CN116842576B - Vehicle desensitization processing method and system based on pedestrian private information - Google Patents
Vehicle desensitization processing method and system based on pedestrian private information Download PDFInfo
- Publication number
- CN116842576B CN116842576B CN202311090635.0A CN202311090635A CN116842576B CN 116842576 B CN116842576 B CN 116842576B CN 202311090635 A CN202311090635 A CN 202311090635A CN 116842576 B CN116842576 B CN 116842576B
- Authority
- CN
- China
- Prior art keywords
- information
- vehicle
- desensitization
- face
- pedestrian
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000586 desensitisation Methods 0.000 title claims abstract description 143
- 238000003672 processing method Methods 0.000 title claims abstract description 19
- 238000000034 method Methods 0.000 claims abstract description 109
- 238000012545 processing Methods 0.000 claims abstract description 21
- 238000007781 pre-processing Methods 0.000 claims description 18
- 238000004891 communication Methods 0.000 claims description 10
- 230000003044 adaptive effect Effects 0.000 abstract description 2
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/62—Protecting access to data via a platform, e.g. using keys or access control rules
- G06F21/6218—Protecting access to data via a platform, e.g. using keys or access control rules to a system of files or objects, e.g. local or distributed file system or database
- G06F21/6245—Protecting personal data, e.g. for financial or medical purposes
- G06F21/6254—Protecting personal data, e.g. for financial or medical purposes by anonymising data, e.g. decorrelating personal data from the owner's identification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/625—License plates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
Abstract
The application relates to the field of internet of vehicles data security, and discloses a vehicle desensitization processing method and system based on pedestrian private information. Three desensitization processes are set, wherein the first desensitization process carries out desensitization treatment on all the sensitive information, the second desensitization process needs to meet the area occupation ratio condition when carrying out desensitization treatment on the face information, and the third desensitization process needs to meet the area occupation ratio and the face similarity condition when carrying out desensitization treatment on the face information. And the distance relation between the current position of the user and the set geographical range is used for automatically selecting the adaptive desensitization process, so that the occupancy rate of the desensitization process to system resources is reduced, and the flexibility of the desensitization process selection is improved. And combining video viewing authority in the desensitization process, so that missing information is avoided. The vehicle desensitization processing system based on pedestrian private information is used for realizing the vehicle desensitization processing method.
Description
Technical Field
The application relates to the field of internet of vehicles data security, in particular to a vehicle desensitization processing method and system based on pedestrian private information.
Background
In the automotive field, in order to ensure the safety compliance of data outside the automobile and prevent the leakage of private data of pedestrians, the desensitization processing of private information of pedestrians in the video outside the automobile collected by an automobile end needs to be realized, and the post-processing of the desensitized video data is performed.
The current industry has no mature pedestrian private information desensitization scheme, and the vehicle end hardware resources are tense and the calculation force is limited, and in the process of desensitizing the pedestrian private information by the vehicle, the following problems mainly exist:
1. the current scheme of desensitizing private information of pedestrians is to identify all the sensitive information in a fuzzy way, identify the sensitive information, desensitize the sensitive information, establish a relevant model in the desensitizing process, and carry out the processes of tracing, matting out, replacing, coding and the like on the sensitive information, wherein the desensitizing way occupies more system resources.
2. Under different scenes, the desensitization scheme is a desensitization mode, the mode is single, and flexible switching cannot be realized, so that higher system resources are continuously occupied.
3. In the desensitization process, if authorized personnel need to know the picture information, the desensitization method of all the information can lead to missing picture identification information, and part of information can not be acquired.
Therefore, a desensitization processing method based on private information of pedestrians is needed, system resources occupied by a desensitization process can be reduced, video viewing authority can be combined in the desensitization process, and desensitization modes are enriched so as to flexibly adapt to different scenes.
Disclosure of Invention
In order to solve the technical problems, the application provides a vehicle desensitization processing method and system based on pedestrian private information, which can reduce the occupancy rate of a desensitization process to system resources on the premise of meeting safety regulations.
The application provides a vehicle desensitization processing method based on pedestrian private information, which comprises the following steps:
step S1: acquiring a designated geographical range input by a vehicle owner;
step S2: the vehicle initiates a query whether to initiate a first desensitization process:
if the first desensitization process is selected to be started, controlling the vehicle to use the first desensitization process to desensitize the private information of the pedestrians in the video shot by the camera;
if the first desensitization process is not started, executing a step S3;
step S3: determining whether the current location of the vehicle is within the specified geographic range:
if the current position of the vehicle is not in the appointed geographic range, executing a step S4;
if the current position of the vehicle is within the specified geographic range, executing a step S5;
step S4: a second desensitization process is started, and the vehicle is controlled to use the second desensitization process to desensitize private information of pedestrians in video shot by the camera;
step S5: and starting a third desensitization process, and controlling the vehicle to use the third desensitization process to desensitize the private information of the pedestrian in the video shot by the camera.
Further, in step S2, the controlling the vehicle to use the first desensitization process to desensitize the private information of the pedestrian in the video shot by the camera specifically includes:
step S21: acquiring data to be desensitized, acquiring video data outside a vehicle by using a vehicle-end camera, and taking the video data outside the vehicle as the data to be desensitized;
step S22: preprocessing the data to be desensitized, and unifying the frame rate, the size and the resolution of the data to be desensitized through the preprocessing process of the data to be desensitized to obtain preprocessed data;
step S23: pedestrian private information identification, namely identifying the pedestrian private information from the preprocessed data, wherein the pedestrian private information comprises face information, structural data and license plate information;
step S24: and desensitizing the identified private information of the pedestrians.
Further, in step 4, controlling the vehicle to use the second desensitization process to desensitize the private information of the pedestrian in the video shot by the camera, specifically including:
step S41: acquiring data to be desensitized, acquiring video data outside a vehicle by using a vehicle-end camera, and taking the video data outside the vehicle as the data to be desensitized;
step S42: preprocessing the data to be desensitized, and unifying the frame rate, the size and the resolution of the data to be desensitized through the preprocessing process of the data to be desensitized to obtain preprocessed data;
step S43: pedestrian private information identification, namely identifying the pedestrian private information from the preprocessed data, wherein the pedestrian private information comprises face information and license plate information;
step S44: the desensitization processing is carried out on the identified private information of the pedestrians, and the method specifically comprises the following steps:
calculating the area ratio of each face in each frame of video picture according to the face information, and judging whether to desensitize the face information according to the area ratio;
and directly desensitizing the license plate information.
Further, calculating the area ratio of each face in each frame of video picture, and judging whether to desensitize the face information according to the area ratio, specifically including:
the area ratio N of each face in each frame of video picture i-m The calculation formula is as follows:
N i-m =S face /S Picture frame (equation 1)
Wherein m is the m-th frame of the video picture, i is the i-th face in the m-th frame of the video picture, N i-m S is the area ratio of the ith face in the mth frame of video picture Face S is the area of the ith face in the mth frame of video picture Picture frame The area of the m-th frame video picture;
by the area ratio N i-m Comparing with a preset area ratio N:
if N i-m N, desensitizing the face information;
if N i-m And if N is less than or equal to N, not processing the face information.
Further, in step 5, the controlling the vehicle to use the third desensitization process to desensitize the private information of the pedestrian in the video shot by the camera specifically includes:
step S51: acquiring data to be desensitized, acquiring video data outside a vehicle by using a vehicle-end camera, and taking the video data outside the vehicle as the data to be desensitized;
step S52: preprocessing the data to be desensitized, and unifying the frame rate, the size and the resolution of the data to be desensitized through the preprocessing process of the data to be desensitized to obtain preprocessed data;
step S53: the pedestrian private information is identified, and the pedestrian private information is identified from the preprocessed data, wherein the pedestrian private information is face information and license plate information;
step S54: desensitizing the identified private information of the pedestrians, which specifically comprises the following steps:
calculating the area ratio of each face in each frame of video picture according to the face information, and judging whether to desensitize the face information according to the area ratio;
if the area ratio is larger than a preset area ratio, extracting the appointed information with video viewing authority in the appointed geographic range, calculating the similarity between each face and the appointed information with video viewing authority in the appointed geographic range, and judging whether to desensitize the face information according to the similarity;
and directly desensitizing the license plate information.
Further, in step S54, if the area ratio is greater than a preset area ratio, a similarity between the face and the specified information having video viewing authority in the specified geographic range is calculated, and whether to desensitize the face information is determined according to the similarity, which specifically includes:
if the similarity P i-m If the similarity threshold value P is more than the similarity threshold value P, the face information is not subjected to desensitization treatment, and a prompt tone is played;
if the similarity P i-m The similarity threshold value P is less than or equal to the similarity threshold value P, desensitizing the face information;
wherein m is the m-th frame of the video picture, and i is the i-th face in the m-th frame of the video picture.
Further, when the similarity P i-m When the similarity threshold value P is more than the similarity threshold value P, playing a prompt tone, wherein the prompt tone comprises name information in information matched with the appointed information with video viewing authority in the appointed geographic range;
further comprises: if P i-m And when more than P and i is more than or equal to 2, the prompt tone does not comprise the title information.
Further, the desensitizing treatment includes: areas to be desensitized are filled in with grey.
Further, the vehicle desensitization processing system based on the pedestrian privacy information comprises: a memory, a communication bus, and a processor;
the memory is used for storing video data and storing executable programs;
the communication bus realizes connection communication between the processor and the memory;
the processor, when executing the executable program, performs the steps corresponding to the vehicle desensitization processing method according to any one of claims 1 to 8.
The embodiment of the application has the following technical effects:
1. the application sets three desensitization processes, wherein the first desensitization process carries out desensitization treatment on all sensitive information, and the second desensitization process and the third desensitization process only carry out desensitization treatment on part of sensitive information. And automatically selecting an adaptive desensitization process through the distance relation between the current position of the user and the set geographic position. When the second desensitization process or the third desensitization process is selected, only partial sensitive information is desensitized, so that the aim of reducing the occupancy rate of the desensitization process to system resources is fulfilled.
2. In the running process of the vehicle, the position of the vehicle is monitored in real time, and whether the current position of the vehicle is in the appointed geographical range input by the vehicle owner is judged, so that different desensitization processes are selected, and the flexibility of the desensitization process selection is improved. Compared with the first desensitization process, the second desensitization process has lower system resource occupancy rate, and compared with the second desensitization process, the third desensitization process has lower system resource occupancy rate, when the distance between the position of the vehicle and the appointed geographic range is changed, the selected desensitization process is changed, and the condition that the desensitization process continuously occupies higher system resources is avoided.
3. The vehicle owner sets the appointed information of the video viewing authority in each appointed geographical range in advance, in the third desensitization process, the similarity between the face information in the video picture and the appointed information of the video viewing authority in the appointed geographical range is judged, and when the similarity meets the condition, the face information in the video picture is not subjected to desensitization treatment, and a corresponding prompt is made. The desensitized video information is sent to the appointed geographic position, and the personnel with corresponding rights can know the required picture information.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are needed in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the present application, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a vehicle desensitization processing method based on pedestrian private information provided by an embodiment of the application;
FIG. 2 is a flow chart of a second desensitization process in an embodiment of the application;
figure 3 is a flow chart of a third desensitization process in an embodiment of the application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be clearly and completely described below. It will be apparent that the described embodiments are only some, but not all, embodiments of the application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the application, are within the scope of the application.
Fig. 1 is a flowchart of a vehicle desensitization processing method based on pedestrian private information, which specifically includes:
step S1: acquiring a designated geographical range input by a vehicle owner; the designated geographic area of the vehicle owner input is typically the important location where the security level is highly desirable.
Step S2: the vehicle initiates a query of whether to start the first desensitization process, namely, the vehicle owner is inquired whether to start the first desensitization process, and whether to start the first desensitization process is judged according to the selection of the vehicle owner:
if the first desensitization process is selected to be started, controlling the vehicle to use the first desensitization process to desensitize private information of pedestrians in video shot by the camera; the desensitization process carries out desensitization treatment on all sensitive information, the desensitization intensity is strongest, and the occupancy rate of the system is highest;
if it is chosen not to start the first desensitization process, step S3 is performed.
Step S3: determining whether the current location of the vehicle is within the specified geographic range: if the current position of the vehicle is not in the appointed geographic range, executing a step S4; and if the current position of the vehicle is within the specified geographic range, executing step S5.
In the running process of the vehicle, the position of the vehicle is monitored in real time, and whether the current position of the vehicle is in the appointed geographical range input by the vehicle owner is judged, so that different desensitization processes are selected, and the flexibility of the desensitization process selection is improved. If the current position of the vehicle is not in the appointed geographic range, a second desensitization process is started; and if the current position of the vehicle is within the specified geographic range, starting a third desensitization process.
Step S4: and a second desensitization process is started, and the vehicle is controlled to use the second desensitization process to desensitize the private information of the pedestrian in the video shot by the camera.
Step S5: and starting a third desensitization process, and controlling the vehicle to use the third desensitization process to desensitize the private information of the pedestrian in the video shot by the camera. Compared with the first desensitization process, the system resource occupancy rate of the second desensitization process is lower; the third desensitization process has a lower occupancy of system resources than the second desensitization process. When the distance between the position of the vehicle and the appointed geographical range is changed, the selected desensitization process is changed, so that the desensitization process is prevented from continuously occupying higher system resources.
In the embodiment of the present application, when executing step S2, the control vehicle uses the first desensitization process to desensitize private information of pedestrians in video shot by the camera, and specifically includes:
step S21: acquiring data to be desensitized, acquiring video data outside the vehicle by using a vehicle-end camera, and taking the video data outside the vehicle as the data to be desensitized;
step S22: preprocessing the data to be desensitized, unifying the frame rate, the size and the resolution of the data to be desensitized through the preprocessing process of the data to be desensitized, and obtaining preprocessed data, so that the subsequent information identification is facilitated;
step S23: pedestrian private information identification, namely identifying pedestrian private information from the preprocessed data, wherein the pedestrian private information comprises face information, structural data and license plate information; the structural data comprises parameters such as video recording acquisition time, acquisition equipment, acquisition places and the like;
step S24: and desensitizing the identified private information of the pedestrians. The method comprises the steps of carrying out desensitization processing on all the private information of the identified pedestrians, including the desensitization processing on face information, structural data and license plate information.
In the desensitization treatment, gray filling is used for the face area, the structural data area and the license plate area which need to be subjected to the desensitization treatment.
The desensitized video can be stored and displayed by the vehicle. When the desensitized video is stored, the desensitized video can be synchronously stored at the vehicle end and the cloud end. Before the desensitization video is displayed, the picture quality of the desensitization video can be improved by means of image enhancement and changing contrast and brightness, and the picture quality of the display is improved. The car owner can also autonomously select whether to play the desensitized video subjected to the desensitization treatment.
In the embodiment of the present application, when step 4 is executed, the vehicle is controlled to use the second desensitization process to desensitize private information of pedestrians in video shot by a camera, and fig. 2 is a flowchart of the second desensitization process in the embodiment of the present application, which specifically includes:
step S41: acquiring data to be desensitized, acquiring video data outside the vehicle by using a vehicle-end camera, and taking the video data outside the vehicle as the data to be desensitized;
step S42: preprocessing the data to be desensitized, unifying the frame rate, the size and the resolution of the data to be desensitized through the preprocessing process of the data to be desensitized, and obtaining preprocessed data, wherein the preprocessed data is convenient for subsequent information identification;
step S43: pedestrian private information identification, namely identifying pedestrian private information from the preprocessed data, wherein the pedestrian private information comprises face information and license plate information;
step S44: the desensitizing treatment of the identified private information of the pedestrians specifically comprises the following steps:
the face information is calculated, the area ratio of each face in each frame of video picture is calculated, and whether the face is desensitized or not is judged according to the area ratio; the second desensitization process needs to meet the area occupation ratio condition when carrying out desensitization processing on the face information, does not carry out desensitization processing on all sensitive information, and reduces the occupation ratio of system resources.
And (5) directly desensitizing the license plate information.
In the embodiment of the application, the area ratio of each face in each frame of video picture is calculated, and whether the face is desensitized or not is judged according to the size of the area ratio, which comprises the following steps:
the occupied area ratio N of each human face in each frame of video picture i-m The calculation formula is as follows:
N i-m =S face /S Picture frame (equation 1)
Wherein m is the m-th frame of the video picture, i is the i-th face in the m-th frame of the video picture, N i-m S is the area ratio of the ith face in the mth frame of video picture Face S is the area of the ith face in the mth frame of video picture Picture frame The area of the m-th frame video picture;
area ratio N i-m and comparing with a preset area ratio N:
if N i-m N, desensitizing the face information;
if N i-m And if N is less than or equal to N, not processing the face information.
The desensitized video can be stored and displayed.
Setting a face area occupation ratio threshold, calculating the occupation ratio of each face in each frame of video picture, and comparing the size of the occupation ratio. The face which cannot be recognized by naked eyes under the current resolution ratio used by the video picture shot by the vehicle-mounted camera can be eliminated through the area ratio, so that the face information which cannot be recognized by naked eyes is not subjected to desensitization treatment, and the operand in the desensitization process is effectively reduced. The method has the advantages that the calculation amount for calculating the area ratio of each face and the comparison area ratio is simpler than the method for desensitizing the face, and the calculation amount is much lower, so that the calculation complexity can be effectively reduced, and the system resource occupancy rate can be reduced.
In the embodiment of the present application, when step S5 is executed, the vehicle is controlled to use the third desensitization process to desensitize private information of pedestrians in video shot by the camera, and fig. 3 is a flowchart of the third desensitization process provided in the embodiment of the present application, which specifically includes:
step S51: acquiring data to be desensitized, acquiring video data outside the vehicle by using a vehicle-end camera, and taking the video data outside the vehicle as the data to be desensitized;
step S52: preprocessing the data to be desensitized, unifying the frame rate, the size and the resolution of the data to be desensitized through the preprocessing process of the video data to be desensitized, and obtaining preprocessed data, so that the subsequent information identification is facilitated;
step S53: the pedestrian private information identification is to identify pedestrian private information from the preprocessed data, wherein the pedestrian private information is face information and license plate information;
step S54: the method comprises the steps of performing desensitization processing on the identified private information of pedestrians, comparing the occupied area ratio of each human face in each frame of video picture, comparing the similarity of the human face information and the human face information in the recorded vehicles, and judging whether the desensitization processing is needed according to the comparison result, wherein the method specifically comprises the following steps:
and calculating the area ratio of each face in each frame of video picture according to the face information, and judging whether to desensitize the face according to the area ratio.
If the area ratio is larger than the preset area ratio, extracting the appointed information with video viewing authority in the appointed geographic range, calculating the similarity between the face and the appointed information with video viewing authority in the appointed geographic range, and judging whether to desensitize the face information according to the similarity.
The third desensitization process needs to meet the area ratio and similarity conditions simultaneously when the face information is desensitized, namely whether the face is desensitized is judged according to the area ratio of the face, and whether the face information is desensitized is judged according to the similarity after the area ratio is met. On the premise of ensuring to meet the safety regulations, the desensitization degree is the lowest, and the occupancy rate of system resources is the lowest. And (5) directly desensitizing the license plate information.
The desensitized video can be stored and displayed.
In the embodiment of the present application, when step S54 is executed, if the area ratio is greater than the preset area ratio, the similarity between the face information and the specified information having the video viewing authority in the specified geographic range is calculated, and whether to desensitize the face information is determined according to the similarity, which specifically includes:
if the similarity P i-m And if the similarity threshold value P is greater than the similarity threshold value P, the face information is not subjected to desensitization processing, and a prompt tone is played, wherein the prompt tone comprises name information in information matched with the appointed information with video viewing authority in the appointed geographic range.
Wherein m is the m-th frame of the video picture, and i is the i-th face in the m-th frame of the video picture.
The vehicle owner sets the appointed information of the video viewing authority in each appointed geographical range in advance, and the appointed information comprises the personnel with the video viewing authorityFace information and title information of the person. Comparing the ith face information in the m-th frame video picture with face information in the appointed information with video viewing authority in the appointed geographic range, and obtaining similarity P i-m When the similarity threshold value P is larger than the similarity threshold value P, the desensitization processing is not carried out on the ith face information in the mth frame of video picture, and meanwhile, a prompt tone is played, wherein the prompt tone comprises name information in information matched with the appointed information with video viewing authority in the appointed geographic range. When the video data after the desensitization of the vehicle is transmitted to the appointed geographic range, the face information of the personnel with the video viewing authority is displayed in the video picture.
Further, if P i-m When the number of the points is more than P and the number of the points is more than or equal to 2, the face information is not subjected to desensitization treatment, the prompt tone is played, but the played prompt tone does not comprise the name information in the information matched with the appointed information with the video viewing authority in the appointed geographic range. In the video picture of a frame, 2 or more face information is matched with face information in appointed information with video viewing authority in an appointed geographic range, and at the moment, the face information meeting the similarity condition is not subjected to desensitization treatment, and the name information in the information matched with the appointed information is not played.
If the similarity P i-m And if the similarity threshold value P is less than or equal to the similarity threshold value P, desensitizing the face information. I.e. the ith face information in the mth frame of video picture is compared with the face information in the appointed information with video viewing authority in the appointed geographical range, the similarity P i-m And the similarity threshold value P is smaller than the similarity threshold value P, so that the face information does not meet the video viewing authority in the appointed geographic range, and the ith face information in the mth frame of video picture needs to be subjected to desensitization processing.
The application also provides a vehicle desensitization processing system based on pedestrian private information, which specifically comprises: a memory, a communication bus, and a processor;
the memory is used for storing video data and storing executable programs;
the communication bus realizes the connection communication between the processor and the memory;
the processor executes the executable program to perform steps corresponding to the vehicle desensitization processing method of any one of the above.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of the present application. As used in this specification, the terms "a," "an," "the," and/or "the" are not intended to be limiting, but rather are to be construed as covering the singular and the plural, unless the context clearly dictates otherwise. The terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method or apparatus comprising such elements.
It should also be noted that the positional or positional relationship indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. are based on the positional or positional relationship shown in the drawings, are merely for convenience of describing the present application and simplifying the description, and do not indicate or imply that the apparatus or element in question must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present application. Unless specifically stated or limited otherwise, the terms "mounted," "connected," and the like are to be construed broadly and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present application will be understood in specific cases by those of ordinary skill in the art.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present application.
Claims (7)
1. A vehicle desensitization processing method based on pedestrian privacy information, characterized in that the method comprises the following steps:
step S1: acquiring a designated geographical range input by a vehicle owner;
step S2: the vehicle initiates a query whether to initiate a first desensitization process:
if the first desensitization process is selected to be started, controlling the vehicle to use the first desensitization process to desensitize the private information of the pedestrians in the video shot by the camera;
if the first desensitization process is not started, executing a step S3;
step S3: determining whether the current location of the vehicle is within a specified geographic range:
if the current position of the vehicle is not in the appointed geographic range, executing a step S4;
if the current position of the vehicle is within the specified geographic range, executing a step S5;
step S4: and starting a second desensitization process, and controlling the vehicle to use the second desensitization process to desensitize the private information of the pedestrian in the video shot by the camera, wherein the specific steps are as follows:
step S41: acquiring data to be desensitized, acquiring video data outside a vehicle by using a vehicle-end camera, and taking the video data outside the vehicle as the data to be desensitized;
step S42: preprocessing the data to be desensitized, and unifying the frame rate, the size and the resolution of the data to be desensitized through the preprocessing process of the data to be desensitized to obtain preprocessed data;
step S43: pedestrian private information identification, namely identifying the pedestrian private information from the preprocessed data, wherein the pedestrian private information comprises face information and license plate information;
step S44: the desensitization processing is carried out on the identified private information of the pedestrians, and the method specifically comprises the following steps:
calculating the area ratio of each face in each frame of video picture according to the face information, and judging whether to desensitize the face information according to the area ratio;
directly desensitizing the license plate information;
step S5: and starting a third desensitization process, and controlling the vehicle to use the third desensitization process to desensitize the private information of the pedestrian in the video shot by the camera, wherein the specific steps are as follows:
step S51: acquiring data to be desensitized, acquiring video data outside a vehicle by using a vehicle-end camera, and taking the video data outside the vehicle as the data to be desensitized;
step S52: preprocessing the data to be desensitized, and unifying the frame rate, the size and the resolution of the data to be desensitized through the preprocessing process of the data to be desensitized to obtain preprocessed data;
step S53: the pedestrian private information is identified, and the pedestrian private information is identified from the preprocessed data, wherein the pedestrian private information is face information and license plate information;
step S54: desensitizing the identified private information of the pedestrians, which specifically comprises the following steps:
calculating the area ratio of each face in each frame of video picture according to the face information, and judging whether to desensitize the face information according to the area ratio;
if the area ratio is larger than a preset area ratio, extracting the appointed information with video viewing authority in the appointed geographic range, calculating the similarity between each face and the appointed information with video viewing authority in the appointed geographic range, and judging whether to desensitize the face information according to the similarity;
and directly desensitizing the license plate information.
2. The pedestrian privacy information-based vehicle desensitization processing method according to claim 1, wherein: in step S2, controlling the vehicle to use the first desensitization process to desensitize the private information of the pedestrian in the video shot by the camera, specifically including:
step S21: acquiring data to be desensitized, acquiring video data outside a vehicle by using a vehicle-end camera, and taking the video data outside the vehicle as the data to be desensitized;
step S22: preprocessing the data to be desensitized, and unifying the frame rate, the size and the resolution of the data to be desensitized through the preprocessing process of the data to be desensitized to obtain preprocessed data;
step S23: pedestrian private information identification, namely identifying the pedestrian private information from the preprocessed data, wherein the pedestrian private information comprises face information, structural data and license plate information;
step S24: and desensitizing the identified private information of the pedestrians.
3. A pedestrian privacy information-based vehicle desensitization processing method according to claim 1, wherein: in step S44, the area ratio of each face in each frame of video frame is calculated, and whether to desensitize the face information is determined according to the area ratio, which specifically includes:
the area ratio N of each face in each frame of video picture i-m The calculation formula is as follows:
N i-m =S face /S Picture frame (equation 1)
Wherein m is the m-th frame of the video picture, i is the i-th face in the m-th frame of the video picture, N i-m S is the area ratio of the ith face in the mth frame of video picture Face S is the area of the ith face in the mth frame of video picture Picture frame The area of the m-th frame video picture;
by the area ratio N i-m Comparing with a preset area ratio N:
if N i-m > N, thenDesensitizing the face information;
if N i-m And if N is less than or equal to N, not processing the face information.
4. The pedestrian privacy information-based vehicle desensitization processing method according to claim 1, wherein: in step S54, if the area ratio is greater than a preset area ratio, calculating the similarity between the face and the specified information having video viewing authority in the specified geographic range, and judging whether to perform desensitization processing on the face information according to the similarity, which specifically includes:
if the similarity P i-m If the similarity threshold value P is more than the similarity threshold value P, the face information is not subjected to desensitization treatment, and a prompt tone is played;
if the similarity P i-m The similarity threshold value P is less than or equal to the similarity threshold value P, desensitizing the face information;
wherein m is the m-th frame of the video picture, and i is the i-th face in the m-th frame of the video picture.
5. The pedestrian privacy information-based vehicle desensitization processing method according to claim 4, wherein: when similarity P i-m When the similarity threshold value P is more than the similarity threshold value P, playing a prompt tone, wherein the prompt tone comprises name information in information matched with the appointed information with video viewing authority in the appointed geographic range;
further comprises: if P i-m And when more than P and i is more than or equal to 2, the prompt tone does not comprise the title information.
6. A pedestrian privacy information-based vehicle desensitization processing method according to any one of claims 1 to 5, wherein:
the desensitization treatment comprises: areas to be desensitized are filled in with grey.
7. A vehicle desensitization processing system based on pedestrian private information is characterized in that:
the vehicle desensitization processing system based on pedestrian privacy information comprises: a memory, a communication bus, and a processor;
the memory is used for storing video data and storing executable programs;
the communication bus realizes connection communication between the processor and the memory;
the processor, when executing the executable program, performs the steps corresponding to the vehicle desensitization processing method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311090635.0A CN116842576B (en) | 2023-08-29 | 2023-08-29 | Vehicle desensitization processing method and system based on pedestrian private information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311090635.0A CN116842576B (en) | 2023-08-29 | 2023-08-29 | Vehicle desensitization processing method and system based on pedestrian private information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116842576A CN116842576A (en) | 2023-10-03 |
| CN116842576B true CN116842576B (en) | 2023-11-28 |
Family
ID=88165471
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311090635.0A Active CN116842576B (en) | 2023-08-29 | 2023-08-29 | Vehicle desensitization processing method and system based on pedestrian private information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116842576B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10586073B1 (en) * | 2014-05-27 | 2020-03-10 | Amazon Technologies, Inc. | Preserving customer data privacy for merchant orders |
| CN113709688A (en) * | 2021-08-24 | 2021-11-26 | 支付宝(杭州)信息技术有限公司 | Data processing method and device applied to vehicle |
| CN113779632A (en) * | 2021-09-14 | 2021-12-10 | 深圳市神州路路通网络科技有限公司 | Vehicle sensitive information protection method, system, equipment and readable storage medium |
| CN115841641A (en) * | 2022-10-29 | 2023-03-24 | 重庆长安汽车股份有限公司 | Desensitization method, system, electronic device and storage medium for vehicle interior video |
| CN116186770A (en) * | 2023-02-14 | 2023-05-30 | 重庆长安汽车股份有限公司 | Image desensitizing method, device, electronic equipment and storage medium |
-
2023
- 2023-08-29 CN CN202311090635.0A patent/CN116842576B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10586073B1 (en) * | 2014-05-27 | 2020-03-10 | Amazon Technologies, Inc. | Preserving customer data privacy for merchant orders |
| CN113709688A (en) * | 2021-08-24 | 2021-11-26 | 支付宝(杭州)信息技术有限公司 | Data processing method and device applied to vehicle |
| CN113779632A (en) * | 2021-09-14 | 2021-12-10 | 深圳市神州路路通网络科技有限公司 | Vehicle sensitive information protection method, system, equipment and readable storage medium |
| CN115841641A (en) * | 2022-10-29 | 2023-03-24 | 重庆长安汽车股份有限公司 | Desensitization method, system, electronic device and storage medium for vehicle interior video |
| CN116186770A (en) * | 2023-02-14 | 2023-05-30 | 重庆长安汽车股份有限公司 | Image desensitizing method, device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116842576A (en) | 2023-10-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11845399B2 (en) | Recording video of an operator and a surrounding visual field | |
| EP1454285B1 (en) | Video monitoring system with object masking | |
| CN111191663B (en) | License plate number recognition method and device, electronic equipment and storage medium | |
| CN112987759A (en) | Image processing method, device and equipment based on automatic driving and storage medium | |
| JP4772115B2 (en) | Method and system for detecting roads at night | |
| JP4410755B2 (en) | Image processing apparatus and monitoring system | |
| CN112016457A (en) | Driver distraction and dangerous driving behavior recognition method, device and storage medium | |
| CN111098863A (en) | Remote driving request method and device for automatic driving vehicle and user terminal | |
| KR20200043391A (en) | Image processing, image processing method and program for image blur correction | |
| DE102018114277A1 (en) | REMOTE-CONTROLLED PARKING AID AUTHENTICATION FOR VEHICLES | |
| CN113619610A (en) | Vehicle driving mode switching method and device, computer equipment and storage medium | |
| CN111717147A (en) | Automatic adjusting system and method for vehicle seat | |
| CN116842576B (en) | Vehicle desensitization processing method and system based on pedestrian private information | |
| CN115935423A (en) | Driving recording method and system with desensitized key privacy information and storage medium | |
| CN112652174B (en) | Parking service control method and system based on face verification | |
| CN117292346A (en) | Vehicle running risk early warning method for driver and vehicle state integrated sensing | |
| CN116524877A (en) | Vehicle-mounted screen brightness adjustment method and device, electronic equipment and storage medium | |
| CN113807119B (en) | Personnel gazing position detection method and device | |
| CN115512337A (en) | Fatigue driving detection method, device, equipment and storage medium | |
| CN111860105A (en) | Driving behavior generation supervision method, device and equipment | |
| CN116071683A (en) | Video processing method and device and terminal | |
| JP2019191859A (en) | Vehicle information presentation device and vehicle information presentation method | |
| CN114312559B (en) | Vehicle driving reminding method, device, equipment and storage medium | |
| CN115346199A (en) | Method and system for predicting getting-off tendency of on-board escaped people | |
| CN116749902A (en) | Control method and device for vehicle-mounted atmosphere regulating equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |