WO2020094088A1 - Procédé de capture d'image, caméra de surveillance et système de surveillance - Google Patents

Procédé de capture d'image, caméra de surveillance et système de surveillance Download PDF

Info

Publication number
WO2020094088A1
WO2020094088A1 PCT/CN2019/116202 CN2019116202W WO2020094088A1 WO 2020094088 A1 WO2020094088 A1 WO 2020094088A1 CN 2019116202 W CN2019116202 W CN 2019116202W WO 2020094088 A1 WO2020094088 A1 WO 2020094088A1
Authority
WO
WIPO (PCT)
Prior art keywords
face target
image
quality
video frame
face
Prior art date
Application number
PCT/CN2019/116202
Other languages
English (en)
Chinese (zh)
Inventor
王晶晶
Original Assignee
杭州海康威视数字技术股份有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 杭州海康威视数字技术股份有限公司 filed Critical 杭州海康威视数字技术股份有限公司
Publication of WO2020094088A1 publication Critical patent/WO2020094088A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10016—Video; Image sequence
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30168—Image quality inspection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30196—Human being; Person
    • G06T2207/30201—Face

Definitions

  • the present application relates to the technical field of video surveillance, in particular to an image capture method, surveillance camera and surveillance system.
  • the surveillance camera captures the face object appearing in the scene, and uploads the captured image to the comparison system.
  • the comparison system extracts the face features from the captured image, and extracts the extracted face features and the black list face features Perform a comparison, and if the similarity of the comparison is greater than a certain threshold, an alarm is generated.
  • the surveillance camera detects the face target, it will capture the face target and upload the captured image to the comparison system.
  • the captured image is likely to appear
  • the face target in occlusion, blur, etc. affects the similarity of the comparison, causing false alarms or false negatives, and the accuracy of the comparison results is low.
  • the purpose of the embodiments of the present application is to provide an image capture method, a monitoring camera, and a monitoring system, so as to ensure that the comparison result of the comparison system has high accuracy.
  • the specific technical solutions are as follows:
  • an image capture method which includes:
  • the face target image is uploaded to the comparison system as a captured image.
  • the method further includes:
  • the next video frame is obtained as the current video frame in the order of first to last video frames
  • the step of determining the face target image of the same face target in the current video frame and the previous video frame includes:
  • the face target frame in the current video frame is assigned the same target frame identifier as the face target frame in the previous video frame with the highest matching degree;
  • the face target image in the face target frame with the same target frame identifier as the previous video frame in the current video frame is the face target image of the same face target.
  • the method further includes:
  • For the same face target determine whether the image quality of the face target image of the face target in the current video frame is better than the image quality of the cached face target image of the face target;
  • the face target image and image quality of the face target in the current video frame are cached
  • the cached face target image of the face target is uploaded to the comparison system as a captured image.
  • the steps of performing quality analysis on the face target image to obtain the image quality of the face target image include:
  • the face target quality parameters of the face target image include at least one or more of the degree of face occlusion, face clarity, and posture;
  • the image quality of the face target image is determined.
  • the image quality includes an image quality score value
  • the steps of performing quality analysis on the face target image to obtain the image quality of the face target image include:
  • the steps to determine whether the image quality meets the preset quality conditions include:
  • an embodiment of the present application provides a surveillance camera, including a surveillance camera, a processor, and a memory, where,
  • Surveillance camera used to collect the current video frame
  • Memory used to store computer programs
  • the processor when used to execute the computer program stored on the memory, implements the following steps:
  • the face target image is uploaded to the comparison system as a captured image.
  • the next video frame is obtained as the current video frame in the order of first to last video frames
  • the processor implements the step of determining the face target image of the same face target in the current video frame and the previous video frame, the specific steps are as follows:
  • the face target frame in the current video frame is assigned the same target frame identifier as the face target frame in the previous video frame with the highest matching degree;
  • the face target image in the face target frame with the same target frame identifier as the previous video frame in the current video frame is the face target image of the same face target.
  • For the same face target determine whether the image quality of the face target image of the face target in the current video frame is better than the image quality of the cached face target image of the face target;
  • the face target image and image quality of the face target in the current video frame are cached
  • the cached face target image of the face target is uploaded to the comparison system as a captured image.
  • the processor when the processor implements the step of performing quality analysis on the face target image to obtain the image quality of the face target image, it specifically implements the following steps:
  • the face target quality parameters of the face target image include at least one or more of the degree of face occlusion, face clarity, and posture;
  • the image quality of the face target image is determined.
  • the image quality includes an image quality score value
  • the processor implements the step of performing quality analysis on the face target image to obtain the image quality of the face target image, it specifically implements the following steps:
  • the processor When the processor implements the step of judging whether the image quality meets the preset quality condition, it specifically implements the following steps:
  • an embodiment of the present application provides a machine-readable storage medium in which a computer program is stored.
  • the computer program is executed by a processor, the image capture method provided in the first aspect of the embodiment of the present application is implemented .
  • an embodiment of the present application provides an application program for execution at runtime: the image capturing method provided in the first aspect of the embodiment of the present application.
  • an embodiment of the present application provides a monitoring system, including a monitoring camera and a comparison system;
  • Surveillance camera used to collect the current video frame; perform face target detection on the current video frame to determine the face target image in the current video frame; perform quality analysis on the face target image to obtain the image quality of the face target image; Whether the image quality meets the preset quality conditions; if it meets, upload the face target image as a captured image to the comparison system;
  • the comparison system is used to compare and alarm the captured images.
  • the monitoring camera collects the current video frame, performs face target detection on the current video frame, and determines the face target image in the current video frame.
  • the target image is subjected to quality analysis to obtain the image quality of the face target image. If the image quality meets the preset quality conditions, the face target image is uploaded to the comparison system as a captured image.
  • the face target can be captured immediately, and the captured image can be uploaded to the comparison system for comparison and alarm.
  • the image quality of the captured image received by the comparison system can meet the preset quality conditions, ensuring that the captured image has a higher image quality when the comparison system performs face feature comparison, thus ensuring the comparison of the comparison system
  • the results have high accuracy, and once the surveillance camera detects that the image quality of the face target image meets the preset quality conditions, it immediately captures the picture and uploads the captured image to the comparison system for comparison and alarm, ensuring the comparison It has high real-time performance when comparing the system.
  • FIG. 1 is a schematic diagram of an operation process of a monitoring system according to an embodiment of this application;
  • FIG. 2 is a schematic flowchart of an image capture method according to an embodiment of the present application.
  • FIG. 3 is an example diagram of capturing a face target image according to an embodiment of the present application.
  • FIG. 4 is a schematic structural diagram of a surveillance camera according to an embodiment of this application.
  • FIG. 5 is a schematic structural diagram of a monitoring system according to an embodiment of this application.
  • the monitoring system mainly captures, compares and alarms face targets.
  • the monitoring system includes a surveillance camera and a comparison system.
  • the comparison system can be a background server, which is mainly used to realize feature extraction, face comparison and alarm.
  • the operation process of the monitoring system is shown in Figure 1.
  • the monitoring camera collects video data, captures the face target image from the video data through the face capture algorithm, and the monitoring camera transmits the captured face target image to the comparison system.
  • the system extracts the face features of the face target image, compares the extracted face features with the face features of all the people in the database, and if the similarity is higher than the preset threshold, an alarm is generated.
  • the captured face target image is mainly transmitted. Therefore, the quality and real-time performance of the face target image seriously affect the performance and real-time performance of the comparison system, that is, monitoring
  • the image capture method performed by the camera is the key to ensuring the performance and real-time performance of the comparison system.
  • the embodiments of the present application provide an image capture method, a monitoring camera, a machine-readable storage medium, and a monitoring system.
  • the execution subject of the image capture method provided in the embodiments of the present application may be a surveillance camera (for example, a smart camera, a network camera, etc.) in the surveillance system, and the surveillance camera may include at least a surveillance camera and a processor equipped with a core processing chip .
  • the method for implementing the image capturing method provided by the embodiments of the present application may be at least one method of software, hardware circuits, and logic circuits provided in the monitoring camera.
  • an image capture method provided by an embodiment of the present application may include the following steps:
  • Surveillance cameras can be installed in all corners of the city, for example, community entrances, intersections, parks, stadiums, etc.
  • the requirements for capturing the face target clearly.
  • the surveillance camera can shoot the surveillance scene in real time to obtain the video data of the surveillance scene, and the video data includes the video frames of each frame and the time stamp of each video frame collected.
  • the current video frame collected needs to be processed.
  • S202 Perform face target detection on the current video frame to determine the face target image in the current video frame.
  • the preset target detection algorithm can be a traditional feature matching algorithm, which can determine the current video frame by face features such as eyes, nose, mouth, ears, etc. Whether the target in is a face target, if it is a face target, a certain area around the face target is divided into a face target frame, and the image in the face target frame or the image within a certain range of the face target frame is a person Face target image; the preset target detection algorithm can also be a more popular intelligent detection algorithm, such as deep neural network.
  • the network model of deep neural network can be obtained by training a large number of face images, by inputting the current video frame into the depth
  • the neural network can obtain the interest area of the face target in the current video frame, and the image in the interest area of the face target or the image within a certain range of the interest area of the face target is the face target image.
  • other methods that can detect the face target in the video frame also belong to the protection scope of the embodiments of the present application, and details are not repeated here.
  • S203 Perform quality analysis on the face target image to obtain the image quality of the face target image.
  • the image quality of the face target image there are many factors that affect the image quality of the face target image, such as the degree to which the face target is blocked in the face target image, the imaging clarity of the face target in the face target image, and the pose of the face target in the face target image and many more.
  • the image quality of the face target image such as contrast, brightness, and so on, which are not listed here.
  • the preset quality analysis algorithm can also assign, for example, good, good, medium, and poor evaluation results to the face target image.
  • S203 may specifically be:
  • the face target quality parameters of the face target image where the face target quality parameters include at least one or more of the degree of face occlusion, face clarity, and posture; according to the face target quality parameters, determine the person The image quality of the face target image.
  • the face target quality parameter refers to the parameter that affects the image quality of the face target image, mainly including the face target's posture, degree of occlusion, and imaging clarity.
  • the facial target quality parameters such as the posture information, degree of occlusion and sharpness of the facial target are based on the comprehensive consideration of the effects of different facial target quality parameters on the image quality to obtain the image quality of the facial target image. For example, in the face target image in the face target frame in the current video frame, the face target A is completely frontal, the face is occluded by 1/10, and the sharpness is very high, it can be determined that the image quality of the face target image is excellent Or, quantify the image quality and assign an image quality score of 9.
  • the image quality may include an image quality score value.
  • S203 can specifically be:
  • the quality score of the face target image is obtained to obtain the image quality score value of the face target image.
  • the image quality can be expressed by a quantized image quality score value.
  • the quality score algorithm is used to score the face target image to obtain a quantized image quality score value.
  • the image quality can also be expressed as the evaluation results of excellent, good, medium, and poor.
  • the preset quality condition is a condition set to determine whether the image quality of the face target image can meet the requirement of higher image quality. If the image quality can meet the preset quality condition, it means that the image quality of the face target image is higher. If it cannot be satisfied, it means that the image quality of the face target image in the current video frame cannot meet the requirements.
  • S204 may specifically be:
  • the preset quality condition may be greater than the preset quality threshold, for example, the preset quality threshold is 8 points, if the quantized image quality score value is greater than 8 points, it means that the face target image can achieve a better image quality High requirements, if the image quality score value is not greater than 8, it means that the face target image can not meet the requirements.
  • the preset quality condition may also be a preset degree of image quality evaluation.
  • the preset quality condition may be that the image quality is good. If the image quality of the face target image reaches good and above, it means that the face target image It can meet the requirement of high image quality. If the image quality of the face target image is not good, it means that the face target image cannot meet the requirements.
  • the image capture method provided by the embodiment of the present application may further perform the following steps:
  • the next video frame is obtained as the current video frame in the order of the video frames from first to last.
  • the current video frame may include multiple face targets.
  • a face target image of any face target if the image quality does not meet the preset quality conditions, it means that the image quality of the face target image of the face target cannot meet the requirements
  • the next video frame can be obtained in sequence, and the next video frame is used as the current video frame to determine the face target image of the same face target in the video frame Whether the quality of the image can meet the requirements.
  • the second step is to determine the face target image of the same face target in the current video frame and the previous video frame.
  • the way to determine the face target image of the same face target in the current video frame and the previous video frame can be using an intelligent target tracking algorithm to track the same face target, or it can be used in the current video frame as in S202
  • the target detection algorithm performs face target detection, and then determines the target frame matching method.
  • the third step is to analyze the quality of the face target image in the current video frame to obtain the image quality of the face target image.
  • the fourth step is to return to S204 until the image quality of the face target image in the current video frame meets the preset quality condition, and upload the face target image as a captured image to the comparison system.
  • the step of determining the face target image of the same face target in the current video frame and the previous video frame may specifically be:
  • the face target frame in the current video frame is assigned the same target frame identifier as the face target frame in the previous video frame with the highest matching degree;
  • the face target image in the face target frame with the same target frame identifier as the previous video frame in the current video frame is the face target image of the same face target.
  • the method of determining the face target image of the same face target in the current video frame and the previous video frame may be to use the target detection algorithm as in S202 for the current video frame to detect the face target, and then match through the face target frame The way is determined.
  • the matching conditions such as whether the size of the face target frame is the same, whether the position offset is less than a certain threshold, whether the motion trajectory meets a certain smoothness, etc. Based on these matching conditions, a certain amount can be allocated between the two face target frames Matching degree, when the matching degree reaches the preset matching degree threshold, it means that the two face target frames are the same as the face target frame of the same face target. The greater the matching degree, the two face target frames are the same The possibility of the face target frame of the face target is greater. Therefore, the face target frame in the current video frame can be assigned the same target frame identifier as the face target frame with the highest matching degree in the previous video. If the target frame identification is the same, it means that the face targets in the face target image are the same target, and different face target frames have different target frame identifications, which are used to distinguish different face targets.
  • the face target can be captured immediately, and the face target image can be uploaded to the comparison system as a captured image ,
  • the captured image compared by the comparison system has a higher image quality, and the captured image received by the comparison system with the higher image quality is uploaded immediately after being captured by the surveillance camera, and has a better quality real-time.
  • the image capturing method provided by the embodiment of the present application may further perform the following steps:
  • For the same face target determine whether the image quality of the face target image of the face target in the current video frame is better than the image quality of the cached face target image of the face target;
  • the face target image and image quality of the face target in the current video frame are cached
  • the cached face target image of the face target is uploaded to the comparison system as a captured image.
  • the surveillance camera sequentially analyzes the quality of the face target image of the face target in each video frame.
  • the first video frame and The image quality of the face target image of the face target in the first video frame is cached. If the image quality of the face target image of the face target in the subsequent video frame is better than the cached image quality, the better Image quality and face target image buffering, overwriting the face target image and image quality of the face target that have been cached. After the face target disappears, the face target image with the best image quality of the face target is cached, and the face target image can be uploaded as a captured image.
  • the way to determine the end of the tracking of the face target may be that the matching degree of the continuous multiple frames to the face target is very low, then the tracking of the face target may be determined to end, or, through the target tracking algorithm, the tracking of the face target may be determined If it is lost, that is, a certain face target cannot be tracked in multiple consecutive frames, then it can be determined that the tracking of the face target ends.
  • the comparison system can finally calibrate the alarm with the comparison result of the captured image with the best image quality, so as to ensure that the final alarm has high accuracy.
  • the surveillance camera only needs to transmit a small number of captured images (up to two), which can not only ensure high real-time performance, but also ensure the accuracy of the comparison results, and save bandwidth resources.
  • the surveillance camera first collects the first frame, detects the face target image of the face target in the first frame, and performs quality analysis on the face target image. If the quality score value is less than the preset quality threshold, the surveillance camera next collects the second frame, detects the face target image of the face target in the second frame again, and performs image quality analysis on the face target image to obtain the image quality The score value is still less than the preset quality threshold. Continue to collect frames 3, 4, and 5 in sequence. The image quality of the obtained face target image is less than the preset quality threshold.
  • the obtained person If the image quality of the face target image is greater than the preset quality threshold, the face target image as a captured image will be uploaded to the comparison system for processing.
  • the target tracking ends for example, at the 50th frame, it is determined that the target tracking ends.
  • the frame with the best cached image quality is not the 6th frame, but the 30th frame, then the face target in the 30th frame is determined.
  • the face target image is uploaded to the comparison system as a captured image.
  • the surveillance camera collects the current video frame, performs face target detection on the current video frame, determines the face target image in the current video frame, and performs quality analysis on the face target image to obtain the image of the face target image Quality, if the image quality meets the preset quality conditions, the face target image is uploaded to the comparison system as a captured image.
  • the face target can be captured immediately, and the captured image can be uploaded to the comparison system for comparison and alarm.
  • the image quality of the captured image received by the comparison system can meet the preset quality conditions, ensuring that the captured image has a higher image quality when the comparison system performs face feature comparison, thus ensuring the comparison of the comparison system
  • the results have high accuracy, and once the surveillance camera detects that the image quality of the face target image meets the preset quality conditions, it immediately captures the picture and uploads the captured image to the comparison system for comparison and alarm, ensuring the comparison It has high real-time performance when comparing the system.
  • an embodiment of the present application provides a surveillance camera. As shown in FIG. 4, it includes a surveillance camera 401, a processor 402, and a memory 403, where,
  • Surveillance camera 401 used to collect the current video frame
  • Memory 403 used to store computer programs
  • the processor 402 is configured to execute the following steps when executing the computer program stored on the memory 403:
  • the face target image is uploaded to the comparison system as a captured image.
  • processor 402 executes the computer program stored in the memory 403, the following steps may also be implemented:
  • the next video frame is obtained as the current video frame in the order of first to last video frames
  • the processor 402 when the processor 402 implements the step of determining the face target image of the same face target in the current video frame and the previous video frame, it may specifically implement the following steps:
  • the face target frame in the current video frame is assigned the same target frame identifier as the face target frame in the previous video frame with the highest matching degree;
  • the face target image in the face target frame with the same target frame identifier as the previous video frame in the current video frame is the face target image of the same face target.
  • processor 402 executes the computer program stored on the memory 403, the following steps may also be implemented:
  • For the same face target determine whether the image quality of the face target image of the face target in the current video frame is better than the image quality of the cached face target image of the face target;
  • the face target image and image quality of the face target in the current video frame are cached
  • the cached face target image of the face target is uploaded to the comparison system as a captured image.
  • processor 402 when the processor 402 implements the step of performing quality analysis on the face target image to obtain the image quality of the face target image, it may specifically implement the following steps:
  • the face target quality parameters of the face target image include at least one or more of the degree of face occlusion, face clarity, and posture;
  • the image quality of the face target image is determined.
  • the image quality includes an image quality score value
  • processor 402 implements the step of performing quality analysis on the face target image to obtain the image quality of the face target image, it may specifically implement the following steps:
  • the processor 402 When the processor 402 implements the step of judging whether the image quality meets the preset quality condition, it specifically implements the following steps:
  • the above memory may include RAM (Random Access Memory, random access memory), or may include NVM (Non-Volatile Memory, non-volatile memory), for example, at least one disk memory.
  • the memory may also be at least one storage device located away from the processor.
  • the above processor may be a general-purpose processor, including CPU (Central Processing Unit), NP (Network Processor), etc .; it may also be DSP (Digital Signal Processing, digital signal processor), ASIC (Application Specific Integrated Circuit), FPGA (Field-Programmable Gate Array) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components.
  • CPU Central Processing Unit
  • NP Network Processor
  • DSP Digital Signal Processing, digital signal processor
  • ASIC Application Specific Integrated Circuit
  • FPGA Field-Programmable Gate Array
  • Other programmable logic devices discrete gates or transistor logic devices, discrete hardware components.
  • Data can be transmitted between the surveillance camera 401, the processor 402, and the memory 403 through a wired connection or a wireless connection, and the surveillance camera can communicate with the comparison system through a wired communication interface or a wireless communication interface.
  • 4 is only an example of data transmission between the surveillance camera 401, the processor 402, and the memory 403 through the bus, and is not intended as a limitation of a specific connection method.
  • the processor of the surveillance camera can read the computer program stored in the memory and run the computer program to realize that the surveillance camera collects the current video frame and performs face target detection on the current video frame to determine Face target image in the current video frame, perform quality analysis on the face target image to obtain the image quality of the face target image, if the image quality meets the preset quality conditions, the face target image is uploaded as a captured image to the comparison To the system.
  • the face target image can be captured immediately, and the captured image can be uploaded to the comparison system for comparison and alarm.
  • the image quality of the captured image received by the comparison system can meet the preset quality conditions, ensuring that the captured image has a higher image quality when the comparison system performs face feature comparison, thus ensuring the comparison of the comparison system
  • the results have high accuracy, and once the surveillance camera detects that the image quality of the face target image meets the preset quality conditions, it immediately captures the picture and uploads the captured image to the comparison system for comparison and alarm, ensuring the comparison It has high real-time performance when comparing the system.
  • embodiments of the present application also provide a machine-readable storage medium, and the machine-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the image capturing method provided by the embodiment of the present application All steps.
  • the machine-readable storage medium stores a computer program that executes the image capture method provided by the embodiments of the present application at runtime, so it can be achieved that the surveillance camera collects the current video frame and performs face target detection on the current video frame , Determine the face target image in the current video frame, and perform quality analysis on the face target image to obtain the image quality of the face target image. If the image quality meets the preset quality conditions, use the face target image as the captured image Upload to the comparison system. Through the quality analysis of the face target image in the current video frame, when the image quality of the face target image meets the preset quality conditions, the face target can be captured immediately, and the captured image can be uploaded to the comparison system for comparison and alarm.
  • the image quality of the captured image received by the comparison system can meet the preset quality conditions, ensuring that the captured image has a higher image quality when the comparison system performs face feature comparison, thus ensuring the comparison of the comparison system
  • the results have high accuracy, and once the surveillance camera detects that the image quality of the face target image meets the preset quality conditions, it immediately captures the picture and uploads the captured image to the comparison system for comparison and alarm, ensuring the comparison It has high real-time performance when comparing the system.
  • An embodiment of the present application also provides an application program for executing at run time: all steps of the image capturing method provided by the embodiment of the present application.
  • the application program executes the image capturing method provided in the embodiment of the present application when it is running, so that it can realize that: the monitoring camera collects the current video frame, performs face target detection on the current video frame, and determines The face target image is subjected to quality analysis to obtain the image quality of the face target image. If the image quality meets the preset quality conditions, the face target image is uploaded to the comparison system as a captured image. Through the quality analysis of the face target image in the current video frame, when the image quality of the face target image meets the preset quality conditions, the face target can be captured immediately, and the captured image can be uploaded to the comparison system for comparison and alarm.
  • the image quality of the captured image received by the comparison system can meet the preset quality conditions, ensuring that the captured image has a higher image quality when the comparison system performs face feature comparison, thus ensuring the comparison of the comparison system
  • the results have high accuracy, and once the surveillance camera detects that the image quality of the face target image meets the preset quality conditions, it immediately captures the picture and uploads the captured image to the comparison system for comparison and alarm, ensuring the comparison It has high real-time performance when comparing the system.
  • the monitoring system may include a monitoring camera 510 and a comparison system 520;
  • the surveillance camera 510 is used to collect the current video frame; perform face target detection on the current video frame to determine the face target image in the current video frame; perform quality analysis on the face target image to obtain the image quality of the face target image; Determine whether the image quality meets the preset quality conditions; if it meets, upload the face target image as a captured image to the comparison system 520;
  • the comparison system 520 is used for comparing and alarming the captured images.
  • the monitoring camera 510 can also be used to implement all the steps provided in the above method embodiments, and no more details are provided here.
  • the comparison system 520 compares and alarms the captured images, which may specifically include: extracting the captured images, and comparing the extracted facial features with the facial features in the blacklist, if the similarity of the comparison is greater than a certain Threshold, then alarm.
  • the monitoring camera collects the current video frame, performs face target detection on the current video frame, determines the face target image in the current video frame, and performs quality analysis on the face target image to obtain the image of the face target image Quality, if the image quality meets the preset quality conditions, the face target image is uploaded to the comparison system as a captured image.
  • the quality analysis of the face target image in the current video frame when the image quality of the face target image meets the preset quality conditions, the face target can be captured immediately, and the captured image can be uploaded to the comparison system for comparison alarm.
  • the image quality of the captured image received by the comparison system can meet the preset quality conditions, ensuring that the captured image has a higher image quality when the comparison system performs face feature comparison, thus ensuring the comparison of the comparison system
  • the results have high accuracy, and once the surveillance camera detects that the image quality of the face target image meets the preset quality conditions, it immediately captures the picture and uploads the captured image to the comparison system for comparison and alarm, ensuring the comparison It has high real-time performance when comparing the system.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Quality & Reliability (AREA)
  • Closed-Circuit Television Systems (AREA)
  • Image Analysis (AREA)
  • Studio Devices (AREA)

Abstract

Cette invention concerne un procédé de capture d'image, une caméra de surveillance et un système de surveillance. Le procédé de capture d'image comprend les étapes consistant à : acquérir une trame vidéo actuelle (S201) ; déterminer une image cible de visage dans une trame vidéo actuelle pendant une détection de cible de visage sur la trame vidéo actuelle (S202) ; analyser la qualité de l'image cible de visage pour obtenir la qualité d'image de l'image cible de visage (S203) ; déterminer si la qualité d'image satisfait une condition de qualité prédéfinie (S204) ; et si tel est le cas, télécharger l'image cible de visage en tant qu'image capturée vers un système de comparaison (S205). Le procédé peut garantir qu'un résultat de comparaison du système de comparaison présente une grande précision.
PCT/CN2019/116202 2018-11-07 2019-11-07 Procédé de capture d'image, caméra de surveillance et système de surveillance WO2020094088A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201811321514.1 2018-11-07
CN201811321514.1A CN111161206A (zh) 2018-11-07 2018-11-07 一种图像抓拍方法、监控相机及监控系统

Publications (1)

Publication Number Publication Date
WO2020094088A1 true WO2020094088A1 (fr) 2020-05-14

Family

ID=70554712

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/116202 WO2020094088A1 (fr) 2018-11-07 2019-11-07 Procédé de capture d'image, caméra de surveillance et système de surveillance

Country Status (2)

Country Link
CN (1) CN111161206A (fr)
WO (1) WO2020094088A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112507816A (zh) * 2020-11-25 2021-03-16 杭州电子科技大学 一种基于屏幕捕捉的监控触发方法及系统

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111652139A (zh) * 2020-06-03 2020-09-11 浙江大华技术股份有限公司 人脸抓拍方法、抓拍装置及存储装置
CN111931712B (zh) * 2020-09-18 2023-05-26 杭州海康威视数字技术股份有限公司 人脸识别方法、装置、抓拍机及系统
CN115914563A (zh) * 2020-11-23 2023-04-04 国网山东省电力公司利津县供电公司 一种提升图像监控准确性的方法
CN112597916B (zh) * 2020-12-24 2021-10-26 中标慧安信息技术股份有限公司 人脸图像抓拍质量分析方法和系统
CN113222638A (zh) * 2021-02-26 2021-08-06 深圳前海微众银行股份有限公司 门店访客信息的架构方法、装置、设备、介质及程序产品
CN113038017A (zh) * 2021-03-24 2021-06-25 重庆中科云从科技有限公司 图像采集方法、装置及计算机可读存储介质
CN113329175A (zh) * 2021-05-21 2021-08-31 浙江大华技术股份有限公司 抓拍方法、装置、电子装置和存储介质
CN113033521B (zh) * 2021-05-25 2022-05-10 南京甄视智能科技有限公司 基于目标分析的周界动态预警方法与系统
CN114627319A (zh) * 2022-05-16 2022-06-14 杭州闪马智擎科技有限公司 目标数据的上报方法、装置、存储介质及电子装置

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080267458A1 (en) * 2007-04-27 2008-10-30 University Of Ottawa Face image log creation
CN102201061A (zh) * 2011-06-24 2011-09-28 常州锐驰电子科技有限公司 基于多阶层过滤人脸识别的智能安全监控系统及方法
CN102262727A (zh) * 2011-06-24 2011-11-30 常州锐驰电子科技有限公司 客户采集终端人脸图像质量实时监控方法
CN102799877A (zh) * 2012-09-11 2012-11-28 上海中原电子技术工程有限公司 人脸图像筛选方法及系统
CN107633208A (zh) * 2017-08-17 2018-01-26 平安科技（深圳）有限公司 电子装置、人脸追踪的方法及存储介质

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4939968B2 (ja) * 2007-02-15 2012-05-30 株式会社日立製作所 監視画像処理方法、監視システム及び監視画像処理プログラム
CN102930261A (zh) * 2012-12-05 2013-02-13 上海市电力公司 一种人脸抓拍识别方法
CN104239881B (zh) * 2013-06-08 2020-04-24 杭州海康威视数字技术股份有限公司 监控视频中目标自动发现和注册方法及其系统
CN104657817A (zh) * 2015-01-28 2015-05-27 四川君逸易视科技有限公司 一种银行柜台人脸抓拍、对比识别、检索及查询方法
CN105488478B (zh) * 2015-12-02 2020-04-07 深圳市商汤科技有限公司 一种人脸识别系统和方法
CN105930822A (zh) * 2016-05-11 2016-09-07 北京格灵深瞳信息技术有限公司 一种人脸抓拍方法及系统
CN107346426B (zh) * 2017-07-10 2021-03-16 深圳市海清视讯科技有限公司 一种基于摄像机人脸识别的人脸信息收集方法
CN107958220B (zh) * 2017-12-06 2021-03-12 杭州魔点科技有限公司 一种基于人脸识别的人脸库压缩处理方法及其智能装置

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080267458A1 (en) * 2007-04-27 2008-10-30 University Of Ottawa Face image log creation
CN102201061A (zh) * 2011-06-24 2011-09-28 常州锐驰电子科技有限公司 基于多阶层过滤人脸识别的智能安全监控系统及方法
CN102262727A (zh) * 2011-06-24 2011-11-30 常州锐驰电子科技有限公司 客户采集终端人脸图像质量实时监控方法
CN102799877A (zh) * 2012-09-11 2012-11-28 上海中原电子技术工程有限公司 人脸图像筛选方法及系统
CN107633208A (zh) * 2017-08-17 2018-01-26 平安科技（深圳）有限公司 电子装置、人脸追踪的方法及存储介质

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112507816A (zh) * 2020-11-25 2021-03-16 杭州电子科技大学 一种基于屏幕捕捉的监控触发方法及系统

Also Published As

Publication number Publication date
CN111161206A (zh) 2020-05-15

Similar Documents

Publication Publication Date Title
WO2020094088A1 (fr) Procédé de capture d'image, caméra de surveillance et système de surveillance
WO2020094091A1 (fr) Procédé de capture d'image, caméra de surveillance et système de surveillance
US10691949B2 (en) Action recognition in a video sequence
WO2019218824A1 (fr) Procédé d'acquisition de piste de mouvement et dispositif associé, support de stockage et terminal
WO2020073505A1 (fr) Procédé, appareil et dispositif de traitement d'image basés sur une reconnaissance d'image, et support d'informations
CN104303193B (zh) 基于聚类的目标分类
WO2020258978A1 (fr) Procédé et dispositif de détection d'objets
WO2020252974A1 (fr) Procédé et dispositif de suivi de multiples objets cibles dans un état de mouvement
CN108549852B (zh) 基于深度网络增强的特定场景下行人检测器自动学习方法
JP6555906B2 (ja) 情報処理装置、情報処理方法、およびプログラム
US20180144476A1 (en) Cascaded-time-scale background modeling
WO2021139049A1 (fr) Procédé de détection, appareil de détection, dispositif de surveillance et support de stockage lisible par ordinateur
WO2021031954A1 (fr) Procédé et appareil de détermination de quantité d'objets, ainsi que support de stockage et dispositif électronique
WO2020233397A1 (fr) Procédé et appareil de détection de cible dans une vidéo, et dispositif informatique et support d'informations
KR102244878B1 (ko) 인공지능 기반의 cctv 보안 시스템 및 보안 방법
CN109905641B (zh) 一种目标监控方法、装置、设备及系统
WO2020114116A1 (fr) Procédé de détection de piéton fondé sur des foules denses, support d'informations et processeur
CN109447022B (zh) 一种镜头类型识别方法及装置
KR20140095333A (ko) 영상에서 객체 추적 방법 및 장치
CN210072642U (zh) 基于视频监控的人群异常行为检测系统
CN110633648B (zh) 一种自然行走状态下的人脸识别方法和系统
CN110942456B (zh) 篡改图像检测方法、装置、设备及存储介质
CN111444758A (zh) 一种基于时空信息的行人重识别方法及装置
KR101826669B1 (ko) 동영상 검색 시스템 및 그 방법
CN111046769A (zh) 一种排队时长检测方法、装置及系统

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19881021

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19881021

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 19881021

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 19.11.2021)

122 Ep: pct application non-entry in european phase

Ref document number: 19881021

Country of ref document: EP

Kind code of ref document: A1