Privacy protection method and device in monitoring high-altitude objects

By detecting and occluding privacy targets in the monitoring images of high-altitude thrown objects, the problem of privacy violations in the prior art is solved, and efficient privacy protection is achieved, suitable for different buildings, reducing costs and complexity.

CN114463264BActive Publication Date: 2024-11-29ZHEJIANG DAHUA TECH CO LTD
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
CN202111624235.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-12-28
Publication Date
2024-11-29
Estimated Expiration
2041-12-28

AI Technical Summary

Technical Problem

The existing high-altitude object throwing monitoring program violates the privacy of high-rise buildings through cameras and lacks effective privacy protection measures.

Method used

By detecting the privacy targets in the high-altitude monitoring image, judging its coordinates and categories, and obstructing the privacy targets that comply with the rules based on preset rules. Use the target tracking algorithm to perform re-checking and management to avoid false detection and misocclusion, and reduce the cost of the problem. 物理辅助设备的依赖。

Benefits of technology

Effectively protect the privacy of residents of high-rise buildings, reduce false inspections and misobstructions, reduce costs, achieve universality and convenience, and is suitable for different buildings and is safe and reliable.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114463264B_ABST
    Figure CN114463264B_ABST
Patent Text Reader

Abstract

The present application discloses a privacy protection method and device in monitoring high-altitude objects. The privacy protection method in monitoring high-altitude objects includes: detecting a privacy target in a monitoring image of high-altitude objects, obtaining the coordinates and category of the privacy target; judging whether the privacy target meets the category rules of the privacy target based on the coordinates of the privacy target; and shielding the privacy target that meets the rules in the monitoring image of high-altitude objects. The present application can protect the privacy of residents of high-rise buildings when using a camera to monitor high-altitude objects.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a privacy protection method and device in monitoring objects thrown from high altitudes. Background Art

[0002] With the development of society and the improvement of living environment, high-rise buildings continue to emerge. While improving the quality of life, they also bring a great hidden danger point - high-altitude throwing. The phenomenon of high-altitude throwing continues despite repeated prohibitions, posing a certain threat to our personal safety and social stability. At present, various solutions are used to solve the problem of high-altitude throwing, but they also bring many privacy-related problems. Most of these solutions use the method of setting up monitoring cameras to monitor high-altitude throwing and other problems, but this solution of using cameras to monitor high-altitude throwing is easy to infringe the privacy of residents in high-rise buildings. Summary of the invention

[0003] The present application provides a privacy protection method and device in monitoring objects dropped from high places, which can protect the privacy of residents of high-rise buildings when using a camera to monitor objects dropped from high places.

[0004] To achieve the above objectives, the present application provides a privacy protection method in high-altitude object dropping monitoring, the method comprising:

[0005] Detect the privacy targets in the high-altitude object monitoring images and obtain the coordinates and categories of the privacy targets;

[0006] Judging whether the privacy target meets the rules of the category of the privacy target based on the coordinates of the privacy target;

[0007] The privacy targets that meet the regulations in the high-altitude object dropping monitoring images are blocked.

[0008] The step of determining whether the privacy target meets the rules of the category of the privacy target based on the coordinates of the privacy target includes:

[0009] Classify the privacy goals that do not meet the rules again to determine the final category of the privacy goals that do not meet the rules;

[0010] When the final category of the non-compliant privacy target belongs to the privacy category, the non-compliant privacy target in the high-altitude object dropping monitoring image is blocked.

[0011] The step of detecting the privacy target in the high-altitude object monitoring image includes:

[0012] The target tracking algorithm is used to re-inspect the privacy targets in the high-altitude object monitoring images.

[0013] Among them, the step of using the target tracking algorithm to perform a supplementary inspection on the privacy target in the high-altitude object monitoring image includes:

[0014] Using the target tracking algorithm to assign an identifier to the detected privacy target, so as to manage the information of the privacy target based on the identifier;

[0015] The step of judging whether the privacy target meets the rule of the category of the privacy target based on the coordinates of the privacy target includes:

[0016] In the case of a rule that has previously confirmed that a privacy goal complies with a category of privacy goals based on identification confirmation, the default privacy goal complies with the rule.

[0017] The step of assigning a label to the detected privacy target using the target tracking algorithm includes:

[0018] When it is confirmed based on the target tracking algorithm that the privacy target is not detected for the first time and the previous category of the privacy target is inconsistent with the current initial category of the privacy target, the previous category of the privacy target is used as the current category of the privacy target.

[0019] The steps of shielding the privacy targets that meet the rules in the high-altitude object dropping monitoring image include:

[0020] Sub-classify the privacy goals that meet the rules to obtain sub-categories of the privacy goals that meet the rules;

[0021] When the subdivision category of the privacy target belongs to the privacy category, the privacy target that meets the rules in the high-altitude object dropping monitoring image is blocked.

[0022] The steps of shielding the privacy targets that meet the rules in the high-altitude object dropping monitoring image include:

[0023] Use different occlusion contents to cover different categories of privacy targets in high-altitude object monitoring images.

[0024] Among them, the step of masking the privacy target that meets the rules in the high-altitude object dropping monitoring image includes:

[0025] The high-altitude object dropping monitoring image after privacy masking is presented on the display interface;

[0026] Among them, the high-altitude object dropping monitoring images stored in the memory are not privacy-blocked.

[0027] To achieve the above objectives, the present application also provides an electronic device, which includes a processor; the processor is used to execute instructions to implement the above method.

[0028] To achieve the above objectives, the present application also provides a computer-readable storage medium, which is used to store instructions / program data, and the instructions / program data can be executed to implement the above method.

[0029] In the privacy protection method for high-altitude object dropping monitoring of the present application, the privacy target in the high-altitude object dropping monitoring image is detected to obtain the coordinates and category of the privacy target in the high-altitude object dropping monitoring image; then, it can be determined whether the privacy target meets the category rules of the privacy target based on the coordinates of the privacy target, and then the privacy target that meets the rules is blocked, so as to filter out the privacy targets that do not meet the rules of size, position, etc., thereby solving the problem of false detection of privacy targets and avoiding occlusion errors caused by false detection; and there is no need for other physical auxiliary equipment such as privacy protection sheets, which can reduce the use of physical auxiliary equipment and unnecessary expenses, and can be applied to different buildings, so as to achieve universality, simple upgrade, convenient and fast use, and safe and reliable. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0031] Figure 1 It is a flowchart of an implementation method of a privacy protection method in high-altitude object dropping monitoring of the present application;

[0032] Figure 2 It is a schematic diagram of the process of privacy target shielding in the first implementation method of the privacy protection method in the high-altitude object throwing monitoring of the present application;

[0033] Figure 3 It is a flowchart of an implementation method of a privacy protection method in high-altitude object dropping monitoring of the present application;

[0034] Figure 4 It is a structural schematic diagram of an embodiment of the electronic device of the present application;

[0035] Figure 5 It is a structural schematic diagram of an implementation method of a computer-readable storage medium of the present application. DETAILED DESCRIPTION

[0036] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without making creative work are within the scope of protection of the present application. In addition, unless otherwise specified (for example, "or in addition" or "or in an alternative"), the term "or" as used herein refers to a non-exclusive "or" (that is, "and / or"). Moreover, the various embodiments described herein are not necessarily mutually exclusive, because some embodiments can be combined with one or more other embodiments to form new embodiments.

[0037] This application provides a privacy protection method for monitoring high-altitude objects. Figure 1 As shown, the privacy protection method in the high-altitude object dropping monitoring of this embodiment includes the following steps. It should be noted that the following step numbers are only used to simplify the description and are not intended to limit the execution order of the steps. The execution order of each step of this embodiment can be changed arbitrarily without violating the technical idea of ​​this application.

[0038] S101: Detect the privacy target in the high-altitude object dropping monitoring image and obtain the coordinates and category of the privacy target.

[0039] The privacy targets in the high-altitude object dropping monitoring image can be detected to obtain the coordinates and categories of the privacy targets in the high-altitude object dropping monitoring image.

[0040] Among them, the privacy target may refer to target areas such as balconies or windows in high-rise buildings from which the situation inside the residents' homes can be viewed.

[0041] This application can detect privacy targets in high-altitude object dropping monitoring images through a multi-target detection (Object Detection, OD) algorithm or a semantic segmentation algorithm, obtain the coordinates of the privacy target, and determine which category the privacy target belongs to, such as balcony or window.

[0042] The coordinates of the privacy target may be the upper left corner coordinates and the lower right corner coordinates of the detection frame of the privacy target, or may be the lower left corner coordinates and the upper right corner coordinates of the detection frame of the privacy target.

[0043] S102: Determine whether the privacy target complies with the rule of the category of the privacy target based on the coordinates of the privacy target.

[0044] After obtaining the coordinates and category of the privacy target based on step S101, it is possible to determine whether the privacy target meets the category rules of the privacy target based on the coordinates of the privacy target, thereby filtering out privacy targets that do not meet the rules of size, position, etc., thereby solving the problem of false detection.

[0045] For example, the privacy target is a balcony or a window. In a high-rise building, balconies or windows generally appear in rows (that is, multiple balconies or multiple windows are in the same row or column), and basically do not appear alone. In other words, it is basically impossible for a balcony or a window to occupy a row or a column alone. Therefore, it can be confirmed that the privacy target that occupies a row and / or a column alone among all the privacy targets of the same category in the high-altitude object throwing monitoring image does not comply with the rules of the privacy target category.

[0046] For another example, the monitoring device stores aspect ratio information of each category of privacy targets in the high-altitude object dropping monitoring image. In this way, in step S102, the aspect ratio of each privacy target can be calculated based on the coordinates of the privacy target, and then it is determined whether the aspect ratio of each privacy target is consistent with the aspect ratio of the category of each privacy target. If not, the privacy target does not meet the rules of the category of the privacy target.

[0047] For another example, the monitoring device stores specific size information such as length and width of each category of privacy targets in the high-altitude object dropping monitoring image. In this way, in step S102, the specific size information such as length and width of each privacy target can be calculated based on the coordinates of the privacy target, and then it is determined whether the specific size information such as length and width of each privacy target is equivalent to the specific size information such as length and width of the category of each privacy target. If not, the privacy target does not meet the rules of the category of the privacy target.

[0048] S103: Masking the privacy targets that meet the rules in the high-altitude object dropping monitoring image.

[0049] After determining whether each privacy target in the high-altitude object dropping monitoring image complies with the rules in step S102, the privacy targets in the high-altitude object dropping monitoring image that comply with the rules can be blocked to filter out privacy targets that do not comply with the rules such as size and position, thereby solving the problem of false detection of privacy targets.

[0050] The Copy operator or the erasure method can be used to block the privacy targets that meet the rules in the high-altitude object monitoring image.

[0051] Specifically, the main function of the Copy operator is to read image data of a certain area size from the image preset by the monitoring device, write it into the privacy target area DstRect, and use the read image data to cover the image data in the privacy target area to achieve the privacy protection effect on the privacy target area DstRect. Figure 2As shown, the copy operator can be used to block the privacy target in the image. In this process, the monitoring device can first obtain the coordinates of the privacy target area DstRect, where (x1, y1) represents the coordinates of the upper left corner of the detection box of the privacy target, and (x2, y2) represents the coordinates of the lower right corner of the detection box of the privacy target. Then, the width W2 (W2 = x2-x1+1) and height H2 (H2 = y2-y1+1) of the privacy target area DstRect are calculated, and the copy original box SrcRect is set to [0, 0, W2-1, H2-1]. The copy operator is called to read the data of the SrcRect box size from the preset image stored in the monitoring device and write it into the privacy target area DstRect, thereby overwriting the data in the privacy target area DstRect box.

[0052] In this embodiment, the monitoring device can only block the privacy targets in the high-altitude object dropping monitoring image displayed on the display interface, and the memory stores the original data that has not been blocked. This can avoid the high-altitude object dropping monitoring image stored in the memory being a privacy-blocked image when the problem of high-altitude object dropping occurs, resulting in the inability to trace the source. Of course, in other embodiments, considering that there may be high confidentiality requirements in some scenarios (for example, some high-rise building residents do not agree to expose their windows and balconies and other privacy targets), privacy blocking on the screen is not enough in these scenarios. Therefore, in this embodiment, especially in the current high-confidentiality situation, the saved unblocked image can be set with access permissions, and only some people (such as public security organs or inspection agencies, etc.) have access authorization, which improves the high security of the saved unblocked images and meets the requirements of high-rise building residents who do not agree to expose their windows and balconies and other privacy targets.

[0053] Furthermore, different types of privacy targets in the high-altitude object dropping monitoring image can be blocked with different blocking contents, so that the monitoring personnel can know the categories of the blocked privacy targets based on the blocking contents, so that the monitoring personnel can obtain more information from the high-altitude object dropping monitoring image with privacy blocking.

[0054] In this embodiment, the privacy target in the high-altitude object dropping monitoring image can be detected to obtain the coordinates and category of the privacy target in the high-altitude object dropping monitoring image; then, based on the coordinates of the privacy target, it can be judged whether the privacy target meets the category rules of the privacy target, and then the privacy target that meets the rules can be blocked, so as to filter out the privacy targets that do not meet the rules such as size and position, thereby solving the problem of false detection of privacy targets and avoiding false detection leading to occlusion errors; and there is no need for other physical auxiliary equipment such as privacy protection sheets, which can reduce the use of physical auxiliary equipment and unnecessary expenses, and can be applied to different buildings, so it can be universal, simple to upgrade, convenient and fast to use, safe and reliable.

[0055] See also Figure 3 , Figure 3 It is a flowchart of another implementation method of the privacy protection method in the high-altitude object dropping monitoring of the present application. The privacy protection method in the high-altitude object dropping monitoring of this implementation method includes the following steps. It should be noted that the following step numbers are only used to simplify the description and are not intended to limit the execution order of the steps. The steps of this implementation method can be arbitrarily changed in execution order without violating the technical ideas of the present application.

[0056] S201: Detect the privacy target in the high-altitude object dropping monitoring image and obtain the coordinates and category of the privacy target.

[0057] S202: Use a target tracking algorithm to perform a supplementary inspection on the privacy target in the high-altitude object monitoring image.

[0058] After the privacy targets in the high-altitude object dropping monitoring image are detected based on step S201, the object tracking (OT) algorithm can be used to perform supplementary inspection on the privacy targets in the high-altitude object dropping monitoring image to solve the problem of missed detection of privacy targets, thereby avoiding the situation where some privacy targets in the high-altitude object dropping monitoring image are not blocked due to missed detection of privacy targets in step S201.

[0059] In step S202, the privacy targets in the high-altitude object dropping monitoring image can be detected again, and the privacy target detection results of step S202 and step S201 can be deduplicated to obtain the coordinates and categories of all privacy targets detected twice in the high-altitude object dropping monitoring image.

[0060] In addition, the privacy target detected in the above step may be assigned an identifier (eg, an ID number) through a target tracking algorithm, so as to manage the information of the privacy target based on the identifier.

[0061] S203: judging whether the privacy target meets the rules of the category of the privacy target based on the coordinates of the privacy target.

[0062] Optionally, in step S203, the output results of the target tracking algorithm in step S202 (such as the identification, coordinates and category of the privacy target) can be processed using a trajectory tracking-based alarm generation library (TBA) algorithm. Specifically, the trajectory tracking-based alarm generation library can use certain rules to make rule judgments on the input target, and the rules may include whether it meets the characteristics of a balcony, window, etc.

[0063] Wherein, when it is confirmed based on the target tracking algorithm that the privacy target is not detected for the first time, and the previous category of the privacy target is inconsistent with the current category of the privacy target, the previous category of the privacy target is used as the current category of the privacy target, and the privacy target is assumed to comply with the rules of the category of the privacy target. Wherein, the current category of the privacy target is the category of the privacy target detected from the current high-altitude object dropping monitoring image in steps S201 and S202. In addition, to facilitate the implementation of the above scheme, during the processing of the first n frames of the high-altitude object dropping monitoring image of the current high-altitude object dropping monitoring image, if it is confirmed that the privacy target complies with the rules of the previous category of the privacy target, the previous category of the privacy target will be recorded in the privacy target information managed based on the privacy target identification, so as to verify the category of the privacy target later.

[0064] Optionally, if it is confirmed based on the target tracking algorithm that the privacy target is not detected for the first time, and the privacy target information based on the identification management of the privacy target confirms that the privacy target has been previously confirmed to comply with the rules of the privacy target category, then in step S203, the privacy target can be assumed to comply with the rules, and there is no need to use the coordinates of the privacy target to determine whether the privacy target complies with the rules of the privacy target category, which can improve the efficiency of the present solution and save privacy masking processing time.

[0065] S204: Classify the privacy goals that do not meet the rules again to determine the final category of the privacy goals that do not meet the rules.

[0066] After the privacy targets are judged based on the rules in step S203, the privacy targets that do not meet the rules can be classified again to determine the final categories of the privacy targets that do not meet the rules, so as to correct the categories of the privacy targets that were incorrectly determined in steps S201 and S202.

[0067] In order to improve the accuracy of target classification, the trained object classification (OC) algorithm can be used to classify privacy targets that do not meet the rules.

[0068] In addition, the trained target classification algorithm can be used to sub-classify the privacy targets that meet the rules to determine the sub-categories of the privacy targets that meet the rules. In this way, the categories of the privacy targets can be accurately classified and judged, and the sub-categories of the privacy targets can be used to accurately judge whether the privacy targets need to be blocked. For example, the window targets that meet the rules can be sub-classified to determine which sub-category of the window targets is a large window, a medium window, or a small window.

[0069] S205: Blocking the privacy target in the high-altitude object dropping monitoring image.

[0070] Based on the above steps, the screened privacy targets in the high-altitude object dropping monitoring image can be blocked.

[0071] The screened privacy targets may include privacy targets that comply with the rules. Preferably, the screened privacy targets may include privacy targets that comply with the rules and whose subdivision categories belong to the privacy category, so that the privacy targets whose subdivision categories do not belong to the privacy category can be prevented from being blocked, for example, when the privacy category does not include small windows, the small windows in the high-altitude object dropping monitoring image can be prevented from being blocked.

[0072] In addition, the screened privacy targets may also include privacy targets that do not conform to the rules but whose final categories belong to the privacy category, so as to avoid the situation where the privacy targets whose categories are wrongly detected are missed and blocked.

[0073] In this embodiment, the installed camera device collects image data that can cover the scene area, and multiple intelligent algorithms are used to judge and process the collected image data to obtain the final required and more accurate regional coordinates, category, ID number, etc. of the privacy target, and then the Copy operator is used to process the image of the corresponding area to achieve the purpose of privacy protection. In this process, OD, OT, TBA, OC and other intelligent algorithms and Copy operators are used to solve the privacy problems exposed in the process of high-altitude throwing monitoring, which has strong versatility and simple upgrade.

[0074] See also Figure 4 , Figure 4 The electronic device 20 of the present application includes a processor 22, which is used to execute instructions to implement the method of any of the above embodiments of the present application and any non-conflicting combination thereof.

[0075] The electronic device 20 may be a camera device, a server or other device, which is not limited here.

[0076] The processor 22 may also be referred to as a CPU (Central Processing Unit). The processor 22 may be an integrated circuit chip having signal processing capabilities. The processor 22 may also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), a graphics processing unit (GPU), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. A general-purpose processor may be a microprocessor, or the processor 22 may be any conventional processor, etc.

[0077] The electronic device 20 may further include a memory 21 for storing instructions and data required for the processor 22 to run.

[0078] See also Figure 5 , Figure 5 It is a schematic diagram of the structure of the computer-readable storage medium in the implementation mode of the present application. The computer-readable storage medium 30 of the embodiment of the present application stores instructions / program data 31, and when the instructions / program data 31 are executed, the method provided by any embodiment of the above-mentioned method of the present application and any non-conflicting combination is implemented. Among them, the instructions / program data 31 can form a program file and be stored in the above-mentioned storage medium 30 in the form of a software product, so that a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor (processor) executes all or part of the steps of each implementation method of the present application. The aforementioned storage medium 30 includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a disk or an optical disk, or a computer, a server, a mobile phone, a tablet and other devices.

[0079] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0080] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0081] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0082] The above are only implementation methods of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A privacy protection method in monitoring high-altitude objects, characterized in that: The method comprises: Detecting a privacy target in a high-altitude object dropping monitoring image, and obtaining the coordinates and category of the privacy target; Determining whether the privacy target meets the rule of the category of the privacy target based on the coordinates of the privacy target; Blocking the privacy targets that meet the rules in the high-altitude object dropping monitoring image; The step of judging whether the privacy target meets the rule of the category of the privacy target based on the coordinates of the privacy target includes: Classifying the privacy goals that do not meet the rules again to determine the final category of the privacy goals that do not meet the rules; When the final category of the non-compliant privacy target belongs to the privacy category, masking the non-compliant privacy target in the high-altitude object dropping monitoring image; The step of shielding the privacy target that complies with the rules in the high-altitude object dropping monitoring image includes: Calculate the width and height of the privacy target area; Call the copy operator to read data of the size of the copy original frame and write it into the privacy target area to cover the privacy target area. The width of the copy original frame is equal to the width of the privacy target area, and the height of the copy original frame is equal to the height of the privacy target area.

2. The method according to claim 1, characterized in that The step of detecting the privacy target in the high-altitude object monitoring image includes: The target tracking algorithm is used to re-inspect the privacy target in the high-altitude object dropping monitoring image.

3. The method according to claim 2, characterized in that The step of using the target tracking algorithm to perform a supplementary inspection on the privacy target in the high-altitude object dropping monitoring image includes: Assigning an identifier to the detected privacy target using the target tracking algorithm, so as to manage the information of the privacy target based on the identifier; The step of judging whether the privacy target meets the rule of the category of the privacy target based on the coordinates of the privacy target comprises: In the case where it is confirmed based on the identification that the privacy target has been previously confirmed to comply with the rule of the category of the privacy target, it is assumed that the privacy target complies with the rule.

4. The method according to claim 3, characterized in that The step of assigning an identification to the detected privacy target by using the target tracking algorithm includes: When it is confirmed based on the target tracking algorithm that the privacy target is not detected for the first time and the previous category of the privacy target is inconsistent with the current initial category of the privacy target, the previous category of the privacy target is used as the current category of the privacy target.

5. The method according to claim 1, characterized in that The step of shielding the privacy target that complies with the rules in the high-altitude object dropping monitoring image includes: Sub-classifying the privacy objectives that meet the rules to obtain sub-categories of the privacy objectives that meet the rules; When the subdivision category of the privacy target belongs to the privacy category, the privacy target that meets the rules in the high-altitude object dropping monitoring image is blocked.

6. The method according to claim 1, characterized in that The step of shielding the privacy target that complies with the rules in the high-altitude object dropping monitoring image includes: Different categories of privacy targets in the high-altitude object monitoring image are masked with different masking contents.

7. The method according to claim 1, characterized in that The step of shielding the privacy target that complies with the rules in the high-altitude object dropping monitoring image includes: The high-altitude object dropping monitoring image after privacy masking is presented on the display interface; Among them, the high-altitude object dropping monitoring images stored in the memory are not privacy-blocked.

8. An electronic device, characterized in that: The electronic device comprises a processor, and the processor is used to execute instructions to implement the steps of the method according to any one of claims 1-7.

9. A computer-readable storage medium having a program and / or an instruction stored thereon, characterized in that: When the program and / or instruction is executed, the steps of the method according to any one of claims 1 to 7 are implemented.

Citation Information

Patent Citations

  • High-altitude throwing object detection method, device and system, electronic device and storage medium

    CN113658219A