CN111985331B - Detection method and device for preventing trade secret from being stolen - Google Patents
Detection method and device for preventing trade secret from being stolen Download PDFInfo
- Publication number
- CN111985331B CN111985331B CN202010695613.7A CN202010695613A CN111985331B CN 111985331 B CN111985331 B CN 111985331B CN 202010695613 A CN202010695613 A CN 202010695613A CN 111985331 B CN111985331 B CN 111985331B
- Authority
- CN
- China
- Prior art keywords
- human body
- key points
- body key
- picture
- processed
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 112
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 46
- 238000012544 monitoring process Methods 0.000 claims abstract description 17
- 238000000034 method Methods 0.000 claims description 16
- 230000006399 behavior Effects 0.000 claims description 14
- 238000004364 calculation method Methods 0.000 claims description 12
- 230000011664 signaling Effects 0.000 claims description 4
- 210000000707 wrist Anatomy 0.000 claims description 4
- 239000000284 extract Substances 0.000 claims description 2
- 238000012549 training Methods 0.000 description 11
- 238000013527 convolutional neural network Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 210000003739 neck Anatomy 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 210000003423 ankle Anatomy 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000004883 computer application Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 210000005069 ears Anatomy 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 210000003127 knee Anatomy 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 230000036544 posture Effects 0.000 description 1
- 238000011895 specific detection Methods 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- 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
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Signal Processing (AREA)
- Human Computer Interaction (AREA)
- Burglar Alarm Systems (AREA)
Abstract
The disclosure provides a detection method and a detection device for preventing a trade secret from being stolen, which relate to the technical field of electronic information, and specifically comprise the following technical scheme: the image acquisition equipment acquires monitoring pictures in a preset area in real time and sends the acquired monitoring pictures to the anti-theft detection equipment; detecting the picture to be processed by adopting a target detection algorithm to obtain the coordinate information and the corresponding confidence coefficient of all photographing devices in the picture to be processed; detecting the picture to be processed by combining the photographing device and the human body key points through a target detection algorithm and a human body key point detection algorithm, and detecting a corresponding target area to obtain coordinate information of all human body key points in the picture to be processed; after coordinate information of all human body key points in the picture to be processed is obtained, a weight value corresponding to each human body key point and a preset threshold value of confidence coefficient of the weight value are set according to the difference of human body parts where the human body key points are located, the existence of a steal function is determined, and an alarm signal is generated or a display screen is controlled to display a warning picture.
Description
Technical Field
The invention relates to a detection method and a detection device for preventing a trade secret from being stolen in the technical field of electronic information. And more particularly to a detection method for preventing a trade secret from being stolen, which is applied to an anti-theft detection apparatus.
Background
With the continuous development of high technology, the enhancement of computer functions and the popularization and application of computer applications, many transactions need to be processed by a computer at present, and data displayed on a computer display screen can be even photographed under the condition of not entering a secret-related place, and if the data are not protected, the data are likely to be stolen in a photographing mode, so that the data are revealed. Computers are an indispensable tool in modern offices, and if no computer exists, some work cannot be performed, and many enterprises can use the computers to store important data and even secrets of many enterprises. Setting the computer access password, whether it is a desktop computer or a portable computer, many employees, including management personnel, often place the computer in a company after work or during outing, so that if an improper idea is available, the employee or other person may steal the computer to view and copy the trade secret in the computer. Thus, a computer storing a trade secret may be left unattended by a thief without setting an access code. When the computer is in work, some people can leave the computer temporarily, some people forget the computer due to carelessness, and even if the starting password is set, other people can enter the computer in the time period. Because of the concealment or camouflage of the special equipment for theft, the special equipment for theft has a certain difficulty in finding or identifying the special equipment for theft, and the special equipment for theft cannot be directly tested by adopting a test method of the special equipment for theft, thereby becoming the difficulty of test work of the special equipment for theft. Although the security management and control of computer equipment and network are basically mature at present, the technical means for preventing the screen from being stolen is still weak, the event that the display information of the computer screen is taken by people and leaked frequently occurs, and serious loss is caused to national security and enterprises and public institutions. In the prior art, the task of object detection is to find all objects (objects) of interest in an image, and determining their position and size is one of the core problems in the field of machine vision. Because various objects have different appearances, shapes and postures, and the interference of factors such as illumination, shielding and the like during imaging is added, target detection is always the most challenging problem in the field of machine vision. Object detection is the basis of many computer vision tasks, which provides reliable information whether we need to implement image-to-text interactions or to identify subtle categories. In order to prevent the handheld photo taking device from determining whether the photo taking action occurs by identifying whether the photo taking device exists in the monitoring picture, a picture or a video is given to judge what kind of object is contained in the picture or the video, and the position of the object and which object or scene each pixel belongs to are positioned. The special equipment for man-machine information visual interaction link to prevent theft and taking photograph and secret leakage can immediately and automatically hide the display content when someone uses equipment such as mobile phones, cameras, video cameras and the like to take the photograph illegally, effectively prevent screen information from being taken and steal, and can identify the user through face recognition, but the detection effect of the special equipment in a single detector is usually poor, and the position of a target is inaccurate. If the photographing device is only held by the user in the hand and does not photograph, the identification method has the problem of easy misjudgment, and the reliability of user experience is reduced.
Conventional target detection methods are generally divided into three stages: a) Selecting candidate regions on a given image; b) Extracting features from the regions; c) Classification is performed using a trained classifier. In stage b), it is often necessary to manually obtain the expression information related to the target in the original input, and further perform classifier learning on the extracted feature information related to the target, however, there are many limitations in the manual feature extraction method. On the one hand, the manual method depends on a specific detection task to a great extent, and for different targets or different forms of the same target, a designer is required to carefully think about how to extract the characteristics of the targets, and the final recognition effect of the model is also limited by the experience of the designer; on the other hand, conventional detection models separate feature extraction from classification training. If the manually extracted features in the feature description are not sufficient to describe a target, some of the lost useful information is no longer recoverable from the classification training. These drawbacks prevent conventional inspection models from achieving a characterization that better meets the target characteristics. Until Deep Convolutional Neural Networks (DCNN) appear, the DPM algorithm has been the most excellent algorithm in the field of target detection, and its basic idea is to extract DPM artificial features (as shown in the following diagram) first, and then classify the DPM artificial features by LATENTSVM. The feature extraction mode has obvious limitations, firstly, DPM features are complex to calculate and the calculation speed is low; secondly, the artificial features have poor object detection effects on rotation, stretching and visual angle changes. These drawbacks limit the application scenarios of the algorithm to a large extent. Target tracking and target detection are classical problems in the computer vision field, but the problems solved by the two are not the same. The input for object detection is typically a picture and the output is the position of a frame containing the object in the picture. The inputs to target tracking are video and the position of the object to be tracked in the first frame. The object detection is applied to pictures or videos for frame-by-frame detection, but the problem is that the object detection algorithm cannot determine which object in the previous frame is the same object as which object in the previous frame. This is the core problem solved by the target tracking algorithm. The object detection algorithm can only recognize specific types of objects, namely the types existing in the training set. While object tracking generally has no requirement for object class, i.e., an excellent object tracking algorithm can accomplish tracking of objects of a class that is not seen in the training set. In terms of accuracy, the detection algorithm can find objects frame by frame, but cannot solve the relevance between objects, that is, the improved YOLOv algorithm can find a class of objects and detect them in substantially real time, but it does not know whether the class is the same object as the class detected by a frame, and the currently mainstream tracking algorithm does so exclusively.
Disclosure of Invention
The invention aims to solve the problem of easy misjudgment in the prior art, and provides a detection method for preventing the stealth of a commercial secret, which can improve the detection accuracy and avoid the misjudgment problem caused by independently detecting a photographing device in the prior art.
The above object of the present invention can be achieved by the following technical solutions: a method of preventing theft of a trade secret, comprising the steps of:
Obtaining a picture to be processed: the image acquisition equipment monitors a preset area taking the photographing device as a center in real time, acquires a monitoring picture in the preset area, acquires a monitoring picture in a sensitive area acquired by the image acquisition equipment, and sends the acquired monitoring picture to the anti-theft detection equipment, wherein the sensitive area is an area which is monitored by the image acquisition equipment and needs to be kept secret;
Detecting whether a steal action exists or not: detecting the picture to be processed by adopting a target detection algorithm to obtain the coordinate information and the corresponding confidence coefficient of all photographing devices in the picture to be processed;
Human body key point detection is carried out on the picture to be processed: detecting the picture to be processed by combining the photographing device and the human body key points through a target detection algorithm and a human body key point detection algorithm, and detecting a corresponding target area to obtain coordinate information of all human body key points in the picture to be processed;
Calculating the weight statistic value of the key points of the human body: after coordinate information of all human body key points in the picture to be processed is obtained, setting a weight value corresponding to each human body key point and a preset threshold value of confidence coefficient of the weight value according to different human body parts where the human body key points are located. After the length of the preset area is determined, acquiring weight statistics values of all human body key points in the preset area, calculating to obtain the weight statistics values of all human body key points in the preset area according to the weight values of all human body key points in the preset area, judging whether the confidence coefficient of each photographing device is larger than a first preset threshold value, when the confidence coefficient of the photographing device is larger than the first preset threshold value, acquiring all human body key points in the preset area by taking the central point coordinates of the boundary frame of the photographing device as an origin, and then calculating to obtain the weight statistics values of all human body key points in the preset area according to the weight values corresponding to each human body key point; and determining that the stealing behavior exists according to the fact that the weight statistical value in the preset area is larger than or equal to a second preset threshold value, and generating an alarm signal or controlling a display screen to display a warning picture.
Compared with the prior art, the invention has the following beneficial effects:
The method comprises the steps of detecting a picture to be processed through a target detection algorithm and a human body key point detection algorithm to obtain position information of a photographing device and coordinate information of human body key points, acquiring a weight statistical value of the human body key points in a preset area taking the photographing device as a center when the confidence coefficient of the photographing device is larger than a first preset threshold value, and determining that the stealing behavior exists when the weight statistical value is larger than or equal to a second preset threshold value. Through combining the photographing device with the key points of the human body, the accuracy of detection can be improved, the misjudgment problem caused by separately detecting the photographing device in the prior art is avoided, and the user experience is improved.
The invention discloses a detection device for preventing a trade secret from being stolen, which is provided by the embodiment of the invention, and is characterized in that a target detection algorithm and a human body key point detection algorithm are used for detecting a picture to be processed to obtain position information of a photographing device and coordinate information of a human body key point, when the confidence of the photographing device is larger than a first preset threshold value, a weight statistical value of the human body key point in a preset area with the photographing device as a center is obtained, and when the weight statistical value is larger than or equal to a second preset threshold value, the existence of a theft behavior is determined. Through combining the photographing device with the key points of the human body, the accuracy of detection can be improved, the misjudgment problem caused by separately detecting the photographing device in the prior art is avoided, and the user experience is improved.
According to the detection method for preventing the trade secret from being stolen, the single-stage target detection classical algorithm SSD completes detection through a plurality of feature maps. Detecting a picture to be processed through a target detection algorithm and a human body key point detection algorithm to obtain position information of a photographing device and coordinate information of human body key points, acquiring a weight statistical value of the human body key points in a preset area taking the photographing device as a center when the confidence coefficient of the photographing device is larger than a first preset threshold value, and determining that the stealing behavior exists when the weight statistical value is larger than or equal to a second preset threshold value. Through combining the photographing device with the key points of the human body, the accuracy of detection can be improved, the misjudgment problem caused by separately detecting the photographing device in the prior art is avoided, and the user experience is improved.
The invention is used for anti-theft detection. The problem of misjudgment caused by the existing photographing device only can be solved.
Drawings
The following drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure.
FIG. 1 is a flow chart of a method of detecting that a trade secret is protected from theft in accordance with the present invention;
FIG. 2 is a schematic diagram of the structural principle of a detection device for preventing the theft of trade secrets;
fig. 3 is a schematic structural view of the detecting device of fig. 2.
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present disclosure as detailed in the accompanying claims.
Detailed Description
See fig. 1. According to the invention, the following steps are used:
Obtaining a picture to be processed: the image acquisition equipment monitors a preset area taking the photographing device as a center in real time, acquires a monitoring picture in the preset area, acquires a monitoring picture in a sensitive area acquired by the image acquisition equipment, and sends the acquired monitoring picture to the anti-theft detection equipment, wherein the sensitive area is an area which is monitored by the image acquisition equipment and needs to be kept secret;
Detecting whether a steal action exists or not: detecting the picture to be processed by adopting a target detection algorithm to obtain the coordinate information and the corresponding confidence coefficient of all photographing devices in the picture to be processed;
Human body key point detection is carried out on the picture to be processed: detecting the picture to be processed by combining the photographing device and the human body key points through a target detection algorithm and a human body key point detection algorithm, and detecting a corresponding target area to obtain coordinate information of all human body key points in the picture to be processed;
Calculating the weight statistic value of the key points of the human body: after coordinate information of all human body key points in the picture to be processed is obtained, setting a weight value corresponding to each human body key point and a preset threshold value of confidence coefficient of the weight value according to different human body parts where the human body key points are located. After the length of the preset area is determined, acquiring weight statistics values of all human body key points in the preset area, calculating to obtain the weight statistics values of all human body key points in the preset area according to the weight values of all human body key points in the preset area, judging whether the confidence coefficient of each photographing device is larger than a first preset threshold value, when the confidence coefficient of the photographing device is larger than the first preset threshold value, acquiring all human body key points in the preset area by taking the central point coordinates of the boundary frame of the photographing device as an origin, and then calculating to obtain the weight statistics values of all human body key points in the preset area according to the weight values corresponding to each human body key point; and determining that the stealing behavior exists according to the fact that the weight statistical value in the preset area is larger than or equal to a second preset threshold value, and generating an alarm signal or controlling a display screen to display a warning picture.
The embodiment of the disclosure provides a detection method for preventing a trade secret from being stolen, which is applied to an anti-theft detection device, and comprises the following steps:
101. And obtaining a picture to be processed.
In an embodiment of the present disclosure, acquiring a picture to be processed includes: and acquiring a monitoring picture in the sensitive area acquired by the image acquisition equipment. The sensitive area can be an area which is monitored by the image acquisition equipment and needs to be kept secret, and the sensitive area can be a place which needs to be kept secret, such as a display screen, a file, a commodity and the like. Taking a display screen as an example, the sensitive area is an area at the display screen where data to be protected is displayed, that is, the sensitive area is an area where the display screen can be photographed.
In the embodiment of the present disclosure, the image capturing apparatus may be an apparatus having a photographing function such as a video camera, a still camera, or the like. The image acquisition device can be a part of the anti-theft detection device, and can also be an external image acquisition device which is connected and communicated with the anti-theft detection device through an external interface; the image acquisition device may also be part of the display screen or an external image acquisition device in communication with the display screen via an external interface. The anti-theft detection device may be part of the display screen or an external device connected to the display screen.
In the embodiment of the disclosure, an image acquisition device monitors a preset area with a photographing device as a center in real time, acquires a monitoring picture in the preset area, and sends the acquired monitoring picture to an anti-theft detection device, wherein the monitoring picture is a color image of W x H.
102. And detecting the picture to be processed by adopting a target detection algorithm to obtain the position information and the corresponding confidence of all photographing devices in the picture to be processed.
In one embodiment, the coordinate information of the photographing apparatus includes center point coordinates of a boundary frame of the photographing apparatus; the photographing device may be a mobile phone, a tablet, a camera, etc. In the embodiment of the disclosure, the target detection algorithm may be a single-stage target detection classical algorithm SSD (TheSingleShotDetector) algorithm, a YOLO (youonlylookonce) target detection algorithm, or the like, where the frame of the single-stage target detection classical algorithm SSD is on a basic CNN network, but may be replaced by other networks, and some additional structures are added, so that the network has the following characteristics: detecting by using a multi-scale feature map; the real-time target detection algorithm YOLO algorithm predicts a plurality of boundingboxes and class probabilities by adopting a single convolutional neural network, integrates target region prediction and target class prediction, and regards a target detection task as regression of target region prediction and class prediction. The real-time object detection algorithm YOLO first divides the image into s×s grids. If the center of an object falls into a grid, the grid is responsible for detecting the object. B Boundingbox and confidence values are predicted in each grid (confidencescore). These confidence scores reflect the confidence that the model contains in the box whether or not it contains the target, and how accurate it predicts the box. A single detector detects different object types at different viewing distances, using window types of different sizes and aspect ratios, sliding windows on the feature map to detect objects; in the selective searching (SELECTIVESEARCH, SS), each pixel is taken as a group, then the texture of each group is calculated, the two groups with the most similar textures are combined together until all areas are combined together, a feature extractor (CNN) firstly extracts the features of the whole image, and the coordinate information and the corresponding confidence coefficient of all photographing devices in the image to be processed are obtained through carrying out target detection on the image to be processed, wherein the coordinate information is expressed by (x, y, w, h), the (x, y) represents the center point coordinates of the boundary frame of the photographing device, and the (w, h) represents the width and the height of the boundary frame of the photographing device.
The image to be processed comprises at least one photographing device, and the coordinate information and the corresponding confidence coefficient of all photographing devices in the image to be processed are obtained by carrying out target detection on the image to be processed.
103. And detecting human body scanning key points of the picture to be processed to obtain coordinate information of all human body key points in the picture to be processed.
The key points of the human body may be joint or five-sense organ positions, and exemplary key points that may be detected on the human body include: left and right eyes, nose, left and right ears, left and right shoulders, left and right elbows, left and right wrists, left and right crotch, left and right knees, left and right ankles, etc. In the embodiment of the disclosure, in order to detect whether the steal function exists, key points of a human body are mainly left and right shoulders, left and right elbows, left and right wrists and necks.
After coordinate information of all human body key points in the picture to be processed is obtained, setting a weight value corresponding to each human body key point according to different human body parts where the human body key points are located. Illustratively, the wrist keypoints have a weight of 25, neck keypoints have a weight of 20, shoulder keypoints have a weight of 15, and elbow keypoints have a weight of 10. Of course, a default weight value may also be used for the weight value corresponding to the human body key point. The detector will make repeated detections for the same target. Non-maximal suppression is used to remove duplicate detections with low confidence, ranked from high to low confidence. Any default weight value is removed from the sequence if it is the same as the class predicted by the current default weight value and the default weight value is greater than 0.5.
104. When the confidence coefficient of the photographing device is larger than a first preset threshold value, acquiring weight statistical values of all human body key points in a preset area taking the photographing device as a center according to the coordinate information of the photographing device and the coordinate information of the human body key points.
In the embodiment of the present disclosure, the preset area may be circular, square, or the like. The length of the preset area (the radius of the circle is the length for the circle, and the side length of the square is the length for the square) can be set according to historical experience, for example, the preset area is the circular area with the radius R, and the value range of the radius R can be 60-100 pixels; the probability of each category can also be calculated according to a preset human body key point training set.
Wherein, how to calculate according to the preset human body key point training set includes: the preset human body key point training set is a training set for detecting human body key points. Specifically, the Euclidean distance between all elbow key points and corresponding shoulder key points in a preset human body key point training set is calculated; calculating the mean value and standard deviation of all Euclidean distances according to the Euclidean distances between all elbow key points and the corresponding shoulder key points; the length of the preset region is determined as twice the sum of the mean and the standard deviation.
After determining the length of the preset area, obtaining the weight statistics of all the human body key points in the preset area comprises the following steps:
When the confidence coefficient of the photographing device is larger than a first preset threshold value, acquiring all human body key points in a preset area taking the central point coordinate of the boundary frame of the photographing device as an origin;
And calculating to obtain the weight statistic value of all the human body key points in the preset area according to the weight value of each human body key point in the preset area.
Specifically, whether the confidence coefficient of each photographing device is larger than a first preset threshold value is judged, when the confidence coefficient of each photographing device is larger than the first preset threshold value, the coordinates of the central point of the boundary frame of the photographing device are taken as the origin, all human body key points in a preset area are obtained, and then the weight statistical value of all the human body key points in the preset area is calculated according to the weight value corresponding to each human body scanning key point.
105. And when the weight statistic value is greater than or equal to a second preset threshold value, determining that the steal behavior exists.
In the embodiment of the present disclosure, the higher the weight statistics value is, the higher the likelihood that the photographing device is used for theft is considered, and therefore, when the weight statistics value in the preset area is greater than or equal to the second preset threshold value, it is determined that the photographing device is used for theft, that is, there is a theft behavior. When it is determined that there is a theft action, an alarm signal may be generated or the display screen may be controlled to display a warning screen.
The preset area is a circle with a radius R as an example. In one embodiment, the first preset threshold value is 0.95, the second preset threshold value is 40, the preset area is a circular area with a radius R, and the value range of the radius R is 60-100 pixels. When the confidence coefficient of the photographing device is larger than 0.95, calculating the weight statistical value of all human body key points in the round area with the radius R by taking the center point coordinate of the boundary frame of the photographing device as the origin, and when the weight statistical value in the preset area is larger than or equal to 40, considering that the photographing device is used for stealing, and controlling the display screen to display a warning picture.
Based on the detection method for preventing the theft of trade secrets described in the embodiment corresponding to fig. 1, the following is an embodiment of the disclosed apparatus, which may be used to perform the embodiment of the disclosed method.
When the confidence coefficient of the photographing device is larger than a first preset threshold value, the SSD completes detection through a plurality of feature graphs, and according to the coordinate information of the photographing device and the coordinate information of the key points of the human body, weight statistics values of all the key points of the human body in a preset area taking the photographing device as a center are calculated, wherein the weight statistics values comprise: when the confidence coefficient of the photographing device is larger than a first preset threshold value, acquiring all human body key points in a preset area taking the central point coordinate of the boundary frame of the photographing device as an origin, and calculating to obtain the weight statistic value of all the human body key points in the preset area according to the weight value corresponding to each human body key point in the preset area.
In one embodiment, before the obtaining of the picture to be processed, the method further comprises: and calculating the average value and standard deviation of Euclidean distances between all elbow key points and corresponding shoulder key points in a preset human body key point training set, and determining twice the average value and standard deviation of Euclidean distances as the length of a preset region.
See fig. 2. The embodiment of the disclosure also provides a detection device for preventing the trade secret from being stolen, which comprises: the system comprises a receiver and a transmitter which are connected with an antenna, a processor which is connected with the common end of the receiver and the transmitter, a memory which stores at least one computer instruction, and a processor which at least comprises one detection module, wherein the processor is connected with the memory, and loads and executes at least one computer instruction, and a target detection algorithm is adopted to detect pictures to be processed and human body key points, so as to obtain coordinate information and corresponding confidence coefficient of all photographing devices in the pictures to be processed and coordinate information of all human body key points; according to the coordinate information of the photographing device and the coordinate information of the human body key points, setting a first preset threshold value larger than the confidence coefficient and a second preset threshold value larger than or equal to the weight statistic value corresponding to each human body key point by utilizing the difference of the human body parts where the human body key points are located, and calculating the weight statistic values of all the human body key points in a preset area taking the photographing device as the center; and generating an alarm signal for determining that the theft behavior exists or controlling a display screen to display an alarm picture according to the fact that the weight statistical value in the preset area is larger than or equal to a second preset threshold value.
The detection method for preventing the trade secret from being stolen described in the embodiment corresponding to the above-mentioned fig. 1 is further provided based on the embodiment of the disclosure of the above-mentioned fig. 2, and the non-transitory computer readable storage medium may be, for example, a read-only memory (english: readOnlyMemory, ROM), a random access memory (english: randomAccessMemory, RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.
Embodiments of the present disclosure provide a processor as shown in fig. 3, comprising: the system comprises a first detection module 202 connected with an acquisition module 201, a calculation module 204 connected with a second detection module 203 and a setting module 206, and a determination module 205 connected with the calculation module 204, wherein the acquisition module 201 respectively transmits acquired pictures to be processed to the first detection module 202 and the second detection module 203 through a behavior chain, and the first detection module 202 detects the pictures to be processed by adopting a target detection algorithm to obtain coordinate information and corresponding confidence of all photographing devices in the pictures to be processed; the second detection module 203 detects key points of the human body on the picture to be processed to obtain coordinate information of all key points of the human body in the picture to be processed; the first detection module 202 and the second detection module 203 send the obtained confidence coefficient and the coordinate information of the human body key points to the calculation module 204 respectively, and when the confidence coefficient of the photographing device is larger than a first preset threshold value, the calculation module 204 calculates the weight statistic value of all the human body key points in a preset area taking the photographing device as the center according to the coordinate information of the photographing device and the coordinate information of the human body key points; the setting module 206 sets a weight value corresponding to each human body key point according to the difference of the human body parts where the human body key points input by the second detecting module 203 are located, and the determining module 205 determines that the theft behavior exists by using the weight statistic value provided by the calculating module 204 to be greater than or equal to a second preset threshold.
The first detection module 202 obtains all human body key points in a preset area taking the center point coordinate of the boundary frame of the photographing device as an origin when the confidence coefficient of the photographing device is larger than a first preset threshold; the calculation module 204 calculates the weight statistics of all the human body key points in the preset area according to the weight value corresponding to each human body key point in the preset area.
In one embodiment, the calculation module 204 calculates euclidean distances between all elbow keypoints and corresponding shoulder keypoints in a preset human body keypoint training set, calculates a mean value and a standard deviation of the euclidean distances according to the euclidean distances, and the determination module 205 determines twice the sum of the mean value and the standard deviation of the euclidean distances as the length of the preset region.
In one embodiment, the coordinate information of the photographing apparatus includes center point coordinates of a boundary frame of the photographing apparatus;
it is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program for instructing relevant hardware, where the program may be stored in a computer readable storage medium, and the storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any adaptations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
Claims (9)
1. A method of preventing theft of a trade secret, comprising the steps of:
Obtaining a picture to be processed: the image acquisition equipment monitors a preset area taking the photographing device as a center in real time, acquires a monitoring picture in the preset area, acquires a monitoring picture in a sensitive area acquired by the image acquisition equipment, and sends the acquired monitoring picture to the anti-theft detection equipment, wherein the sensitive area is an area which is monitored by the image acquisition equipment and needs to be kept secret;
Detecting whether a steal action exists or not: detecting the picture to be processed by adopting a target detection algorithm to obtain the coordinate information and the corresponding confidence coefficient of all photographing devices in the picture to be processed;
Human body key point detection is carried out on the picture to be processed: detecting the picture to be processed by combining the photographing device and the human body key points through a target detection algorithm and a human body key point detection algorithm, and detecting a corresponding target area to obtain coordinate information of all human body key points in the picture to be processed;
Calculating the weight statistic value of the key points of the human body: after coordinate information of all human body key points in the picture to be processed is obtained, setting a preset threshold value of a weight value corresponding to each human body key point and the confidence coefficient thereof according to the difference of human body parts where the human body key points are located, acquiring a weight statistical value of the human body key points in a preset area taking the photographing device as the center when the confidence coefficient of the photographing device is larger than a first preset threshold value, determining that a steal action exists according to the weight statistical value in the preset area being larger than or equal to a second preset threshold value, and generating an alarm signal or controlling a display screen to display a warning picture;
After the length of the preset area is determined, acquiring weight statistics values of all human body key points in the preset area, calculating to obtain the weight statistics values of all human body key points in the preset area according to the weight values of all human body key points in the preset area, judging whether the confidence coefficient of each photographing device is larger than a first preset threshold value, when the confidence coefficient of the photographing device is larger than the first preset threshold value, acquiring all human body key points in the preset area by taking the central point coordinates of the boundary frame of the photographing device as an origin, and then calculating to obtain the weight statistics values of all human body key points in the preset area according to the weight values corresponding to each human body key point; and determining that the stealing behavior exists according to the fact that the weight statistical value in the preset area is larger than or equal to a second preset threshold value, and generating an alarm signal or controlling a display screen to display a warning picture.
2. A method of preventing theft of a trade secret according to claim 1, wherein: the method for obtaining the picture to be processed comprises the following steps: and acquiring a monitoring picture in a sensitive area acquired by the image acquisition equipment, wherein the sensitive area is an area, a file and a commodity which need to be kept secret at a display screen for displaying data to be protected.
3. A method of preventing theft of a trade secret according to claim 1, wherein: the object detection algorithm comprises a single detector and an algorithm thereof, wherein the single detector comprises a real-time object detection algorithm YOLO, a single-stage object detection algorithm SSD and RETINANET, and detects different object types at different observation distances, and the object is detected by sliding windows on a feature map by using window types with different sizes and aspect ratios; in the selective search, each pixel is taken as a group, then the textures of each group are calculated, the two groups with the most similar textures are combined together until all areas are combined together, the feature extractor CNN firstly extracts the features of the whole image, and the coordinate information and the corresponding confidence coefficient of all photographing devices in the image to be processed are obtained by carrying out target detection on the image to be processed.
4. A method of preventing theft of a trade secret according to claim 1, wherein: the detected key points include: the weight of the wrist key points is 25, the weight of the neck key points is 20, the weight of the shoulder key points is 15, and the weight of the elbow key points is 10.
5. A method of preventing theft of a trade secret according to claim 1, wherein: the first preset threshold value is 0.95, the second preset threshold value is 40, the preset area is a circular area with radius R, and the value range of the radius R is 60-100 pixels.
6. A method of preventing theft of a trade secret according to claim 1, wherein: when the confidence coefficient of the photographing device is larger than 0.95, calculating the weight statistical value of all human body key points in the round area with the radius R by taking the center point coordinate of the boundary frame of the photographing device as the origin, and when the weight statistical value in the preset area is larger than or equal to 40, considering that the photographing device is used for stealing, and controlling the display screen to display a warning picture.
7. A tamper detection device for preventing a trade secret using the method of claim 1, comprising: the system comprises a receiver and a transmitter which are connected with an antenna, and a processor which is connected with the common end of the receiver and the transmitter, wherein the memory stores at least one computer instruction, the processor loads and executes the at least one computer instruction, and a target detection algorithm is adopted to detect a picture to be processed and detect key points of a human body, so that coordinate information and corresponding confidence coefficient of all photographing devices in the picture to be processed and coordinate information of all key points of the human body are obtained; according to the coordinate information of the photographing device and the coordinate information of the human body key points, setting a first preset threshold value larger than the confidence coefficient and a second preset threshold value larger than or equal to the weight statistic value corresponding to each human body key point by utilizing the difference of the human body parts where the human body key points are located, and calculating the weight statistic values of all the human body key points in a preset area taking the photographing device as the center; and generating an alarm signal for determining that the theft behavior exists or controlling a display screen to display an alarm picture according to the fact that the weight statistical value in the preset area is larger than or equal to a second preset threshold value.
8. A tamper detection device for preventing a trade secret according to claim 7, wherein: the processor comprises: the system comprises a first detection module (202) connected with an acquisition module (201), a calculation module (204) connected with a second detection module (203) and a setting module (206), and a determination module (205) connected with the calculation module (204), wherein the acquisition module (201) sends acquired pictures to be processed to the first detection module (202) and the second detection module (203) through a behavior chain, and the first detection module (202) detects the pictures to be processed by adopting a target detection algorithm to obtain coordinate information and corresponding confidence of all photographing devices in the pictures to be processed; the second detection module (203) detects human body key points of the picture to be processed to obtain coordinate information of all human body key points in the picture to be processed; the first detection module (202) and the second detection module (203) respectively send the obtained confidence coefficient and the coordinate information of the human body key points to the calculation module (204), and when the confidence coefficient of the photographing device is larger than a first preset threshold value, the calculation module (204) calculates the weight statistic value of all the human body key points in a preset area taking the photographing device as the center according to the coordinate information of the photographing device and the coordinate information of the human body key points; the setting module (206) sets a weight value corresponding to each human body key point according to the difference of the human body parts where the human body key points input by the second detection module (203) are located, and the determining module (205) determines that the theft behavior exists by using the weight statistical value provided by the calculating module (204) to be larger than or equal to a second preset threshold value.
9. A tamper detection device for preventing a trade secret according to claim 7, wherein: when the confidence coefficient of the photographing device is larger than a first preset threshold value, a first detection module (202) acquires all human body key points in a preset area taking the central point coordinate of the boundary frame of the photographing device as an origin; the calculation module (204) calculates and obtains the weight statistic value of all the human body key points in the preset area according to the weight value corresponding to each human body key point in the preset area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010695613.7A CN111985331B (en) | 2020-07-20 | 2020-07-20 | Detection method and device for preventing trade secret from being stolen |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010695613.7A CN111985331B (en) | 2020-07-20 | 2020-07-20 | Detection method and device for preventing trade secret from being stolen |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111985331A CN111985331A (en) | 2020-11-24 |
| CN111985331B true CN111985331B (en) | 2024-05-10 |
Family
ID=73438669
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010695613.7A Active CN111985331B (en) | 2020-07-20 | 2020-07-20 | Detection method and device for preventing trade secret from being stolen |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111985331B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114067441B (en) * | 2022-01-14 | 2022-04-08 | 合肥高维数据技术有限公司 | Shooting and recording behavior detection method and system |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002369125A (en) * | 2001-06-06 | 2002-12-20 | Canon Inc | Photographing apparatus and picture erasing method thereof |
| CN107066983A (en) * | 2017-04-20 | 2017-08-18 | 腾讯科技（上海）有限公司 | A kind of auth method and device |
| CN107294622A (en) * | 2016-04-01 | 2017-10-24 | 北京中密安信息安全技术有限公司 | Wireless detection method of stealing secret information |
| CN108140123A (en) * | 2017-12-29 | 2018-06-08 | 深圳前海达闼云端智能科技有限公司 | Face living body detection method, electronic device and computer program product |
| CN108182396A (en) * | 2017-12-25 | 2018-06-19 | 中国电子科技集团公司电子科学研究院 | A kind of automatic identification is taken pictures the method and device of behavior |
| CN110060441A (en) * | 2019-06-14 | 2019-07-26 | 三星电子（中国）研发中心 | Method and apparatus for terminal anti-theft |
| CN110070015A (en) * | 2019-04-12 | 2019-07-30 | 重庆科芮智能科技有限公司 | Image-recognizing method and device, system |
| CN110096972A (en) * | 2019-04-12 | 2019-08-06 | 重庆科芮智能科技有限公司 | Data guard method, apparatus and system |
| CN110134565A (en) * | 2019-04-12 | 2019-08-16 | 重庆科芮智能科技有限公司 | Environment light detection method and device |
| CN110163100A (en) * | 2019-04-17 | 2019-08-23 | 中国电子科技网络信息安全有限公司 | The anti-display of taking pictures of one kind |
| CN111062239A (en) * | 2019-10-15 | 2020-04-24 | 平安科技（深圳）有限公司 | Human body target detection method and device, computer equipment and storage medium |
| CN111200781A (en) * | 2018-11-19 | 2020-05-26 | 林桦 | Anti-photographing method and system based on computer vision and radio direction finding positioning |
| CN111259461A (en) * | 2020-01-20 | 2020-06-09 | 北京科芮智盈技术有限公司 | Anti-stealing-lighting method, terminal equipment and system |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106295567B (en) * | 2016-08-10 | 2019-04-12 | 腾讯科技（深圳）有限公司 | A kind of localization method and terminal of key point |
| CN107239728B (en) * | 2017-01-04 | 2021-02-02 | 赛灵思电子科技(北京)有限公司 | Unmanned aerial vehicle interaction device and method based on deep learning attitude estimation |
-
2020
- 2020-07-20 CN CN202010695613.7A patent/CN111985331B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002369125A (en) * | 2001-06-06 | 2002-12-20 | Canon Inc | Photographing apparatus and picture erasing method thereof |
| CN107294622A (en) * | 2016-04-01 | 2017-10-24 | 北京中密安信息安全技术有限公司 | Wireless detection method of stealing secret information |
| CN107066983A (en) * | 2017-04-20 | 2017-08-18 | 腾讯科技（上海）有限公司 | A kind of auth method and device |
| CN108182396A (en) * | 2017-12-25 | 2018-06-19 | 中国电子科技集团公司电子科学研究院 | A kind of automatic identification is taken pictures the method and device of behavior |
| CN108140123A (en) * | 2017-12-29 | 2018-06-08 | 深圳前海达闼云端智能科技有限公司 | Face living body detection method, electronic device and computer program product |
| CN111200781A (en) * | 2018-11-19 | 2020-05-26 | 林桦 | Anti-photographing method and system based on computer vision and radio direction finding positioning |
| CN110070015A (en) * | 2019-04-12 | 2019-07-30 | 重庆科芮智能科技有限公司 | Image-recognizing method and device, system |
| CN110096972A (en) * | 2019-04-12 | 2019-08-06 | 重庆科芮智能科技有限公司 | Data guard method, apparatus and system |
| CN110134565A (en) * | 2019-04-12 | 2019-08-16 | 重庆科芮智能科技有限公司 | Environment light detection method and device |
| CN110163100A (en) * | 2019-04-17 | 2019-08-23 | 中国电子科技网络信息安全有限公司 | The anti-display of taking pictures of one kind |
| CN110060441A (en) * | 2019-06-14 | 2019-07-26 | 三星电子（中国）研发中心 | Method and apparatus for terminal anti-theft |
| CN111062239A (en) * | 2019-10-15 | 2020-04-24 | 平安科技（深圳）有限公司 | Human body target detection method and device, computer equipment and storage medium |
| CN111259461A (en) * | 2020-01-20 | 2020-06-09 | 北京科芮智盈技术有限公司 | Anti-stealing-lighting method, terminal equipment and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111985331A (en) | 2020-11-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110188724B (en) | Method and system for helmet positioning and color recognition based on deep learning | |
| WO2020215552A1 (en) | Multi-target tracking method, apparatus, computer device, and storage medium | |
| TWI686774B (en) | Human face live detection method and device | |
| US8750573B2 (en) | Hand gesture detection | |
| US8792722B2 (en) | Hand gesture detection | |
| CN108182396B (en) | Method and device for automatically identifying photographing behavior | |
| US20130170711A1 (en) | Edge detection image capture and recognition system | |
| US20140369567A1 (en) | Authorized Access Using Image Capture and Recognition System | |
| US20130163822A1 (en) | Airborne Image Capture and Recognition System | |
| US20130163823A1 (en) | Image Capture and Recognition System Having Real-Time Secure Communication | |
| CN101715111B (en) | Method for automatically searching abandoned object in video monitoring | |
| KR101781358B1 (en) | Personal Identification System And Method By Face Recognition In Digital Image | |
| CN109448326B (en) | Geological disaster intelligent group defense monitoring system based on rapid image recognition | |
| CN101167086A (en) | Human detection and tracking for security applications | |
| US20220180534A1 (en) | Pedestrian tracking method, computing device, pedestrian tracking system and storage medium | |
| WO2018056355A1 (en) | Monitoring device | |
| CN112287868B (en) | Human body action recognition method and device | |
| CN112183472A (en) | Method for detecting whether test field personnel wear work clothes or not based on improved RetinaNet | |
| CN113269091A (en) | Personnel trajectory analysis method, equipment and medium for intelligent park | |
| CN112287823A (en) | Facial mask identification method based on video monitoring | |
| CN110619239A (en) | Application interface processing method and device, storage medium and terminal | |
| CN112183219A (en) | Public safety video monitoring method and system based on face recognition | |
| CN111325133A (en) | Image processing system based on artificial intelligence recognition | |
| KR101454644B1 (en) | Loitering Detection Using a Pedestrian Tracker | |
| CN114140745A (en) | Method, system, device and medium for detecting personnel attributes of construction site |
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 |