Visual perception theory guided depth motion estimation

Authors:
Bing Li;De Xu;Songhe Feng;Fangshi Wang
Affiliations:
Beijing Key Lab of Intelligent Telecommunications Software and Multimedia, Beijing University of Posts and Communications, Beijing, China;Institute of Computer Science, Beijing Jiaotong University, Beijing, China;Institute of Computer Science, Beijing Jiaotong University, Beijing, China;Institute of Computer Science, Beijing Jiaotong University, Beijing, China
Venue:
MMM'07 Proceedings of the 13th international conference on Multimedia Modeling - Volume Part I
Year:
2007

Citing 6
Cited 0

Recovering Affine Motion and Defocus Blur Simultaneously

IEEE Transactions on Pattern Analysis and Machine Intelligence
Optic Flow Field Segmentation and Motion Estimation Using a Robust Genetic Partitioning Algorithm

IEEE Transactions on Pattern Analysis and Machine Intelligence
Independent 3D Motion Detection Based on Depth Elimination in Normal Flow Fields

CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
Estimating face-pose consistency based on synthetic view space

IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans
Hexagon-based search pattern for fast block motion estimation

IEEE Transactions on Circuits and Systems for Video Technology
Motion estimation using spatio-temporal contextual information

IEEE Transactions on Circuits and Systems for Video Technology

Quantified Score

Hi-index	0.00

Visualization

Abstract

Motion estimation is an important and computationally intensive task in video coding and video analysis. But existent motion estimation algorithms mainly focus on 2-D image plane motion and neglect the motion in depth direction, which we call it depth motion in this paper. There are even few researches on the depth motion, their methods are complex and most of them need binocular images. In this work, visual perception theory is used to estimate the depth motion. A novel depth motion estimate method is proposed base on visual perception theory and it can estimate the depth motion from just monocular video. Experimental results show that our model is simple, effective and corresponds to the human perception.