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

Method and system for pedestrian fall detection and storage medium

A pedestrian detection and pedestrian technology, applied in the field of computer vision, can solve the problems of difficult to effectively represent the fall behavior, describe the low dimensionality of action semantic features, achieve excellent human body foreground segmentation performance, avoid false detection or void, and high robustness Effect

Pending Publication Date: 2022-01-04
黑龙江雨谷科技有限公司
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] This application provides a method, system and storage medium for pedestrian fall detection to solve the problem in the prior art. In the existing fall detection methods, the feature dimension for describing action semantics is low, and it is difficult to effectively represent the pedestrian fall from different angles. Technical Issues in Falling Behavior

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 system for pedestrian fall detection and storage medium
  • Method and system for pedestrian fall detection and storage medium
  • Method and system for pedestrian fall detection and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be described and illustrated below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application, and are not intended to limit the present application. Based on the embodiments provided in the present application, all other embodiments obtained by persons of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0029] Obviously, the accompanying drawings in the following description are only some examples or embodiments of the present application, and those skilled in the art can also apply the present application to other similar scenarios. In addition, it can also be understood that although such development efforts may be complex and lengthy, for those of ...

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 for pedestrian fall detection. The method comprises the following steps of: S1, acquiring video data of normal activities and fall of human beings; S2, constructing an initial training set according to the video data; S3, according to the initial training set, constructing and training a YOLACT pedestrian detection model; S4, according to the YOLACT pedestrian detection model, performing pedestrian head and center point trajectory tracking; S5, acquiring three-dimensional pedestrian trajectory features according to the pedestrian head and central point trajectory; and S6, training a bidirectional gating circulation unit classification network according to the three-dimensional pedestrian trajectory features, and detecting pedestrian fall. The calculation speed of YOLACT pedestrian target detection can meet the real-time requirement, powerful preprocessing support is provided for subsequent tumble feature analysis, and pedestrian tumble in a complex environment and at different shooting angles is effectively monitored. A system for pedestrian fall detection and a storage medium are also disclosed.

Description

technical field [0001] The present invention relates to the technical field of computer vision, in particular to a method, system and storage medium for pedestrian fall detection. Background technique [0002] In my country's social life, pedestrians fall outdoors, especially the situation that elderly people fall outdoors. It is a prerequisite for pedestrians to be rescued in time to find that pedestrians have fallen. At present, the research on fall motion recognition mainly focuses on the indoor environment, and there is not much research on the fall motion recognition in the outdoor environment. [0003] When pedestrians fall outdoors, such as sudden myocardial infarction, fainting, or accidental falls, it is easy for no one to call the police or the rescue is not timely in the road section with few pedestrians; or in the road section with many pedestrians, the elderly The group may also be unsupported or afraid to help due to social and environmental problems, resultin...

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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/048G06N3/045G06F18/2415
Inventor 国强王亚妮王文博戚连刚
Owner 黑龙江雨谷科技有限公司
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