Screen candid photographing identification method based on cascade detection

Abstract

The invention relates to a screen candid photographing identification method and device based on cascade detection, electronic equipment and a storage medium. The method comprises the following steps: acquiring a first image in front of a preset screen based on preset image acquisition equipment; the first detection model detects the first image based on a first preset image detection algorithm, and determines whether the first image contains a mobile phone; if the first image contains the mobile phone, intercepting an image of the mobile phone in the image as a second image; and the second detection model detects the second image based on a second preset image detection algorithm to determine whether the second image contains a camera, and if the second image contains the camera, it is determined that a screen candid shooting behavior exists. According to the method, a cascade detection algorithm is adopted, a low-cost RGB camera is used as input, and real-time identification of illegal screen shooting behaviors can be realized only by adopting a processor (without a GPU (Graphic Processing Unit) graphics card) of a working computer, so that illegal leakage of information is prevented.

Description

Background Art

[0002] In many important confidential places such as enterprises, banks, government departments, and military units, it is strictly forbidden to illegally shoot work computer screens to prevent confidential activities. Existing screen anti-secret shooting technologies mainly include frequency difference-based methods, active photoelectric detection methods, and image detection-based methods. The frequency difference-based method changes the display area update frequency by adding equipment to avoid being shot by mobile phone cameras. This method is expensive and is more likely to affect the staff's experience of watching computer screens, causing damage to human eye health. The active photoelectric detection method uses the reflection of infrared light signals to determine whether there is shooting behavior. The photoelectric transmitting module, photoelectric receiving module, and processing module in this solution are expensive, and smooth mirror objects such as glass water cups around the venue will affect the accuracy of the system.

[0003] In the prior art, a shooting behavior detection method, device, equipment and storage medium obtain a single-frame video image of a target person through a preset monitoring device; perform landmark recognition on the single-frame video image through a target detection network; if there is an image acquisition device in the single-frame video image, perform position association detection on the image acquisition device, the hand, side face and ear of the target person according to the intersection and union ratio function; if the image acquisition device is in a candidate state, perform perspective transformation on the camera of the image acquisition device to generate a corresponding camera perspective transformation plane; if the angle between the camera perspective transformation plane and the plane of the single-frame video image is less than or equal to the preset angle, it is determined that the image acquisition device is in a shooting state, and an early warning message is generated and sent to an early warning terminal. This method can automatically identify and detect illegal screen shooting behaviors, but when the side face and ears of the photographed person are in the blind spot of the field of vision, accurate identification cannot be performed.

[0004] In the prior art, a shooting behavior detection method, device, electronic device and storage medium are provided, which obtain an image sequence captured by a monitoring device; detect an image acquisition device and a target display device in the image sequence, and respectively determine a first 3D bounding box of the image acquisition device and a second 3D bounding box of the target display device; determine a first plane of the display screen of the image acquisition device in the first 3D bounding box, and determine a second plane of the display screen of the target display device in the second 3D bounding box; based on the positional relationship between the first plane and the second plane, determine whether there is a target shooting behavior. Through this application, the problems of many false detections and false alarms and low detection accuracy in the detection of customer privacy shooting in the related art are solved, and the judgment of shooting behavior is determined according to the positional relationship between the image acquisition device and the target display device. However, this solution requires 3D detection, the model is large and complex, and the performance requirements for the equipment are high, which is not convenient for conventional deployment.

[0005] Therefore, one or more methods are needed to solve the above problems.

[0006] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0007] The purpose of the present disclosure is to provide a screen candid camera recognition method, device, electronic device and computer-readable storage medium based on cascade detection, thereby overcoming one or more problems caused by the limitations and defects of the relevant technology at least to a certain extent.

[0008] According to one aspect of the present disclosure, a screen candid camera recognition method based on cascade detection is provided, comprising:

[0009] Capturing a first image in front of a preset screen based on a preset image acquisition device, and sending the first image to a first detection model;

[0010] The first detection model detects the first image based on a first preset image detection algorithm to determine whether the first image contains a shooting device that violates the regulations in screen-shooting behavior;

[0011] If the first image contains a shooting device that has violated the regulations on screen capture, an image of the shooting device that has violated the regulations on screen capture in the image is captured as a second image, and the second image is sent to a second detection model;

[0012] The second detection model detects the second image based on a second preset image detection algorithm to determine whether the second image contains a camera target. If the second image contains a camera target, it is determined that screen candid photography has occurred.

[0013] In an exemplary embodiment of the present disclosure, the method further includes:

[0014] The preset image acquisition device is an RGB camera with an image processor integrated with the host of the preset screen.

[0015] In an exemplary embodiment of the present disclosure, the method further includes:

[0016] The first preset image detection algorithm is the YOLOX-s algorithm. Based on the YOLOX-s algorithm, the first image is detected to determine whether the first image contains a mobile phone target.

[0017] In an exemplary embodiment of the present disclosure, the method further includes:

[0018] The first image is detected based on a first preset image detection algorithm. If the first image does not contain a mobile phone target, it is determined that there is no screen candid photography behavior.

[0019] In an exemplary embodiment of the present disclosure, the method further includes:

[0020] If the first image contains a mobile phone target, an image of the mobile phone target in the image is captured as a second image, and the second image is sent to a second detection model.

[0021] In an exemplary embodiment of the present disclosure, the method further includes:

[0022] The second preset image detection algorithm includes a Backbone module, a Neck module, and a head module of YOLOX.

[0023] In an exemplary embodiment of the present disclosure, the method further includes:

[0024] The Backbone module includes 3 groups of CONV+CBAM attention modules, wherein the first group CONV is 4 layers of convolution and maximum pooling layer, and the image resolution is downsampled to 28*28*256, the second group CONV is 6 layers of convolution and maximum pooling layer, and the image resolution is downsampled to 14*14*512, and the third group CONV is 4 layers of convolution and maximum pooling layer, and the image resolution is downsampled to 7*7*1024;

[0025] The Neck module concatenates the 7*7*1024 feature map with the 14*14*512 feature map in the channel dimension to obtain a 14*14*1536 feature map.

[0026] The head module of YOLOX receives the 14*14*1536 input CBAM attention module and the feature map of 7*7*1024 resolution and generates the detection result.

[0027] In one aspect of the present disclosure, a screen candid camera recognition device based on cascade detection is provided, comprising:

[0028] An image acquisition module, used for acquiring a first image in front of a preset screen based on a preset image acquisition device, and sending the first image to a first detection model;

[0029] A first detection module, configured to detect the first image using a first detection model based on a first preset image detection algorithm to determine whether the first image contains a shooting device that has violated the regulations in screen-shooting behavior;

[0030] An image capture module, configured to capture an image of the camera that has illegally captured the screen in the image as a second image if the first image contains a camera that has illegally captured the screen, and send the second image to a second detection model;

[0031] The second detection module is used for the second detection model to detect the second image based on the second preset image detection algorithm to determine whether the second image contains a camera target. If the second image contains a camera target, it is determined that screen candid photography exists.

[0032] In one aspect of the present disclosure, there is provided an electronic device, comprising:

[0033] Processor; and

[0034] A memory having computer-readable instructions stored thereon, wherein the computer-readable instructions, when executed by the processor, implement the method according to any one of the above items.

[0035] In one aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method according to any one of the above items is implemented.

[0036] In an exemplary embodiment of the present disclosure, a method for identifying screen candid shooting based on cascade detection is disclosed, wherein the method comprises: collecting a first image in front of a preset screen based on a preset image acquisition device; a first detection model detects the first image based on a first preset image detection algorithm to determine whether the first image contains a mobile phone; if the first image contains a mobile phone, an image of the mobile phone in the image is intercepted as a second image; a second detection model detects the second image based on a second preset image detection algorithm to determine whether the second image contains a camera, and if the second image contains a camera, it is determined that there is screen candid shooting. The present disclosure adopts a cascade detection algorithm, takes a low-cost RGB camera as input, and only needs to use the processor of a working computer (without a GPU graphics card) to realize real-time identification of illegal screen shooting behavior to prevent illegal information leakage.

[0037] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The above and other features and advantages of the present disclosure will become more apparent by describing in detail example embodiments thereof with reference to the attached drawings.

[0039] Figure 1 A flow chart of a method for identifying screen candid photography based on cascade detection according to an exemplary embodiment of the present disclosure is shown;

[0040] Figure 2 A logic diagram of a screen candid camera recognition method based on cascade detection according to an exemplary embodiment of the present disclosure is shown;

[0041] Figure 3 A schematic diagram of the structure of a second detection model of a screen candid camera recognition method based on cascade detection according to an exemplary embodiment of the present disclosure is shown;

[0042] Figure 4 A schematic block diagram of a screen candid camera recognition device based on cascade detection according to an exemplary embodiment of the present disclosure is shown;

[0043] Figure 5 A block diagram schematically shows an electronic device according to an exemplary embodiment of the present disclosure;

[0044] Figure 6 A schematic diagram of a computer-readable storage medium according to an exemplary embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0045] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be comprehensive and complete and will fully convey the concepts of the example embodiments to those skilled in the art. The same reference numerals in the figures represent the same or similar parts, and thus their repeated description will be omitted.

[0046] In addition, the described features, structures or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced without one or more of the specific details, or other methods, components, materials, devices, steps, etc. may be adopted. In other cases, known structures, methods, devices, implementations, materials or operations are not shown or described in detail to avoid blurring the various aspects of the present disclosure.

[0047] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or these functional entities or parts of functional entities may be implemented in one or more software hardened modules, or these functional entities may be implemented in different networks and / or processor devices and / or microcontroller devices.

[0048] In this exemplary embodiment, a screen candid camera recognition method based on cascade detection is first provided; Figure 1As shown in , the screen candid camera recognition method based on cascade detection may include the following steps:

[0049] Step S110, capturing a first image in front of a preset screen based on a preset image capturing device, and sending the first image to a first detection model;

[0050] Step S120: the first detection model detects the first image based on a first preset image detection algorithm to determine whether the first image contains a shooting device that has violated the regulations in taking pictures of the screen;

[0051] Step S130: if the first image contains a camera that has illegally captured the screen, an image of the camera that has illegally captured the screen in the image is captured as a second image, and the second image is sent to a second detection model;

[0052] Step S140: The second detection model detects the second image based on a second preset image detection algorithm to determine whether the second image contains a camera target. If the second image contains a camera target, it is determined that screen candid photography has occurred.

[0053] In an exemplary embodiment of the present disclosure, a method for identifying screen candid shooting based on cascade detection is disclosed, wherein the method comprises: collecting a first image in front of a preset screen based on a preset image acquisition device; a first detection model detects the first image based on a first preset image detection algorithm to determine whether the first image contains a mobile phone; if the first image contains a mobile phone, an image of the mobile phone in the image is intercepted as a second image; a second detection model detects the second image based on a second preset image detection algorithm to determine whether the second image contains a camera, and if the second image contains a camera, it is determined that there is screen candid shooting. The present disclosure adopts a cascade detection algorithm, takes a low-cost RGB camera as input, and only needs to use the processor of a working computer (without a GPU graphics card) to realize real-time identification of illegal screen shooting behavior to prevent illegal information leakage.

[0054] Next, a screen candid camera recognition method based on cascade detection in this example embodiment will be further described.

[0055] Embodiment 1:

[0056] In step S110, a first image in front of a preset screen may be captured based on a preset image capture device, and the first image may be sent to a first detection model.

[0057] In the embodiment of this example, the method further includes:

[0058] The preset image acquisition device is an RGB camera with an image processor integrated with the host of the preset screen.

[0059] In step S120, the first detection model may be used to detect the first image based on a first preset image detection algorithm to determine whether the first image contains a shooting device that violates the regulations in screen capturing behavior.

[0060] In the embodiment of this example, the method further includes:

[0061] The first preset image detection algorithm is the YOLOX-s algorithm. Based on the YOLOX-s algorithm, the first image is detected to determine whether the first image contains a mobile phone target.

[0062] In the embodiment of this example, the method further includes:

[0063] The first image is detected based on a first preset image detection algorithm. If the first image does not contain a mobile phone target, it is determined that there is no screen candid photography behavior.

[0064] In step S130, if the first image includes a shooting device that has engaged in illegal screen-shooting behavior, an image of the shooting device that has engaged in illegal screen-shooting behavior in the image may be captured as a second image, and the second image may be sent to a second detection model.

[0065] In the embodiment of this example, the method further includes:

[0066] If the first image contains a mobile phone target, an image of the mobile phone target in the image is captured as a second image, and the second image is sent to a second detection model.

[0067] In step S140, the second detection model can detect the second image based on the second preset image detection algorithm to determine whether the second image contains a camera target. If the second image contains a camera target, it is determined that screen candid photography exists.

[0068] In the embodiment of this example, the method further includes:

[0069] The second preset image detection algorithm includes a Backbone module, a Neck module, and a head module of YOLOX.

[0070] In the embodiment of this example, the method further includes:

[0071] The Backbone module includes 3 groups of CONV+CBAM attention modules, wherein the first group CONV is 4 layers of convolution and maximum pooling layer, and the image resolution is downsampled to 28*28*256, the second group CONV is 6 layers of convolution and maximum pooling layer, and the image resolution is downsampled to 14*14*512, and the third group CONV is 4 layers of convolution and maximum pooling layer, and the image resolution is downsampled to 7*7*1024;

[0072] The Neck module concatenates the 7*7*1024 feature map with the 14*14*512 feature map in the channel dimension to obtain a 14*14*1536 feature map.

[0073] The head module of YOLOX receives the 14*14*1536 input CBAM attention module and the feature map of 7*7*1024 resolution and generates the detection result.

[0074] Embodiment 2:

[0075] In the embodiment of this example, the present invention will use a cascade detection algorithm to detect the solution of the mobile phone camera to realize the hidden camera recognition of the screen. Figure 2 As shown, the original image captured by the camera is first input into the detection model 1 to determine whether there is a mobile phone device. If there is no mobile phone device, it means that there is no candid shooting. However, when a mobile phone device appears, the mobile phone target is cut and processed and sent to the detection model 2 to detect whether there is a camera target. If there is a camera target, it is determined that there is candid shooting, otherwise it is normal.

[0076] In the embodiment of this example, both detection model 1 and detection model 2 are 2D target detection algorithms, where detection model 1 is the YOLOX-s algorithm, which directly inputs the original 2D image captured by the camera and detects the mobile phone target in the image through model reasoning. If there is no mobile phone device in the image, it is determined that there is no candid photography behavior. For the detected mobile phone device, the mobile phone target will be intercepted and input into detection model 2 for further judgment.

[0077] In the embodiment of this example, since the input image of detection model 2 is a mobile phone target selected by a frame, the length and width of its input image are usually less than 100 pixels. When facing a low-resolution input image, if a conventional target detection model similar to detection model 1 is used, the input target will completely lose its texture information after the common multiple downsampling operation, which seriously affects the detection accuracy. To address this problem, the present application designs detection model 2, the specific structure of which is as follows: Figure 3As shown in the figure, there are mainly 3 groups of CONV+CBAM attention modules in the Backbone of detection model 2. The first group of CONV is 4 layers of convolution and maximum pooling layer, which downsamples the image resolution to 28*28*256. The second group of CONV is 6 layers of convolution and maximum pooling layer, which downsamples the image resolution to 14*14*512. The third group of CONV is 4 layers of convolution and maximum pooling layer, which downsamples the image resolution to 7*7*1024. Then in the Neck part, the 7*7*1024 feature map is upsampled and concatenated with the 14*14*512 feature map in the channel dimension to obtain a 14*14*1536 feature map. Finally, the 14*14*1536 is input into the CBAM attention module and concatenated with the 7*7*1024 resolution feature map. Figure 1 Then, the data are sent to the head module of YOLOX to get the final result.

[0078] In the embodiment of this example, the model deployment details include that the detection algorithm in the entire system is deployed using the openvino tool, and GPU is not used for reasoning. This can greatly improve the wide application of the system, and any ordinary computer can be deployed and run, while also reducing the difficulty of system deployment and installation. At the same time, the detection frame rate can reach 15 frames per second, which fully meets the real-time monitoring needs.

[0079] In the embodiment of this example, the present invention only needs to use a single visible light camera, the operating environment does not rely on the GPU graphics card, the application scenarios are wider, the installation and deployment are more convenient, the cost is low and the accuracy is high; the customized detection model 2 in the present invention takes into account the two advantages of lightweight and high precision, and is combined with the entire recognition system to realize efficient and accurate screen candid camera recognition.

[0080] It should be noted that, although the steps of the method in the present disclosure are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.

[0081] In addition, in this exemplary embodiment, a screen candid camera recognition device based on cascade detection is also provided. Figure 4 As shown, the screen candid camera recognition device 400 based on cascade detection may include: an image acquisition module 410, a first detection module 420, an image interception module 430 and a second detection module 440. Among them:

[0082] An image acquisition module 410 is used to acquire a first image in front of a preset screen based on a preset image acquisition device, and send the first image to a first detection model;

[0083] A first detection module 420, configured to detect the first image using a first detection model based on a first preset image detection algorithm to determine whether the first image contains a shooting device that has violated the regulations in taking pictures of the screen;

[0084] An image capture module 430 is configured to capture an image of the camera that has illegally captured the screen in the image as a second image if the first image contains a camera that has illegally captured the screen, and send the second image to a second detection model;

[0085] The second detection module 440 is used for the second detection model to detect the second image based on the second preset image detection algorithm to determine whether the second image contains a camera target. If the second image contains a camera target, it is determined that screen candid photography exists.

[0086] The specific details of each of the above-mentioned screen candid photography recognition device modules based on cascade detection have been described in detail in the corresponding screen candid photography recognition method based on cascade detection, so they will not be repeated here.

[0087] It should be noted that although several modules or units of a screen candid camera recognition device 400 based on cascade detection are mentioned in the above detailed description, this division is not mandatory. In fact, according to an embodiment of the present disclosure, the features and functions of two or more modules or units described above can be concretized in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided into multiple modules or units to be concretized.

[0088] In addition, in an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided.

[0089] It will be appreciated by those skilled in the art that various aspects of the present invention may be implemented as systems, methods or program products. Therefore, various aspects of the present invention may be specifically implemented in the following forms, namely: complete hardware embodiments, complete software embodiments (including firmware, microcode, etc.), or embodiments combining hardware and software aspects, which may be collectively referred to herein as "circuits", "modules" or "systems".

[0090] Refer to the following Figure 5 An electronic device 500 according to such an embodiment of the present invention is described. Figure 5 The electronic device 500 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0091] like Figure 5As shown, the electronic device 500 is in the form of a general computing device. The components of the electronic device 500 may include but are not limited to: at least one processing unit 510, at least one storage unit 520, a bus 530 connecting different system components (including the storage unit 520 and the processing unit 510), and a display unit 540.

[0092] The storage unit stores program codes, which can be executed by the processing unit 510, so that the processing unit 510 performs the steps according to various exemplary embodiments of the present invention described in the above “Exemplary Method” section of this specification. For example, the processing unit 510 can perform the following steps: Figure 1 Steps S110 to S140 shown in FIG.

[0093] The storage unit 520 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 5201 and / or a cache storage unit 5202 , and may further include a read-only storage unit (ROM) 5203 .

[0094] The storage unit 520 may also include a program / utility 5204 having a set (at least one) of program modules 5205, such program modules 5205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0095] Bus 530 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0096] The electronic device 500 may also communicate with one or more external devices 570 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 500, and / or may communicate with any device that enables the electronic device 500 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 550. Furthermore, the electronic device 500 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 560. As shown, the network adapter 560 communicates with other modules of the electronic device 500 via a bus 530. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 500, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0097] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the example embodiments described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the embodiment of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiment of the present disclosure.

[0098] In an exemplary embodiment of the present disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the above method of the present specification is stored. In some possible embodiments, various aspects of the present invention can also be implemented in the form of a program product, which includes a program code, and when the program product is run on a terminal device, the program code is used to enable the terminal device to perform the steps according to various exemplary embodiments of the present invention described in the above "Exemplary Method" section of the present specification.

[0099] refer to Figure 6 As shown, a program product 600 for implementing the above method according to an embodiment of the present invention is described, which can adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto. In this document, a readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, an apparatus or a device.

[0100] The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0101] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, in which readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Readable signal media may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0102] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0103] Program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0104] In addition, the above-mentioned figures are only schematic illustrations of the processes included in the method according to an exemplary embodiment of the present invention, and are not intended to be limiting. It is easy to understand that the processes shown in the above-mentioned figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0105] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary technical means in the art that are not disclosed in the present disclosure. The specification and examples are to be considered as exemplary only, and the true scope and spirit of the present disclosure are indicated by the claims.

[0106] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A screen candid camera recognition method based on cascade detection, characterized in that: The method comprises: Capturing a first image in front of a preset screen based on a preset image acquisition device, and sending the first image to a first detection model; The first detection model detects the first image based on a first preset image detection algorithm to determine whether the first image contains a shooting device that violates the regulations in screen-shooting behavior; If the first image contains a shooting device that has violated the regulations on screen capture, an image of the shooting device that has violated the regulations on screen capture in the image is captured as a second image, and the second image is sent to a second detection model; The second detection model detects the second image based on a second preset image detection algorithm to determine whether the second image contains a camera target. If the second image contains a camera target, it is determined that screen candid photography has occurred.

2. The method according to claim 1, characterized in that The method further comprises: The preset image acquisition device is an RGB camera with an image processor integrated with the host of the preset screen.

3. The method according to claim 1, characterized in that The method further comprises: The first preset image detection algorithm is the YOLOX-s algorithm. Based on the YOLOX-s algorithm, the first image is detected to determine whether the first image contains a mobile phone target.

4. The method according to claim 3, characterized in that The method further comprises: The first image is detected based on a first preset image detection algorithm. If the first image does not contain a mobile phone target, it is determined that there is no screen candid photography behavior.

5. The method according to claim 3, characterized in that The method further comprises: If the first image contains a mobile phone target, an image of the mobile phone target in the image is captured as a second image, and the second image is sent to a second detection model.

6. The method according to claim 5, characterized in that The method further comprises: The second preset image detection algorithm includes a Backbone module, a Neck module, and a head module of YOLOX.

7. The method according to claim 6, characterized in that The method further comprises: The Backbone module includes 3 groups of CONV+CBAM attention modules, wherein the first group CONV is 4 layers of convolution and maximum pooling layer, and the image resolution is downsampled to 28*28*256, the second group CONV is 6 layers of convolution and maximum pooling layer, and the image resolution is downsampled to 14*14*512, and the third group CONV is 4 layers of convolution and maximum pooling layer, and the image resolution is downsampled to 7*7*1024; The Neck module concatenates the 7*7*1024 feature map with the 14*14*512 feature map in the channel dimension to obtain a 14*14*1536 feature map. The head module of YOLOX receives the 14*14*1536 input CBAM attention module and the feature map of 7*7*1024 resolution and generates the detection result.

8. A screen candid camera recognition device based on cascade detection, characterized in that: The device comprises: An image acquisition module, used for acquiring a first image in front of a preset screen based on a preset image acquisition device, and sending the first image to a first detection model; A first detection module, configured to detect the first image using a first detection model based on a first preset image detection algorithm to determine whether the first image contains a shooting device that has violated the regulations in screen-shooting behavior; An image capture module, configured to capture an image of the camera that has illegally captured the screen in the image as a second image if the first image contains a camera that has illegally captured the screen, and send the second image to a second detection model; The second detection module is used for the second detection model to detect the second image based on the second preset image detection algorithm to determine whether the second image contains a camera target. If the second image contains a camera target, it is determined that screen candid photography exists.

9. An electronic device, characterized in that: include Processor; and A memory having computer-readable instructions stored thereon, wherein the computer-readable instructions, when executed by the processor, implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images