Video backtracking method and device, electronic equipment and readable storage medium

Abstract

The invention discloses a video backtracking method and device, electronic equipment and a readable storage medium, which are applied to the technical field of video surveillance, and the method comprises the following steps: after an awakening signal of a system is triggered and before the system is completely awakened, collecting brightness information and infrared information of multiple missing frames; after the system is completely awakened, collecting color video information of a preset duration; and the brightness information, the infrared information and the color video information of the multiple missing frames are analyzed and processed to obtain the video information of the time period from the time when the wake-up signal of the system is triggered to the time when the system is completely awakened, so that the video backtracking is realized, and the security and the security effect of the security system are improved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of video surveillance technology, and in particular to a video backtracking method, device, electronic device and computer-readable storage medium. Background Art

[0002] In current security camera systems, when the system enters low power consumption, the image sensor's photo and video functions will be disabled. Only when an external trigger event wakes up the system will the security camera system restart and initialize and start the image sensor. Therefore, during the period from the occurrence of the trigger event to the system waking up the image sensor, the security camera system cannot record real-time video and image information, but this period may also contain very important video information. This period may last for several seconds or even more than ten seconds. The lack of video during this period affects the security effect of the security camera system.

[0003] In view of this, how to supplement the video information during this period is particularly important. Summary of the invention

[0004] The purpose of the embodiments of the present invention is to provide a video retracing method, device, electronic device and computer-readable storage medium, which can realize video retracing during use to improve the security and security effect of the security system.

[0005] In order to solve the above technical problems, an embodiment of the present invention provides a video backtracking method, comprising:

[0006] After a wake-up signal of the system is triggered and before the system is fully awakened, collecting brightness information and infrared information of multiple missing frames;

[0007] After the system is fully awakened, collecting color video information of a preset duration;

[0008] The brightness information, infrared information, and color video information of the multiple missing frames are analyzed and processed to obtain video information of the time period from when the wake-up signal of the system is triggered to when the system is fully awakened.

[0009] Optionally, analyzing and processing the brightness information, infrared information and color video information of the multiple missing frames to obtain video information after the wake-up signal is triggered and before the system wakes up includes:

[0010] Analyzing and processing the video information to obtain brightness information, infrared information and a biological information model of each frame of color image;

[0011] For each missing frame, determining background information of the missing frame according to brightness information corresponding to the missing frame and brightness information of each color image frame;

[0012] Determine the target biological posture information corresponding to the missing frame based on the infrared information of the missing frame and the infrared information of each frame of the color image and the biological information model;

[0013] Obtaining color image information corresponding to the missing frame according to the color image corresponding to the target biological posture information and the background information corresponding to the missing frame;

[0014] Based on the color image information corresponding to the missing frames of each frame, video information from after the wake-up signal is triggered to before the system wakes up is obtained.

[0015] Optionally, the analyzing and processing the video information to obtain brightness information, infrared information and a biological information model of each frame of color image includes:

[0016] Identify and analyze the video information to obtain background information and biological information of each frame of color image;

[0017] Establishing a biological information model corresponding to the color image based on the background information and the biological information;

[0018] For each frame of the color image, corresponding brightness information and infrared information are proposed;

[0019] Each posture contour model is determined according to the infrared information, and each posture contour model is made to correspond to a corresponding biological information model.

[0020] Optionally, determining the background information of the missing frame according to the brightness information corresponding to the missing frame and the brightness information of each frame of the color image includes:

[0021] Based on the brightness information of the missing frame, obtaining brightness information of each pixel of the missing frame;

[0022] According to the brightness information of each frame of the color image, the brightness information of each pixel point of each frame of the color image is obtained;

[0023] For each pixel of the missing frame, comparing the brightness information of the pixel with the brightness information of the corresponding pixel of each frame of the color image, and determining the target pixel with the closest brightness information;

[0024] The pixel of the target pixel is assigned to the corresponding pixel on the missing frame to obtain the pixel of each pixel on the missing frame, so as to determine the background information of the missing frame.

[0025] Optionally, the determining the target biological posture information corresponding to the missing frame based on the infrared information of the missing frame and the infrared information of each frame of the color image and the biological information model includes:

[0026] A target posture contour model is determined based on the infrared information of the missing frame, each of the posture contour models and the corresponding biological information model.

[0027] Optionally, determining a target posture contour model based on the infrared information of the missing frame, each of the posture contour models and a corresponding biological information model includes:

[0028] According to the infrared information of the missing frame, a target posture contour model having the highest similarity to the infrared information is matched from each of the posture contour models.

[0029] Optionally, obtaining the color image information corresponding to the missing frame according to the color image corresponding to the target biological posture information and the background information corresponding to the missing frame includes:

[0030] The corresponding color image information on the color image corresponding to the target posture contour model is assigned to the corresponding position on the background information of the missing frame to obtain the color image information corresponding to the missing frame.

[0031] Optionally, after obtaining the video information of the time period from when the wake-up signal of the system is triggered to when the system is fully awakened, the method further includes:

[0032] The video information is spliced ​​with the color video information of the preset duration.

[0033] The embodiment of the present invention further provides a video retracing device, including:

[0034] A first acquisition module, used for acquiring brightness information and infrared information of multiple missing frames after a wake-up signal of the system is triggered and before the system is fully awakened;

[0035] A second acquisition module is used to acquire color video information of a preset duration after the system is fully awakened;

[0036] The processing module is used to analyze and process the brightness information, infrared information and color video information of multiple missing frames to obtain the video information of the time period from when the wake-up signal of the system is triggered to when the system is fully awakened.

[0037] An embodiment of the present invention further provides an electronic device, including:

[0038] Memory for storing computer programs;

[0039] A processor is used to implement the steps of the video retracing method as described above when executing the computer program.

[0040] An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the video tracing method described above are implemented.

[0041] A video backtracking method, device, electronic device and computer-readable storage medium are provided in an embodiment of the present invention. The method includes: collecting brightness information and infrared information of multiple missing frames after the system wake-up signal is triggered and before the system is fully awakened; collecting color video information of a preset duration after the system is fully awakened; analyzing and processing the brightness information, infrared information and color video information of the multiple missing frames to obtain video information of the time period between the system wake-up signal being triggered and the system being fully awakened.

[0042] It can be seen that in the embodiment of the present invention, by collecting the brightness information and infrared information of multiple missing frames after the system wake-up signal is triggered and before the system is fully awakened, and collecting the color video information of a preset length after the system is fully awakened, and then analyzing and processing the brightness information, infrared information, and color video information of the multiple missing frames, it is possible to obtain the video information during the period from when the system wake-up signal is triggered to when the system is fully awakened, thereby realizing the backtracking of the video to improve the safety and security effect of the security system. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the prior art and the drawings required for use in the embodiments are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0044] Figure 1 A schematic diagram of a flow chart of a video backtracking method provided by an embodiment of the present invention;

[0045] Figure 2 A schematic diagram of a flow chart of another video retracing method provided by an embodiment of the present invention;

[0046] Figure 3 A schematic diagram of a flow chart of another video retracing method provided by an embodiment of the present invention;

[0047] Figure 4 A schematic diagram of brightness information and color images collected by an image sensor before and after being awakened provided by an embodiment of the present invention;

[0048] Figure 5 A schematic diagram of infrared information collected by an image sensor before and after being awakened provided by an embodiment of the present invention;

[0049] Figure 6 A schematic diagram of the structure of a video retracing device provided by an embodiment of the present invention;

[0050] Figure 7 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention;

[0051] Figure 8 A schematic diagram of the structure of a computer-readable storage medium provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0052] The embodiments of the present invention provide a video retracing method, device, electronic device and computer-readable storage medium, which can realize video retracing during use to improve the security and security effect of a security system.

[0053] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0054] Please refer to Figure 1 , Figure 1 A schematic flow chart of a video retracing method provided by an embodiment of the present invention. The method comprises:

[0055] S110: after the system wake-up signal is triggered and before the system is fully awakened, collect brightness information and infrared information of multiple missing frames;

[0056] It should be noted that when the security camera system enters low power consumption mode, it switches to brightness and infrared acquisition mode. After the system wake-up signal is triggered, the system starts to wake up. Before the system is fully awakened, the brightness information and infrared information of each missing frame are collected. The missing frame refers to the data frame from the time when the system wake-up signal is triggered to the time when the system is fully awakened.

[0057] Specifically, before the system is fully awakened, the brightness information and infrared information will not stop updating, and the system saves all brightness information and infrared information from the time when the wake-up signal is triggered to the time when the system completely exits the low power consumption mode.

[0058] S120: After the system is fully awakened, color video information of a preset duration is collected;

[0059] Specifically, after the system is fully awakened (that is, the system completely exits the low power consumption mode), color RGB video recording starts, and color video information of a preset duration is returned.

[0060] S130: Analyze and process the brightness information, infrared information, and color video information of the multiple missing frames to obtain video information of the time period from when the system wake-up signal is triggered to when the system is fully awakened.

[0061] It should be noted that, by combining the color video information of the preset time after the system is fully awakened and the brightness information and infrared information of multiple missing frames after the system awakening signal is triggered and before the system is fully awakened, the color image information of each missing frame in the time period between the system awakening signal being triggered and the system being fully awakened can be obtained, thereby obtaining the video information during this period and completing the video backtracking. Specifically, the video data can be backtracked through the fitting algorithm.

[0062] The video backtracking process can also refer to Figure 2 That is, when the system is in low power mode, the system's image sensor enters brightness and infrared mode, and the system determines whether there is an external trigger to wake up the system. If so, multiple frames of brightness information and infrared information are collected and saved. If not, the system continues to be in brightness and infrared mode. During the process of collecting and saving multiple frames of brightness information and infrared information, it can continue to determine whether the wake-up is completed. If the wake-up is not completed, the brightness information and infrared information continue to be collected and saved. If the wake-up is completed, the system starts to collect and save RGB images of a preset length, and further uses a fitting algorithm to combine the collected and saved brightness information, infrared information and RGB images to perform video backtracking to obtain video data with completed backtracking.

[0063] Furthermore, the process of analyzing and processing the brightness information, infrared information and color video information of the multiple missing frames in S130 to obtain the video information after the wake-up signal is triggered and before the system wakes up may include:

[0064] Analyze and process the video information to obtain the brightness information, infrared information and biological information model of each frame of color image;

[0065] For each missing frame, determining background information of the missing frame according to brightness information corresponding to the missing frame and brightness information of each color image frame;

[0066] Based on the infrared information of the missing frame and the infrared information of each color image frame and the biological information model, the target biological posture information corresponding to the missing frame is determined;

[0067] According to the color image corresponding to the target biological posture information and the background information corresponding to the missing frame, the color image information corresponding to the missing frame is obtained;

[0068] Based on the color image information respectively corresponding to each missing frame, the video information from after the wake-up signal is triggered to before the system wakes up is obtained.

[0069] It should be noted that in actual applications, color video information includes multiple frames of color images. By extracting and recognizing video information of a preset length, the brightness information and infrared information of each frame of color image can be obtained, and the biological information model of each frame of image can also be obtained.

[0070] Furthermore, the above process of analyzing and processing the video information to obtain the brightness information, infrared information and biological information model of each frame of the color image may include:

[0071] Identify and analyze the video information to obtain the background information and biological information of each frame of color image;

[0072] Establishing a bioinformatics model corresponding to the color image based on background information and bioinformatics;

[0073] For each frame of color image, the corresponding brightness information and infrared information are proposed;

[0074] Each posture contour model is determined according to the infrared information, and each posture contour model is corresponded to the corresponding biological information model.

[0075] Specifically, in order to improve the accuracy of backtracking, each color image in the video information can be segmented and extracted to obtain the background information and biological information corresponding to each color image. Then, the corresponding background model (i.e., the corresponding brightness information) and biological information model (i.e., the corresponding infrared information) can be further established by combining the background information and biological information of each color image. The brightness information and infrared information of each color image can also be extracted. The posture contour model corresponding to each color image can be determined based on the infrared information. Of course, when there are multiple organisms in the color infrared image, the posture contour model corresponding to each organism in the color image can be determined. Then, the corresponding biological information model can be matched for each posture contour model, wherein the corresponding color image and its position in the color image can be determined based on the biological information model.

[0076] It should be noted that, for each missing frame, the background information of the missing frame can be obtained according to the brightness information of the missing frame combined with the brightness information of each color image frame, which can be specifically achieved in the following way:

[0077] Based on the brightness information of the missing frame, the brightness information of each pixel of the missing frame is obtained;

[0078] According to the brightness information of each frame of color image, the brightness information of each pixel point of each frame of color image is obtained;

[0079] For each pixel of the missing frame, compare the brightness information of the pixel with the brightness information of the corresponding pixel of each frame of the color image to determine the target pixel with the closest brightness information;

[0080] The pixel value of the target pixel point is assigned to the corresponding pixel point on the missing frame, and the pixel value of each pixel point on the missing frame is obtained to determine the background information of the missing frame.

[0081] Specifically, for each missing frame, the brightness information of each pixel on the missing frame can be obtained based on the brightness information corresponding to the missing frame. Of course, the brightness information of each pixel on the color image can also be obtained based on the brightness information of each frame of the color image. Then, the brightness information of a pixel on the missing frame is compared with the brightness information of the pixel at the same position on each frame of the color image, so that the pixel with the closest brightness information (that is, the highest brightness information similarity) can be determined, and the pixel of the pixel on the corresponding color image is assigned to the corresponding pixel on the missing frame, so as to determine the pixel of a pixel of the missing frame. According to this method, the corresponding pixel can be determined for each pixel on the missing frame, so that the background information of the missing frame can be accurately obtained, that is, the background information of the image corresponding to the missing frame can be obtained. For each missing frame, the background information corresponding to each missing frame can be obtained.

[0082] It should be noted that after obtaining the background information of the image corresponding to the missing frame, the target biological posture information corresponding to the missing frame can be further determined according to the infrared information of the missing frame combined with the infrared information of each color image frame and the biological information model. The specific implementation process may include:

[0083] The target posture contour model can be further determined based on the infrared information of the missing frame, each posture contour model obtained above and the corresponding biological information model. Specifically, the posture contour model with the highest similarity to the infrared information can be matched from various posture contour models based on the infrared information of the missing frame, and the posture contour model with the highest similarity can be used as the target posture contour model, so as to accurately determine the posture of the organism in the image corresponding to the missing frame.

[0084] It should be noted that after determining the target posture contour model, the color image information of the corresponding position on the color image corresponding to the target posture contour model can be further assigned to the corresponding position on the background information of the missing frame, so that the complete color image information corresponding to the missing frame can be obtained, and further, the color image information corresponding to each missing frame can be obtained. Then, based on the color image information corresponding to each missing frame, the video information from the time when the wake-up signal is triggered to the time when the system wakes up can be obtained.

[0085] Specifically, after obtaining the video information from when the wake-up signal is triggered to before the system wakes up, the end of the video information can be spliced ​​with the beginning of the color video information of a preset duration to obtain complete video information. The present invention uses less (brightness and infrared information) to restore the real retrospective video information. The method involved in this invention is flexible in application, highly scalable, and easy to integrate, solving the problem of incomplete video information of the triggering event.

[0086] Below Figures 3 to 5 Take this as an example to illustrate:

[0087] For example, the image sensor in the security camera system can collect 10s of brightness information and infrared information from the beginning of wake-up to the full wake-up. The brightness information during this period can be represented as A, and the brightness data of each missing frame is arranged in time as A1, A2...An (such as Figure 4 As shown); the infrared data information can be represented as B, and the infrared data of each missing frame is arranged in time as B1, B2...Bn (as shown Figure 5 shown).

[0088] After the image sensor is fully awakened, it can collect 5 frames (or n frames) of video information. The brightness information of each frame can be represented by a, and the brightness data of each frame is arranged in time as a1, a2, a3...an (such as Figure 4 As shown); infrared information can be represented as b, and each frame of data is arranged in time as b1, b2...bn (as shown Figure 5 The specific implementation process of video backtracking is as follows:

[0089] Using the video data captured in RGB mode (all n frames of RGB images), the background information and biological information are distinguished for each frame of color image, and based on the background information and biological information of each frame of color image, an image model (background model and biological model) is established, that is, one frame image model = background information model + biological information model. It should be noted that the background information in the infrared image has a small difference with the ambient temperature, while the biological information has a large difference with the ambient temperature.

[0090] From the video data shot in color RGB mode, the corresponding frame-by-frame color image brightness information (a1~an) and infrared information (b1~bn) are extracted respectively, and the brightness information of each pixel point of the information missing frame A1 is compared with the brightness information of the corresponding pixel points from a1 to an in turn according to the coordinates, and the am closest to the brightness information of A1 is found (am refers to the brightness information of the corresponding pixel point in the am-th frame RGB image), and the RGB image pixel of the pixel point corresponding to the brightness information is assigned to the corresponding pixel point on A1. At this point, the RGB image backtracking of one pixel is completed. By analogy, when all the pixels in A1 are assigned the corresponding pixels of the RGB image and the brightness is adjusted, the background information of the A1 frame image is completed. The biological model obtained above is matched one by one with the infrared information of b1 to bn, and a corresponding biological posture model is established. The corresponding posture contour model (such as squatting, standing, walking, front, side, back, raising head, lowering head, swinging arms, jumping and other details) can be further extracted. The infrared information B1 of the missing frame and the posture contour models of b0 to bn are compared one by one to determine the closest target posture contour model. The RGB image information corresponding to the target posture contour model is assigned to B1, that is, assigned to the corresponding position of the missing frame, so that combined with the background information of the missing frame, the color image of the corresponding missing frame can be obtained. The background and biological information are fitted, and each frame is fitted by the above method to obtain the color image of each missing frame, thereby obtaining the video information from the time the wake-up signal is triggered to the time the system wakes up.

[0091] It can be seen that in the embodiment of the present invention, by collecting the brightness information and infrared information of multiple missing frames after the system wake-up signal is triggered and before the system is fully awakened, and collecting the color video information of a preset length after the system is fully awakened, and then analyzing and processing the brightness information, infrared information, and color video information of the multiple missing frames, it is possible to obtain the video information during the period from when the system wake-up signal is triggered to when the system is fully awakened, thereby realizing the backtracking of the video and ensuring the integrity of the video information, so as to improve the safety and security effect of the security system.

[0092] Based on the above embodiment, the embodiment of the present invention further provides a video retracing device. Figure 6 , the device comprises:

[0093] The first acquisition module 11 is used to acquire brightness information and infrared information of multiple missing frames after the system wake-up signal is triggered and before the system is fully awakened;

[0094] The second acquisition module 12 is used to acquire color video information of a preset duration after the system is fully awakened;

[0095] The processing module 13 is used to analyze and process the brightness information, infrared information, and color video information of the multiple missing frames to obtain the video information of the time period from when the system wake-up signal is triggered to when the system is fully awakened.

[0096] It should be noted that the video retracing device in the embodiment of the present invention has the same beneficial effects as the video retracing method provided in the above embodiment, and for the specific introduction of the video retracing method involved in the embodiment of the present invention, please refer to the above embodiment, and the embodiment of the present invention will not be repeated here.

[0097] Figure 7 A structural diagram of an electronic device provided in an embodiment of the present application, such as Figure 7 As shown, the electronic device includes: a memory 20 for storing a computer program;

[0098] The processor 21 is used to implement the steps of the video backtracking method in the above embodiment when executing a computer program.

[0099] The electronic device provided in this embodiment may include but is not limited to a smart phone, a tablet computer, a laptop computer or a desktop computer.

[0100] Among them, the processor 21 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 21 can be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 21 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 21 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 21 may also include an AI (Artificial Intelligence) processor, which is used to process computing operations related to machine learning.

[0101] The memory 20 may include one or more computer-readable storage media, which may be non-transitory. The memory 20 may also include a high-speed random access memory, and a non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In this embodiment, the memory 20 is at least used to store the following computer program 201, wherein, after the computer program is loaded and executed by the processor 21, the relevant steps of the video backtracking method disclosed in any of the aforementioned embodiments can be implemented. In addition, the resources stored in the memory 20 may also include an operating system 202 and data 203, etc., and the storage method may be short-term storage or permanent storage. Among them, the operating system 202 may include Windows, Unix, Linux, etc. Data 203 may include but is not limited to a set offset, etc.

[0102] In some embodiments, the electronic device may further include a display screen 22 , an input / output interface 23 , a communication interface 24 , a power source 25 , and a communication bus 26 .

[0103] Those skilled in the art will understand that Figure 7 The structure shown in the figure does not constitute a limitation on the electronic device, and may include more or fewer components than shown in the figure.

[0104] It is understandable that if the video retracing method in the above embodiment is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium to execute all or part of the steps of each embodiment method of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), electrically erasable programmable ROM, register, hard disk, removable disk, CD-ROM, magnetic disk or optical disk and other media that can store program codes.

[0105] Based on this, Figure 8 As shown, the embodiment of the present invention further provides a computer-readable storage medium, on which a computer program 31 is stored. When the computer program 31 is executed by a processor, the steps of the above-mentioned video tracing method are implemented.

[0106] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0107] It should also be noted that, in this specification, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the statement "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device including the element.

[0108] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0109] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0110] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A video backtracking method, characterized in that: include: After a wake-up signal of the system is triggered and before the system is fully awakened, collecting brightness information and infrared information of multiple missing frames; After the system is fully awakened, collecting color video information of a preset duration; The brightness information, infrared information, and color video information of the multiple missing frames are analyzed and processed to obtain video information of the time period from when the wake-up signal of the system is triggered to when the system is fully awakened.

2. The video retracing method according to claim 1, characterized in that: The analyzing and processing of the brightness information, infrared information and color video information of the multiple missing frames to obtain the video information after the wake-up signal is triggered and before the system wakes up includes: Analyzing and processing the video information to obtain brightness information, infrared information and a biological information model of each frame of color image; For each missing frame, determining background information of the missing frame according to brightness information corresponding to the missing frame and brightness information of each color image frame; Determine the target biological posture information corresponding to the missing frame based on the infrared information of the missing frame and the infrared information of each frame of the color image and the biological information model; Obtaining color image information corresponding to the missing frame according to the color image corresponding to the target biological posture information and the background information corresponding to the missing frame; Based on the color image information corresponding to the missing frames of each frame, video information from after the wake-up signal is triggered to before the system wakes up is obtained.

3. The video retracing method according to claim 2, characterized in that: The analyzing and processing of the video information to obtain brightness information, infrared information and a biological information model of each frame of color image includes: Identify and analyze the video information to obtain background information and biological information of each frame of color image; Establishing a biological information model corresponding to the color image based on the background information and the biological information; For each frame of the color image, corresponding brightness information and infrared information are proposed; Each posture contour model is determined according to the infrared information, and each posture contour model is made to correspond to a corresponding biological information model.

4. The video retracing method according to claim 3, characterized in that: The determining the background information of the missing frame according to the brightness information corresponding to the missing frame and the brightness information of each frame of the color image includes: Based on the brightness information of the missing frame, obtaining brightness information of each pixel of the missing frame; According to the brightness information of each frame of the color image, the brightness information of each pixel point of each frame of the color image is obtained; For each pixel of the missing frame, comparing the brightness information of the pixel with the brightness information of the corresponding pixel of each frame of the color image, and determining the target pixel with the closest brightness information; The pixel of the target pixel is assigned to the corresponding pixel on the missing frame to obtain the pixel of each pixel on the missing frame, so as to determine the background information of the missing frame.

5. The video retracing method according to claim 3, characterized in that: The step of determining the target biological posture information corresponding to the missing frame based on the infrared information of the missing frame, the infrared information of each color image frame, and the biological information model comprises: A target posture contour model is determined based on the infrared information of the missing frame, each of the posture contour models and the corresponding biological information model.

6. The video retracing method according to claim 5, characterized in that: The step of determining a target posture contour model based on the infrared information of the missing frame, each posture contour model and a corresponding biological information model comprises: According to the infrared information of the missing frame, a target posture contour model having the highest similarity to the infrared information is matched from each of the posture contour models.

7. The video retracing method according to claim 6, characterized in that: The step of obtaining the color image information corresponding to the missing frame according to the color image corresponding to the target biological posture information and the background information corresponding to the missing frame comprises: The corresponding color image information on the color image corresponding to the target posture contour model is assigned to the corresponding position on the background information of the missing frame to obtain the color image information corresponding to the missing frame.

8. The video retracing method according to any one of claims 1 to 7, characterized in that: After obtaining the video information of the time period between when the wake-up signal of the system is triggered and when the system is fully awakened, the method further includes: The video information is spliced ​​with the color video information of the preset duration.

9. A video retracing device, characterized in that: include: A first acquisition module, used for acquiring brightness information and infrared information of multiple missing frames after a wake-up signal of the system is triggered and before the system is fully awakened; A second acquisition module, used for acquiring color video information of a preset duration after the system is fully awakened; The processing module is used to analyze and process the brightness information, infrared information and color video information of multiple missing frames to obtain the video information of the time period from when the wake-up signal of the system is triggered to when the system is fully awakened.

10. An electronic device, characterized in that: include: Memory for storing computer programs; A processor, configured to implement the steps of the video retracing method according to any one of claims 1 to 8 when executing the computer program.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the video tracing method according to any one of claims 1 to 8 are implemented.

Images