combinations, and different on-off combinations correspond to different lighting conditions. In step 320, a control parameter is generated according to the on-off combination of the light group, and the control parameter is sent to the light group to control the on-off of each light in the light group, so that the camera can collect sample images under the corresponding lighting conditions. It can also include: Step 321, generating control parameters according to the target combination in each of the on / off combinations, and sending the control parameters to the lamp group to control the on / off of each light in the lamp group; Step 322, receiving a sensing signal from the light sensing element, and determining whether the lamp group has completed the adjustment of each of the light-emitting lamps based on the control parameter according to the sensing signal; Step 323, when it is determined that the lamp group has completed the adjustment of each of the light-emitting lamps, sending a collection drive signal to the camera; the camera collects sample images according to the collection drive signal under the lighting conditions corresponding to the target combination within the collection time corresponding to the collection drive signal; Step 324, returning to and executing the step of generating control parameters according to the target combination in each of the on-off combinations, until the target combination is the last one in each of the on-off combinations.

[0043] A control parameter is generated according to a target combination in each on-off combination of the light group, and the control parameter is sent to the light group to control the on-off of each light in the light group, wherein the target combination is any one of the on-off combinations of the light group.

[0044] Furthermore, the photosensitive element senses the lighting conditions of the light group, generates a corresponding sensing signal, receives the sensing signal of the photosensitive element, determines the lighting conditions of the light group according to the sensing signal, and compares it with the lighting conditions corresponding to the target combination to determine whether the light group has completed the adjustment of each light-emitting lamp based on the issued control parameters. When it is determined that the light group has completed the adjustment of each light-emitting lamp, a collection drive signal is sent to the camera, and the camera collects sample images under the lighting conditions corresponding to the target combination according to the collection drive signal within the collection time corresponding to the collection drive signal, and obtains a set of sample images under the lighting conditions corresponding to the target combination.

[0045] Furthermore, the step of repeatedly returning to and executing the step of generating control parameters according to the target combination in each of the light-on and light-off combinations is performed until the target combination is the last one of the light-on and light-off combinations, that is, after completing the acquisition of sample images under the lighting conditions corresponding to the target combination, a light-on and light-off combination is reselected from the remaining combinations in each of the light-on and light-off combinations as the target combination, and the above-mentioned process of acquiring sample images is repeated, thereby obtaining sample images acquired under different lighting conditions.

[0046] In some embodiments, the collected sample images need to be saved, and the saving location may be a storage area of ​​the controller or a preset storage area in the collection device, which is not specifically limited. After step 300, the following may also be included: Step 401, generating a first folder according to the acquisition task, and generating a subfolder under the first folder according to the lighting condition and the target location; Step 402: Classify and save the collected sample images into the subfolders under the first folder according to the lighting conditions and the target positions.

[0047] A first folder is generated according to the acquisition task, and then multiple subfolders are generated under the first folder according to the lighting conditions and the target position of the camera, and the collected sample images are classified and saved in each subfolder under the first folder according to the different lighting conditions and target positions. Optionally, sample images collected under the same lighting conditions are saved in the same subfolder as a group of sample images, and sample images collected under different lighting conditions are saved in different subfolders; sample images collected at the same light target position are saved in the same subfolder, and sample images collected at different target positions are saved in different subfolders as a group of sample images.

[0048] Optionally, subfolders are generated based on lighting conditions and the target position of the camera. When classifying and saving sample images, sample images collected by the camera under the same lighting conditions at the same position are saved in the same subfolder, sample images collected under different lighting conditions at the same position are saved in different subfolders, and sample images collected at different positions under the same lighting conditions are saved in different subfolders.

[0049] Furthermore, after step 402, the following steps may also be included: Step 403, sending each of the sub-folders to the user terminal; the user terminal saves each of the sub-folders into a second folder, where the second folder is generated when the acquisition task is generated; Step 404, receiving the annotation information of the target image sent by the user terminal; the annotation information is generated by the user terminal according to the user's annotation operation on the target image, the target image is any one of the sample images in the target subfolder, and the target subfolder is any one of the subfolders under the second folder; Step 405 : annotate each sample image in the target sub-file corresponding to the target image according to the annotation information to construct a sample data set.

[0050] Each subfolder is sent to the user terminal, and the user terminal saves each subfolder into a second folder, which is generated when the acquisition task is generated. That is, in the user terminal, after establishing communication with the controller, when the acquisition task is generated according to the task information configured by the user, a corresponding folder is generated for this acquisition task, which is used to store the sample images collected by the camera in this acquisition task. Optionally, both the first folder and the second folder can be named according to the task information of the acquisition task.

[0051] Furthermore, the labeling information of the target image sent by the user terminal is received, where the labeling information is generated by the user terminal according to the user's labeling operation on the target image, and the target image is any one of the sample images in the target subfolder, and the target subfolder is any one of the subfolders under the second folder.

[0052] Based on the sample images stored in the user terminal, the user can randomly select a sample image in a subfolder for annotation, including but not limited to annotating the positions of fixed features in the sample image, and the user terminal generates corresponding annotation information according to the user's annotation operation.

[0053] Furthermore, according to the received annotation information, each sample image in the target subfolder corresponding to the target image is annotated to construct a sample data set. It can be understood that after the camera is installed and fixed, its installation position and the relative position of the shared vehicle are fixed. Under normal circumstances, the part of the shared vehicle that can be photographed by the camera is fixed, and the fixed part of the shared vehicle that can be photographed by the camera is the fixed feature. Therefore, in the image captured by the camera, the position of the fixed feature is also fixed. By annotating the position of the fixed feature, the position of the fixed feature of other sample images in the same subfolder can be annotated, thereby constructing a sample data set for model training, and the trained model can recognize the fixed features.

[0054] Optionally, the transmission of the collected sample images can be a one-time transmission after the completion of the collection task, or can be sent while the collection is in progress. In some embodiments, a corresponding first folder is generated when the collection task is received, and after the sample images are collected, a corresponding subfolder is generated under the first folder for storing the collected sample images according to the lighting conditions and the target position of the camera, and the generated sub-file is sent to the user terminal, and then the collected sample images are synchronized to the user terminal in real time. Furthermore, the execution progress of the collection task can also be synchronized to the user terminal in real time, that is, the collection status of the sample images under various lighting conditions at the current position of the camera is displayed in the user terminal.

[0055] In this embodiment, by adjusting the position of the camera and the lighting conditions of the light group, sample images of the camera at different positions and under different lighting conditions can be collected, and different on and off combinations of the light group can simulate light of different angles and / or different intensities.

[0056] Based on this, after the camera rotates through different positions, the collected sample images can basically cover most installation situations of the camera on shared vehicles. Even if there are deviations or differences in the position of the camera during the actual installation process when the sample image is collected, the trained model can basically accurately identify the same features of the same model.

[0057] Furthermore, since the light during sample image collection is changed by changing the lighting combination, after collecting enough sample images, the sample images are sufficient to enable the trained model to perform feature recognition under different lighting conditions, and can effectively counteract the influence of light on model recognition, thereby enabling shared vehicles to adapt to actual environmental changes after being put into use.

[0058] The acquisition device and the image acquisition system of the shared vehicle parking camera provided by the present invention are described below. The acquisition device and the image acquisition system of the shared vehicle parking camera described below can be referenced to each other with the image acquisition method of the shared vehicle parking camera described above.

[0059] The embodiment of the present invention further provides a collection device, which includes a controller, a camera, a mounting hole array of the camera, and a light group arranged around the mounting hole array, wherein the reference Figure 3 , the controller further comprises: The task receiving module 10 is used to receive the acquisition task of the user terminal; the acquisition task includes the lighting conditions and the target position of the camera in the installation hole array; A task analysis module 20, used to determine the on and off combination of each light in the light group according to the lighting conditions; The acquisition control module 30 is used to drive the camera to the target position according to the acquisition task, and control the on and off of each light in the light group based on the on and off combination, so that the camera can acquire sample images under the lighting conditions.

[0060] In one embodiment, the target location includes multiple locations, the controller is further connected to the vehicle central control of the shared vehicle, the vehicle central control is connected to a sensor, and the sensor is used to detect the speed of the shared vehicle; the acquisition control module 30 is also used to: Driving the camera to each of the target positions in sequence according to the acquisition task, and obtaining the speed of the shared vehicle when driving the camera to any of the target positions, and determining whether the shared vehicle meets the preset acquisition condition according to the speed of the shared vehicle; When the shared vehicle meets the preset acquisition conditions, control parameters are generated according to the on-off combination, and the control parameters are sent to the light group to control the on-off of each light in the light group so that the camera can collect sample images under the lighting conditions.

[0061] In one embodiment, the acquisition device further includes a light sensing element, and the light-off combination includes multiple light-off combinations; the acquisition control module 30 is further used to: Generate control parameters according to the target combination in each of the on / off combinations, and send the control parameters to the light group to control the on / off of each light in the light group; receiving a sensing signal from the light sensing element, and determining, according to the sensing signal, whether the lamp group has completed the adjustment of each of the light-emitting lamps based on the control parameter; When it is determined that the lamp group has completed the adjustment of each of the light-emitting lamps, a collection drive signal is sent to the camera; the camera collects sample images according to the collection drive signal under the lighting conditions corresponding to the target combination within the collection time corresponding to the collection drive signal; Return to and execute the step of generating control parameters according to the target combination in each of the on-off combinations until the target combination is the last one in each of the on-off combinations.

[0062] In one embodiment, the controller further includes a storage module, configured to: Generate a first folder according to the acquisition task, and generate a subfolder under the first folder according to the lighting condition and the target location; The collected sample images are classified and saved in each of the subfolders under the first folder according to the lighting conditions and the target positions.

[0063] In one embodiment, the controller further includes a marking module, configured to: Sending each of the subfolders to the user terminal; the user terminal saving each of the subfolders into a second folder, where the second folder is generated when the acquisition task is generated; Receiving annotation information of a target image sent by the user terminal; the annotation information is generated by the user terminal according to the user's annotation operation on the target image, the target image is any one of the sample images in the target subfolder, and the target subfolder is any one of the subfolders under the second folder; Each sample image in the target sub-file corresponding to the target image is labeled according to the labeling information to construct a sample data set.

[0064] The embodiment of the present invention also provides an image acquisition system for a shared vehicle parking camera, which can implement the steps of the sample image acquisition method described in the above embodiments. Figure 2 As shown, the system includes a collection device and a user terminal. The collection device includes a controller, a camera, a mounting hole array for the camera and a light group. The light group is arranged around the mounting hole array.

[0065] The controller is communicatively connected to the user terminal, and the controller further includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the image acquisition method for the shared vehicle parking camera described in the above embodiments are implemented.

[0066] In one embodiment, the acquisition device further includes a camera base and a photosensitive element. Figure 4The camera base is used to install the camera, the camera installation hole array is arranged on the camera base, and the light group is arranged around the camera base.

[0067] Furthermore, the photosensitive element is used to sense the lighting conditions of the light group, and the controller is also connected to the vehicle central control of the shared vehicle. The vehicle central control is connected to a sensor, and the sensor is used to detect the speed of the shared vehicle.

[0068] Optionally, the camera base can be fixed under the basket of the shared vehicle, the camera is installed at any mounting hole in the mounting hole array on the base, the light group is a controllable light, and the controller is used to control the light of the light group and drive the camera. Exemplarily, the light group is composed of a plurality of LED lights.

[0069] The mounting hole array provided on the camera base may be a plurality of card slots or mounting screw holes. The user may manually adjust the position of the camera or may adopt an electric drive method to drive the camera to change the mounting position.

[0070] The acquisition device and the image acquisition system of the shared vehicle parking camera provided in the embodiments of the present invention can be referenced with the image acquisition method of the shared vehicle parking camera described in the above embodiments, and will not be repeated here.

[0071] Figure 5 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 5 As shown, the electronic device may include: a processor 510, a communications interface 520, a memory 530 and a communication bus 540, wherein the processor 510, the communications interface 520 and the memory 530 communicate with each other through the communication bus 540. The processor 510 may call the logic instructions in the memory 530 to execute the steps of the image acquisition method of the shared vehicle parking camera, for example including: Receiving a collection task from a user terminal; the collection task includes lighting conditions and a target position of the camera in the mounting hole array; Determine the on and off combination of each light-emitting lamp in the lamp group according to the lighting conditions; The camera is driven to the target position according to the acquisition task, and the on and off of each light in the light group is controlled based on the on and off combination, so that the camera can acquire sample images under the lighting conditions.

[0072] In addition, the logic instructions in the above-mentioned memory 530 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0073] On the other hand, the present invention further provides a computer program product, the computer program product includes a computer program, the computer program can be stored in a non-transitory computer-readable storage medium, and when the computer program is executed by a processor, the computer can execute the steps of the image acquisition method of the shared vehicle parking camera provided by the above methods, for example, including: Receiving a collection task from a user terminal; the collection task includes lighting conditions and a target position of the camera in the mounting hole array; Determine the on and off combination of each light-emitting lamp in the lamp group according to the lighting conditions; The camera is driven to the target position according to the acquisition task, and the on and off of each light in the light group is controlled based on the on and off combination, so that the camera can acquire sample images under the lighting conditions.

[0074] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the image acquisition method for a shared vehicle parking camera provided by the above methods, for example, including: Receiving a collection task from a user terminal; the collection task includes lighting conditions and a target position of the camera in the mounting hole array; Determine the on and off combination of each light-emitting lamp in the lamp group according to the lighting conditions; The camera is driven to the target position according to the acquisition task, and the on and off of each light in the light group is controlled based on the on and off combination, so that the camera can acquire sample images under the lighting conditions.

[0075] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0076] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0077] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for collecting images from a shared vehicle parking camera, characterized in that: A controller used in a collection device, the controller being in communication connection with a user terminal; the collection device further comprising a camera, an array of mounting holes for the camera, and a light group arranged around the array of mounting holes; the image collection method comprising: receiving a collection task from the user terminal; the collection task including lighting conditions and a target position of the camera in the mounting hole array; Determine the on and off combination of each light-emitting lamp in the light group according to the lighting conditions; The camera is driven to the target position according to the acquisition task, and the on and off of each light in the light group is controlled based on the on and off combination, so that the camera can acquire sample images under the lighting conditions.

2. The image acquisition method of the shared vehicle parking camera according to claim 1, characterized in that: The target positions include multiple ones, the controller is further connected to the vehicle central control of the shared vehicle, the vehicle central control is connected to a sensor, and the sensor is used to detect the speed of the shared vehicle; the camera is driven to the target position according to the acquisition task, and the on and off of each light in the light group is controlled based on the on and off combination, so that the camera can acquire sample images under the lighting conditions, including: Driving the camera to each of the target positions in sequence according to the acquisition task, and obtaining the speed of the shared vehicle when driving the camera to any of the target positions, and determining whether the shared vehicle meets the preset acquisition condition according to the speed of the shared vehicle; When the shared vehicle meets the preset acquisition conditions, control parameters are generated according to the on-off combination, and the control parameters are sent to the light group to control the on-off of each light in the light group so that the camera can collect sample images under the lighting conditions.

3. The image acquisition method of the shared vehicle parking camera according to claim 2, characterized in that: The acquisition device further includes a light sensing element, and the on-off combination includes a plurality of light sensing elements; the control parameters are generated according to the on-off combination, and the control parameters are sent to the light group to control the on-off of each light in the light group, so that the camera can acquire sample images under the lighting conditions, including: Generate control parameters according to the target combination in each of the on / off combinations, and send the control parameters to the light group to control the on / off of each light in the light group; receiving a sensing signal from the light sensing element, and determining, according to the sensing signal, whether the lamp group has completed the adjustment of each of the light-emitting lamps based on the control parameter; When it is determined that the lamp group has completed the adjustment of each of the light-emitting lamps, a collection drive signal is sent to the camera; the camera collects sample images according to the collection drive signal under the lighting conditions corresponding to the target combination within the collection time corresponding to the collection drive signal; Return to and execute the step of generating control parameters according to the target combination in each of the on-off combinations until the target combination is the last one in each of the on-off combinations.

4. The image acquisition method of the shared vehicle parking camera according to claim 1, characterized in that: After driving the camera to the target position according to the acquisition task and controlling the on and off of each light in the light group based on the on and off combination so that the camera can acquire a sample image under the illumination condition, the method further includes: Generate a first folder according to the acquisition task, and generate a subfolder under the first folder according to the lighting condition and the target location; The collected sample images are classified and saved in each of the subfolders under the first folder according to the lighting conditions and the target positions.

5. The image acquisition method of the shared vehicle parking camera according to claim 4 is characterized in that: After the collected sample images are classified and saved into the subfolders under the first folder according to the illumination conditions, the method further includes: Sending each of the subfolders to the user terminal; the user terminal saving each of the subfolders into a second folder, where the second folder is generated when the acquisition task is generated; Receiving annotation information of a target image sent by the user terminal; the annotation information is generated by the user terminal according to the user's annotation operation on the target image, the target image is any one of the sample images in the target subfolder, and the target subfolder is any one of the subfolders under the second folder; Each sample image in the target sub-file corresponding to the target image is labeled according to the labeling information to construct a sample data set.

6. A collection device, characterized in that: The invention comprises a controller, a camera, a mounting hole array of the camera, and a light group arranged around the mounting hole array, wherein the controller further comprises: A task receiving module, used to receive a collection task from the user terminal; the collection task includes lighting conditions and a target position of the camera in the mounting hole array; A task analysis module, used to determine the on and off combination of each light in the light group according to the lighting conditions; The acquisition control module is used to drive the camera to the target position according to the acquisition task, and control the on and off of each light in the light group based on the on and off combination, so that the camera can acquire sample images under the lighting conditions.

7. An image acquisition system for a shared vehicle parking camera, characterized in that: It includes a collection device and a user terminal, wherein: The acquisition device includes a controller, a camera, a mounting hole array of the camera, and a light group arranged around the mounting hole array; The controller is communicatively connected with the user terminal; The controller further includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps of the image acquisition method for a shared vehicle parking camera as described in any one of claims 1 to 5 are implemented.

8. The image acquisition system of the shared vehicle parking camera according to claim 7, characterized in that: The acquisition device also includes a camera base and a photosensitive element, and the mounting hole array is arranged on the camera base; the photosensitive element is used to sense the lighting conditions of the light group, and the controller is also connected to the vehicle central control of the shared vehicle, and the vehicle central control is connected to a sensor, and the sensor is used to detect the speed of the shared vehicle.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the image acquisition method of the shared vehicle parking camera as described in any one of claims 1 to 5 are implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the image acquisition method of a shared vehicle parking camera as described in any one of claims 1 to 5 are implemented.