Motion estimation of deformable objects with motion inertia information

Authors:
Young Wook Sohn;Moon Gi Kang
Affiliations:
Yonsei University, Seodaemun-Ku, Seoul, South Korea;Yonsei University, Seodaemun-Ku, Seoul, South Korea
Venue:
CGIM '08 Proceedings of the Tenth IASTED International Conference on Computer Graphics and Imaging
Year:
2008

Citing 7
Cited 0

Bayesian Estimation of Motion Vector Fields

IEEE Transactions on Pattern Analysis and Machine Intelligence
Performance of optical flow techniques

International Journal of Computer Vision
Adaptively weighted vector-median filters for motion-fields smoothing

ICASSP '96 Proceedings of the Acoustics, Speech, and Signal Processing, 1996. on Conference Proceedings., 1996 IEEE International Conference - Volume 04
Motion vector correction based on the pattern-like image analysis

IEEE Transactions on Consumer Electronics
Highly efficient predictive zonal algorithms for fast block-matching motion estimation

IEEE Transactions on Circuits and Systems for Video Technology
Hybrid de-interlacing algorithm based on motion vector reliability

IEEE Transactions on Circuits and Systems for Video Technology
Block-based motion vector smoothing for periodic pattern region

ICIAR'07 Proceedings of the 4th international conference on Image Analysis and Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

When finding true motion vectors in block-based motion estimation, deformable objects cause motion error due to their texture or shape change. We propose the usage of motion inertia to find robust block-based motion vectors in the deformable objects. When input vectors are not reliable, then previous frame vectors are recursively averaged to calculate motion inertia vectors. Experimental results show robust vectors with the propose method, preserving the shapes of objects in motion compensated frames.