Voting method for the detection of subpixel flow field

Authors:
Atsushi Imiya;Keisuke Iwawaki
Affiliations:
National Institute of Informatics, 2-1-2 Hitotsubashi, Chiyoda-ku 101-8430, Tokyo, Japan and Media Technology Division, Institute of Media and Information Technology, Chiba University, 1-33 Yayoi- ...;Shizuoka Pioneer Co., 15-1 Aza-Nishihontani, Koonosu, Hukurio 437-8511, Shizuoka, Japan and School of Science and Technology, Chiba University, 1-33 Yayoi-cho, Inage-ku, 263-8522 Chiba, Japan
Venue:
Pattern Recognition Letters
Year:
2003

Citing 11
Cited 2

On the estimation of optical flow: relations between different approaches and some new results

Artificial Intelligence
Computation of component image velocity from local phase information

International Journal of Computer Vision
Performance of optical flow techniques

International Journal of Computer Vision
The computation of optical flow

ACM Computing Surveys (CSUR)
Recovering 3-D motion parameters from optical flow field using randomized Hough transform

Pattern Recognition Letters
Motion analysis by random sampling and voting process

Computer Vision and Image Understanding
Robust Linear and Support Vector Regression

IEEE Transactions on Pattern Analysis and Machine Intelligence
The statistics of optical flow

Computer Vision and Image Understanding
Efficient randomized algorithms for robust estimation of circular arcs and aligned ellipses

Computational Geometry: Theory and Applications
The Linear l1 Estimator and the Huber M-Estimator

SIAM Journal on Optimization
Statistical Optimization and Geometric Visual Inference

AFPAC '97 Proceedings of the International Workshop on Algebraic Frames for the Perception-Action Cycle

Variational analysis of spherical images

CAIP'05 Proceedings of the 11th international conference on Computer Analysis of Images and Patterns
Optical flow computation for compound eyes: variational analysis of omni-directional views

BVAI'05 Proceedings of the First international conference on Brain, Vision, and Artificial Intelligence

Quantified Score

Hi-index	0.10

Visualization

Abstract

In this paper, we show that the randomized sampling and voting process detects optical flow. Using an appropriate number of images from a sequence of images, our method detects subpixel motion in this sequence. We use the accumulator space for the unification of these flow vectors which are computed from different time intervals. Numerical examples for the test image sequences show the performance of our method.