MDL-Based Segmentation and Motion Modeling in a Long Image Sequence of Scene with Multiple Independently Moving Objects

Authors:
Haisong Gu;Yoshiaki Shirai;Minoru Asada
Affiliations:
-;-;-
Venue:
IEEE Transactions on Pattern Analysis and Machine Intelligence
Year:
1996

Citing 5
Cited 10

Scene Segmentation from Visual Motion Using Global Optimization

IEEE Transactions on Pattern Analysis and Machine Intelligence
Image Flow Segmentation and Estimation by Constraint Line Clustering

IEEE Transactions on Pattern Analysis and Machine Intelligence
Motion segmentation and qualitative dynamic scene analysis from an image sequence

International Journal of Computer Vision
Computing occluding and transparent motions

International Journal of Computer Vision
Stochastic Complexity in Statistical Inquiry Theory

Stochastic Complexity in Statistical Inquiry Theory

Spatiotemporal Segmentation Based on Region Merging

IEEE Transactions on Pattern Analysis and Machine Intelligence
Geometric Information Criterion for Model Selection

International Journal of Computer Vision
Perceptual organization based computational model for robust segmentation of moving objects

Computer Vision and Image Understanding
Calibration of a Moving Camera Using a Planar Pattern: Optimal Computation, Relibility Evaluation, and Stabilization by Model Selection

ECCV '00 Proceedings of the 6th European Conference on Computer Vision-Part II
Object Recognition for Video Retrieval

CIVR '02 Proceedings of the International Conference on Image and Video Retrieval
Multiple motion analysis: in spatial or in spectral domain?

Computer Vision and Image Understanding
Uncertainty Modeling and Model Selection for Geometric Inference

IEEE Transactions on Pattern Analysis and Machine Intelligence
Seeded region growing: an extensive and comparative study

Pattern Recognition Letters
The generalized MDL approach for summarization

VLDB '02 Proceedings of the 28th international conference on Very Large Data Bases
Spatio-temporal video object segmentation via scale-adaptive 3D structure tensor

EURASIP Journal on Applied Signal Processing

Quantified Score

Hi-index	0.14

Visualization

Abstract

This paper presents a method for spatiotemporal segmentation of long image sequences of scenes which include multiple independently moving objects, based on the minimum description length (MDL) principle. First, a family of motion models is constructed, each of which corresponds to a physically meaningful motion such as translation with constant velocity or a combination of translation and rotation. Then, the motion description length is formulated. When an object changes the type of the motion or a new part of an object appears, the corresponding temporal or spatial segmentation is carried out. Ambiguous segmentation of two consecutive images can be resolved by minimizing the motion description length in a long sequence of images. Experiments on several real image sequences show the validity of our method.