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

Motion segmentation method based on mixtures-of-dynamic-textures-based spatiotemporal saliency detection

A dynamic texture and motion segmentation technology, applied in image analysis, image data processing, instruments, etc., can solve the problem that single-mode dynamic texture cannot accurately describe the real scene, and achieve the effect of improving accuracy, obvious effect, and obvious interference suppression

Inactive Publication Date: 2012-06-20
SHANGHAI JIAO TONG UNIV
View PDF2 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method is based on a single-modal dynamic texture model. In real scenes, dynamic backgrounds are often not single-modal, but multi-modal. Single-modal dynamic textures cannot accurately describe real scenes.

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 mixtures-of-dynamic-textures-based spatiotemporal saliency detection
  • Motion segmentation method based on mixtures-of-dynamic-textures-based spatiotemporal saliency detection
  • Motion segmentation method based on mixtures-of-dynamic-textures-based spatiotemporal saliency detection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] The embodiment of the present invention will be described in detail below. The embodiment is implemented on the premise of the technical solution of the present invention, and a detailed operation process is given.

[0032] The present invention provides a motion segmentation method based on MDT space-time saliency detection, and the process of the method is:

[0033] Given a video sequence V, each element is l(m,n,t)∈L=R 3 , the dimension of the state space x is n, and the size of the center window is n c pixels, the structural window size used to model dynamic textures is n p , the time window is τ frame;

[0034] Do the following for each pixel of each frame:

[0035] take center window of size n c ×n c×τ, the neighborhood window size is 4n c ×4n c ×τ;

[0036] Modeling window n with texture p ×n p ×τ overlays the center window up and move, as the texture sampling of the central area, and then use the EM algorithm to estimate its texture parameters. ...

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 discloses a motion segmentation method based on mixtures-of-dynamic-textures-based spatiotemporal saliency detection. The method comprises the following steps of: 1, modeling a background by adopting mixtures of dynamic textures; 2, defining a spatiotemporal saliency discrimination function by utilizing a Kullback-Leibler (KL) divergence, and calculating a saliency map; and 3, processing a saliency threshold value to obtain a motion segmentation result. By the method, a motional object can be accurately segmented in a complex environment with a highly-dynamic background and a motional camera; and compared with the conventional method, the invention greatly improves complex scene processing and noise suppression, has relatively higher robustness and can be applied to various complex motion scenes.

Description

technical field [0001] The present invention relates to a moving target segmentation method in the technical field of information processing, in particular to a motion segmentation method based on mixed dynamic texture (Mixtures of Dynamic Textures, MDT) spatiotemporal saliency detection. Background technique [0002] The task of motion segmentation is to extract moving objects as completely as possible from a video sequence. There are two difficulties in this task: (1) high dynamic background, motion segmentation often encounters situations where the background is also moving, such as swaying branches, rain and snow, pedestrians, water waves, etc.; (2) camera motion, in many practical applications , the camera is not fixed. Traditional methods usually make the following assumptions to simplify the problem: (1) the camera is stationary; or (2) the camera motion parameters can be obtained or calculated; or (3) the background satisfies a given model, such as a Gaussian mixtur...

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): G06T7/20G06T7/215
Inventor 周文明姚莉秀杨杰
Owner SHANGHAI JIAO TONG 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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com