Swimming pool anti-drowning identification method based on machine learning

A machine learning and recognition method technology, applied in character and pattern recognition, instruments, alarms, etc., can solve problems such as untimely detection of drowning and rescue equipment affecting swimming experience, so as to reduce operating pressure, reduce configuration, and solve blind spots in vision. Effect

Pending Publication Date: 2020-02-28
王迪
View PDF10 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention proposes a swimming pool anti-drowning recognition method based on machine learning to solve the technical problems in the existing drowning rescue methods that human factors lead to untimely drowning detection and rescue equipment affects swimming experience

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
  • Swimming pool anti-drowning identification method based on machine learning

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment

[0028] The specific content is as follows: Before all people enter the swimming pool, they will watch the pre-recorded video. The content of the video is the introduction of drowning actions and anti-drowning functions, so that the two parties form an agreement: when they feel that they have signs of drowning (or danger) ) and make specified gestures, such as comparing hearts, making fists, waving hands, etc. On this basis, the recognition part can be divided into active recognition and passive prediction. In the active identification branch, the drowning person or the person who feels the danger of drowning actively makes the previously agreed gesture, and the external camera on the shore of the swimming pool will automatically take a picture every 5 frames from the video stream, and take the picture Upload to BaiDu API for gesture recognition. If the recognition result is the specified gesture, the drowning alarm will be sent to the lifeguard on duty, and the person who sent...

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 provides a swimming pool anti-drowning identification method based on machine learning. The method comprises an above-water surface identification method and an under-water surface identification method. Cameras are installed on a bank side and the wall of a swimming pool. Whether drowning occurs is judged by processing a video stream; the problem of a visual field blind area existing in the swimming pool is solved; a lifeguard can check the safety condition of the swimming pool at any time; a real-time video in the swimming pool is analyzed by using a machine learning technology, and if the drowning situation is judged to occur through an algorithm, the drowning information can be sent to the lifeguard in time, so that the problem that the lifeguard cannot focus all the timeis solved; the lifeguard labor deployment can be reduced, and the swimming pool operation pressure is reduced; moreover, the method does not need any auxiliary equipment worn by the swimmer, and doesnot affect the swimming experience.

Description

technical field [0001] The invention relates to a swimming pool anti-drowning recognition method based on machine learning. Background technique [0002] According to the authoritative figures released by the World Health Organization (WHO), 372,000 people die from drowning every year in the world, which is 2 / 3 of the number of people who die from malnutrition, and more than half of the number of deaths from malaria. In our country, young people under the age of 25, especially children aged 1-4, are the main victims of drowning. Compared with car accidents, electric shocks, accidental falls, etc., drowning has always been the leading cause of death from unintentional injuries in children and adolescents. [0003] Traditional swimming pool lifeguards rely on lifeguards to observe with human eyes. Because the signs of drowning are vertical legs and irregular ladder-like movements with hands, they cannot call for help or wave for help. Due to problems such as blind spots in t...

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): G08B21/08H04N7/18H04N5/247G06K9/00G06K9/62
CPCG08B21/08H04N7/18G06V20/35G06V20/10H04N23/90G06F18/2411G06F18/214
Inventor 王迪
Owner 王迪
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