Stereo and motion correspondences using nonlinear optimization method

Authors:
Eunkwang Park;Kwangyun Wohn
Affiliations:
Dept. of Elec. and Comp. Eng., Natl. Univ. of Singapore, Singapore, Singapore and Elec. Eng. and Comp. Sci., Div. of Comp. Sci., Korea Adv. Inst. of Sci. and Technol., Daejeon, Republic of Korea;Dept. of Elec. and Comp. Eng., Natl. Univ. of Singapore, Singapore, Singapore and Elec. Eng. and Comp. Sci., Div. of Comp. Sci., Korea Adv. Inst. of Sci. and Technol., Daejeon, Republic of Korea
Venue:
Computer Vision and Image Understanding
Year:
2006

Citing 12
Cited 0

Applying temporal constraints to the dynamic stereo problem

Computer Vision, Graphics, and Image Processing - Lectures notes in computer science, Vol. 201 (G. Goos and J. Hartmanis, Eds.)
Binocular Image Flows: Steps Toward Stereo-Motion Fusion

IEEE Transactions on Pattern Analysis and Machine Intelligence
Determining Object Translation Information Using Stereoscopic Motion

IEEE Transactions on Pattern Analysis and Machine Intelligence
Combinatorial optimization: algorithms and complexity

Combinatorial optimization: algorithms and complexity
Correspondenceless Stereo and Motion: Planar Surfaces

IEEE Transactions on Pattern Analysis and Machine Intelligence
Three-dimensional motion computation and object segmentation in a long sequence of stereo frames

International Journal of Computer Vision
The invisible hand algorithm: solving the assignment problem with statistical physics

Neural Networks
A Graduated Assignment Algorithm for Graph Matching

IEEE Transactions on Pattern Analysis and Machine Intelligence
Stereo-Motion with Stereo and Motion in Complement

IEEE Transactions on Pattern Analysis and Machine Intelligence
Digital Picture Processing

Digital Picture Processing
Computers and Intractability: A Guide to the Theory of NP-Completeness

Computers and Intractability: A Guide to the Theory of NP-Completeness
A Multiple-Baseline Stereo

IEEE Transactions on Pattern Analysis and Machine Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a new approach for using stereo and motion correspondences to solve the problem of tracking multiple independently moving features. In this approach, quantitative relational structure (QRS) is proposed as a framework for the integration of stereo-motion correspondences. The similarity function, tightly coupled to stereo and motion cues, is constructed on QRS, and then energy function E2 consisting of the similarity function is defined. The tracking problem can be converted into the maximization problem of the energy function E2. The stereo and motion correspondences that maximize E2 are recovered by applying an extended graduated assignment algorithm. The relaxation labeling method is also presented for the comparison with the proposed method. Experimental results are presented to illustrate the performance of the proposed method.