Human body re-recognition method and human body re-recognition system

A technology of re-identification and human body, which is applied in character and pattern recognition, instruments, computer parts, etc., can solve the problems of reducing the accuracy rate of human body re-identification and image blurring, and achieve the effect of improving clarity and accuracy

Inactive Publication Date: 2013-05-08
信帧机器人技术(北京)有限公司
View PDF1 Cites 26 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] When the monitoring time is night and the light in the monitoring area is dim, the color information in the obtained video is not obvious, and the existing human body re-identification methods are generally based on color, but the images in the obtained video are all Fuzzy, reducing the accuracy of human body re-identification

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Human body re-recognition method and human body re-recognition system
  • Human body re-recognition method and human body re-recognition system
  • Human body re-recognition method and human body re-recognition system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0085] figure 1 It is a flow chart of the human body re-identification method provided by Embodiment 1 of the present invention, see figure 1 shown, including:

[0086] Step 101: Determine the motion area in the video to be detected to form the range of human body detection;

[0087] Step 102: Divide the image forming the human body detection range into multiple color channels, perform grayscale stretching, and form a grayscale stretched image;

[0088] Step 103: Perform human body detection on the image after gray-scale stretching to obtain a human body image;

[0089] Step 104: initially matching the human body in the human body image with the pre-stored human body sample;

[0090] Step 105: judge whether the matching is successful according to the preliminary matching result; if not, then jump to step 106; if yes, then jump to step 107;

[0091] Step 106: saving the detected human body to a human body sample;

[0092] Step 107: Exactly match the human body in the hum...

Embodiment 2

[0100] see figure 2 , in the human body re-identification method provided in Embodiment 2 of the present invention, on the basis of the above-mentioned Embodiment 1, the motion area in the video to be detected is determined, and the range of human body detection formed specifically includes:

[0101] Step 201: Use the frame difference method to detect the moving target of the video, and obtain the foreground picture of each frame of the picture in the video;

[0102] Step 202: Determine the area where the foreground picture is located as the motion area, forming a human body detection range.

[0103] In the second embodiment, in a video to be detected, when a moving person or other object passes by, the first frame in the video is used as the background image, and the other images are compared with the background image, and there is no change The changed part is used as the background, and the changed part is used as the foreground image. The changed part is the moving area ...

Embodiment 3

[0106] see image 3 , in the human body recognition method provided by Embodiment 3 of the present invention, on the basis of Embodiment 2 above,

[0107] Determining motion regions in the video to be detected also includes:

[0108] After obtaining the foreground picture of each frame picture in the video, the obtained foreground picture is filtered using erosion and dilation algorithms.

[0109] In the third embodiment, the motion area in the video to be detected is determined to form the range of human body detection, which specifically includes:

[0110] Step 301: Use the frame difference method to detect the moving target of the video, and obtain the foreground picture of each frame of the picture in the video;

[0111] Step 302: After obtaining the foreground picture of each frame of picture in the video, filter the obtained foreground picture using erosion and expansion algorithm;

[0112] Step 303: Determine that the area where the filtered foreground picture is locat...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to the field of computer vision and pattern recognition, in particular to a human body re-recognition method and a human body re-recognition system. The human body re-recognition method comprises the steps: confirming motion areas in a to-be-detected video, and forming a range of human body detection; dividing images which form the range of the human body detection into a plurality of color channels, carrying out gray stretch and forming gray-stretched images; carrying out the human body detection on the gray-stretched images and obtaining human body images; carrying out preliminary matching on a human body in the human body image and a pre-stored human body sample; if the preliminary matching fails, storing the detected human body into the human body sample; if the preliminary matching succeeds, carrying out accurate matching on the human body in the human body image and the pre-stored human body sample; judging whether the matching is successful or not according to a result of the accurate matching; if not, storing the detected human body to the human body sample; and if yes, outputting the corresponding human body sample. The gray stretch is conducted on the images from the plurality of color channels, so that the original blurry images are cleared, and accuracy of human body re-recognition is improved.

Description

technical field [0001] The invention relates to the fields of computer vision and pattern recognition, in particular to a human body re-identification method and a human body re-identification system. Background technique [0002] At present, when a camera is used for monitoring, people or objects moving in the video are generally the focus of attention. For example, when monitoring in a residential area, whether the license plate number lights of the people and vehicles appearing in the monitoring area belong to the community are the key points that need special attention. [0003] When the monitoring time is night and the light in the monitoring area is dim, the color information in the obtained video is not obvious, and the existing human body re-identification methods are generally based on color, but the images in the obtained video are all Fuzzy, which reduces the accuracy of human body re-identification. Contents of the invention [0004] The invention provides a ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00
Inventor 王海峰王晓萌何小波董博杨宇张凯歌
Owner 信帧机器人技术(北京)有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap