Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Pedestrian occlusion and orientation detection method

A technology of occlusion detection and pedestrian detection, applied in the field of computer vision, can solve the problem of low accuracy of pedestrian occlusion detection results and achieve high accuracy

Active Publication Date: 2020-09-08
HUAZHONG UNIV OF SCI & TECH
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Aiming at the above defects or improvement needs of the prior art, the present invention provides a pedestrian occlusion and orientation detection method to solve the inaccuracy of pedestrian occlusion detection results caused by relying on the area of ​​the visible part of the pedestrian for occlusion detection in the prior art. less technical issues

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
  • Pedestrian occlusion and orientation detection method
  • Pedestrian occlusion and orientation detection method
  • Pedestrian occlusion and orientation detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0048] A pedestrian occlusion detection method, such as figure 1 shown, including the following steps:

[0049] S11. Use the pre-trained pedestrian detection model to detect the image to be detected, obtain the pedestrian detection frame, cut out the pedestrian target from the image to be detected according to the obtained pedestrian detection frame, obtain a single pedestrian target image, and analyze the pedestrian target image The pedestrian key points in the image are detected, and then the confidence of each key point on the image to be detected is obtained;

[0050] Among them, such as figure 2 As shown, the pedestrian key points include: nose, left eye, right eye, left ear, right ear, left shoulder, right shoulder, left elbow, right elbow, left wrist, right wrist, left hip, right hip, left knee, right knee, left Ankle and right ankle; pedestrian parts include: head, shoulder, left arm, right arm, buttocks, torso, left leg, and right leg; among them, the key points of...

Embodiment 2

[0063] A pedestrian occlusion detection method, which is applied to the occlusion detection scene of the access control system, such as Figure 4 As shown, it specifically includes the following steps:

[0064] S21. Use the pre-trained pedestrian detection model to detect the image to be detected, obtain the pedestrian detection frame, cut out the pedestrian target from the image to be detected according to the obtained pedestrian detection frame, obtain a single pedestrian target image, and perform the pedestrian target image The key points of the pedestrian in the image are detected, and then the coordinates and confidence of each key point of the pedestrian on the image to be detected are obtained;

[0065] In this embodiment, key points of pedestrians include: nose, left eye, right eye, left ear, right ear, left shoulder, right shoulder, left elbow, right elbow, left wrist, right wrist, left hip, right hip, left knee, right knee , left ankle, and right ankle; pedestrian p...

Embodiment 3

[0073] A pedestrian orientation detection method, which is applied to an access control system occlusion detection scene, specifically includes the following steps:

[0074] S31. According to the steps S21-S23 in the pedestrian occlusion detection method provided in Embodiment 2, obtain the pedestrian detection frame carrying the pedestrian position information;

[0075] S32. Make statistics on the pedestrian part information on the left or right border of the obtained pedestrian detection frame carrying the pedestrian part information, and judge the pedestrian by comparing the quantity of the left half of the human body and the right half of the human body on the left or right border orientation. Specifically, if the left half of the human body on the left boundary is more than the right half of the human body or the right half of the human body is more than the left half of the human body on the right boundary, the pedestrian faces the camera; if the right half of the human ...

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 pedestrian shielding and orientation detection method. The method comprises the following steps: 1, ; s11, detecting the to-be-detected image by adopting the pedestrian detection model to obtain a pedestrian detection frame, cutting a pedestrian target from the to-be-detected image according to the pedestrian detection frame to obtain a single pedestrian target image, anddetecting pedestrian key points in the pedestrian target image to obtain confidence coefficients of the key points on the to-be-detected image; s12, according to the relationship between the key points and the parts in the human body structure, obtaining the occlusion prediction score of each part of the pedestrian in combination with the confidence of each obtained key point; s13, respectively comparing the occlusion prediction score of each part of the pedestrian with a preset part occlusion threshold value, and judging whether each part of the pedestrian is occluded or not; according to the method, the shielding state of each part of the pedestrian is judged without depending on the area of the visible part of the pedestrian, so that the accuracy of the shielding detection result is relatively high, and the shielded part can be accurately detected.

Description

technical field [0001] The invention belongs to the field of computer vision, and more specifically relates to a pedestrian occlusion and orientation detection method. Background technique [0002] Occlusion analysis in pedestrian detection is an important research field in the field of computer vision applications. Occlusion is the main practical problem in pedestrian detection, because the scene in the real world is full of many people or objects, and it is inevitable to appear in the process of pedestrian detection. Inter-class occlusion and intra-class occlusion, especially in the access control system, have higher requirements for pedestrian detection and are more sensitive to pedestrian occlusion and orientation judgment, but computers do not have good perception and prediction of occluded things like humans, so research A pedestrian occlusion and orientation detection method has important significance. [0003] The existing occlusion detection method divides the resu...

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
IPC IPC(8): G06K9/00G06N3/04
CPCG06V40/165G06V40/103G06N3/045
Inventor 韩守东潘孝枫郑丽君夏晨斐
Owner HUAZHONG UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com