A swimming pool drowning detection method based on spatio-temporal neighborhood features

A technology of neighborhood features and detection methods, applied in biometric identification, instruments, computing, etc., can solve the problems of reducing the amount of data processing and high monitoring accuracy

Active Publication Date: 2020-10-23
青岛联合创智科技有限公司
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to overcome the shortcomings of inaccurate and inadequate monitoring in the prior art, and seek to design a swimming pool drowning detection method based on spatio-temporal neighborhood features, which can effectively reduce the amount of data processing and have high monitoring accuracy

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
  • A swimming pool drowning detection method based on spatio-temporal neighborhood features
  • A swimming pool drowning detection method based on spatio-temporal neighborhood features
  • A swimming pool drowning detection method based on spatio-temporal neighborhood features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0028] In order to achieve the above purpose, the swimming pool drowning detection method based on spatio-temporal neighborhood features involved in this embodiment specifically includes the following process steps:

[0029] 1. Using the features of spatio-temporal fragments for background modeling:

[0030] First, the video image sequence of the swimming pool is collected in real time by a camera installed above the water surface, and is transmitted to a computer connected to the camera. order measurement standard; set the intensity set of N pixels contained in the neighborhood of pixel point p at time t as S(p,t)={x 1 ,x 2 ,....,x N}, first cluster these observations from the pixels in the model area and in the process of background learning, and then obtain a compact model by comparing the similarity of the two observations; by dividing the neighborhood segment of the pixel point P Defined as an ordered pixel subset intensity in the neighborhood, such as I({1,4,12}; P) ref...

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 belongs to the technical field of video monitoring, and relates to a swimming pool drowning detection method based on spatio-temporal neighborhood features. Based on the image sequence captured by the swimming pool camera, the above-mentioned images are processed by a computer to monitor and detect. The main process includes the following steps: One is background modeling using the features of spatio-temporal segments, the other is establishing a database of observations to determine the strength of the field around each pixel, and the third is performing foreground detection, including pixel processing and Judging the position of the limbs of the person in the swimming pool by analyzing the body of the detected prospect. When the analysis result meets all the characteristics of drowning, it is judged as drowning. The fourth is to call the police for rescue. When a drowning person is detected, the alarm system is activated. Rescue in time. The monitoring and detection method is scientific and accurate. It can accurately locate the person who fell into the water and give an alarm, which improves the safety of the swimming pool. Only grayscale images are processed, reducing the amount of original data.

Description

Technical field: [0001] The invention belongs to the technical field of video monitoring, and relates to a method for monitoring and early warning of swimming pool drowning behavior, in particular to a swimming pool drowning detection method based on spatio-temporal neighborhood features. Background technique: [0002] Swimming is a very common and effective way of exercising, and it is very popular among people. With the economic development and social progress of our country, there are more and more indoor swimming pool facilities, but the safety of swimming pools cannot be ignored. Scholars often lose their balance and choke in the water because they are not familiar with the nature of water, which may cause drowning accidents. Some swimmers who have learned to swim are also prone to drowning accidents due to cramps, sudden collisions, sudden illnesses, and mental stress. A drowning situation has occurred. Most of the detection systems in domestic swimming pools rely on ...

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 Patents(China)
IPC IPC(8): G06K9/00G06K9/34G06K9/62G08B21/08
CPCG08B21/08G06V40/10G06V10/267G06F18/23213
Inventor 纪刚于腾周粉粉安帅周萌萌商胜楠
Owner 青岛联合创智科技有限公司
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