Operation method of data privacy protection system based on block chain

Abstract

The invention discloses a block chain-based data privacy protection system operation method, which comprises a block chain storage node, a picture analysis module and a pedestrian privacy data protection module, and is characterized in that the block chain storage node is used for collecting and storing vehicle monitoring picture information; the picture analysis module is used for analyzing the collected and stored vehicle monitoring picture, and the pedestrian privacy protection module is used for collecting protection measures for pedestrian privacy data in the monitoring picture according to an analysis result of the picture analysis module to avoid pedestrian privacy leakage. The block chain storage node and the pedestrian privacy data protection module are both in network connection with the picture analysis module, the block chain storage node comprises a monitoring picture collection module and a picture cutting setting module, and the monitoring picture collection module is used for calling picture data monitored and collected during vehicle parking. The method has the characteristics of low leakage risk and good use experience.

Description

Technical Field

[0001] The present invention relates to the field of data protection technology, and specifically to an operating method of a blockchain-based data privacy protection system. Background Art

[0002] In recent years, with the rapid development of smart electric vehicles, the ownership, possession, and use rights of vehicle data have undergone complex changes. The data generated by smart electric vehicles is complex and diverse, including vehicle data, driving environment data, user driving behavior data, the operating status of automated driving systems, and related privacy data. Some automakers have introduced a "Sentinel" mode, which monitors the surrounding environment at all times while parked and provides this data to the owner. This significantly reduces the risk of vandalism while parked, thus protecting vehicle safety. This has been widely praised. However, it has also been controversial because its indiscriminate collection of surrounding environmental information poses a risk of leaking information about passersby's portraits, behavior, and whereabouts. This has led to restrictions on smart vehicles in many areas, prohibiting parking. To comply with relevant regulations, automakers are unable to further develop features such as "Sentinel" mode, which allows for remote, real-time monitoring of the vehicle's environment. This has hindered the development of smart electric vehicles. Therefore, it is imperative to design blockchain-based data privacy protection systems and methods that minimize the risk of leakage and provide a good user experience. Summary of the Invention

[0003] The purpose of the present invention is to provide a blockchain-based data privacy protection system and operation method to solve the problems raised in the above background technology.

[0004] In order to solve the above technical problems, the present invention provides the following technical solutions: a data privacy protection system and method based on blockchain, including a blockchain storage node, an image analysis module and a pedestrian privacy data protection module. The blockchain storage node is used to collect and store vehicle monitoring image information, the image analysis module is used to analyze the collected and stored vehicle monitoring images, and the pedestrian privacy protection module is used to collect protection measures for pedestrian privacy data in the monitoring images based on the analysis results of the image analysis module to avoid pedestrian privacy leakage. The blockchain storage node and the pedestrian privacy data protection module are both connected to the image analysis module network.

[0005] According to the above technical solution, the blockchain storage node includes a monitoring screen acquisition module and a screen cropping setting module. The monitoring screen acquisition module is used to retrieve the screen data collected during the vehicle parking period, and the screen cropping setting module is used to crop the screen edges of the collected monitoring screen.

[0006] According to the above technical solution, the image analysis module includes a dynamic portrait recognition and tracking module, a pedestrian facial position prediction module and a pedestrian image activity index analysis module. The dynamic portrait recognition and tracking module is used to continuously identify and track pedestrian portraits in the monitoring image. The pedestrian facial position prediction module is used to predict the changing trend of the pedestrian facial position based on the recognition and tracking data of the dynamic portrait recognition and tracking module. The pedestrian image activity index analysis module is used to analyze the activity of the current pedestrian based on the monitored pedestrian image.

[0007] According to the above technical solution, the dynamic portrait recognition and tracking module further includes a portrait screen ratio recognition submodule and a facial recognition submodule. The portrait screen ratio recognition submodule is used to dynamically output the portrait screen ratio according to the ratio of the pedestrian screen selected by the tracking frame to the monitoring screen, and obtain the change in the range of "coding" of the pedestrian based on the output portrait screen ratio. The facial recognition submodule is used to identify the pedestrian's facial area in the pedestrian portrait screen.

[0008] According to the above technical solution, the pedestrian screen activity index analysis module further includes a pedestrian torso fitting submodule, a category judgment submodule and an output submodule. The pedestrian torso fitting submodule is used to fit the pedestrian torso contour and obtain the ratio of the pedestrian head contour length value to the torso contour length value. The category judgment submodule is used to judge the pedestrian category. The output submodule is used to output the pedestrian activity index according to the pedestrian category.

[0009] According to the above technical solution, the pedestrian privacy data protection module includes a screen image processing module, an abnormal behavior judgment module and a privacy protection module. The screen image processing module is used to code the pedestrian's face according to the screen analysis results. The abnormal behavior judgment module is used to judge the pedestrian's abnormal behavior based on the pedestrian's face prediction results and real-time dynamic tracking. The privacy protection module is used to strengthen the privacy protection processing of the pedestrian image when it is judged that the pedestrian has abnormal behavior.

[0010] The method for operating a data privacy protection system based on blockchain comprises the following steps: Step S1: obtaining a monitoring image captured during vehicle parking, and cropping the edges of the monitoring image; Step S2: After a pedestrian enters the monitoring screen, the dynamic portrait recognition and tracking module is used to dynamically identify and track the new person and frame them; Step S3: Identify the basic area m of the pedestrian portrait to be coded based on the proportion of the portrait frame to the monitoring screen. Step S4: identifying the pedestrian's facial area in the pedestrian portrait image through the facial recognition submodule and performing real-time dynamic tracking; Step S5: Record the trajectory of the pedestrian's face in the picture and predict the position of the pedestrian's face in the picture; Step S6: The pedestrian image activity index analysis module further analyzes the pedestrian image, determines its activity index, and provides an additional area value n for coding based on the activity index; Step S7: Based on the given image processing reaction period T, the image processing module linearly performs coding processing on a circle with an area of m+n, with the position after period T as the center. The mosaic processing depth of the circle with an area of m in the middle of the circle is greater than the mosaic processing depth of the outer ring with an area of n. Step S8: When the distance between the pedestrian face prediction result and the real-time dynamic tracking position exceeds the preset threshold, the pedestrian behavior is judged to be abnormal, and the privacy protection module is activated to code the entire pedestrian frame area.

[0011] According to the above technical solution, step S6 further includes: Step S61: When a pedestrian enters the edge area of the cropped surveillance image, the pedestrian image is locked, and the image contour is fitted and a contour line is drawn; Step S62: obtaining a ratio b between the length of the pedestrian's head outline and the length of the newcomer's torso outline; Step S63: Based on the judgment criteria of the category judgment submodule, a threshold value B of the ratio between children and adults is preset in advance. When the ratio b>B, the child is judged to be a child, otherwise it is judged to be an adult; Step S64: Outputting a fixed pedestrian activity index Z based on the determined category; Step S65: When the pedestrian activity index Z is larger, the additional area value n for coding is larger.

[0012] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: the present invention, through the setting of cropping the screen, performs identification and coding position processing in advance when the human face does not appear on the monitoring screen, and predicts the pedestrian position and facial dynamic picture in real time within the monitoring screen, analyzes the newcomer's screen activity index, and codes the picture. When the instantaneous change distance exceeds the threshold, the whole body is directly coded, thereby effectively avoiding the problem of mosaic separation caused by processing delays due to complex changes in the external environment and certain delays in image processing when processing privacy data in the prior art, which leads to missed coding when the newcomer just enters the monitoring screen and sudden irregular activities of the behavior in the screen. Therefore, the protection effect of pedestrian privacy data is greatly improved, and at the same time, the problem of limiting the development of the "sentinel" model is solved, thereby promoting social progress. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings: Figure 1 It is a schematic diagram of the system module composition of the present invention. DETAILED DESCRIPTION

[0014] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0015] See also Figure 1 The present invention provides a technical solution: a data privacy protection system and method based on blockchain, including a blockchain storage node, a picture analysis module and a pedestrian privacy data protection module. The blockchain storage node is used to collect and store vehicle monitoring picture information, the picture analysis module is used to analyze the collected and stored vehicle monitoring pictures, and the pedestrian privacy protection module is used to collect protection measures for pedestrian privacy data in the monitoring pictures according to the analysis results of the picture analysis module to avoid pedestrian privacy leakage. The blockchain storage node and the pedestrian privacy data protection module are both connected to the picture analysis module network.

[0016] The blockchain storage node includes a monitoring screen acquisition module and a screen cropping setting module. The monitoring screen acquisition module is used to retrieve the screen data collected during the vehicle parking period, and the screen cropping setting module is used to crop the edges of the collected monitoring screen.

[0017] The image analysis module includes a dynamic portrait recognition and tracking module, a pedestrian facial position prediction module and a pedestrian image activity index analysis module. The dynamic portrait recognition and tracking module is used to continuously identify and track pedestrian portraits in the monitoring image. The pedestrian facial position prediction module is used to predict the changing trend of the pedestrian facial position based on the recognition and tracking data of the dynamic portrait recognition and tracking module. The pedestrian image activity index analysis module is used to analyze the current pedestrian activity based on the monitored pedestrian image.

[0018] The dynamic portrait recognition and tracking module further includes a portrait screen ratio recognition submodule and a facial recognition submodule. The portrait screen ratio recognition submodule is used to dynamically output the portrait screen ratio according to the ratio of the pedestrian screen selected by the tracking frame to the monitoring screen, and obtain the change in the range of "coding" of the pedestrian based on the output portrait screen ratio. The facial recognition submodule is used to identify the facial area of the pedestrian in the pedestrian portrait screen.

[0019] The pedestrian image activity index analysis module further includes a pedestrian torso fitting submodule, a category judgment submodule and an output submodule. The pedestrian torso fitting submodule is used to fit the pedestrian torso contour and obtain the ratio of the pedestrian head contour length value to the torso contour length value. The category judgment submodule is used to judge the pedestrian category. The output submodule is used to output the pedestrian activity index according to the pedestrian category.

[0020] The pedestrian privacy data protection module includes an image processing module, an abnormal behavior judgment module and a privacy protection module. The image processing module is used to blur the pedestrian's face based on the image analysis results. The abnormal behavior judgment module is used to judge the pedestrian's abnormal behavior based on the pedestrian's facial prediction results and real-time dynamic tracking. The privacy protection module is used to strengthen the privacy protection processing of the pedestrian image when it is judged that the pedestrian has abnormal behavior.

[0021] The method for operating a data privacy protection system based on blockchain comprises the following steps: Step S1: Obtaining a surveillance image captured during vehicle parking and cropping the edges of the surveillance image. By cropping the image in advance, the privacy of pedestrians is prevented from being leaked due to system processing delays when pedestrians directly enter the surveillance image, thereby achieving the effect of image preprocessing. Step S2: When a pedestrian enters the surveillance image, the dynamic portrait recognition and tracking module is used to dynamically identify and track the new person and frame the image. The size ratio of the framed portrait can then reflect the approximate distance between the pedestrian and the vehicle, thereby providing a more accurate basic coding range during image processing. Step S3: Identify the basic area m of the pedestrian portrait to be coded based on the proportion of the portrait frame to the monitoring screen. Step S4: identifying the pedestrian's facial area in the pedestrian portrait image through the facial recognition submodule and performing real-time dynamic tracking; Step S5: Record the trajectory of the pedestrian's face in the image and predict the position of the pedestrian's face in the image. The prediction method mainly uses the direction of the trajectory, the speed of the movement, and the speed of the change in the size ratio of the portrait frame to obtain an accurate prediction value. Step S6: The pedestrian image activity index analysis module further analyzes the pedestrian image, determines its activity index, and assigns an additional area value n for coding based on the activity index. By pre-cropping the image, the pedestrian activity index can also be analyzed in advance before the pedestrian enters the cropped image. The activity index is mainly related to age. Under the same external factors, children are more likely to perform unexpected behaviors such as "jumping," "squatting," and "running" when walking. By further adding a preventive additional coding range to the basic coding range and dynamically adjusting the additional coding range according to different target types, high security and high data privacy protection are achieved to prevent leakage, as well as malicious dissemination and profit-seeking. At the same time, the impact of excessive coding on the visual perception of the monitoring image is reduced, achieving a balanced effect of security and image quality. Step S7: Based on the given image processing reaction period T, the image processing module linearly performs coding processing on a circle with an area of m+n, with the position after period T as the center. The mosaic processing depth of the circle with an area of m in the middle of the circle is greater than the mosaic processing depth of the outer ring with an area of n. Step S8: When the distance between the pedestrian face prediction result and the real-time dynamic tracking position exceeds the preset threshold, the pedestrian behavior is judged to be abnormal, and the privacy protection module is activated to code the entire pedestrian frame area.

[0022] Step S6 further comprises: Step S61: When a pedestrian enters the edge area of the cropped surveillance image, the pedestrian image is locked, and the image contour is fitted and a contour line is drawn; Step S62: obtaining a ratio b between the length of the pedestrian's head outline and the length of the newcomer's torso outline; Step S63: Based on the judgment criteria of the category judgment submodule, a threshold value B of the ratio between children and adults is preset in advance. When the ratio b>B, the child is judged to be a child, otherwise it is judged to be an adult; Step S64: Outputting a fixed pedestrian activity index Z based on the determined category; Step S65: The larger the pedestrian screen activity index Z, the larger the additional coding range area value n is given; by setting the cropped screen, when the face does not appear on the monitoring screen, the identification and coding position processing are done in advance, and in the monitoring screen, the pedestrian position and facial dynamic picture are predicted in real time, the newcomer's screen activity index is analyzed, and the picture is coded. When the instantaneous change distance exceeds the threshold, the whole body is directly coded, thereby effectively avoiding the problem of mosaic separation caused by the complex changes in the external environment and a certain delay in picture processing when the picture data privacy processing of the existing technology is incomplete due to the complex changes in the external environment and a certain delay in picture processing, resulting in the omission of coding when the newcomer just enters the monitoring screen and the processing delay caused by the sudden irregular activity of the behavior in the picture. This greatly improves the protection effect of pedestrian privacy data, and at the same time solves the problem of limiting the development of the "sentinel" model, promoting social progress.

[0023] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0024] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art will be able to modify the technical solutions described in the aforementioned embodiments or substitute equivalents for some of the technical features. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. A method for operating a data privacy protection system based on blockchain, comprising the following steps: Step S1: obtaining a monitoring image captured during vehicle parking, and cropping the edges of the monitoring image; Step S2: After a pedestrian enters the monitoring screen, the dynamic portrait recognition and tracking module is used to dynamically identify and track the new person and frame them; Step S3: Identify the basic area m of the pedestrian portrait to be coded based on the proportion of the portrait frame to the monitoring screen. Step S4: identifying the pedestrian's facial area in the pedestrian portrait image through the facial recognition submodule and performing real-time dynamic tracking; Step S5: Record the trajectory of the pedestrian's face in the picture and predict the position of the pedestrian's face in the picture; Step S6: The pedestrian image activity index analysis module further analyzes the pedestrian image, determines its activity index, and provides an additional area value n for coding based on the activity index; Step S7: Based on the given image processing reaction period T, the image processing module linearly performs coding processing on a circle with an area of m+n, with the position after period T as the center. The mosaic processing depth of the circle with an area of m in the middle of the circle is greater than the mosaic processing depth of the outer ring with an area of n. Step S8: When the distance between the pedestrian face prediction result and the real-time dynamic tracking position exceeds the preset threshold, the pedestrian behavior is judged to be abnormal, and the privacy protection module is activated to code the entire pedestrian frame area.

2. The method for operating a blockchain-based data privacy protection system according to claim 1, characterized in that: The step S6 further comprises: Step S61: When a pedestrian enters the edge area of the cropped surveillance image, the pedestrian image is locked, and the image contour is fitted and a contour line is drawn; Step S62: obtaining a ratio b between the length of the pedestrian's head outline and the length of the newcomer's torso outline; Step S63: Based on the judgment criteria of the category judgment submodule, a threshold value B of the ratio between children and adults is preset in advance. When the ratio b>B, the child is judged to be a child, otherwise it is judged to be an adult; Step S64: Outputting a fixed pedestrian activity index Z based on the determined category; Step S65: When the pedestrian activity index Z is larger, the additional area value n for coding is larger.

Images