Image processing-based charging space anti-occupancy method, device and equipment

Abstract

The embodiment of the application provides a charging parking space anti-occupying method, device and equipment based on image processing, and relates to the technical field of image processing. The method comprises the following steps: acquiring a parking space image of a target charging parking space collected by at least one image collection device; performing identification processing on each parking space image to obtain a first identification result; determining a second identification result according to license plate color information in the first identification result; if it is determined that the second identification result represents a charging vehicle, acquiring first video data of the target charging parking space collected by each image collection device, and performing identification processing on the first video data to obtain a third identification result; if it is determined that the third identification result represents that the target vehicle does not have a charging behavior within a first preset time period, generating warning information; wherein the warning information is used to prompt the target vehicle to drive away from the target charging parking space. The method can effectively avoid the occupation of the charging parking space and reduce the labor cost.

Description

Technical Field

[0001] This application relates to the field of image processing technology, and in particular to a method, apparatus and equipment for preventing the occupancy of charging parking spaces based on image processing. Background Technology

[0002] With the rapid development of new energy vehicle technology and the integration of smart grid technology in the power system, the number of charging parking spaces is increasing. When parking spaces are scarce, some non-charging vehicle owners may occupy charging station locations, preventing other drivers from charging and wasting charging space resources. Therefore, it is necessary to implement measures to prevent the occupation of charging parking spaces.

[0003] In existing technologies, staff members are arranged to manually coordinate on-site operations to handle the occupancy of charging spaces.

[0004] However, the above methods, which rely on manual supervision, have low processing efficiency and also lead to high labor costs. Summary of the Invention

[0005] This application provides a method, apparatus, and device for preventing charging parking spaces from being occupied based on image processing, which can effectively prevent charging parking spaces from being occupied and reduce labor costs.

[0006] In a first aspect, embodiments of this application provide a method for preventing the occupancy of charging parking spaces based on image processing, including:

[0007] Acquire parking space images of the target charging parking space captured by at least one image acquisition device; and perform recognition processing on each of the parking space images to obtain a first recognition result; wherein, the first recognition result includes the license plate color information of the target vehicle currently parked in the target charging parking space; the license plate color information includes the license plate color of the front of the target vehicle and the license plate color of the rear of the vehicle.

[0008] The second recognition result is determined based on the license plate color information in the first recognition result;

[0009] If the second recognition result indicates that the target vehicle is a charging vehicle, then the first video data of the target charging parking space collected by each of the image acquisition devices is obtained, and the first video data is processed for recognition to obtain a third recognition result.

[0010] If the third identification result indicates that the target vehicle has not been charging within the first preset time period, a warning message is generated; wherein, the warning message is used to prompt the target vehicle to leave the target charging parking space.

[0011] In one possible implementation, the images of each parking space are subjected to recognition processing to obtain a first recognition result, including:

[0012] The images of each parking space are processed to obtain a fourth recognition result; wherein the fourth recognition result includes at least one vehicle image of the target vehicle currently parked in the target charging parking space.

[0013] Based on the vehicle images, the license plate location information of the target vehicle is determined; wherein, the license plate location information represents the installation position of the license plate of the target vehicle.

[0014] The first recognition result is determined based on the license plate location information and the images of each vehicle.

[0015] In one possible implementation, determining the license plate location information of the target vehicle based on each of the vehicle images includes:

[0016] Image recognition processing is performed on each of the vehicle images to obtain a feature set; wherein, the feature set includes the license plate image, the front image set, and the rear image set of the target vehicle; the front image set includes front images of the target vehicle from different acquisition angles; the rear image set includes rear images of the target vehicle from different acquisition angles.

[0017] The feature set is processed to obtain the feature data of the target vehicle; wherein, the feature data includes the appearance structure of the license plate of the target vehicle under different acquisition angles and the proportion of the license plate in the corresponding license plate image;

[0018] Based on the feature data, the license plate location information of the target vehicle is determined.

[0019] In one possible implementation, determining the first recognition result based on the license plate location information and each of the vehicle images includes:

[0020] Based on the license plate location information, the vehicle image is processed to obtain the pixel information of the vehicle image; wherein, the pixel information includes the number and color distribution of pixels in the license plate area of ​​the vehicle image;

[0021] The first recognition result is determined based on the pixel information of each vehicle image.

[0022] In one possible implementation, the first video data is subjected to recognition processing to obtain a third recognition result, including:

[0023] The first video data is processed to obtain the charging head information and charging port information of the target vehicle;

[0024] Based on the charging head information and the charging port information, the first video data is processed for motion recognition to obtain the third recognition result.

[0025] In one possible implementation, the method further includes:

[0026] If the second identification result indicates that the target vehicle is a non-charging vehicle, then the warning information is generated.

[0027] In one possible implementation, the method further includes:

[0028] If the third identification result indicates that the target vehicle has not engaged in charging behavior within the second preset time period, a notification message is generated; wherein the second preset time period is longer than the first preset time period; the notification message is used to notify staff to perform on-site manual processing.

[0029] In one possible implementation, the method further includes:

[0030] The first video data is processed to obtain the charging head information and charging port information of the target vehicle;

[0031] The second video data of the target charging parking space is collected; and the second video data is processed for action recognition based on the charging head information and the charging port information to obtain a fifth recognition result.

[0032] If the fifth identification result indicates that the target vehicle has completed charging, then the third video data of the target charging parking space is collected; and the third video data is processed to obtain the sixth identification result.

[0033] If it is determined that the sixth identification result indicates that the target vehicle has not left the target charging parking space within the third preset time period, then the warning information is generated.

[0034] Secondly, embodiments of this application provide an image processing-based anti-occupancy device for charging parking spaces, comprising:

[0035] The first identification module is used to acquire parking space images of target charging parking spaces acquired by at least one image acquisition device; and to perform identification processing on each of the parking space images to obtain a first identification result; wherein, the first identification result includes the license plate color information of the target vehicle currently parked in the target charging parking space; the license plate color information includes the license plate color of the front of the target vehicle and the license plate color of the rear of the vehicle.

[0036] The determining module is used to determine the second recognition result based on the license plate color information in the first recognition result;

[0037] The second identification module is used to, if it is determined that the second identification result indicates that the target vehicle is a charging vehicle, acquire the first video data of the target charging parking space acquired by each of the image acquisition devices, and perform identification processing on the first video data to obtain a third identification result.

[0038] The warning module is used to generate a warning message if it is determined that the third identification result indicates that the target vehicle has not been charging within a first preset time period; wherein the warning message is used to prompt the target vehicle to leave the target charging parking space.

[0039] In one possible implementation, the first identification module is specifically configured to: perform identification processing on each of the parking space images to obtain a fourth identification result; wherein the fourth identification result includes at least one vehicle image of the target vehicle currently parked in the target charging parking space; determine the license plate location information of the target vehicle based on each of the vehicle images; wherein the license plate location information represents the license plate installation position of the target vehicle; and determine the first identification result based on the license plate location information and each of the vehicle images.

[0040] In one possible implementation, the first recognition module is specifically configured to: perform image recognition processing on each of the vehicle images to obtain a feature set; wherein the feature set includes a set of license plate images, a set of front images, and a set of rear images of the target vehicle; the set of front images includes front images of the target vehicle from different acquisition angles; the set of rear images includes rear images of the target vehicle from different acquisition angles; perform feature processing on the feature set to obtain feature data of the target vehicle; wherein the feature data includes the appearance structure of the license plate of the target vehicle from different acquisition angles and the proportion of the license plate occupying the corresponding license plate image; and determine the license plate position information of the target vehicle based on the feature data.

[0041] In one possible implementation, the first recognition module is further configured to: perform recognition processing on the vehicle image based on the license plate location information to obtain pixel information of the vehicle image; wherein the pixel information includes the number and color distribution of pixels in the license plate area of ​​the vehicle image; and determine the first recognition result based on the pixel information of each vehicle image.

[0042] In one possible implementation, the second identification module is specifically used to: perform identification processing on the first video data to obtain the charging head information and charging port information of the target vehicle; and perform motion recognition processing on the first video data based on the charging head information and the charging port information to obtain the third identification result.

[0043] In one possible implementation, the device is further configured to: generate the warning information if it is determined that the second identification result indicates that the target vehicle is a non-charging vehicle.

[0044] In one possible implementation, the device is further configured to: generate notification information if it is determined that the third identification result indicates that the target vehicle has not engaged in charging behavior within a second preset time period; wherein the second preset time period is longer than the first preset time period; the notification information is used to notify staff to perform on-site manual processing.

[0045] In one possible implementation, the device is further configured to: perform recognition processing on the first video data to obtain the charging head information and charging port information of the target vehicle; collect second video data of the target charging parking space; and perform motion recognition processing on the second video data according to the charging head information and the charging port information to obtain a fifth recognition result; if it is determined that the fifth recognition result indicates that the target vehicle has completed charging, then collect third video data of the target charging parking space; and perform recognition processing on the third video data to obtain a sixth recognition result; if it is determined that the sixth recognition result indicates that the target vehicle has not left the target charging parking space within a third preset time period, then generate the warning information.

[0046] Thirdly, embodiments of this application provide an electronic device, including: a memory and a processor;

[0047] The memory stores computer-executed instructions;

[0048] The processor executes computer execution instructions stored in the memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0049] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect.

[0050] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.

[0051] The charging parking space anti-occupancy method, device, and equipment provided in this application embodiment automatically identify the license plate colors of the front and rear of the target vehicle in the target charging parking space. When the target vehicle is determined to be a charging vehicle based on the identified license plate colors, the first video data of the target charging parking space is acquired and processed. If it is determined that the target vehicle has not been charging within a preset time period, a warning message is generated to prompt the target vehicle to leave the target charging parking space. Thus, the charging parking space can be effectively avoided from being occupied and labor costs can be reduced. Attached Figure Description

[0052] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0053] Figure 1 This application provides an illustration of an application scenario.

[0054] Figure 2 A flowchart illustrating a method for preventing the occupancy of charging parking spaces based on image processing, provided in an embodiment of this application;

[0055] Figure 3 A flowchart illustrating another image processing-based method for preventing the occupancy of charging parking spaces provided in this application embodiment;

[0056] Figure 4 A schematic diagram illustrating the principle of a method for preventing non-charging vehicles from occupying charging parking spaces, provided in an embodiment of this application;

[0057] Figure 5 A schematic diagram illustrating a process for preventing non-charging vehicles from occupying charging parking spaces, provided as an embodiment of this application;

[0058] Figure 6 A schematic diagram of a charging parking space anti-occupancy device based on image processing provided in this application embodiment;

[0059] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0060] The accompanying drawings have illustrated specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to specific embodiments. Detailed Implementation

[0061] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0062] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use, processing, transmission, provision, disclosure, and application of the relevant data all comply with relevant laws, regulations, and standards, necessary confidentiality measures have been taken, they do not violate public order and good morals, and corresponding operation portals are provided for users to choose to authorize or refuse.

[0063] Furthermore, the technical solution involved in this application, which involves big data analysis of user information (including but not limited to personal biometrics, identity data, consumption data, asset data, electronic terminal operation data, etc.) and the use of artificial intelligence technology for automated decision-making, and makes decisions that have a significant impact on personal rights based on the results of automated decision-making, provides users with corresponding operation entry points for users to choose to agree to or reject the results of automated decision-making; if the user chooses to reject, the process will proceed to the expert decision-making process.

[0064] It should be noted that this application can be used in the field of image processing technology, or in any field other than image processing technology. The application field of this application is not limited.

[0065] Figure 1 This application provides an illustration of an application scenario, such as... Figure 1 As shown, the specific application scenarios of this application include: With the rapid development of new energy vehicle technology and the combination of smart grid technology of power system, the number of charging parking spaces is increasing, and some non-charging vehicle owners will occupy the charging pile locations.

[0066] Based on the above scenarios, it is clear that arranging for manual monitoring presents technical problems such as low processing efficiency and high labor costs.

[0067] The image processing-based method for preventing the occupancy of charging parking spaces provided in this application automatically identifies the license plate colors of the front and rear of the target vehicle in the target charging parking space. Based on the identified license plate colors, when it is determined that the target vehicle is a charging vehicle, the method acquires and processes the first video data of the target charging parking space. If it is determined that the target vehicle has not been charging within a preset time period, a warning message is generated to prompt the target vehicle to leave the target charging parking space. This method solves the technical problems of low processing efficiency and high labor costs.

[0068] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0069] Figure 2 This application provides a flowchart illustrating a method for preventing the occupancy of charging parking spaces based on image processing, as shown in the embodiments below. Figure 2 As shown, the method includes:

[0070] 201. Acquire parking space images of the target charging parking space captured by at least one image acquisition device; and perform recognition processing on each parking space image to obtain a first recognition result; wherein, the first recognition result includes the license plate color information of the target vehicle currently parked in the target charging parking space; the license plate color information includes the license plate color of the front of the target vehicle and the license plate color of the rear of the vehicle.

[0071] For example, the execution subject of this embodiment can be an electronic device, hereinafter referred to as the device. The device can be installed on the charging pile of the target charging space, and the charging pile can also be equipped with at least one image acquisition device (such as a digital camera or video camera) to acquire and transmit image data or video data from different angles and orientations in the target charging space area to the device. When a vehicle drives into the target charging space, the device acquires the parking space images of the target charging space acquired by all image acquisition devices in real time, and performs recognition processing on each parking space image based on image recognition technology and target detection technology to obtain the license plate color information of the target vehicle currently parked in the target charging space, i.e., the first recognition result. The license plate color information includes the license plate color of the front and rear of the target vehicle, such as blue, black, green, yellow, etc., and is synchronously recorded into the system for processing.

[0072] For example, deep learning image recognition methods utilize deep learning algorithms such as convolutional neural networks. By training on a large amount of image data of vehicles of different brands, structures, and appearances, the machine learns to automatically recognize features in the images. Using this trained deep learning image recognition technology, images of each parking space are processed to obtain the initial recognition result. Deep learning image recognition technology has powerful learning and generalization capabilities, enabling it to handle complex image recognition tasks and gradually improve recognition accuracy.

[0073] The charging piles are mainly installed behind the charging spaces, and each charging pile has a camera installed on top, which captures clearer images and has a better shooting angle. In addition, the cameras can be powered directly from the charging pile using DC power, ensuring long-term stable operation of the cameras.

[0074] 202. Determine the second recognition result based on the license plate color information in the first recognition result.

[0075] For example, the device processes the license plate color information in the first identification result based on preset rules to obtain a second identification result, thereby determining whether the target vehicle is a charging vehicle. For instance, based on the preset mapping relationship between green new energy license plates and charging vehicles, and new energy vehicles that require charging, if it is determined that the license plate color of the front and rear of the target vehicle is green, then the target vehicle is a new energy vehicle that requires charging, such as pure electric, plug-in hybrid, and range-extended electric vehicles. If the license plate color of the front and rear of the target vehicle is blue, yellow, black, or other colors not associated with green new energy license plates, then it is determined that the target vehicle is a non-new energy vehicle that does not require charging.

[0076] 203. If the second recognition result indicates that the target vehicle is a charging vehicle, then the first video data of the target charging parking space collected by each image acquisition device is obtained, and the first video data is processed to obtain the third recognition result.

[0077] For example, if the device determines that the target vehicle is a charging vehicle, it acquires the first video data of the target charging space within a first preset time period from all image acquisition devices to characterize the scene video in the target charging space area; and based on video parsing technology and target detection and tracking technology, it parses and identifies the charging behavior of the target vehicle in the target charging space area to obtain the third identification result, so as to determine whether the target vehicle has charging behavior within the first preset time period.

[0078] 204. If it is determined that the third identification result indicates that the target vehicle has not been charging within the first preset time period, a warning message is generated; wherein, the warning message is used to prompt the target vehicle to leave the target charging parking space.

[0079] For example, if the device determines that the target vehicle has not been charging within a first preset time period, it generates and outputs a warning message through an alarm device to remind the target vehicle that it needs to leave the target charging parking space.

[0080] For example, if the device determines that it will not perform the charging action within 2 minutes, it will issue a warning and drive away the vehicle through an external loudspeaker to prevent the vehicle from not charging and occupying the charging space.

[0081] This embodiment provides a method for preventing the occupancy of charging parking spaces based on image processing. By automatically identifying the license plate colors of the front and rear of the target vehicle in the target charging parking space, and determining that the target vehicle is a charging vehicle based on the identified license plate colors, the method acquires and processes the first video data of the target charging parking space. If it is determined that the target vehicle is not charging within a preset time period, a warning message is generated to prompt the target vehicle to leave the target charging parking space. Thus, it can effectively prevent the charging parking space from being occupied and reduce labor costs.

[0082] Figure 3 A flowchart illustrating another image processing-based method for preventing the occupancy of charging parking spaces provided in this application embodiment is shown below. Figure 3 As shown, the method includes:

[0083] 301. Obtain a parking space image of the target charging parking space acquired by at least one image acquisition device.

[0084] For example, this step can be referred to as step 201, which will not be repeated here.

[0085] 302. Perform recognition processing on the images of each parking space to obtain a fourth recognition result; wherein the fourth recognition result includes at least one vehicle image of the target vehicle currently parked in the target charging parking space.

[0086] For example, Figure 4 This is a schematic diagram illustrating the principle of a method for preventing non-charging vehicles from occupying charging parking spaces, as provided in an embodiment of this application. Figure 5 This application provides a schematic diagram of a process for preventing non-charging vehicles from occupying charging parking spaces, as illustrated in the embodiments of this application. Figure 4 , Figure 5As shown, professional image sensor equipment (such as digital cameras and camcorders) is used to acquire and save images of vehicles of different brands, structures, and appearances. These images are then used to train the algorithm, and the resulting images and recognition algorithms are integrated into a panoramic high-definition camera system. Each camera in the panoramic high-definition camera system is mounted on top of the charging pile, with an angle that completely covers and identifies vehicles in the entire charging space, thus enabling on-site operation. The device calls pre-trained deep learning algorithms such as convolutional neural networks to process all the images of the charging space, identifying the target vehicle currently parked in the charging space and distinguishing it from other objects. This yields at least one image of the target vehicle currently parked in the target charging space, which is the fourth recognition result.

[0087] 303. Based on the images of each vehicle, determine the license plate location information of the target vehicle; wherein, the license plate location information represents the installation position of the license plate of the target vehicle.

[0088] For example, after a vehicle is identified, the device calls a pre-trained deep learning algorithm such as a convolutional neural network to process all vehicle images, determine and mark the location of the license plate area in the vehicle image, so as to obtain the license plate installation location of the target vehicle, i.e., the license plate location information, such as the coordinate information of the detection box where the license plate is located in the vehicle image, and synchronously records the license plate location information into the system for processing.

[0089] In one example, step 303 includes the following steps:

[0090] The first step of step 303 is to perform image recognition processing on each vehicle image to obtain a feature set; wherein, the feature set includes the license plate image of the target vehicle, the set of front images of the vehicle, and the set of rear images of the vehicle; the set of front images of the vehicle includes front images of the target vehicle from different acquisition angles; the set of rear images of the vehicle includes rear images of the target vehicle from different acquisition angles.

[0091] The second step of step 303 is to perform feature processing on the feature set to obtain the feature data of the target vehicle; wherein, the feature data includes the appearance structure of the license plate of the target vehicle under different acquisition angles and the proportion of the license plate occupying the corresponding license plate image.

[0092] The third step of step 303 is to determine the license plate location information of the target vehicle based on the feature data.

[0093] For example, combined Figure 4 , Figure 5The device, based on image recognition technology, performs image recognition processing on each vehicle image, collecting multiple images of the vehicle's front and rear from various angles to obtain a feature set corresponding to all vehicle images. This feature set includes images of the target vehicle's license plate, front images, and rear images. The front image set includes images of the target vehicle's front from different acquisition angles, and the rear image set includes images of the target vehicle's rear from different acquisition angles. By combining the collected images of the vehicle's front and rear from various angles with images of the license plate from different angles, feature processing is performed on each image in the feature set to obtain feature data. This feature data includes the appearance structure of the target vehicle's license plate from different acquisition angles and the proportion of the license plate occupying the corresponding image. Based on the appearance structure of the license plate from different angles and its proportion in the image, the device identifies the license plate installation area and related license plate information. Once a vehicle enters a charging station parking space, the device can quickly identify the license plate installation location and determine whether a license plate is present.

[0094] 304. Determine the first recognition result based on the license plate location information and the images of each vehicle.

[0095] For example, the device uses target detection technology to determine the target to be detected in each vehicle image corresponding to the license plate location information based on the license plate location information, and uses image color recognition technology to identify the target to be detected, thereby determining the color of the license plate at the front and rear of the target vehicle.

[0096] In one example, step 304 includes:

[0097] Step 1: Based on the license plate location information, perform recognition processing on the vehicle image to obtain the pixel information of the vehicle image; the pixel information includes the number and color distribution of pixels in the license plate area of ​​the vehicle image.

[0098] Step 2: Determine the first recognition result based on the pixel information of each vehicle image.

[0099] Specifically, based on target detection technology, the device determines the license plate region corresponding to the license plate location information in each vehicle image of the target vehicle. Then, based on image processing technology, it performs recognition processing on the license plate region corresponding to the license plate location information to obtain the number and color distribution of pixels in the license plate region of each vehicle image, i.e., pixel information. Finally, based on a clustering algorithm, the device performs clustering processing on the pixel information of each vehicle image to obtain the license plate color of the front and rear of the target vehicle.

[0100] For example, combining Figure 4 , Figure 5Image processing algorithms are used to analyze pixel information in a vehicle image to determine its primary color. K-means clustering can be used to divide pixels into several clusters, each representing a color. By calculating the number of pixels and color distribution in each cluster, the primary color can be determined, thus identifying the license plate color. Specifically, when processing each vehicle image, its color space must first be converted from Red, Green, Blue (RGB) to a space more suitable for color analysis, such as the Hue-Saturation-Value (HSV) color model space or the Lab color space, to reflect differences in visual color perception. After conversion to HSV or Lab color space, each pixel in the vehicle image is represented by a new set of values. Color quantization techniques, such as octree quantization, are used to reduce color by constructing a color tree and progressively reducing the number of leaf nodes. Based on clustering analysis, the dominant color in a vehicle image is identified by grouping colors. For example, the K-means clustering algorithm iteratively divides colors into K groups, where colors within each group are as similar as possible, while colors between different groups are as distinct as possible. Using K-means or other clustering methods, the colors in an image can be effectively divided into several dominant color groups. Then, the dominant color of the image is determined by calculating the average color or center color of each group. After clustering analysis, the colors within each group are unified to a central color, which becomes the dominant color of the image. Furthermore, weights can be assigned based on parameters such as the proportion and brightness of each color in the image to determine the final dominant color tone. This results in the final color of the license plate.

[0101] 305. Determine the second recognition result based on the license plate color information in the first recognition result.

[0102] For example, this step can be referred to as step 202, which will not be repeated here.

[0103] 306. If the second identification result indicates that the target vehicle is a charging vehicle, then the first video data of the target charging parking space collected by each image acquisition device is obtained.

[0104] For example, this step can be referred to as step 203, which will not be repeated here.

[0105] In one example, after step 305, the method further includes: if it is determined that the second identification result indicates that the target vehicle is a non-charging vehicle, then a warning message is generated.

[0106] For example, if the device determines that the target vehicle is a non-charging vehicle, it generates and outputs warning information through the warning device to remind the target vehicle to leave the target charging parking space. For example, if the vehicle is identified as having a blue, yellow, or black license plate, which is not a green new energy vehicle, it is determined to be a non-new energy vehicle. The external speaker matched with the panoramic camera starts to activate and warn and drive away the non-charging vehicle to avoid occupying the charging parking space.

[0107] 307. The first video data is processed to obtain the charging head information and charging port information of the target vehicle.

[0108] For example, combined Figure 4 , Figure 5 After determining that the target vehicle is a charging vehicle and collecting the first video data of the target charging space within the first preset time period, the device uses video analysis technology, such as image acquisition methods and image deep learning image methods, to analyze and identify the first video data to obtain the charging head information and charging port information of the target vehicle, such as the image and brand name of the charging head and the image and brand name of the charging port.

[0109] 308. Based on the charging head information and charging port information, perform motion recognition processing on the first video data to obtain the third recognition result.

[0110] For example, combined Figure 4 , Figure 5 The device uses target detection technology to collect images of vehicles and people from the first video data and begins to identify vehicle and person information. Based on target tracking technology, it tracks the charging head corresponding to the charging head information, the charging port corresponding to the charging port information, and the vehicle and people corresponding to the vehicle and person information. It identifies the actions of the vehicle and people taking off the charging head and inserting the charging head into the car charging port, thus obtaining whether the target vehicle has charging behavior within the first preset time period in the third identification result. This information is simultaneously recorded into the system for further processing.

[0111] 309. If it is determined that the third identification result indicates that the target vehicle has not been charging within the first preset time period, a warning message is generated; wherein, the warning message is used to prompt the target vehicle to leave the target charging parking space.

[0112] For example, this step can be referred to as step 204, which will not be repeated here.

[0113] In one example, after step 308, the method further includes: if it is determined that the third identification result indicates that the target vehicle has not engaged in charging behavior within the second preset time period, then a notification message is generated; wherein the second preset time period is longer than the first preset time period; the notification message is used to notify staff to perform on-site manual processing.

[0114] For example, combined Figure 4 , Figure 5 If the device determines that the target vehicle is not charging within the second preset time period, it can generate and output a notification message to notify staff to handle the situation on-site. The second preset time period is longer than the first preset time period.

[0115] For example, if a person removes the charging head from the charging station and inserts it into the charging port of the vehicle in the parking space within 2 minutes, the charging behavior will not trigger an alarm; if no charging action is performed within 2 minutes, an external loudspeaker will sound a warning to drive the person away; if no action is taken for more than 10 minutes, personnel will be notified to arrive at the scene to handle the situation.

[0116] In one example, after step 309, the following is also included:

[0117] Step 1: Recognize and process the first video data to obtain the charging head information and charging port information of the target vehicle.

[0118] Step 2: Collect the second video data of the target charging parking space; and perform motion recognition processing on the second video data based on the charging head information and charging port information to obtain the fifth recognition result.

[0119] Step 3: If the fifth recognition result indicates that the target vehicle has completed charging, then the third video data of the target charging parking space is collected; and the third video data is processed to obtain the sixth recognition result.

[0120] Step 4: If the sixth identification result indicates that the target vehicle has not left the target charging parking space within the third preset time period, a warning message is generated.

[0121] Specifically, the device acquires first video data of the target charging parking space over a period of time, previously captured by a camera. Using image acquisition methods and deep learning image processing techniques, it analyzes and processes this first video data to obtain the target vehicle's charging head and charging port information, such as images of the charging head and brand name, and images of the charging port and brand name. Then, the device uses a camera to acquire second video data of the target charging parking space over a period of time in real time. Based on target detection technology, it captures images of vehicles and personnel from the second video data and begins to identify vehicle and personnel information. Based on the charging head and charging port information, it identifies the corresponding charging head and charging port. Based on target tracking technology, it tracks and processes the charging head, charging port, and vehicle and personnel, and performs action recognition processing to identify actions such as unplugging the charging head from the charging port and plugging it back into the charging pile, obtaining a fifth recognition result to determine whether the target vehicle has completed charging. The device can also use the charging pile's vehicle charging detection technology to monitor the target vehicle's charging status in real time to determine whether charging is complete. If the device determines that the target vehicle has completed charging, it uses a camera to collect video data of the target charging space over a period of time (the second video data); and the vehicle's stationary status, which determines whether the target vehicle has left the target charging space within the third preset time period in the sixth identification result. This data is then simultaneously entered into the system for processing. If the device determines that the target vehicle has not left the target charging space within the third preset time period, it generates and outputs a warning message to remind the target vehicle to leave the target charging space.

[0122] For example, combining Figure 4 , Figure 5 By collecting video data and using a judgment algorithm, the system identifies continuous actions of personnel as the standard for determining whether the vehicle is fully charged or charging is complete. Once charging is detected, the staff unplugs the charging head from the charging port and plugs it back into the charging pile, then a timer begins. The vehicle must leave the charging space within 2 minutes. If the vehicle does not leave within the specified time, an alarm is triggered to ensure the full and reasonable use of the parking spaces. The main function is to identify when new energy vehicles have fully charged and must leave the charging space to prevent long-term occupation of the space.

[0123] In this embodiment, based on the above embodiments, on the one hand, when it is determined that the target vehicle is a charging vehicle, but the target vehicle does not charge or occupies the charging station parking space, it is also necessary to require the target vehicle to leave the charging parking space area; on the other hand, after the vehicle is fully charged, the continuous actions of the personnel are identified through video data. If the vehicle does not leave within the specified time, an alarm is triggered to ensure the full and reasonable use of the parking space.

[0124] Figure 6A schematic diagram of a charging parking space anti-occupancy device based on image processing is provided in an embodiment of this application, as shown below. Figure 6 As shown, the device includes:

[0125] The first recognition module 401 is used to acquire parking space images of the target charging parking space acquired by at least one image acquisition device; and to perform recognition processing on each parking space image to obtain a first recognition result; wherein, the first recognition result includes the license plate color information of the target vehicle currently parked in the target charging parking space; the license plate color information includes the license plate color of the front of the target vehicle and the license plate color of the rear of the vehicle.

[0126] The determining module 402 is used to determine the second recognition result based on the license plate color information in the first recognition result;

[0127] The second identification module 403 is used to, if it is determined that the second identification result indicates that the target vehicle is a charging vehicle, acquire the first video data of the target charging parking space collected by each image acquisition device, and perform identification processing on the first video data to obtain the third identification result.

[0128] The warning module 404 is used to generate a warning message if it is determined that the third identification result indicates that the target vehicle has not been charging within the first preset time period; wherein the warning message is used to prompt the target vehicle to leave the target charging parking space.

[0129] In one possible implementation, the first identification module 401 is specifically used for: performing identification processing on each parking space image to obtain a fourth identification result; wherein the fourth identification result includes at least one vehicle image of the target vehicle currently parked in the target charging parking space; determining the license plate location information of the target vehicle based on each vehicle image; wherein the license plate location information represents the license plate installation position of the target vehicle; and determining the first identification result based on the license plate location information and each vehicle image.

[0130] In one possible implementation, the first recognition module 401 is specifically used for: performing image recognition processing on each vehicle image to obtain a feature set; wherein the feature set includes a set of license plate images, a set of front images, and a set of rear images of the target vehicle; the set of front images includes front images of the target vehicle from different acquisition angles; the set of rear images includes rear images of the target vehicle from different acquisition angles; performing feature processing on the feature set to obtain feature data of the target vehicle; wherein the feature data includes the appearance structure of the license plate of the target vehicle from different acquisition angles and the proportion of the license plate occupying the corresponding license plate image; and determining the license plate position information of the target vehicle based on the feature data.

[0131] In one possible implementation, the first recognition module 401 is further specifically used to: perform recognition processing on the vehicle image based on the license plate location information to obtain the pixel information of the vehicle image; wherein, the pixel information includes the number and color distribution of pixels in the license plate area of ​​the vehicle image; and determine the first recognition result based on the pixel information of each vehicle image.

[0132] In one possible implementation, the second identification module 403 is specifically used to: perform identification processing on the first video data to obtain the charging head information and charging port information of the target vehicle; and perform action recognition processing on the first video data based on the charging head information and charging port information to obtain a third identification result.

[0133] In one possible implementation, the device is further configured to: generate a warning message if it is determined that the second identification result characterizes the target vehicle as a non-charging vehicle.

[0134] In one possible implementation, the device is further configured to: generate a notification message if it is determined that the third identification result indicates that the target vehicle has not engaged in charging behavior within a second preset time period; wherein the second preset time period is longer than the first preset time period; the notification message is used to notify staff to perform on-site manual processing.

[0135] In one possible implementation, the device is further configured to: perform recognition processing on the first video data to obtain the charging head information and charging port information of the target vehicle; collect the second video data of the target charging parking space; and perform motion recognition processing on the second video data based on the charging head information and charging port information to obtain a fifth recognition result; if it is determined that the fifth recognition result indicates that the target vehicle has completed charging, then collect the third video data of the target charging parking space; and perform recognition processing on the third video data to obtain a sixth recognition result; if it is determined that the sixth recognition result indicates that the target vehicle has not left the target charging parking space within a third preset time period, then generate a warning message.

[0136] The apparatus in this embodiment can execute the technical solutions in the above method. Its specific implementation process and technical principles are the same, and will not be repeated here.

[0137] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application, such as... Figure 7 As shown, the electronic device includes: a memory 501 and a processor 502; the memory 501 is a memory used to store instructions executable by the processor 502.

[0138] The processor 502 is configured to perform the method provided in the above embodiments.

[0139] The electronic device also includes a receiver 503 and a transmitter 504. The receiver 503 is used to receive instructions and data sent by other devices, and the transmitter 504 is used to send instructions and data to external devices.

[0140] The specific implementation process of the processor can be found in the above method embodiments, and its implementation principle and technical effect are similar, so it will not be repeated here.

[0141] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0142] This application also provides a chip for executing instructions, which is used to execute the technical solutions in the above embodiments.

[0143] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed on a computer, cause the computer to perform the technical solutions described above.

[0144] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory, electrically erasable programmable read-only memory, erasable programmable read-only memory, programmable read-only memory, read-only memory, magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0145] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an application-specific integrated circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0146] This application also provides a computer program product, which includes a computer program stored in a computer-readable storage medium. At least one processor can read the computer program from the computer-readable storage medium, and when the at least one processor executes the computer program, it can implement the technical solutions in the above embodiments.

[0147] The technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0148] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0149] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A method for preventing the occupancy of charging parking spaces based on image processing, characterized in that, include: Acquire parking space images of the target charging parking space captured by at least one image acquisition device; The images of each parking space are then processed to obtain a first recognition result; wherein, the first recognition result includes the license plate color information of the target vehicle currently parked in the target charging parking space; the license plate color information includes the license plate color of the front of the target vehicle and the license plate color of the rear of the vehicle. The second recognition result is determined based on the license plate color information in the first recognition result; If the second recognition result indicates that the target vehicle is a charging vehicle, then the first video data of the target charging parking space collected by each of the image acquisition devices is obtained, and the first video data is processed for recognition to obtain a third recognition result. If the third identification result indicates that the target vehicle has not been charging within the first preset time period, a warning message is generated; wherein, the warning message is used to prompt the target vehicle to leave the target charging parking space.

2. The method according to claim 1, characterized in that, The images of each parking space are processed for recognition to obtain a first recognition result, including: The images of each parking space are processed to obtain a fourth recognition result; wherein the fourth recognition result includes at least one vehicle image of the target vehicle currently parked in the target charging parking space. Based on the vehicle images, the license plate location information of the target vehicle is determined; wherein, the license plate location information represents the installation position of the license plate of the target vehicle. The first recognition result is determined based on the license plate location information and the images of each vehicle.

3. The method according to claim 2, characterized in that, Based on the vehicle images, the license plate location information of the target vehicle is determined, including: Image recognition processing is performed on each of the vehicle images to obtain a feature set; wherein, the feature set includes the license plate image, the front image set, and the rear image set of the target vehicle; the front image set includes front images of the target vehicle from different acquisition angles; the rear image set includes rear images of the target vehicle from different acquisition angles. The feature set is processed to obtain the feature data of the target vehicle; wherein, the feature data includes the appearance structure of the license plate of the target vehicle under different acquisition angles and the proportion of the license plate in the corresponding license plate image; Based on the feature data, the license plate location information of the target vehicle is determined.

4. The method according to claim 2, characterized in that, Based on the license plate location information and the images of each vehicle, the first recognition result is determined, including: Based on the license plate location information, the vehicle image is processed to obtain the pixel information of the vehicle image; wherein, the pixel information includes the number and color distribution of pixels in the license plate area of ​​the vehicle image; The first recognition result is determined based on the pixel information of each vehicle image.

5. The method according to claim 1, characterized in that, The first video data is processed to obtain a third recognition result, including: The first video data is processed to obtain the charging head information and charging port information of the target vehicle; Based on the charging head information and the charging port information, the first video data is processed for motion recognition to obtain the third recognition result.

6. The method according to claim 1, characterized in that, The method further includes: If the second identification result indicates that the target vehicle is a non-charging vehicle, then the warning message is generated.

7. The method according to claim 1, characterized in that, The method further includes: If the third identification result indicates that the target vehicle has not engaged in charging behavior within the second preset time period, a notification message is generated; wherein the second preset time period is longer than the first preset time period; the notification message is used to notify staff to perform on-site manual processing.

8. The method according to any one of claims 1-7, characterized in that, The method further includes: The first video data is processed to obtain the charging head information and charging port information of the target vehicle; The second video data of the target charging parking space is collected; and the second video data is processed for action recognition based on the charging head information and the charging port information to obtain a fifth recognition result. If the fifth identification result indicates that the target vehicle has completed charging, then the third video data of the target charging parking space is collected; and the third video data is processed to obtain the sixth identification result. If it is determined that the sixth identification result indicates that the target vehicle has not left the target charging parking space within the third preset time period, then the warning information is generated.

9. A charging parking space anti-occupancy device based on image processing, characterized in that, include: The first identification module is used to acquire parking space images of the target charging parking space collected by at least one image acquisition device; The images of each parking space are then processed to obtain a first recognition result; wherein, the first recognition result includes the license plate color information of the target vehicle currently parked in the target charging parking space; the license plate color information includes the license plate color of the front of the target vehicle and the license plate color of the rear of the vehicle. The determining module is used to determine the second recognition result based on the license plate color information in the first recognition result; The second identification module is used to, if it is determined that the second identification result indicates that the target vehicle is a charging vehicle, acquire the first video data of the target charging parking space acquired by each of the image acquisition devices, and perform identification processing on the first video data to obtain a third identification result. The warning module is used to generate a warning message if it is determined that the third identification result indicates that the target vehicle has not been charging within a first preset time period; wherein the warning message is used to prompt the target vehicle to leave the target charging parking space.

10. An electronic device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-8.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-8.

12. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method described in any one of claims 1-8.

Images