Car moving notification method and system, electronic equipment and storage medium

Abstract

The invention relates to the technical field of vehicles, and provides a vehicle moving notification method and system, electronic equipment and a storage medium, and the method comprises the steps: obtaining an environment image around a to-be-moved vehicle; based on the distance between the pedestrian and the to-be-moved vehicle in the environment image, screening the pedestrian to obtain a target pedestrian; and performing stay duration detection and / or action detection on the target pedestrian, and sending a vehicle moving notification to a vehicle owner terminal based on a detection result. According to the car moving notification method and system, the electronic equipment and the storage medium provided by the invention, the parking lot does not need to input information, devices and facilities near the parking space do not need to be depended on, and a large amount of car owner data does not need to be acquired, so that the labor cost is saved, the car moving efficiency is improved, and the car owner information safety is protected. Meanwhile, according to the scheme, the user can be reminded to move the car in an active reminding mode, and compared with a passive reminding mode, the method is convenient and fast to use and wide in application range.

Description

Technical Field

[0001] The present invention relates to the field of vehicle technology, and in particular to a vehicle moving notification method, system, electronic equipment and storage medium. Background Art

[0002] With the development of economy, the number of vehicles is increasing, and the parking spaces in various communities, office buildings, shopping malls, etc. are seriously insufficient. Various disputes caused by parking problems have a great impact on people's lives and social order.

[0003] In the related art, in order to enable others to contact the owner of the vehicle that needs to be moved, there are usually the following ways to remind others to move the vehicle: one is that the parking lot registers the owner's contact information when the vehicle is parked, or the owner directly leaves the contact information in a conspicuous position on the vehicle to achieve the purpose of notifying the moving operation. Although the above methods can meet the needs of use to a certain extent, on the one hand, the efficiency of the moving vehicle contact operation is low, the labor intensity is high, and it is easy to cause the owner's information to be leaked; on the other hand, the data coverage is small and cannot effectively and comprehensively cover the contact information of the owners of each vehicle in the parking lot, resulting in the inability to flexibly move the vehicle as needed, causing great inconvenience to the parking lot management and emergency event handling.

[0004] Another method is to take a photo of the vehicle license plate through a surveillance camera when there is a need to move the vehicle, and send the photo information to an information server based on a cloud computing platform. Then, the vehicle information and owner information are identified through the license plate. The information server based on the cloud computing platform compares the currently received vehicle license plate information with the extracted vehicle information and owner information, and notifies the owner to move the vehicle. This method requires the information server of the cloud computing platform to establish a data connection with the vehicle information system of the traffic management department to obtain the vehicle license plate and the owner's contact information, which poses an information security risk. In addition, all related solutions passively notify the owner to move the vehicle when there is a need to move the vehicle, which is inefficient. Summary of the invention

[0005] The present invention provides a vehicle moving notification method, system, electronic device and storage medium, which are used to solve the defects of low efficiency of vehicle moving notification and easy leakage of vehicle owner information in the prior art.

[0006] The present invention provides a vehicle moving notification method, comprising: Acquire an environmental image around the vehicle to be moved; Based on the distance between the pedestrian in the environment image and the vehicle to be moved, the pedestrian is screened to obtain a target pedestrian; The target pedestrian is subjected to a stay duration detection and / or action detection, and a vehicle moving notification is sent to the vehicle owner terminal based on the detection result.

[0007] According to the vehicle moving notification method provided by the present invention, the pedestrians are screened based on the distance between the pedestrians and the vehicle to be moved in the environment image to obtain the target pedestrians, including: Preliminarily screening the pedestrians based on the distance between the pedestrians and the vehicle to be moved in the environment image to obtain first candidate pedestrians and non-candidate pedestrians; Determining a second candidate pedestrian from the non-candidate pedestrians based on clothing features of the non-candidate pedestrians; The target pedestrian is determined based on the first candidate pedestrian and the second candidate pedestrian.

[0008] According to the vehicle moving notification method provided by the present invention, the pedestrian is preliminarily screened based on the distance between the pedestrian and the vehicle to be moved in the environment image to obtain a first candidate pedestrian, including: Performing pedestrian detection on the environment image to obtain a detection position of the pedestrian in the environment image; Based on the pixel coincidence between a preset position in the environment image and the detection position, the pedestrians are preliminarily screened to obtain the first candidate pedestrian, wherein the preset position is determined based on a preset distance from the vehicle to be moved.

[0009] According to the vehicle moving notification method provided by the present invention, the method further includes: Based on the parking position and vehicle identification of the vehicle to be moved, confirming that the vehicle to be moved joins a nearby parking group; When a vehicle moving request is received in the nearby parking group, character recognition is performed on the text corresponding to the vehicle moving request, and if the character recognition result includes the vehicle identification, a vehicle moving notification is sent.

[0010] According to the vehicle moving notification method provided by the present invention, the method further includes: When it is detected that the vehicle to be moved has started, confirm that the vehicle to be moved exits the nearby parking group.

[0011] According to the vehicle moving notification method provided by the present invention, the vehicle moving notification is sent to the vehicle owner terminal based on the detection result, and then further includes: The environment image is sent to the monitoring system of the vehicle owner terminal, so that the vehicle owner can judge the vehicle moving notification based on the environment image.

[0012] According to the vehicle moving notification method provided by the present invention, the method further includes: Receive user's judgment information on the vehicle moving notification; Associating the judgment information of the vehicle moving notification with the corresponding sample environment image to obtain a sample data set; The vehicle moving notification model is optimized and iterated based on the sample data set, and the vehicle moving notification model is used to send a vehicle moving notification based on the environment image.

[0013] 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, any of the above-mentioned vehicle moving notification methods is implemented.

[0014] The present invention also provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the vehicle moving notification method described in any one of the above methods is implemented.

[0015] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements any of the above-mentioned vehicle moving notification methods.

[0016] The vehicle moving notification method, system, electronic device and storage medium provided by the present invention obtain an environmental image around the vehicle to be moved; screen pedestrians based on the distance between the pedestrians and the vehicle to be moved in the environmental image to obtain a target pedestrian; perform a stay duration detection and / or action detection on the target pedestrian, and send a vehicle moving notification to the vehicle owner's terminal based on the detection result. This solution does not require parking lot information entry, does not rely on devices and facilities near parking spaces, and does not require the acquisition of a large amount of vehicle owner data, which saves labor costs, improves vehicle moving efficiency, and protects the security of vehicle owner information. At the same time, this solution can realize the active reminder method to prompt users to move the vehicle, which is more convenient and faster than the passive reminder method, and has a wider range of applications. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] 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.

[0018] Figure 1 This is one of the flow charts of the vehicle moving notification method provided by the present invention.

[0019] Figure 2 This is one of the flow charts of step 120 in the vehicle moving notification method provided by the present invention.

[0020] Figure 3 This is the second flowchart of step 120 in the vehicle moving notification method provided by the present invention.

[0021] Figure 4 This is the second flow chart of the vehicle moving notification method provided by the present invention.

[0022] Figure 5 It is a structural schematic diagram of the vehicle moving notification system provided by the present invention.

[0023] Figure 6 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] In related technologies, in order to enable others to contact the owner of a vehicle that needs to be moved, one method is for the parking lot to register the owner's contact information when the vehicle is parked, or the owner directly leaves the contact information in a conspicuous place in the vehicle; the other method relies on the information server of the cloud computing platform to establish a data connection relationship with the vehicle information system of the traffic management department to obtain the vehicle license plate and the owner's contact information. Both methods passively notify the owner to move the vehicle when there is a need to move the vehicle, which is inefficient and easily causes the owner's information to be leaked.

[0026] In response to the above problems, an embodiment of the present invention proposes a method for notifying a vehicle to be moved, in which an environmental image around the vehicle to be moved is obtained; pedestrians are screened based on the distance between the pedestrians and the vehicle to be moved in the environmental image to obtain a target pedestrian; the target pedestrian is subjected to a stay duration detection and / or action detection, and a vehicle moving notification is sent to the vehicle owner's terminal based on the detection result. This solution does not require the parking lot to enter information, does not rely on devices and facilities near the parking space, and does not require the acquisition of a large amount of vehicle owner data, which saves labor costs, improves vehicle moving efficiency, and protects the security of vehicle owner information. At the same time, this solution can realize the active reminder method to prompt the user to move the vehicle, which is more convenient and faster than the passive reminder method, and has a wider range of applications.

[0027] The embodiments of the present invention can be applied to scenarios where a vehicle moving notification is required, such as scenarios where a temporarily parked vehicle may need to be moved. The execution subject of the method can be an electronic device such as a terminal device, a computer, a server, a server cluster, or a specially designed vehicle moving notification device, or a vehicle moving notification device set in the electronic device, and the vehicle moving notification device can be implemented by software, hardware, or a combination of the two.

[0028] In the description of the embodiments of the present invention, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0029] Figure 1 FIG. 1 is one of the flow charts of the vehicle moving notification method provided by the present invention, such as Figure 1 As shown, the method comprises the following steps: Step 110, obtaining an image of the environment around the vehicle to be moved.

[0030] Specifically, the vehicle to be moved may be a vehicle that is currently in a temporarily parked state and may need to be moved later. The environmental image around the vehicle to be moved can be acquired through an image acquisition device installed on the vehicle. When the vehicle is parked safely, the owner can turn on the image acquisition device to capture the environmental image. The image acquisition device can be turned on manually, voice controlled, or remotely controlled, and the embodiment of the present invention does not specifically limit this. The environmental image may be a video frame acquired in real time. The image acquisition device can be connected to a vehicle moving notification device to ensure that the acquired environmental image can be transmitted to the vehicle moving notification device in real time. The environmental image reflects the environmental information around the vehicle to be moved. For example, the environmental image may include information such as other temporarily parked vehicles and pedestrians in the surrounding area.

[0031] Step 120 , based on the distance between the pedestrian and the vehicle to be moved in the environment image, the pedestrians are screened to obtain the target pedestrian.

[0032] Considering that most of the related technologies remind the car owner to move the car after manually discovering the need to move the car, this method is a passive notification, which is inefficient and easy to cause the leakage of the car owner's information. The embodiment of the present invention proposes an active reminder method to prompt the user to move the car.

[0033] Usually, if the vehicle to be moved affects the traffic order nearby, there may be pedestrians around the vehicle to be moved to remind the vehicle to be moved in time. For example, the target pedestrian may be a pedestrian who is close to the vehicle to be moved and is around the vehicle to request the vehicle to be moved, or it may be a traffic policeman who is maintaining traffic order.

[0034] The target pedestrians can be identified by screening them based on the distance between them and the vehicle to be moved in the environment image. Pedestrians can be identified from the environment image using image processing techniques such as edge detection and contour extraction. The distance between each pedestrian and the vehicle to be moved can be calculated using the pixel distance in the image or the actual physical distance. Pedestrians who are closer to the vehicle to be moved are screened as target pedestrians based on the preset distance threshold.

[0035] In other embodiments, even if the distance between the pedestrian and the vehicle to be moved is not within the preset distance range, it is possible to further identify whether the pedestrian is a traffic maintenance personnel, such as a traffic police. If a traffic police appears in the monitoring area, the probability of needing to move the vehicle is high, and the target pedestrians may include pedestrians and traffic police who are closer to the vehicle to be moved.

[0036] Step 130 , performing a stay duration detection and / or action detection on the target pedestrian, and sending a vehicle moving notification to the vehicle owner terminal based on the detection result.

[0037] Specifically, considering that some target pedestrians are close to the vehicle to be moved, but may just be pedestrians passing by the vehicle to be moved, in order to further improve the accuracy of the vehicle moving notification, it is necessary to further detect the target pedestrians.

[0038] Stay time detection refers to detecting the length of time a target pedestrian stays in the monitoring area. If the stay time exceeds a preset threshold (such as 30 seconds or 1 minute, etc.), it is considered that the pedestrian may be waiting for a vehicle to move.

[0039] Action detection refers to the use of action recognition technology, such as deep learning models or posture estimation algorithms, to detect the actions of target pedestrians. If a pedestrian is detected to make an action related to moving a vehicle (such as approaching a vehicle, checking the vehicle, preparing to make a phone call, posting a receipt on the vehicle, etc.), the action is considered to be related to reminding the vehicle to move.

[0040] Here, the stay time detection can be performed first, and on this basis, the action detection is further performed on the target pedestrian whose stay time exceeds the preset threshold. If the action detection result meets the preset action, a vehicle moving notification is sent; the vehicle moving notification can also be sent based on the stay time detection result and any one of the action detection results, that is, if the stay time detection result indicates that the stay time exceeds the preset threshold, or the action detection result indicates that the action meets the preset action, then the vehicle moving notification is sent.

[0041] The vehicle moving notification can be automatically sent to the vehicle owner's terminal through the vehicle moving notification device. The vehicle owner's terminal can be pre-bound, for example, it can be a mobile phone or other terminal device. The vehicle moving notification can be sent to the owner of the vehicle to be moved through SMS, phone call, APP push, etc. The notification content may include the reason for moving the vehicle, the recommended time for moving the vehicle, etc., such as "There is a traffic police patrol near the vehicle, please move the vehicle as soon as possible".

[0042] The method provided by the embodiment of the present invention obtains the environmental image around the vehicle to be moved, screens pedestrians based on the distance between the pedestrians and the vehicle to be moved in the environmental image, obtains the target pedestrian, performs residence time detection and / or motion detection on the target pedestrian, and sends a vehicle moving notification to the vehicle owner's terminal based on the detection result. This solution does not require the parking lot to enter information, does not need to rely on devices and facilities near the parking space, and does not need to obtain a large amount of vehicle owner data, which saves labor costs, improves vehicle moving efficiency, and protects the security of vehicle owner information. At the same time, this solution can realize the active reminder method to prompt the user to move the vehicle, which is convenient and fast compared to the passive reminder method, and has a wider range of applications.

[0043] Preferably, in order to further improve the accuracy of the vehicle moving notification, after receiving the vehicle moving notification, the vehicle owner can also check the remote monitoring system on the terminal to check the situation near the vehicle to be moved, determine whether the vehicle moving notification is accurate, and confirm whether the vehicle needs to be moved.

[0044] Based on any of the above embodiments, Figure 2 is one of the flow charts of step 120 in the vehicle moving notification method provided by the present invention, such as Figure 2 As shown, based on the distance between the pedestrians and the vehicle to be moved in the environment image, the pedestrians are screened to obtain the target pedestrians, that is, step 120 specifically includes: Step 121, preliminarily screening pedestrians based on the distance between the pedestrians and the vehicle to be moved in the environment image to obtain first candidate pedestrians and non-candidate pedestrians; Step 122, determining a second candidate pedestrian from the non-candidate pedestrians based on clothing features of the non-candidate pedestrians; Step 123: Determine a target pedestrian based on the first candidate pedestrian and the second candidate pedestrian.

[0045] Specifically, the determination of the target pedestrian can be obtained through multiple screenings. First, the pedestrians are preliminarily screened based on the distance between the pedestrians and the vehicle to be moved in the environmental image. Pedestrians are accurately identified from the environmental image using image processing techniques, such as edge detection and contour extraction. The actual physical distance between each pedestrian and the vehicle to be moved is calculated using the pixel distance in the image or in combination with the camera's parameters and position information. According to a preset distance threshold (for example, the distance threshold can be set to 1m), pedestrians who are closer to the vehicle to be moved are screened as the first candidate pedestrians, while pedestrians who are farther away are considered non-candidate pedestrians.

[0046] Considering that in some scenarios, for example, the traffic police may be far away from the vehicle to be moved, beyond the preset distance threshold, the first candidate pedestrian may be missed. Therefore, in order to further improve the accuracy of the vehicle moving reminder, it is necessary to screen the non-candidate pedestrians again and select the pedestrians who may be traffic maintenance personnel as the target pedestrians.

[0047] Considering that traffic maintenance personnel have obvious dressing habits during road traffic law enforcement, the second candidate pedestrian can be determined from the non-candidate pedestrians based on their clothing features. The clothing features of the non-candidate pedestrians are extracted and analyzed, and the clothing features may specifically include clothing color, texture, style, hat, shoes and other features.

[0048] Using machine learning or deep learning algorithms, such as pedestrian re-identification algorithms based on traditional manual features or pedestrian re-identification models based on deep learning, non-candidate pedestrians are further screened according to their clothing features.

[0049] If the clothing features of some non-candidate pedestrians match preset specific conditions (such as the clothing features of traffic maintenance personnel), these pedestrians are determined as second candidate pedestrians, and the second candidate pedestrians may be traffic maintenance personnel.

[0050] Then, the first candidate pedestrian and the second candidate pedestrian are both taken as target pedestrians. It is understandable that the target pedestrian may include pedestrians and traffic police who are closer to the vehicle to be moved, and may also include traffic police who are farther away from the vehicle to be moved.

[0051] The method provided by the embodiment of the present invention obtains a first candidate pedestrian by distance screening, obtains a second candidate pedestrian by clothing feature screening, and determines a target pedestrian based on the first candidate pedestrian and the second candidate pedestrian, which can improve the recognition accuracy of the target pedestrian, thereby improving the accuracy of the vehicle moving notification prompt.

[0052] Based on any of the above embodiments, Figure 3 This is a second flow chart of step 120 in the vehicle moving notification method provided by the present invention, such as Figure 3As shown, based on the distance between the pedestrian and the vehicle to be moved in the environment image, the pedestrians are preliminarily screened to obtain the first candidate pedestrian, that is, step 121 specifically includes: Step 121-1, performing pedestrian detection on the environment image to obtain the detection position of the pedestrian in the environment image; Step 121 - 2 , based on the pixel coincidence between the preset position in the environment image and the detection position, the pedestrians are preliminarily screened to obtain the first candidate pedestrian, and the preset position is determined based on the preset distance between the vehicle to be moved.

[0053] Specifically, pedestrian detection methods based on global features, human body parts or stereo vision can be used to process environmental images and identify pedestrians in the image. The algorithm will output the detection position of each pedestrian, usually in the form of a rectangular box containing the main part of the pedestrian. The detected pedestrian position is verified to ensure the accuracy of the detection result, which can be verified by manual annotation or comparison with other sensor data.

[0054] For determining the first candidate pedestrian, a preset position may be first determined in the environment image. One or more preset positions may be determined in the environment image according to a preset distance (e.g., 1 meter) between the pedestrian and the vehicle to be moved. The preset position may be one or more rectangular frames, and the size and position of the frame are adjusted according to the preset distance and the shooting angle of the camera.

[0055] Then, for each detected pedestrian position, the pixel coincidence between it and the preset position is calculated. The pixel coincidence can be obtained by calculating the ratio of the intersection area to the union area between two rectangular boxes. According to the preset pixel coincidence threshold (such as 80%), the pedestrian with a high coincidence with the preset position is screened out as the first candidate pedestrian. The selection of the pixel coincidence threshold should be adjusted according to the actual situation to ensure the accuracy and reliability of the screening results.

[0056] The method provided by the embodiment of the present invention can accurately detect pedestrians in the environment image and preliminarily screen the pedestrians according to the preset distance between them and the vehicle to be moved, thereby providing strong support for the subsequent determination of target pedestrians.

[0057] Based on any of the above embodiments, Figure 4 FIG. 2 is a flow chart of the method for notifying the vehicle moving provided by the present invention. Figure 4 As shown, the method also includes: Step 410, based on the parking position and vehicle identification of the vehicle to be moved, confirming that the vehicle to be moved joins a nearby parking group; Step 420: When a vehicle moving request is received in a nearby parking group, character recognition is performed on the text corresponding to the vehicle moving request. If the character recognition result includes a vehicle identification, a vehicle moving notification is sent.

[0058] Specifically, in other passive reminder scenarios, in order to effectively protect the security of the personal privacy information of the car owner, the car moving notification method provided by the embodiment of the present invention is implemented through a nearby parking group.

[0059] The parking position of the vehicle to be moved can be obtained through a vehicle positioning device (such as a built-in GPS positioning system or a Beidou positioning system). The vehicle identification can uniquely identify the vehicle, for example, it can be a vehicle license plate number, and the vehicle identification can be extracted from vehicle registration information or a license plate recognition system.

[0060] According to the parking location of the vehicle to be moved, use geographic information system (GIS) technology to determine the nearby parking area where it is located. Divide the parking area into one or more parking groups, each group contains parked vehicles within a certain range. Add the vehicle identification and parking location information of the vehicle to be moved to the database of the corresponding parking group. Ensure the real-time update and accuracy of vehicle information within the group. The parking group can automatically name each user's personal nickname with the vehicle identification.

[0061] Other vehicles or managers in nearby parking groups can send vehicle moving requests through mobile phone apps, text messages, phone calls, etc. The system receives and stores these requests, and records the source and time of the requests. Preprocess the received vehicle moving request text, such as removing noise, adjusting image size, etc. Use optical character recognition (OCR) technology or natural language processing (NLP) algorithms to perform character recognition on the text. Extract key information from the recognition results, especially those related to vehicle identification. Match the vehicle identification in the recognition results with the vehicle information in the parking group database. If the match is successful, it means that the vehicle moving request is for the vehicle to be moved.

[0062] Once it is confirmed that the vehicle moving request is for the vehicle to be moved, the system immediately generates a vehicle moving notification. The notification content includes information such as the source, time, reason, and vehicle ID of the requester. The vehicle moving notification is sent to the owner or driver of the vehicle to be moved via mobile phone text messages, APP push, phone calls, etc.

[0063] The method provided in the embodiment of the present invention notifies the user of the vehicle to move the vehicle by joining a nearby parking group, which can be applied to passive reminder scenarios and effectively protect the security of the personal privacy information of the vehicle owner.

[0064] Based on any of the above embodiments, the method further includes: When it is detected that the vehicle to be moved has started, confirm that the vehicle to be moved exits the nearby parking group.

[0065] Specifically, the vehicle moving notification device can use the vehicle's built-in sensors (such as engine start sensors) or OBD (on-board diagnostic system) interface to monitor the vehicle's start status in real time. When the vehicle starts, the relevant sensor will send a signal to the vehicle moving notification device to record the timestamp of the vehicle starting.

[0066] Match the start signal with the vehicle identification (such as license plate number, VIN code, etc.) to ensure that the start signal is sent by the target vehicle to be moved. Reduce the possibility of false alarms through multiple verification methods (such as timestamp comparison, signal strength analysis, etc.).

[0067] Once the vehicle to be moved is confirmed to have started, the status of the vehicle is immediately updated in the database of the nearby parking group and marked as "left". Ensure that all relevant information in the parking group (such as vehicle location, status, etc.) can be updated synchronously in real time so that other vehicles or managers can understand the situation in a timely manner.

[0068] Optionally, based on actual needs, a notification can be sent to other vehicles or managers in the parking group that the vehicle to be moved has left. The notification content should include the vehicle ID, departure time, and possible follow-up action suggestions (such as releasing parking spaces, etc.). If resources (such as parking spaces) in the parking group are associated with the vehicle to be moved, these resources will be released after the vehicle leaves. The entire process of vehicle departure, including time, status changes, etc., is recorded for subsequent analysis.

[0069] Based on any of the above embodiments, sending a vehicle moving notification based on the detection result further includes: The environment image is displayed visually so that the user can make judgments on the vehicle moving notification based on the environment image.

[0070] Specifically, in order to further improve the accuracy of the vehicle moving notification, after sending the vehicle moving notification to the vehicle owner's terminal, the vehicle owner can view the vehicle's surrounding environment information through the monitoring system to make a judgment on the vehicle moving notification.

[0071] The processed environment image is displayed to the user through a mobile phone APP, web page or other visualization platform to monitor the environment information near the vehicle to be moved. Add interactive functions such as zooming, dragging, and rotating on the display platform to enable users to view image details more freely. For example, text descriptions can also be added next to or below the image, such as the specific reason for the request to move the vehicle, so that users can understand more background information.

[0072] Based on the displayed environment image and additional information, the user judges the car moving notification and decides whether to execute the car moving operation. The user can feedback the execution status of the car moving decision to the system through the display platform or other communication methods, such as moving the car or refusing to move the car.

[0073] The system records the user's judgment results and feedback for subsequent analysis and audit. The system conducts statistical analysis on the user's judgment results and feedback to understand the user's behavior habits and preferences, and provides reference for optimizing system functions and improving user experience.

[0074] Based on any of the above embodiments, the vehicle moving notification method further includes: Receive user's judgment information on the vehicle moving notification; Associating the judgment information of the car moving notification with the corresponding sample environment image to obtain a sample data set; The vehicle moving notification model is optimized and iterated based on the sample data set, and the vehicle moving notification model is used to send a vehicle moving notification based on the environment image.

[0075] Specifically, user feedback channels are established through mobile phone APP, text messages, phone calls, web pages, etc. to ensure that users can easily submit judgment information on the car moving notification. The system automatically or manually collects the judgment information submitted by the user, including whether the user agrees to move the car, the time and reason for moving the car, and the user's satisfaction.

[0076] The collected judgment information is preprocessed, such as removing duplicate data, processing missing values, standardizing data formats, etc., to ensure data quality.

[0077] The user judgment information is associated with the corresponding sample environment image to form a complete sample data set.

[0078] Divide the sample data set into training set, validation set, and test set for subsequent model training and evaluation. Use deep learning frameworks and image recognition algorithms (such as convolutional neural networks (CNNs)) to train the car moving notification model based on the training set data. During the training process, continuously adjust model parameters and optimize model performance until the model achieves satisfactory accuracy on the validation set. Use the test set data to evaluate the trained model, including indicators such as accuracy, recall, and F1 score. Based on the evaluation results, analyze the advantages and disadvantages of the model to provide direction for subsequent model optimization.

[0079] The model is optimized and iterated based on user judgment information and model evaluation results. Optimization methods include adjusting the model structure, increasing the amount of data, using data enhancement technology, regularization methods, optimization algorithms, etc. The optimized model is deployed to the actual system to generate and send vehicle moving notifications based on environmental images. Monitor the performance of the model in actual operation and adjust and optimize the model parameters in a timely manner.

[0080] With the continuous accumulation of user judgment information and the emergence of new technologies, the car moving notification model can be continuously iterated and optimized to improve the accuracy and robustness of the model.

[0081] Based on any of the above embodiments, a vehicle moving notification method is provided, including: After parking, the owner turns on the vehicle moving notification system, and the vehicle starts moving detection, which is mainly divided into two aspects: active detection and passive reminder.

[0082] For active detection: S1, the on-board camera obtains the environmental image around the vehicle to be moved. Perform pedestrian detection on the environmental image to obtain the detection position of the pedestrian in the environmental image; based on the pixel coincidence between the preset position in the environmental image and the detection position, perform preliminary screening of pedestrians to obtain the first candidate pedestrian and non-candidate pedestrians, and the preset position is determined based on the preset distance from the vehicle to be moved. Based on the clothing features of the non-candidate pedestrians, determine the second candidate pedestrian from the non-candidate pedestrians; based on the first candidate pedestrian and the second candidate pedestrian, determine the target pedestrian. Specifically including: Pedestrians near the vehicle are detected in real time based on the YOLOv5 model. Pedestrian samples near the vehicle are extracted in real time through the on-board camera, and the collected pedestrian samples are classified based on the ROI area. The target pedestrians are initially screened and two types of pedestrians are obtained: traffic police and pedestrians near the vehicle. The screening process is as follows: a) Screening pedestrians at a specific distance; Pedestrian samples are detected based on common pedestrian detection algorithms. Predetermine the pixel points of pedestrians within 1m in the image, compare the position of the collected pedestrians in the image with the set value, and if the pixel overlap rate is >80%, it meets the requirements and serves as the preliminary screening basis for pedestrians near the vehicle. They are the first candidate pedestrians. Samples that do not meet the distance requirements are non-candidate pedestrians and are reserved for further screening.

[0083] b) For the above-mentioned reserved non-candidate pedestrians, a deep learning algorithm is used to identify color, clothing, hats, etc., and pedestrians who may be traffic police are screened out as the second candidate pedestrians.

[0084] c) The first candidate pedestrian in the sample + the second candidate pedestrian are all the target pedestrians obtained by preliminary screening.

[0085] S2, perform stop time detection and / or action detection on the target pedestrian, and send a vehicle moving notification to the vehicle owner's terminal based on the detection results. Perform stop time detection on the selected samples. If the stop time is greater than 30 seconds, it is reserved for the next step of detection and the vehicle owner is notified. The vehicle owner receives a possible vehicle moving prompt on the mobile phone; perform action detection on the selected samples. If the action of posting a receipt is detected, it is preliminarily identified as a traffic police, and the vehicle owner is notified that the vehicle needs to be moved.

[0086] S3, the environment image is sent to the monitoring system of the car owner's terminal, so that the car owner can judge the notification of moving the car based on the environment image. After receiving the prompt, the car owner checks on the mobile phone. The device has a built-in remote monitoring system, which can check the situation near the vehicle through the monitoring system to determine whether the system push is accurate.

[0087] S4, receiving the judgment information of the user on the car moving notification; associating the judgment information of the car moving notification with the corresponding sample environment image to obtain a sample data set; optimizing and iterating the car moving notification model based on the sample data set, the car moving notification model is used to send the car moving notification based on the environment image. According to the judgment situation, the recognition situation is added to the database as a training sample, and the algorithm model is continuously optimized to improve the recognition accuracy and system performance.

[0088] For passive reminders: S5, based on the parking position and vehicle identification of the vehicle to be moved, confirm that the vehicle to be moved joins the nearby parking group; when a vehicle moving request is received in the nearby parking group, character recognition is performed on the text corresponding to the vehicle moving request, and if the character recognition result includes the vehicle identification, a vehicle moving notification is sent. When it is detected that the vehicle to be moved has started, confirm that the vehicle to be moved exits the nearby parking group.

[0089] The car computer obtains the GPS of the temporary parking location and creates a nearby parking group based on the GPS; the personal nickname in the group is automatically named by the license plate number. When nearby parked car owners need to move their cars, the group will remind the users who are waiting to move their cars. Based on OCR text detection, the system detects the keywords of moving the car + the current license plate number and notifies the car owner to move the car. After the vehicle is started, the group will be automatically disbanded.

[0090] The method provided by the embodiment of the present invention does not need to obtain a large amount of car owner data, nor does it depend on whether the parking lot is intelligent. After temporarily parking at any location, if a person needs to be notified to move the car, the solution can be used to assist in the reminder.

[0091] The following is a description of the vehicle moving notification system provided by the present invention. The vehicle moving notification system described below and the vehicle moving notification method described above can be referenced to each other.

[0092] Based on any of the above embodiments, Figure 5 Schematic diagram of the structure of the vehicle moving notification system provided by the present invention. Figure 5 As shown, the system includes: an image acquisition device 510 installed on the vehicle to be moved, and a vehicle moving notification device 520; An image acquisition device, used to acquire an environmental image around the vehicle to be moved, and send the environmental image to the vehicle moving notification device; The vehicle moving notification device is used to screen pedestrians based on the distance between pedestrians and vehicles in the environmental image to obtain target pedestrians; and to perform stay time detection and / or action detection on the target pedestrians, and send a vehicle moving notification to the vehicle owner terminal based on the detection results.

[0093] The device provided by the embodiment of the present invention does not need to input parking lot information, does not need to rely on devices and facilities near the parking space, and does not need to obtain a large amount of car owner data, which saves labor costs, improves the efficiency of moving the car, and protects the security of the car owner's information. At the same time, this solution can realize the active reminder method to prompt the user to move the car, which is more convenient and faster than the passive reminder method, and has a wider range of applications.

[0094] Based on any of the above embodiments, the vehicle moving notification device is specifically used for: Preliminarily screening the pedestrians based on the distance between the pedestrians and the vehicle to be moved in the environment image to obtain first candidate pedestrians and non-candidate pedestrians; Determining a second candidate pedestrian from the non-candidate pedestrians based on clothing features of the non-candidate pedestrians; The target pedestrian is determined based on the first candidate pedestrian and the second candidate pedestrian.

[0095] Based on any of the above embodiments, the vehicle moving notification device is specifically used for: Performing pedestrian detection on the environment image to obtain a detection position of the pedestrian in the environment image; Based on the pixel coincidence between a preset position in the environment image and the detection position, the pedestrians are preliminarily screened to obtain the first candidate pedestrian, wherein the preset position is determined based on a preset distance from the vehicle to be moved.

[0096] Based on any of the above embodiments, the vehicle moving notification device is further used for: Based on the parking position and vehicle identification of the vehicle to be moved, confirming that the vehicle to be moved joins a nearby parking group; When a vehicle moving request is received in the nearby parking group, character recognition is performed on the text corresponding to the vehicle moving request, and if the character recognition result includes the vehicle identification, a vehicle moving notification is sent.

[0097] Based on any of the above embodiments, the vehicle moving notification device is further used for: When it is detected that the vehicle to be moved has started, confirm that the vehicle to be moved exits the nearby parking group.

[0098] Based on any of the above embodiments, the vehicle moving notification device is further used for: The environment image is sent to the monitoring system of the vehicle owner terminal, so that the vehicle owner can judge the vehicle moving notification based on the environment image.

[0099] Based on any of the above embodiments, the vehicle moving notification device is further used for: Receive user's judgment information on the vehicle moving notification; Associating the judgment information of the vehicle moving notification with the corresponding sample environment image to obtain a sample data set; The vehicle moving notification model is optimized and iterated based on the sample data set, and the vehicle moving notification model is used to send a vehicle moving notification based on the environment image.

[0100] Figure 6 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 6 As shown, the electronic device may include: a processor 610, a communication interface 620, a memory 630 and a communication bus 640, wherein the processor 610, the communication interface 620 and the memory 630 communicate with each other through the communication bus 640. The processor 610 may call the logic instructions in the memory 630 to execute the vehicle moving notification method, which includes: obtaining an environmental image around the vehicle to be moved; screening the pedestrians based on the distance between the pedestrians in the environmental image and the vehicle to be moved to obtain target pedestrians; performing stay time detection and / or action detection on the target pedestrian, and sending a vehicle moving notification to the vehicle owner terminal based on the detection result.

[0101] In addition, the logic instructions in the above-mentioned memory 630 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.

[0102] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the vehicle moving notification method provided by the above-mentioned methods, which includes: obtaining an environmental image around the vehicle to be moved; based on the distance between the pedestrians in the environmental image and the vehicle to be moved, screening the pedestrians to obtain target pedestrians; performing stay time detection and / or action detection on the target pedestrian, and sending a vehicle moving notification to the vehicle owner terminal based on the detection results.

[0103] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, it is implemented to execute the vehicle moving notification method provided by the above-mentioned methods, the method comprising: obtaining an environmental image around the vehicle to be moved; based on the distance between the pedestrians in the environmental image and the vehicle to be moved, screening the pedestrians to obtain target pedestrians; performing stay time detection and / or action detection on the target pedestrians, and sending a vehicle moving notification to the vehicle owner terminal based on the detection results.

[0104] 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.

[0105] 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.

[0106] 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 notifying a vehicle to move, characterized in that: include: Acquire an environmental image around the vehicle to be moved; Based on the distance between the pedestrian in the environment image and the vehicle to be moved, the pedestrian is screened to obtain a target pedestrian; The target pedestrian is subjected to a stay duration detection and / or action detection, and a vehicle moving notification is sent to the vehicle owner terminal based on the detection result.

2. The vehicle moving notification method according to claim 1, characterized in that: The step of screening the pedestrians based on the distance between the pedestrians in the environment image and the vehicle to be moved to obtain the target pedestrians includes: Preliminarily screening the pedestrians based on the distance between the pedestrians and the vehicle to be moved in the environment image to obtain first candidate pedestrians and non-candidate pedestrians; Determining a second candidate pedestrian from the non-candidate pedestrians based on clothing features of the non-candidate pedestrians; The target pedestrian is determined based on the first candidate pedestrian and the second candidate pedestrian.

3. The vehicle moving notification method according to claim 2, characterized in that: The preliminarily screening the pedestrian based on the distance between the pedestrian and the vehicle to be moved in the environment image to obtain a first candidate pedestrian includes: Performing pedestrian detection on the environment image to obtain a detection position of the pedestrian in the environment image; Based on the pixel coincidence between a preset position in the environment image and the detection position, the pedestrians are preliminarily screened to obtain the first candidate pedestrian, wherein the preset position is determined based on a preset distance from the vehicle to be moved.

4. The vehicle moving notification method according to claim 1, characterized in that: The method further comprises: Based on the parking position and vehicle identification of the vehicle to be moved, confirming that the vehicle to be moved joins a nearby parking group; When a vehicle moving request is received in the nearby parking group, character recognition is performed on the text corresponding to the vehicle moving request, and if the character recognition result includes the vehicle identification, a vehicle moving notification is sent.

5. The vehicle moving notification method according to claim 4, characterized in that: The method further comprises: When it is detected that the vehicle to be moved has started, confirm that the vehicle to be moved exits the nearby parking group.

6. The vehicle moving notification method according to any one of claims 1 to 5, characterized in that: The method further includes sending a vehicle moving notification to the vehicle owner terminal based on the detection result: The environment image is sent to the monitoring system of the vehicle owner terminal, so that the vehicle owner can judge the vehicle moving notification based on the environment image.

7. The vehicle moving notification method according to claim 6, characterized in that: The method further comprises: Receive user's judgment information on the vehicle moving notification; Associating the judgment information of the vehicle moving notification with the corresponding sample environment image to obtain a sample data set; The vehicle moving notification model is optimized and iterated based on the sample data set, and the vehicle moving notification model is used to send a vehicle moving notification based on the environment image.

8. A vehicle moving notification system, characterized in that: include: An image acquisition device installed on the vehicle to be moved, and a vehicle moving notification device; The image acquisition device is used to acquire an environmental image around the vehicle to be moved, and send the environmental image to the vehicle moving notification device; The vehicle moving notification device is used to screen the pedestrians based on the distance between the pedestrians and the vehicle in the environmental image to obtain target pedestrians; and perform stay time detection and / or action detection on the target pedestrians, and send a vehicle moving notification to the vehicle owner terminal based on the detection results.

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 vehicle moving notification method according to any one of claims 1 to 7 is 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 vehicle moving notification method according to any one of claims 1 to 7 is implemented.

Images