New measurements for stereo-motion correspondences

Authors:
Eunkwang Park;Kwangyun Wohn
Affiliations:
Interaction and Entertainment Research Center, Nanyang Technological University, Singapore;Division of Computer Science, Department of Electrical Engineering & Computer Science, Korea Advanced of Science and Technology, Daejeon, Korea
Venue:
ICCOMP'06 Proceedings of the 10th WSEAS international conference on Computers
Year:
2006

Citing 7
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
Correspondenceless Stereo and Motion: Planar Surfaces

IEEE Transactions on Pattern Analysis and Machine Intelligence
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
Stereo and motion correspondences using nonlinear optimization method

Computer Vision and Image Understanding

Quantified Score

Hi-index	0.00

Visualization

Abstract

New similarity function S3 and energy function E3 of multiple feature tracking are formulated for especially rapidly changing motion in this paper. Stereo and motion cues are tightly coupled in the similarity function S3. Thus this property makes the similarity function S3 control repetition ambiguity almost completely. Seven assignment matrices to maximize the seventh dimensional nonlinear energy function E3 is obtained for applying the similar algorithm which we previously proposed in [3]. Even though proposed measurements suggest perfect solution for feature tracking, it needs high computational processing time.