一种基于互补投票的高效光流计算方法

方明; 徐晶; 高氏秀则; 金子俊一; 徐洪华

doi:10.3724/SP.J.1004.2013.01080

一种基于互补投票的高效光流计算方法

doi: 10.3724/SP.J.1004.2013.01080 cstr: 32138.14.SP.J.1004.2013.01080

1.
长春理工大学长春 130022;
2.
北海道大学札幌 060-0814;
3.
室兰工业大学北海道 050-8585

基金项目:

Supported by Jilin Province Science and Technology Development Program (20120333) and Japan Grants-in-Aid for Scientific Research (21700181)

详细信息

通讯作者:
方明

计量
- 文章访问数: 1564
- HTML全文浏览量: 70
- PDF下载量: 1410
- 被引次数: 0
出版历程
- 收稿日期: 2012-08-27
- 修回日期: 2013-02-22
- 刊出日期: 2013-07-20

Efficient Computation of Optical Flow Using Complementary Voting

1.
Changchun University of Science and Technology, Changchun 130022, China;
2.
Hokkaido University, Kita 14, Nishi 9, Kita-ku, Sapporo 060-0814, Japan;
3.
Muroran Institute of Technology, 27-1 Mizumoto-cho, Muroran 050-8585, Japan

Funds:

Supported by Jilin Province Science and Technology Development Program (20120333) and Japan Grants-in-Aid for Scientific Research (21700181)

摘要

摘要: 描述了一个基于互补投票的高效、带有信赖度的光流计算方法,简称CMV方法.为了计算一个感兴趣区域的光流, 我们首先分割这个区域为若干个子区域,然后利用一个匹配策略计算每一个子区域的相似度分布.这些相似度分布被用来抽取两种类型的投票角色:正投票和负投票.随后,这两种投票角色在一个准则的控制下被用来获取一个最优的投票结果, 这个投票结果将决定光流及其信赖度. 为了削减CMV的计算复杂度,我们提出了一个基于正投票的(PV-based)负投票策略.实验结果显示,CMV方法能够有效计算低质量图像序列的光流,并且这个新的负投票策略在几乎没有影响性能的情况下极大地削减了算法的计算复杂度.
- 块匹配 /
- 互补投票 /
- 负投票 /
- 鲁棒性 /
- 光流
Abstract: This paper describes an efficient complementary voting based estimation algorithm of optical flow with reliability mea- sure, called CMV. To estimate the optical flow of an interest region, we divide the region into subreferences, then compute the similarity profile for each subreference using a certain matching criterion. These similarity profiles are employed to extract two kinds of voting roles positive voting and negative voting. Subsequently, the two kinds of voting roles are carried out to obtain an optimal voting result which is used to estimate an optical flow and a reliability value under a control criterion. To reduce the computational complexity of the CMV, we propose a PV-based negative voting strategy. Experimental results show that the CMV is effective for estimating optical flow in poor-quality image sequence, and that the new negative voting strategy greatly reduces the computation complexity without degradation of the performance.
- Block matching /
- complementary voting /
- negative voting /
- robustness /
- optical flow

HTML全文

参考文献(21)

[1]	Horn B K P, Schunck B G. Determining optical flow. Artificial Intelligence, 1981, 17(1-3): 185-203
[2]	Barron J L, Fleet D J, Beauchemin S S. Performance of optical flow techniques. International Journal of Computer Vision (IJCV), 1994, 12(1): 43-77
[3]	DeSouza G N, Kak A C. Vision for mobile robot navigation: a survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(2): 237-267
[4]	Santos-Victor J, Sandini G, Curotto F, Garibaldi S. Divergent stereo for robot navigation: learning from bees. In: Proceedings of the 1993 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. New York, NY: IEEE, 1993. 434-439
[5]	Caccia M. Vision-based ROV horizontal motion control: Near-seafloor experimental results. Control Engineering Practice, 2007, 15(6): 703-714
[6]	Kinoshita K, Enokidani M, Izumida M, Murkami K. Tracking of a moving object using one-dimensional optical flow with a rotating observer. In: Proceedings of the 9th International Conference on Control, Automation, Robotics and Vision (ICARCV). Singapore: IEEE, 2006. 1-6
[7]	Fan Y, Balasuriya A P. Target tracking by underwater robots. In: Proceedings of the 2001 IEEE International Conference on Systems, Man, and Cybernetics. Tucson, AZ: IEEE, 2001. 696-701
[8]	Krishnamurthy R, Moulin P, Woods J W. Optical flow techniques applied to video coding. In: Proceedings of the 2007 International Conference on Image Processing. Washington, DC: IEEE, 2007. 570-573
[9]	van der Zwaan A S, Bernardino A, Santos-Victor J. Visual station keeping for floating robots in unstructured environments. Robotics and Autonomous Systems, 2002, 39(3-4): 145-155
[10]	Beauchemin S S, Barron J L. The computation of optical flow. ACM Computing Surveys, 1995, 27(3): 433-467
[11]	Fleet D J, Jepson A D. Computation of component image velocity from local phase information. International Journal of Computer Vision (IJCV), 1990, 5(1): 77-104
[12]	Heeger D J. Optical flow using spatiotemporal filters. International Journal of Computer Vision (IJCV), 1988, 1(4): 279-302
[13]	McCane B, Novins K, Crannitch D, Galvin B. On benchmarking optical flow. Computer Vision and Image Understanding, 2001, 84(1): 126-143
[14]	Ullah F, Kaneko S, Igarashi S. Orientation code matching for robust object search. IEICE Transactions on Information and Systems, 2001, E48-D(8): 999-1006
[15]	Ullah F, Kaneko S. Using orientation codes for rotation-invariant template matching. Pattern Recognition, 2004, 37(2): 201-209
[16]	Kita Y. Change detection using joint intensity histogram. The Institute of Electronics, Information and Communication Engineers, 2007, J90-D(8): 1957-1965 (in Japanese)
[17]	Bi G A, Li X M, Meng C, See S. LFM signal detection using LPP-Hough transform. Signal Processing, 91(6): 1432- 1443
[18]	Chen W Y. Color image steganography scheme using DFT, SPIHT codec, and modified differential phase-shift keying techniques. Applied Mathematics and Computation, 2008, 196(1): 40-54
[19]	Roodaki H, Rabiee H R, Ghanbari M. Rate-distortion optimization of scalable video codecs. Signal Processing: Image Communication, 2010, 25(4): 276-286
[20]	Fumihiko S. Robust image matching for occlusion using vote by block matching. IEICE Transactions on Information and Systems, 2001, D-II J84-D-II(10): 2270-2279 (in Japanese)
[21]	Pentland A S, Horowitz B. Recovery of nonrigid motion and structure. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1991, 13(7): 730-742