Drowning behavior online identification method based on machine vision

A recognition method and machine vision technology, applied in the field of computer vision, can solve the problems of reducing monitoring effect, intelligent analysis of swimming pool images, and increasing the monitoring work intensity of managers, so as to improve the system detection rate and achievement rate, reduce labor costs, The effect of reducing hardware requirements

Active Publication Date: 2019-09-06
ZHEJIANG UNIV
View PDF6 Cites 22 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Unfortunately, the mode of this video surveillance system is still only in the traditional mode, without the necessary intelligent analysis of the swimming pool screen, it is c

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
  • Drowning behavior online identification method based on machine vision
  • Drowning behavior online identification method based on machine vision
  • Drowning behavior online identification method based on machine vision

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0042] The present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be noted that the following embodiments are intended to facilitate the understanding of the present invention, but do not limit it in any way.

[0043] The invention provides an online recognition method for drowning behavior based on machine vision. The system can use the existing monitoring system or the camera installed on the water robot, combined with cloud server computing, and use the accelerated lightweight OpenPose to recognize the posture of the human body in the image. , through the convolutional neural network classifier to judge whether a drowning behavior has occurred, and then send an alarm so that rescuers can perceive the drowning event in time and save lives in time.

[0044] like figure 1 As shown, a method for online recognition of drowning behavior based on machine vision includes: image acquisition module, image tr...

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 drowning behavior online identification method based on machine vision. The drowning behavior online identification method comprises: acquiring an image; preprocessing; performing image transmission: transmitting the preprocessed image to a cloud server through a wireless network; performing offline training of OpenPose: the cloud server performs offline training of a model suitable for extracting key points of a human body in water based on lightweight acceleration of OpenPose, and the offline training classifier is used for training a neural network-based binary classifier after human body key points are extracted, and is used for judging whether people are drowned or not; and performing server online monitoring: the cloud server operates the improved lightweight acceleration OpenPose to extract human body key points in the image, performs drowning judgment on the key points, calculates the danger degree and outputs alarm information. The drowning behavior online identification method can be used on a small robot on water, a fixed camera on water or a fixed camera under water, is used for identifying the real-time posture of a swimmer, discriminating andearly warning drowning suspicious postures, and assists a lifeguard in drowning identification at a swimming pool, a seaside and the like.

Description

technical field [0001] The invention relates to the field of computer vision, in particular to a method for online recognition of drowning behavior based on machine vision. Background technique [0002] With the rapid development of informatization and networking, video surveillance systems have gradually been used in swimming pools. They can monitor the swimming pool site through video, and can get real-time continuous video images, which provides great help for managers. Unfortunately, the mode of this video surveillance system is still only in the traditional mode, without the necessary intelligent analysis of the swimming pool screen, it is completely based on "human eyes" or "personal experience", which will not only greatly reduce the monitoring effect, but also increased the monitoring work intensity of managers. The intelligent video analysis technology is becoming more and more mature, but in the monitoring system of the swimming pool, it is urgent to identify, jud...

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): G06K9/00G06K9/62
CPCG06V40/10G06F18/241
Inventor 杨边江张珀鸣陈宣羽王柯钦林含蕾王超屠德展侯迪波
Owner ZHEJIANG UNIV
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