Bio-inspired motion-adaptive estimation algorithm of sequence image

LI Shuai; FAN Xiao-guang; XU Yue-lei; LI Wen-qian; HUANG Jin-ke

doi:10.13374/j.issn2095-9389.2017.08.014

Volume 39 Issue 8

Aug. 2017

Turn off MathJax

Article Contents

Article Navigation > Chinese Journal of Engineering > 2017 > 39(8): 1238-1243

LI Shuai, FAN Xiao-guang, XU Yue-lei, LI Wen-qian, HUANG Jin-ke. Bio-inspired motion-adaptive estimation algorithm of sequence image[J]. Chinese Journal of Engineering, 2017, 39(8): 1238-1243. doi: 10.13374/j.issn2095-9389.2017.08.014

Citation:

LI Shuai, FAN Xiao-guang, XU Yue-lei, LI Wen-qian, HUANG Jin-ke. Bio-inspired motion-adaptive estimation algorithm of sequence image[J]. Chinese Journal of Engineering, 2017, 39(8): 1238-1243. doi: 10.13374/j.issn2095-9389.2017.08.014

Citation:

PDF( 6090 KB)

Bio-inspired motion-adaptive estimation algorithm of sequence image

doi: 10.13374/j.issn2095-9389.2017.08.014

1) School Aeronautics and Astronautics Engineering, Air Force Engineering University, Xi'an 710038, China
2) Shaanxi Fashion Engineering University, Xianyang 712046, China

Received Date: 2016-09-13

Abstract

Abstract

To overcome the insufficiencies of varying illumination, large displacement estimation, and outlier removal, a motion-adaptive V1-MT (MAV1MT) motion estimation algorithm based on machine learning and a bio-inspired model of sequence image was proposed, starting from the theory of visual cognition. First, a structure-texture decomposition technique based on the Rudin Osher Fatemi (ROF) model was introduced to manage the variation in illumination and color. Then, a pooling stage at the MT level with non-normalization, which combines the afferent V1 responses using the adaptive weights trained by ridge regression, is modeled to obtain the local velocities. Finally, through introducing the coarse-to-fine method and pyramid structure subsampling of the local motion, the MAV1MT model is used on realistic video. Theoretical analysis and experimental results suggest the new algorithm, which is more fitting to information processing features of the human visual system, has universal, effective and robust motion perception performance.
- optical flow,
- V1,
- MT,
- spatial-temporal filter,
- motion perception,
- ridge regression

FullText(HTML)

References(10)

References

[1]	Fortun D, Bouthemy P, Kervrann C. Optical flow modeling and computation:a survey. Comput Vision Image Understanding, 2015, 134:1
[2]	Horn B K P, Schunck B G. Determining optical flow. Artif Intelligence, 1981, 17(1-3):185
[3]	Butler D J, Wulff J, Stanley G B, et al. A naturalistic open source movie for optical flow evaluation//12th European Conference on Computer Vision. Firenze, 2012:611
[4]	Revaud J, Weinzaepfel P, Harchaoui Z, et al. Epicflow:edge-preserving interpolation of correspondences for optical flow//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Boston, 2015:1164
[6]	Heeger D J. Optical flow using spatiotemporal filters. Int J Comput Vision, 1988, 1(4):279
[7]	Rust N C, Mante V, Simoncelli E P, et al. How MT cells analyze the motion of visual patterns. Nat Neurosci, 2006, 9(11):1421
[8]	Nishimoto S, Gallant J L. A three-dimensional spatiotemporal receptive field model explains responses of area MT neurons to naturalistic movies. J Neurosci, 2011, 31(41):14551
[9]	Solari F, Chessa M, Medathati N V K, et al. What can we expect from a V1-MT feedforward architecture for optical flow estimation?. Signal Processing:Image Commun, 2015, 39:342
[10]	Wedel A, Pock T, Zach C, et al. An improved algorithm for TV-L¹ optical flow//Statistical and Geometrical Approaches to Visual Motion Analysis. Berlin, 2009:23
[12]	Baker S, Scharstein D, Lewis J P, et al. A database and evaluation methodology for optical flow. Int J Comput Vision, 2011, 92(1):1