Privacy protection method, device and equipment based on vehicle sunshade curtain and medium

Abstract

The invention discloses a privacy protection method and device based on a vehicle sunshade curtain, equipment and a medium. The method comprises the steps of obtaining image data around a vehicle and authorized personnel information corresponding to the vehicle; performing target detection and behavior analysis on the image data, and determining at least one target person included in the image data and a behavior category corresponding to the target person; matching the target personnel according to the authorized personnel information; if the target person and the authorized person information are not matched, determining a suspicious level of the target person according to a behavior category corresponding to the target person; wherein the suspicious level is used for representing the suspicious degree of the target person; according to the suspicious level, a sunshade curtain of the vehicle is controlled to descend by a distance corresponding to the suspicious level, so that privacy protection is conducted on the vehicle; wherein the height of the suspicious level and the size of the distance are in positive correlation. According to the method, the intelligence of vehicle control and the privacy of the vehicle can be improved, and the use experience of the vehicle can be improved. The method can be widely applied to the technical field of vehicles.

Description

Technical Field

[0001] This application relates to the technical field of vehicles, and in particular to a privacy protection method, device, equipment and medium based on a vehicle sunshade curtain. Background Art

[0002] Vehicles are the main means of transportation in modern society and are widely used in daily commuting, long-distance travel and cargo transportation. With technological progress, vehicle design not only focuses on performance and safety, but also increasingly pays attention to comfort and privacy protection. The sunshade curtain is a part of the vehicle interior, mainly used to block sunlight, adjust the light inside the vehicle and protect privacy. It is commonly found on the windows and the rear windshield and is made of various materials such as cloth, mesh or plastic. Using a sunshade curtain in a vehicle can block external views, prevent the items or personal activities inside the vehicle from being spied on, reduce the visibility of valuable items inside the vehicle, and reduce the risk of theft.

[0003] In related technologies, the use of traditional vehicle interior sunshade curtains is often controlled by the driver and passengers themselves. For example, when the driver and passengers do not want to be disturbed or spied on, they may lower the sunshade curtain to improve the privacy inside the vehicle. This implementation method is relatively troublesome for users, and the degree of vehicle intelligence is insufficient, resulting in a poor user experience.

[0004] In summary, the problems existing in the related technologies need to be solved urgently. Summary of the Invention

[0005] The purpose of this application is to solve at least to some extent one of the technical problems existing in the related technologies.

[0006] To this end, an object of an embodiment of this application is to provide a privacy protection method, device, equipment and medium based on a vehicle sunshade curtain.

[0007] To achieve the above technical purpose, the technical solutions adopted in the embodiments of this application include:

[0008] On the one hand, an embodiment of this application provides a privacy protection method based on a vehicle sunshade curtain, and the method includes:

[0009] Obtain image data around the vehicle and information about authorized personnel corresponding to the vehicle;

[0010] Perform target detection and behavior analysis on the image data to determine at least one target person included in the image data and the behavior category corresponding to the target person;

[0011] Match the target person according to the authorized personnel information;

[0012] If the information of the target person does not match the information of the authorized person, determine the suspicious level of the target person according to the behavior category corresponding to the target person; wherein, the suspicious level is used to characterize the suspicious degree of the target person.

[0013] According to the suspicious level, control the sunshade of the vehicle to descend by a corresponding distance to protect the privacy of the vehicle; wherein, there is a positive correlation between the level of the suspicious level and the magnitude of the distance.

[0014] In addition, according to the privacy protection method based on the vehicle sunshade in the above embodiments of the present application, the following additional technical features may also be included:

[0015] Further, in an embodiment of the present application, the performing target detection and behavior analysis on the image data to determine at least one target person included in the image data and the behavior category corresponding to the target person includes:

[0016] Input the image data into a deep convolutional neural network model, and extract the feature data corresponding to the image data through the deep convolutional neural network model.

[0017] According to the feature data, determine at least one of the target persons included in the image data through the deep convolutional neural network model, and identify the area where the target person is located.

[0018] According to the feature data and the image data of the area where the target person is located, determine the behavior category corresponding to the target person through the deep convolutional neural network model.

[0019] Further, in an embodiment of the present application, the information of the authorized person includes reference images of several authorized persons; the matching of the target person according to the information of the authorized person includes:

[0020] According to the area where the target person is located, intercept the image data to obtain the target image corresponding to the target person.

[0021] Determine the similarity between the target image and each of the reference images.

[0022] If the similarity between the target image and any one of the reference images is greater than or equal to a preset threshold, determine that the target person matches the information of the authorized person.

[0023] If the similarity between the target image and any one of the reference images is less than the preset threshold, determine that the target person does not match the information of the authorized person.

[0024] Further, in an embodiment of the present application, determining the suspicious level of the target person according to the behavior category corresponding to the target person includes:

[0025] If the behavior category corresponding to the target person is the reciprocating pacing behavior, determine that the suspicious level of the target person is low;

[0026] If the behavior category corresponding to the target person is the staring behavior, determine that the suspicious level of the target person is medium;

[0027] If the behavior category corresponding to the target person is the security threat behavior, determine that the suspicious level of the target person is high.

[0028] Further, in an embodiment of the present application, controlling the sunshade of the vehicle to descend a corresponding distance according to the suspicious level includes:

[0029] If it is determined that the suspicious level of the target person is low, medium or high, detect whether there are occupants in the vehicle;

[0030] If there are occupants in the vehicle, send a prompt notification to the occupants; wherein, the prompt notification is used to inform the occupants that the sunshade is about to descend;

[0031] When no termination instruction from the occupants is received within the first time period after the prompt notification is sent, control the sunshade of the vehicle to descend a corresponding distance according to the suspicious level.

[0032] Further, in an embodiment of the present application, controlling the sunshade of the vehicle to descend a corresponding distance according to the suspicious level further includes:

[0033] If there are no occupants in the vehicle, control the sunshade of the vehicle to descend a corresponding distance according to the suspicious level, and send an alarm notification to the owner of the vehicle.

[0034] Further, in an embodiment of the present application, controlling the sunshade of the vehicle to descend a corresponding distance according to the suspicious level includes:

[0035] If it is determined that the suspicious level of the target person is low, control the sunshade of the vehicle to descend a first distance at a first speed;

[0036] If it is determined that the suspicious level of the target person is medium, control the sunshade of the vehicle to descend a second distance at a second speed;

[0037] If it is determined that the suspicious level of the target person is high, control the sunshade of the vehicle to descend a third distance at a third speed;

[0038] Wherein, the second speed is greater than the first speed and less than the third speed, and the second distance is greater than the first distance and less than the third distance.

[0039] On the other hand, an embodiment of the present application provides a privacy protection device based on a vehicle sunshade, and the device includes:

[0040] An acquisition unit, configured to acquire image data around the vehicle and authorized personnel information corresponding to the vehicle;

[0041] An analysis unit, configured to perform object detection and behavior analysis on the image data to determine at least one target person included in the image data and the behavior category corresponding to the target person;

[0042] A matching unit, configured to match the target person according to the authorized personnel information;

[0043] A processing unit, configured to determine the suspicious level of the target person according to the behavior category corresponding to the target person if the target person does not match the authorized personnel information; wherein, the suspicious level is used to characterize the suspicious degree of the target person;

[0044] A control unit, configured to control the sunshade of the vehicle to descend a corresponding distance according to the suspicious level to protect the privacy of the vehicle; wherein, there is a positive correlation between the level of the suspicious level and the size of the distance.

[0045] On the other hand, an embodiment of the present application provides an electronic device, including:

[0046] At least one processor;

[0047] At least one memory, configured to store at least one program;

[0048] When the at least one program is executed by the at least one processor, the at least one processor is caused to implement the above-mentioned privacy protection method based on a vehicle sunshade.

[0049] On the other hand, an embodiment of the present application further provides a computer-readable storage medium, in which a program executable by a processor is stored, and the program executable by the processor is used to implement the above-mentioned privacy protection method based on a vehicle sunshade when executed by the processor.

[0050] The advantages and beneficial effects of the present application will be partially given in the following description, partially will become obvious from the following description, or will be understood through the practice of the present application:

[0051] A privacy protection method, device, equipment and medium based on a vehicle sunshade disclosed in an embodiment of the present application obtain image data around the vehicle and authorized personnel information corresponding to the vehicle; perform object detection and behavior analysis on the image data to determine at least one target person included in the image data and the behavior category corresponding to the target person; match the target person according to the authorized personnel information; if the target person does not match the authorized personnel information, determine the suspicious level of the target person according to the behavior category corresponding to the target person; wherein, the suspicious level is used to characterize the suspicious degree of the target person; according to the suspicious level, control the sunshade of the vehicle to descend a corresponding distance to protect the privacy of the vehicle; wherein, there is a positive correlation between the level of the suspicious level and the size of the distance. This method can automatically control the vehicle sunshade to achieve privacy protection of the in-vehicle environment, without manual operation, which can improve the intelligence of vehicle control and the privacy of the vehicle, and is beneficial to improving the use experience of the vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following introduces the accompanying drawings of the relevant technical solutions in the embodiments of the present application or the prior art. It should be understood that the accompanying drawings in the following introduction are only for conveniently and clearly presenting some embodiments of the technical solutions in the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative efforts.

[0053] Figure 1 It is a schematic diagram of the implementation environment of a privacy protection method based on a vehicle sunshade provided in an embodiment of the present application;

[0054] Figure 2 It is a schematic flowchart of a privacy protection method based on a vehicle sunshade provided in an embodiment of the present application;

[0055] Figure 3 It is a schematic structural diagram of a privacy protection device based on a vehicle sunshade provided in an embodiment of the present application;

[0056] Figure 4 It is a schematic structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0057] The present application will be further described below in conjunction with the accompanying drawings of the specification and specific embodiments. The described embodiments should not be regarded as limitations of the present application. All other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present application.

[0058] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments. However, it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict.

[0059] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0060] 1) Artificial Intelligence (AI) is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technology in computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a way similar to human intelligence. Artificial intelligence also studies the design principles and implementation methods of various intelligent machines to enable the machines to have the functions of perception, reasoning, and decision-making.

[0061] Artificial intelligence technology is an interdisciplinary subject with a wide range of fields, including both hardware-level and software-level technologies. The basic technologies of artificial intelligence generally include sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, pre-trained model technology, operation / interaction systems, mechatronics, etc. Among them, the pre-trained model, also known as the large model or the foundation model, can be widely applied to downstream tasks in various directions of artificial intelligence after fine-tuning. The software technologies of artificial intelligence mainly include several major directions such as computer vision technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0062] 2) Machine Learning (ML) is an interdisciplinary subject involving multiple fields such as probability theory, statistics, approximation theory, convex analysis, and algorithm complexity theory. It specifically studies how computers simulate or implement human learning behaviors to acquire new knowledge or skills and reorganize the existing knowledge structure to continuously improve their own performance. Machine learning is the core of artificial intelligence and the fundamental way to make computers intelligent, and its applications cover all fields of artificial intelligence. Machine learning and deep learning usually include technologies such as artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and rote learning. The pre-trained model is the latest development result of deep learning, which integrates the above technologies.

[0063] 3) Computer Vision (CV), an important branch of Artificial Intelligence (AI), is dedicated to enabling computers to "see" and understand visual information from images or videos. By simulating the functions of the human visual system, it enables computers to automatically process, analyze, and understand visual data.

[0064] 4) Object detection models, an important type of model in the field of computer vision, are used to identify and locate specific objects in images or videos. Different from simple image classification tasks, object detection not only requires identifying the object categories in the image but also determining the positions of the objects (usually represented by bounding boxes) and other information.

[0065] Vehicles are the main means of transportation in modern society and are widely used in daily commuting, long-distance travel, and cargo transportation. With technological advancements, vehicle design not only focuses on performance and safety but also increasingly on comfort and privacy protection. Sunshades are part of the vehicle interior and are mainly used to block sunlight, adjust the interior light, and protect privacy. They are commonly found on windows and rear windshields and are made of various materials such as fabric, mesh, or plastic. Using sunshades in vehicles can block external views, prevent the peeping of items or personal activities inside the vehicle, reduce the visibility of valuable items inside the vehicle, and lower the risk of theft.

[0066] In related technologies, the use of traditional vehicle interior sunshades is often controlled by the driver or passengers themselves. For example, when the driver or passengers do not want to be disturbed or spied on, they may lower the sunshade to improve the privacy inside the vehicle. This implementation method is relatively troublesome for users, and the lack of vehicle intelligence leads to a poor user experience.

[0067] In view of this, an embodiment of this application provides a privacy protection method based on vehicle sunshades, which obtains image data around the vehicle and the authorized personnel information corresponding to the vehicle; performs object detection and behavior analysis on the image data to determine at least one target person included in the image data and the behavior category corresponding to the target person; matches the target person according to the authorized personnel information; if the target person does not match the authorized personnel information, determines the suspicious level of the target person according to the behavior category corresponding to the target person; where the suspicious level is used to characterize the suspicious degree of the target person; controls the sunshade of the vehicle to descend a corresponding distance according to the suspicious level to protect the privacy of the vehicle; where there is a positive correlation between the level of the suspicious level and the size of the distance. This method can automatically control the vehicle sunshade to achieve privacy protection of the interior environment, without manual operation, which can improve the intelligence of vehicle control and the privacy of the vehicle, and is conducive to improving the vehicle use experience.

[0068] Please refer toFigure 1 , Figure 1 shows a schematic diagram of the implementation environment of a privacy protection method based on a vehicle sunshade provided in an embodiment of the present application. In this implementation environment, the main software and hardware entities involved include a terminal device 110 and a background server 120. The terminal device 110 and the background server 120 are communicatively connected.

[0069] Specifically, the privacy protection method based on a vehicle sunshade provided in an embodiment of the present application can be executed solely on the side of the terminal device 110, or executed based on data interaction between the terminal device 110 and the background server 120. The terminal device 110 can be an in-vehicle terminal; the background server 120 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0070] A communication connection can be established between the terminal device 110 and the background server 120 through a wireless network or a wired network. The wireless network or the wired network uses standard communication technologies and / or protocols. The network can be set as the Internet, or any other network, such as including but not limited to any combination of a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), a mobile, wired or wireless network, a private network or a virtual private network.

[0071] Of course, it can be understood that Figure 1 the implementation environment in Figure 1 is only some optional application scenarios of the privacy protection method based on a vehicle sunshade provided in an embodiment of the present application, and the actual application is not fixed to the

[0072] software and hardware environment shown.

[0073] Please refer to Figure 2 , Figure 2 which is a schematic diagram of a privacy protection method based on a vehicle sunshade provided in an embodiment of the present application. The privacy protection method based on a vehicle sunshade includes but is not limited to:

[0074] Step 210: Obtain the image data around the vehicle and the authorized personnel information corresponding to the vehicle;

[0075] Step 220: Perform object detection and behavior analysis on the image data to determine at least one target person included in the image data and the behavior category corresponding to the target person;

[0076] Step 230: Match the target person according to the authorized personnel information;

[0077] Step 240: If the target person does not match the authorized personnel information, determine the suspicious level of the target person according to the behavior category corresponding to the target person; wherein, the suspicious level is used to characterize the suspicious degree of the target person;

[0078] Step 250: According to the suspicious level, control the sunshade of the vehicle to descend a corresponding distance to protect the privacy of the vehicle; wherein, there is a positive correlation between the level of the suspicious level and the size of the distance.

[0079] In the embodiment of the present application, a privacy protection method based on the vehicle sunshade is provided. This method can automatically control the vehicle sunshade to achieve the privacy protection of the interior environment of the vehicle, without manual operation, which can improve the intelligence of vehicle control and the privacy of the vehicle, and is beneficial to improving the use experience of the vehicle.

[0080] Specifically, in the embodiment of the present application, when realizing privacy protection based on the control of the vehicle sunshade, the image data around the vehicle can be obtained. The vehicle in the embodiment of the present application can be any vehicle type equipped with a sunshade, and the present application does not limit this. When obtaining the image data around the vehicle, it can be collected by the camera carried by the vehicle itself. Generally speaking, a range for obtaining the image data around the vehicle can be set. For example, the image data within five meters around the vehicle can be obtained. Of course, the specific range size can be set according to actual needs.

[0081] In the embodiments of the present application, the authorized personnel information corresponding to the vehicle is also obtained. Here, the authorized personnel information records the information related to the authorized personnel corresponding to the vehicle. The authorized personnel refer to those who have the operation authority for the vehicle, which can be designated by the vehicle owner himself / herself, such as the family members or friends of the vehicle owner. The authorized personnel information may include the images of the authorized personnel. These information can be uploaded by the vehicle owner to the management platform corresponding to the vehicle. When controlling the vehicle, the relevant information can be obtained from the management platform. Exemplarily, for example, the management platform can establish and back up the associated information corresponding to each vehicle, store the authorized personnel information as a kind of associated information together with the identification information of the vehicle itself. When controlling a certain vehicle, the corresponding authorized personnel information can be retrieved according to the identification information of the vehicle. Of course, it should be noted that the authorized personnel information belongs to the privacy information of the vehicle owner. Relevant authorization is required for storage, acquisition, and use, and attention should be paid to the security of the information.

[0082] After obtaining the image data, target detection and behavior analysis can be performed on the image data. In the embodiments of the present application, the purpose of performing target detection on the image data is to identify the personnel included in the image data, which is denoted as the target personnel. The purpose of performing behavior analysis on the image data is to determine the behavior category corresponding to the target personnel. In the embodiments of the present application, the specific situations of the behavior categories can be preset. For example, there can be preset passing-by behavior, reciprocating pacing behavior, gazing behavior, and security threat behavior, etc. For example, if a certain target personnel passes by around the vehicle, it can be determined that the corresponding behavior category is passing-by behavior; if a certain target personnel walks repeatedly around the vehicle, it can be determined that the corresponding behavior category is reciprocating pacing behavior; if a certain target personnel stops beside the vehicle for a certain period of time and looks in the direction of the vehicle, it can be determined that the corresponding behavior category is gazing behavior; if a certain target personnel approaches the vehicle with tools and attempts to forcefully open the car door or window, then it can be determined that the corresponding behavior category is security threat behavior. Of course, it can be understood that the above is only for an exemplary introduction of the behavior categories corresponding to the target personnel. In actual applications, more behavior categories can also be set, or the above behavior categories can be deleted or replaced. The present application places no restrictions on this.

[0083] It should be noted that in the embodiments of the present application, when performing target detection and behavior analysis based on the image data, the image data relied on can be multiple consecutive images. The present application places no restrictions on this.

[0084] Specifically, when performing object detection and behavior analysis on image data, in some scenarios, it may be the case that the object detection result indicates that there is one or more target persons in the current image data. At this time, the behavior category of each target person will be detected; in other scenarios, it may be the case that the object detection result indicates that there are no target persons in the current image data. At this time, the subsequent process of this method can be terminated, and the image data around the vehicle can continue to be acquired.

[0085] In the embodiments of the present application, if it is determined that there are target persons in the image data, the target persons can be matched according to the authorized personnel information. If it is found that a target person belongs to an authorized person, it can be determined that the target person and the authorized personnel information match; if it is found that a target person does not belong to an authorized person, it can be determined that the target person and the authorized personnel information do not match. In the case where the target person and the authorized personnel information match, it can be considered that the target person is a reliable person and there is no need to perform privacy protection on him / her. In contrast, if the target person and the authorized personnel information do not match, it means that the target person is a stranger. At this time, the suspicious level of the target person can be determined in combination with the behavior category corresponding to the target person. In the embodiments of the present application, the suspicious level can be used to characterize the suspicious degree of the target person.

[0086] Exemplarily, for example, in the embodiments of the present application, three suspicious levels can be set, namely low level, medium level, and high level. When determining the suspicious level corresponding to a target person, if the behavior category of the target person has little to do with vehicle privacy, such as the target person just passing by the vehicle, it can be determined that the suspicious degree of the target person is 0 and does not belong to any suspicious level. In contrast, if the behavior category of the target person is related to vehicle privacy, the corresponding suspicious level can be determined according to the behavior category. Specifically, if the behavior category corresponding to the target person is a reciprocating pacing behavior, it can be determined that the suspicious level of the target person is low; if the behavior category corresponding to the target person is a staring behavior, it can be determined that the suspicious level of the target person is medium; if the behavior category corresponding to the target person is a security threat behavior, it can be determined that the suspicious level of the target person is high. Of course, it can be understood that in the embodiments of the present application, the setting method of the suspicious level can be further refined according to the behavior category, and the present application does not limit this.

[0087] In the embodiments of the present application, after determining the suspicious level corresponding to the target person, the sunshade of the vehicle can be controlled to descend by a corresponding distance according to the suspicious level. Each suspicious level can correspond to a distance, and there is a positive correlation between the level of the suspicious level and the magnitude of the distance. In other words, the higher the suspicious level, the greater the descending distance; the lower the suspicious level, the smaller the descending distance. Exemplarily, taking the aforementioned suspicious levels including low level, medium level, and high level as an example, if the determined suspicious level is low level, the sunshade that can descend by 50% of the window height can be used; if the determined suspicious level is medium level, the sunshade that can descend by 70% of the window height can be used; if the determined suspicious level is high level, the sunshade that can descend by 100% of the window height can be used. Of course, the specific descending distance can be flexibly set as needed, and the present application does not limit this.

[0088] It should be noted that in the embodiments of the present application, there may be a situation where the image data simultaneously includes multiple target persons. If none of the multiple target persons match the authorized person information, the suspicious level corresponding to each of them can be determined, and then the sunshade of the vehicle can be controlled to descend by a corresponding distance according to the highest suspicious level among them. In this way, better privacy protection can be achieved.

[0089] It can be understood that in the embodiments of the present application, a privacy protection method based on the vehicle sunshade is provided, which includes: obtaining image data around the vehicle and the authorized person information corresponding to the vehicle; performing target detection and behavior analysis on the image data to determine at least one target person included in the image data and the behavior category corresponding to the target person; matching the target person according to the authorized person information; if the target person does not match the authorized person information, determining the suspicious level of the target person according to the behavior category corresponding to the target person, where the suspicious level is used to represent the suspicious degree of the target person; controlling the sunshade of the vehicle to descend by a corresponding distance according to the suspicious level to protect the privacy of the vehicle, where there is a positive correlation between the level of the suspicious level and the magnitude of the distance. This method can automatically control the vehicle sunshade to achieve privacy protection of the in-vehicle environment, without manual operation, which can improve the intelligence of vehicle control and the privacy of the vehicle, and is beneficial to improving the vehicle use experience.

[0090] Specifically, in some embodiments, the performing target detection and behavior analysis on the image data to determine at least one target person included in the image data and the behavior category corresponding to the target person includes:

[0091] Inputting the image data into a deep convolutional neural network model, and extracting the feature data corresponding to the image data through the deep convolutional neural network model;

[0092] Based on the feature data, at least one of the target persons included in the image data is determined through the deep convolutional neural network model, and the area where the target person is located is marked;

[0093] Based on the feature data and the image data of the area where the target person is located, the behavior category corresponding to the target person is determined through the deep convolutional neural network model.

[0094] In the embodiments of the present application, when performing object detection and behavior recognition on image data, in some embodiments, a deep convolutional neural network model may be used. A deep convolutional neural network (CNN) is a deep learning model specifically used for processing image data. Its core structure includes a convolutional layer, a pooling layer, and a fully connected layer, and it can automatically extract hierarchical features of images. In the embodiments of the present application, the image data may be input into the deep convolutional neural network model, and the feature data corresponding to the image data is extracted through the deep convolutional neural network model. The data format of the feature data may include numerical values, vectors, matrices, or tensors, etc. Then, based on the feature data, at least one target person included in the image data can be determined, and the area where the target person is located is marked. For example, a bounding box may be generated to label the area of the identified target person. In the embodiments of the present application, based on the feature data and the image data of the area where the target person is located, further classification prediction may be performed through the deep convolutional neural network model to determine the behavior category corresponding to the target person.

[0095] Specifically, in the embodiments of the present application, the specific type of the deep convolutional neural network (CNN) used may be flexibly selected according to requirements. For example, the R-CNN series may be selected: such as R-CNN, Fast R-CNN, Faster R-CNN, which can generate candidate regions through a region proposal network (RPN) and then perform classification and regression. Of course, in some other embodiments, other types may also be selected, such as the YOLO model or the SSD model, etc. The present application does not limit this.

[0096] Specifically, in some embodiments, the authorized person information includes reference images of several authorized persons; the matching of the target person according to the authorized person information includes:

[0097] According to the area where the target person is located, the image data is intercepted to obtain the target image corresponding to the target person;

[0098] Determine the similarity between the target image and each of the reference images;

[0099] If the similarity between the target image and any one of the reference images is greater than or equal to a preset threshold, it is determined that the information of the target person and the authorized person matches;

[0100] If the similarity between the target image and any one of the reference images is less than the preset threshold, it is determined that the information of the target person and the authorized person does not match.

[0101] As mentioned above, the information of the authorized person may include an image of the authorized person. In the embodiments of the present application, it is denoted as a reference image. When matching the target person, the matching can be realized based on the reference image. For example, after identifying the area where the target person is located from the image data, the image data can be intercepted to obtain the target image corresponding to the target person. Then, the similarity between the target image and each reference image can be determined. The similarity can be used to characterize the similarity degree between two objects. Generally, the value range of the similarity can be marked with a percentage, specifically between 0-100%. The higher the similarity, the closer the two objects are; on the contrary, the lower the similarity, the less close the two objects are. If the similarity between two objects is 0%, it means that the two are completely irrelevant; if the similarity between two objects is 100%, it means that the two are exactly the same.

[0102] In the embodiments of the present application, for the similarity, a preset threshold (such as 80%) can be set. If the similarity between the target image and any one of the reference images is greater than or equal to the preset threshold, it means that the target person is very likely to be the authorized person corresponding to the reference image. At this time, it can be determined that the information of the target person and the authorized person matches. On the contrary, if the similarity between the target image and all the reference images is less than the preset threshold, it means that the target person is very likely not to be the authorized person. At this time, it can be determined that the information of the target person and the authorized person does not match. Of course, it can be understood that the size of the preset threshold can be flexibly adjusted according to actual needs, and the present application does not limit this.

[0103] Specifically, in some embodiments, the controlling the sunshade of the vehicle to descend a corresponding distance according to the suspicious level includes:

[0104] If it is determined that the suspicious level of the target person is low, medium or high, detect whether there are passengers in the vehicle;

[0105] If there are passengers in the vehicle, send a prompt notification to the passengers; wherein, the prompt notification is used to inform the passengers that the sunshade is about to descend;

[0106] When no termination instruction from the passengers is received within the first time period after the prompt notification is sent, control the sunshade of the vehicle to descend a corresponding distance according to the suspicious level.

[0107] In the embodiments of the present application, when it is determined that the suspicious level of the target person is not the level indicating that the degree of suspicion is 0, for example, when it belongs to any one of low level, medium level or high level, the sunshade of the vehicle can be controlled to descend. However, in some scenarios, the driver and passengers may need to communicate with people outside. If the people outside are determined to be target persons at a certain suspicious level, the direct descent of the sunshade will affect the communication needs of the driver and passengers. To this end, in the embodiments of the present application, when it is determined that the sunshade of the vehicle needs to be controlled to descend currently, it can be further detected whether there are driver and passengers in the vehicle. If not, the sunshade of the vehicle can be directly controlled to descend by a corresponding distance according to the suspicious level, and an alarm notification can be sent to the owner of the vehicle. In some cases, for example, if the suspicious level is high, the vehicle can also be controlled to give an alarm.

[0108] On the contrary, if there are currently driver and passengers in the vehicle, in the embodiments of the present application, a prompt notification can be sent to the driver and passengers to prompt him (or them) that the sunshade is about to descend. The way of the prompt notification can be voice prompt, fixed ring prompt or text prompt, etc. The present application does not limit this. If the driver and passengers do not want the sunshade to descend, they can give feedback to this prompt notification and issue a termination instruction, such as through voice interaction or clicking on the screen of the vehicle, etc. When the termination instruction is received, the descent operation of the sunshade can be stopped. On the contrary, if the driver and passengers do not give feedback to the prompt notification, it means that it can be normally lowered. In the embodiments of the present application, when no termination instruction from the driver and passengers is received within the first time period after the prompt notification is sent, the sunshade of the vehicle can be controlled to descend by a corresponding distance according to the suspicious level.

[0109] It can be understood that the strategy in the embodiments of the present application can intelligently realize the descent control of the sunshade, and can reduce the requirement for the operation complexity of the driver and passengers. When privacy protection is required, the driver and passengers can realize the descent and shielding of the sunshade without operation or feedback, which can improve the practicability.

[0110] Specifically, in some embodiments, the controlling the sunshade of the vehicle to descend by a corresponding distance according to the suspicious level includes:

[0111] If it is determined that the suspicious level of the target person is low level, controlling the sunshade of the vehicle to descend at a first speed by a first distance;

[0112] If it is determined that the suspicious level of the target person is medium level, controlling the sunshade of the vehicle to descend at a second speed by a second distance;

[0113] If it is determined that the suspicious level of the target person is high level, controlling the sunshade of the vehicle to descend at a third speed by a third distance;

[0114] Wherein, the second speed is greater than the first speed and less than the third speed, and the second distance is greater than the first distance and less than the third distance.

[0115] In the embodiments of the present application, when the sunshade curtain is lowered, the speed and distance of the descent can be determined according to the level of suspicion. Specifically, the higher the level of suspicion, the faster the descent speed can be controlled. For example, if the level of suspicion of the target person is low, the first speed can be used to control the sunshade curtain of the vehicle to descend by the first distance; if the level of suspicion of the target person is medium, the second speed can be used to control the sunshade curtain of the vehicle to descend by the second distance, where the second speed is greater than the first speed and the second distance is greater than the first distance. Similarly, if the level of suspicion of the target person is high, the third speed can be used to control the sunshade curtain of the vehicle to descend by the third distance, where the third speed is greater than the second speed and the third distance is greater than the second distance. The specific magnitudes of these speeds and distances are not limited in the present application.

[0116] Referring to Figure 3 , in the embodiments of the present application, a privacy protection device based on a vehicle sunshade curtain is further provided, including:

[0117] An acquisition unit 310, configured to acquire image data around the vehicle and information about authorized personnel corresponding to the vehicle;

[0118] An analysis unit 320, configured to perform target detection and behavior analysis on the image data to determine at least one target person included in the image data and the behavior category corresponding to the target person;

[0119] A matching unit 330, configured to match the target person according to the information about authorized personnel;

[0120] A processing unit 340, configured to, if the target person does not match the information about authorized personnel, determine the level of suspicion of the target person according to the behavior category corresponding to the target person; wherein, the level of suspicion is used to characterize the degree of suspicion of the target person;

[0121] A control unit 350, configured to control the sunshade curtain of the vehicle to descend a corresponding distance according to the level of suspicion to protect the privacy of the vehicle; wherein, there is a positive correlation between the level of suspicion and the magnitude of the distance.

[0122] It can be understood that the content in the above method embodiments is applicable to the device embodiments of the present application. The functions specifically implemented by the device embodiments of the present application are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those of the above method embodiments.

[0123] Referring to Figure 4, embodiments of the present application provide an electronic device, including:

[0124] At least one processor 410;

[0125] At least one memory 420, configured to store at least one program;

[0126] When the at least one program is executed by the at least one processor 410, the at least one processor 410 is caused to implement the above-mentioned privacy protection method based on a vehicle sunshade.

[0127] Similarly, the content in the above method embodiments is applicable to the embodiments of this electronic device. The functions specifically implemented by the embodiments of this electronic device are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those in the above method embodiments.

[0128] Embodiments of the present application further provide a computer-readable storage medium, which stores a program executable by the processor 410. The program executable by the processor 410 is used to execute the above-mentioned privacy protection method based on a vehicle sunshade when executed by the processor 410.

[0129] Similarly, the content in the above method embodiments is applicable to the embodiments of this computer-readable storage medium. The functions specifically implemented by the embodiments of this computer-readable storage medium are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those in the above method embodiments.

[0130] In some alternative embodiments, the functions / operations mentioned in the block diagram may not occur in the order mentioned in the operation diagram. For example, depending on the functions / operations involved, two consecutive blocks shown may actually be executed substantially simultaneously or the blocks can sometimes be executed in the reverse order. In addition, the embodiments presented and described in the flowcharts of the present application are provided by way of example for the purpose of providing a more comprehensive understanding of the technology. The disclosed method is not limited to the operations and logical flows presented herein. Alternative embodiments are contemplated, in which the order of various operations is changed and sub-operations described as part of a larger operation are executed independently.

[0131] In addition, although the present application has been described in the context of functional modules, it should be understood that, unless otherwise stated to the contrary, one or more of the functions and / or features may be integrated in a single physical device and / or software module, or one or more functions and / or features may be implemented in separate physical devices or software modules. It should also be understood that a detailed discussion of the actual implementation of each module is not necessary for understanding the present application. Rather, given the attributes, functions, and internal relationships of the various functional modules in the devices disclosed herein, the actual implementation of the modules will be understood within the ordinary skills of an engineer. Thus, those skilled in the art can implement the present application as set forth in the claims without undue experimentation. It should also be understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present application, which is determined by the full scope of the appended claims and their equivalents.

[0132] If a function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or a part of this 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 for causing a device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present application. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs that can store program codes.

[0133] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a definite sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or in conjunction with these instruction execution systems, apparatuses, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0134] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection (electronic device) having one or more wirings, a portable computer diskette (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable media can even be paper or other suitable media on which a program can be printed, as the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or otherwise processing it as appropriate, and then storing it in a computer memory.

[0135] It should be understood that various parts of the present application can be implemented by hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following techniques well-known in the art can be used: a discrete logic circuit having logic gate circuits for implementing logical functions on data signals, an application-specific integrated circuit having appropriate combinational logic gate circuits, a programmable gate array (PGA), a field-programmable gate array (FPGA), etc.

[0136] In the above description of this specification, the descriptions referring to the terms "one embodiment / example", "another embodiment / example", or "certain embodiments / examples", etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0137] Although the embodiments of the present application have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present application, and the scope of the present application is defined by the claims and their equivalents.

[0138] The above has specifically described the preferred embodiments of the present application, but the present application is not limited to the embodiments. Those skilled in the art can make various equivalent deformations or substitutions without departing from the spirit of the present application, and these equivalent deformations or substitutions are all included within the scope defined by the claims of the present application.

Claims

1. A privacy protection method based on a vehicle sunshade, characterized in that: The method comprises: Acquire image data around the vehicle and authorized personnel information corresponding to the vehicle; Performing target detection and behavior analysis on the image data to determine at least one target person contained in the image data and a behavior category corresponding to the target person; Matching the target person according to the authorized person information; If the target person and the authorized person information do not match, determine the target person's suspicious level according to the behavior category corresponding to the target person; wherein the suspicious level is used to characterize the degree of suspicion of the target person; According to the suspicious level, the sunshade of the vehicle is controlled to be lowered to a corresponding distance so as to protect the privacy of the vehicle; wherein the suspicious level and the distance are positively correlated.

2. A privacy protection method based on a vehicle sunshade according to claim 1, characterized in that: The performing target detection and behavior analysis on the image data to determine at least one target person contained in the image data and a behavior category corresponding to the target person includes: Inputting the image data into a deep convolutional neural network model, and extracting feature data corresponding to the image data through the deep convolutional neural network model; According to the feature data, determining at least one target person contained in the image data through the deep convolutional neural network model, and identifying the area where the target person is located; Based on the feature data and the image data of the area where the target person is located, the behavior category corresponding to the target person is determined by the deep convolutional neural network model.

3. A privacy protection method based on a vehicle sunshade according to claim 2, characterized in that: The authorized person information includes reference images of several authorized persons; matching the target person according to the authorized person information includes: According to the area where the target person is located, the image data is intercepted to obtain a target image corresponding to the target person; Determining the similarity between the target image and each of the reference images; If the similarity between the target image and any of the reference images is greater than or equal to a preset threshold, it is determined that the target person and the authorized person information match; If the similarity between the target image and any of the reference images is less than the preset threshold, it is determined that the target person information does not match the authorized person information.

4. The privacy protection method based on vehicle sunshade according to claim 1 is characterized in that: Determining the suspicious level of the target person according to the behavior category corresponding to the target person includes: If the behavior category corresponding to the target person is reciprocating pacing behavior, the suspicious level of the target person is determined to be low; If the behavior category corresponding to the target person is staring behavior, determining that the suspicious level of the target person is medium; If the behavior category corresponding to the target person is a security threat behavior, it is determined that the suspicious level of the target person is high.

5. A privacy protection method based on a vehicle sunshade according to claim 4, characterized in that: The step of controlling the sunshade of the vehicle to be lowered by a corresponding distance according to the suspicious level includes: If the target person's suspicious level is determined to be low, medium or high, detecting whether there is a driver or passenger in the vehicle; If the driver or passenger is in the vehicle, a prompt notification is sent to the driver or passenger; wherein the prompt notification is used to inform the driver or passenger that the sunshade is about to be lowered; When no termination instruction is received from the driver or passenger within a first time period after the prompt notification is issued, the sunshade of the vehicle is controlled to be lowered by a corresponding distance according to the suspicious level.

6. A privacy protection method based on a vehicle sunshade according to claim 5, characterized in that: The step of controlling the sunshade of the vehicle to be lowered by a corresponding distance according to the suspicious level further includes: If the driver or passenger does not exist in the vehicle, the sunshade of the vehicle is controlled to be lowered by a corresponding distance according to the suspicious level, and a warning notification is sent to the owner of the vehicle.

7. The privacy protection method based on vehicle sunshade according to claim 4 is characterized in that: The step of controlling the sunshade of the vehicle to be lowered by a corresponding distance according to the suspicious level includes: If it is determined that the suspicious level of the target person is low, controlling the sunshade of the vehicle to descend a first distance at a first speed; If it is determined that the target person's suspicion level is medium, controlling the sunshade of the vehicle to descend a second distance at a second speed; If it is determined that the suspicious level of the target person is high, controlling the sunshade of the vehicle to descend by a third distance at a third speed; The second speed is greater than the first speed and less than the third speed, and the second distance is greater than the first distance and less than the third distance.

8. A privacy protection device based on a vehicle sunshade, characterized in that: The device comprises: An acquisition unit, used to acquire image data around the vehicle and authorized personnel information corresponding to the vehicle; an analysis unit, configured to perform target detection and behavior analysis on the image data, and determine at least one target person contained in the image data and a behavior category corresponding to the target person; A matching unit, used for matching the target person according to the authorized person information; A processing unit, configured to determine the suspicious level of the target person according to the behavior category corresponding to the target person if the target person information does not match the authorized person information; wherein the suspicious level is used to characterize the degree of suspicion of the target person; A control unit is used to control the distance to which the sunshade of the vehicle is lowered according to the suspicious level, so as to protect the privacy of the vehicle; wherein the level of the suspicious level and the size of the distance are positively correlated.

9. An electronic device, characterized in that: include: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements a privacy protection method based on a vehicle sunshade as described in any one of claims 1-7.

10. A computer-readable storage medium storing a program executable by a processor, characterized in that: The processor-executable program is used to implement a privacy protection method based on a vehicle sunshade as described in any one of claims 1-7 when executed by the processor.

Images