Motion analysis and segmentation through spatio-temporal slices processing

This paper presents new approaches in characterizing and segmenting the content of video. These approaches are developed based upon the pattern analysis of spatio-temporal slices. While traditional approaches to motion sequence analysis tend to formulate computational methodologies on two or three a...

Full description

Saved in:
Bibliographic Details
Main Authors: NGO, Chong-wah, PONG, Ting-Chuen, ZHANG, Hong-Jiang
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2003
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/6329
https://ink.library.smu.edu.sg/context/sis_research/article/7332/viewcontent/10.1.1.99.4330.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
Description
Summary:This paper presents new approaches in characterizing and segmenting the content of video. These approaches are developed based upon the pattern analysis of spatio-temporal slices. While traditional approaches to motion sequence analysis tend to formulate computational methodologies on two or three adjacent frames, spatio-temporal slices provide rich visual patterns along a larger temporal scale. In this paper, we first describe a motion computation method based on a structure tensor formulation. This method encodes visual patterns of spatio-temporal slices in a tensor histogram, on one hand, characterizing the temporal changes of motion over time, on the other hand, describing the motion trajectories of different moving objects. By analyzing the tensor histogram of an image sequence, we can temporally segment the sequence into several motion coherent subunits, in addition, spatially segment the sequence into various motion layers. The temporal segmentation of image sequences expeditiously facilitates the motion annotation and content representation of a video, while the spatial decomposition of image sequences leads to a prominent way of reconstructing background panoramic images and computing foreground objects.