Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Motion segmentation method based on deterministic fitting

A motion segmentation and deterministic technology, applied in the field of computer vision, can solve the problems of high computational time complexity and low MSMC calculation accuracy, and achieve the effect of reducing segmentation error rate, reliable and stable segmentation results, and promoting development and progress

Active Publication Date: 2019-04-12
MINJIANG UNIV
View PDF7 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these segmentation methods often have some problems, such as MC and TPV calculation time complexity is large, MSMC calculation accuracy is not high

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
  • Motion segmentation method based on deterministic fitting
  • Motion segmentation method based on deterministic fitting
  • Motion segmentation method based on deterministic fitting

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0028] like figure 1 As shown, the present embodiment provides a motion segmentation method based on deterministic fitting, comprising the following steps:

[0029] Step S1: Obtain a group of videos as input videos, and obtain the motion trajectory of feature points of the input videos;

[0030] Step S2: performing superpixel segmentation on each frame of the input video to obtain grouping information of matching pairs of feature points in each continuous frame;

[0031] Step S3: performing model fitting on every two consecutive frames in the input video to obtain a sampling subset and model assumptions;

[0032] Step S4: According to the obtained model assumption, calculate the residual between the matching pair of feature points, and the residual is used to calculate the similarity between the matching pair of feature points to obtain a similarity m...

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 motion segmentation method based on deterministic fitting. According to the method, a deterministic model fitting method is introduced to obtain a stable and reliable motionsegmentation result. The motion segmentation method mainly comprises the following steps: S1, preparing a data set; s2, performing super-pixel segmentation on each frame of the input video; s3, performing model fitting on every two continuous frames in the video; s4, calculating the similarity between the feature point matching pairs according to the obtained residual error information; s5, accumulating the similarity matrix to generate an affine matrix; and S6, sparse clustering is carried out according to the affine matrix to obtain a segmentation result, and motion segmentation is completed. According to the method, the overall segmentation error rate is effectively reduced; in addition, a reliable and stable segmentation result can be obtained, and scientific development and progressare promoted.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a motion segmentation method based on deterministic fitting. Background technique [0002] Computer vision is an important part of computer, and motion segmentation is an important application field in computer vision. Motion segmentation refers to identifying and segmenting different motion models according to different motion model parameters in a video. In the current trend of increasing data size, it is obviously of great significance to effectively analyze the motion model in video sequences. [0003] Currently, motion segmentation methods are applied in many fields, such as video surveillance, object tracking, behavior recognition, and so on. In recent years, experts and scholars have proposed many motion segmentation methods. These segmentation methods can be divided into: two-frame and multi-frame based segmentation methods. Among them, the two-frame-based seg...

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): G06K9/00G06K9/34G06K9/62
CPCG06V20/40G06V10/267G06F18/23213G06F18/2411
Inventor 肖国宝李佐勇徐戈
Owner MINJIANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products