Unlock instant, AI-driven research and patent intelligence for your innovation.

Boundary chain code-based old person fall-down detection algorithm

A detection method and technology for the elderly, applied in the field of computer vision, can solve problems such as complex algorithms and poor real-time performance, and achieve the effect of reducing complexity, strong adaptability, and accurate fall detection results.

Inactive Publication Date: 2017-03-08
WUXI LWSN TECH
View PDF4 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Its algorithm is complex and its real-time performance is poor

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
  • Boundary chain code-based old person fall-down detection algorithm
  • Boundary chain code-based old person fall-down detection algorithm
  • Boundary chain code-based old person fall-down detection algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0012] A technical scheme of an elderly fall detection algorithm based on boundary chain codes disclosed in the present invention:

[0013] 1. Target extraction: The gray value of each pixel in the video sequence is a discrete random distribution. According to when a random variable obeys the Beta distribution, the three-time estimation method can be used to estimate the mean and standard deviation of the variable. Use the first three frames of the current frame to estimate the background and standard deviation, according to the aforementioned three-time estimation, where:

[0014] a=max(f k-1 , f k-2 , f k-3 ) (1)

[0015] b=median(f k-1 , f k-2 , f k-3 ) (2)

[0016] c=min(f k-1 , f k-2 , f k-3 ) (3)

[0017] The mean and standard deviation are defined by:

[0018]

[0019]

[0020] in is f k Background estimation for framed images.

[0021] current frame f k (x, y) and its background image The difference image D obtained by difference k (x, y), exp...

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 field of computer vision and discloses a boundary chain code-based old person fall-down detection algorithm. The algorithm comprises the steps of firstly extracting a moving target, namely, an old person in a monitored video through a PERT background modeling-based moving target detection algorithm, and performing median filtering and morphological processing on the extracted moving target to obtain a complete target; secondly performing profile tracking on a target region to sequentially find out boundary points, and generating a boundary chain code; and finally adjusting the length of the boundary chain code by utilizing interpolation, and judging whether the moving target falls down or not by performing Euclidean space distance comparison with a fall-down model. According to the boundary chain code-based old person fall-down detection algorithm, the complexity of the old person fall-down detection algorithm can be lowered and a relatively accurate fall-down detection result can be obtained; and the boundary chain code-based old person fall-down detection algorithm has relatively high adaptability for different scenes.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and in particular relates to an elderly fall detection algorithm based on boundary chain codes. Background technique [0002] As of the end of 2013, my country's population aged 60 and above was 202.43 million, accounting for 14.9% of the total population, and the population aging situation is serious. At present, the children of many families have no time to take care of the elderly due to working outside, so the health maintenance of the elderly is very important. For most older adults, falls are one of the causes of serious injury. Studies have shown that 20-30% of the elderly experience pain caused by falls to varying degrees. Therefore, obtaining fall information quickly and accurately to provide timely assistance to the injured can greatly improve medical efficiency and reduce the number of accidents caused by delayed detection of falls. One step closer to hurt. [0003] At prese...

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): G06K9/00G06T7/246
CPCG06T2207/10016G06T2207/30196G06V40/23
Inventor 彭力邵伟
Owner WUXI LWSN TECH