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

New gait area segmentation algorithm of time and space fusion

A technology of region segmentation and spatio-temporal fusion, applied in computing, image analysis, image data processing, etc., can solve problems such as not getting segmentation results

Inactive Publication Date: 2016-04-27
安徽勤勉知识产权代理有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Typical video object segmentation algorithms are based on change region detection, based on non-parametric models, based on parametric models, and based on morphological processing, etc., but these methods mostly use the relevant information of one or more adjacent frames in time domain To detect the moving target of the current frame, this idea has indeed achieved good results for the segmentation of rigid moving targets, but for non-rigid moving targets such as human motion, complete segmentation results are often not obtained.

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

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0009] This specific embodiment adopts the following technical scheme: it includes the following steps: new time domain segmentation, morphological post-processing, spatial domain segmentation, temporal and spatial fusion, experimental analysis and comparison.

[0010] The new time domain segmentation includes background subtraction and symmetric frame difference, and the background subtraction and symmetric frame difference binary results are added.

[0011] The morphological post-processing includes erosion, dilation, opening and closing operations, boundary extraction, and image connection processing.

[0012] The airspace segmentation includes watershed algorithm segmentation of images in the airspace, wavelet decomposition of images in the airspace, and watershed algorithm segmentation in the airspace wavelet domain.

[0013] This specific embodiment can overcome the disadvantages of the existing space-time fusion algorithm, not only can achieve good results for the segme...

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 relates to a new gait area segmentation algorithm of time and space fusion. The algorithm comprises the following steps of new time domain segmentation, morphological post-treatment, spatial domain segmentation, time and space fusion and experimental analysis and comparison. According to the invention, the defects of present algorithms based on time and space fusion can be overcome, a rigid motion object can be segmented effectively, and a complete segmentation result can be obtained from a non-rigid motion object as human motion.

Description

Technical field: [0001] The invention relates to a gait image sequence algorithm, in particular to a new space-time fusion gait region segmentation algorithm. Background technique: [0002] In gait image sequences, there are many methods for estimating human moving objects, each of which has its own advantages and disadvantages, and is suitable for different occasions. The algorithm based on spatio-temporal fusion is a classic method of extracting semantically meaningful objects in video sequences. There are already a large number of literatures on video object segmentation. Typical video object segmentation algorithms are based on change region detection, based on non-parametric models, based on parametric models, and based on morphological processing, etc., but these methods mostly use the relevant information of one or more adjacent frames in time domain To detect the moving target of the current frame, this idea has indeed achieved good results for the segmentation of r...

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): G06T7/00G06T7/20
Inventor 张雨蒙
Owner 安徽勤勉知识产权代理有限公司