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

A method suitable for segmenting salient human body instances in video image

An in-image, salient technology, applied in the field of image processing, which can solve the problem of difficult segmentation of pedestrian objects, etc.

Active Publication Date: 2018-12-18
ANHUI UNIVERSITY
View PDF5 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Thus, it is difficult for current methods to segment individual pedestrian objects

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 method suitable for segmenting salient human body instances in video image
  • A method suitable for segmenting salient human body instances in video image
  • A method suitable for segmenting salient human body instances in video image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0068] The structural features of the present invention will now be described in detail in conjunction with the accompanying drawings.

[0069]The segmentation method proposed by the present invention is developed on the detection result of the moving object. On the extracted moving foreground area, it is judged whether there is an occlusion situation. Optical flow, etc., and then in terms of motion persistence constraints, use optical flow features to perform regional clustering to calculate the probability of foreground targets and calculate the optical flow difference between adjacent frames in the region; in terms of structural consistency constraints, perform multi-feature voting based on rough outlines to calculate foreground The maximum possible area of ​​the target and the saliency of the detection area; finally, these constraint items are put into the energy model to constrain the energy of the whole image, so as to realize the modeling and solution of the entangled mo...

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

To address the shortcomings of the prior art, the invention provides a method suitable for segmenting salient human body instances in a video image, which introduces the motion persistence and the time-space structure consistency of a moving object in a video sequence, and realizes a human body instances segmentation method combining optical flow clustering, saliency detection and multi-feature voting based on the two constraints. For continuity of motion, the strategy of calculating the probability of foreground targets based on the clustering of optical flow regions is used, that is, clustering regions based on optical flow characteristics and calculating foreground probability by taking the area of regions as weights; for spatio-temporal structure consistency, a multi-feature voting strategy based on fusion saliency detection and rough contour is proposed and, based on saliency detection and adjacent frame light interest difference, the method optimizes the target foreground with complete contour at pixel level, so as to achieve the case segmentation of unoccluded mobile pedestrians.

Description

technical field [0001] The invention belongs to the technical field of image processing, in particular to a method applicable to the segmentation of salient human body instances in video images. Background technique [0002] Instance segmentation refers to distinguishing the specific objects of each category, that is, instances, on the basis of dividing each pixel in the image into a corresponding category. However, the object category of instance segmentation is wide, and it is mostly applied to different types of rigid objects. [2-4] , there is not much research on human instance segmentation for flexible people. Existing work on human instance segmentation [3,5,6] When the pedestrians in the video are walking upright, the movements are simple, and the interaction and occlusion are the least, better segmentation results can be obtained. However, the situation of pedestrians in actual scenes is usually more complicated, and there are often multiple people who are close t...

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
IPC IPC(8): G06T7/215G06K9/62G06N3/04G06T7/11G06T7/246
CPCG06N3/04G06T7/11G06T7/215G06T7/246G06T2207/10016G06F18/23
Inventor 方贤勇张晶晶李薛剑孙恒飞傅张军孙皆安汪粼波蒋昆鲍恒星周森
Owner ANHUI UNIVERSITY
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