Method and device for detecting posture of human body

A technology of human posture and detection method, which is applied in the field of image processing, can solve the problems of human body occlusion, deformation sensitivity, lower final recognition rate, and inability to determine the posture of the person, so as to achieve the effect of improving accuracy

Inactive Publication Date: 2017-11-17
深圳市深网视界科技有限公司
View PDF9 Cites 39 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the deficiencies in the prior art, one of the purposes of the present invention is to provide a human body posture detection method, which can solve the problem that the detection result of the existing pedestrian detection method cannot determine the posture of the person, and pedestrian recognition has a negative impact on the human body. Occlusion, deformation, etc. are more sensitive, and sending sideways or occluded pedestrian detection results to the recognition module will significantly reduce the final recognition rate.
[0006] The second object of the present invention is to provide a human body posture detection device, which can solve the problem that the detection result of the existing pedestrian detection device cannot determine the posture of the person, and pedestrian recognition is sensitive to the occlusion and deformation of the human body. Sending the detection results of sideways or occluded pedestrians to the recognition module will significantly reduce the final recognition rate
[0007] The third object of the present invention is to provide a human body posture detection device, which can solve the problem that the detection result of the existing pedestrian detection device cannot determine the posture of the person, and pedestrian recognition is sensitive to the occlusion and deformation of the human body. Sending the detection results of sideways or occluded pedestrians to the recognition module will significantly reduce the final recognition rate

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
  • Method and device for detecting posture of human body
  • Method and device for detecting posture of human body
  • Method and device for detecting posture of human body

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0055] Such as figure 1 A human posture detection method comprising the following steps:

[0056] Step S110, acquiring a character image, in this embodiment, the character image is figure 2For example, the character image includes a pedestrian area 10 and a background area 20, and the pedestrian area 10 includes a plurality of key points, the key points include left shoulder point 11 and right shoulder point 12, or left crotch point 13 and right crotch point Point 14.

[0057] Step S120, detecting the position of the pedestrian area 10 in the person image and the width of the pedestrian area 10, and detecting the number of key points and the position of the key point in the person image.

[0058] Specifically, the detection results represent the position of the pedestrian area 10 with four values ​​(x, y, w, h), where (x, y) represents the coordinates of the center point of the pedestrian area 10 in the person image, and w represents The width of the pedestrian area 10, h ...

Embodiment 2

[0095] Such as Figure 4 The shown human posture detection device includes:

[0096] An acquisition module 110, configured to acquire a person image, the person image includes a pedestrian area and a background area, the pedestrian area includes a plurality of key points, the key points include left shoulder points and right shoulder points, or include left crotch points and right shoulder points crotch point;

[0097] A detection module 120, configured to detect the position of the pedestrian area in the person image and the width of the pedestrian area, and detect the number of key points and the position of the key point in the person image;

[0098] The first marking module 130 is configured to mark the character image as an unoccluded state if the number of the key points is equal to the preset number;

[0099] A calculation module 140, configured to calculate the first distance between the left shoulder point and the right shoulder point, or calculate the second distan...

Embodiment 3

[0118] Such as Figure 5 The shown human posture detection device includes: a processor 200 and a memory 300 for storing processor 200 executable instructions;

[0119] The processor 200 is configured to:

[0120] Acquire a person image, the person image includes a pedestrian area and a background area, the pedestrian area includes a plurality of key points, the key points include left shoulder points and right shoulder points, or include left crotch points and right crotch points;

[0121] Detecting the position of the pedestrian area in the person image and the width of the pedestrian area, and detecting the number of key points and the position of the key point in the person image;

[0122] If the number of the key points is equal to the preset number, then mark the person image as an unoccluded state;

[0123] calculating a first distance between the left shoulder point and the right shoulder point, or calculating a second distance between the left crotch point and the r...

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 discloses a method and device for detecting the posture of a human body. The method comprises the steps of acquiring a figure image, wherein the figure image comprises a pedestrian area and a background area, and the pedestrian area comprises a left shoulder point and a right shoulder point; detecting the position of the pedestrian area in the figure image and the width of the pedestrian area, and detecting the number of key points and the position of each key point in the figure image; if the number of the key points is equal to the preset number, marking the figure image to be an unblocked state; calculating a first distance between the left shoulder point and the right shoulder point; and if the first distance is not less than a turn-back threshold, marking the figure image to be a non-turn-back state. The state of the figure image is judged according to the number of the key points and the distance between the key points. Classification can be performed on a plurality of figure images according to the state of the figure images, or unblocked figure images without a turn-back state are selected to perform the next step of operations such as pedestrian recognition, so that the accuracy of pedestrian recognition can be improved.

Description

technical field [0001] The invention relates to image processing technology, in particular to a method and device for detecting human posture. Background technique [0002] Pedestrian recognition has great application prospects in surveillance video, image retrieval and other applications. The basis of pedestrian recognition is to obtain the area where pedestrians are located from pictures or videos, that is, pedestrian detection. [0003] Pedestrian detection is to detect the position of pedestrians in the video. The difficulty of this problem is that the pedestrians in the surveillance video have great posture changes. In different scenes, there may be different interference backgrounds that cause false detections, and there are also human body occlusions, etc. question. [0004] Some of the existing pedestrian detection is realized through Faster RCNN (Faster region based convolution network). Faster RCNN is a general-purpose detection algorithm. It uses a regression m...

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
CPCG06V40/23G06V40/103
Inventor 徐鹏飞赵瑞王露王涛
Owner 深圳市深网视界科技有限公司
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