Affine Colour Optical Flow Computation

详细信息    查看全文

• 作者：Ming-Ying Fan (17)
  Atsushi Imiya (18)
  Kazuhiko Kawamoto (19)
  Tomoya Sakai (20)
  
• 刊名：Lecture Notes in Computer Science
• 出版年：2013
• 出版时间：2013
• 年：2013
• 卷：8047
• 期：1
• 页码：515-522
• 全文大小：1568KB
• 参考文献：1. Horn, B.K.P., Schunck, B.G.: Determining optical flow. Artificial Intelligence聽17, 185鈥?04 (1981) CrossRef
  2. Bouguet, J.-Y.: Pyramidal implementation of the Lucas Kanade feature tracker description of the algorithm, In: Intel Corporation. Microprocessor Research Labs, OpenCV Documents (1999)
  3. Lucas, B.D., Kanade, T.: An iterative image registration technique with an application to stereo vision. In: International Joint Conference on Artificial Intelligence, pp. 674鈥?79 (1981)
  4. Golland, P., Bruckstein, A.M.: Motion from color CVIU, vol.聽68, pp. 346鈥?62 (1997)
  5. Andrews, R.J., Lovell, B.C.: Color optical flow. In: Proc. Workshop on Digital Image Computing, pp. 135鈥?39 (2003)
  6. van de Weijer, J., Gevers, T.: Robust optical flow from photometric invariants. In: Proc. ICIP, pp. 1835鈥?838 (2004)
  7. Barron, J.L., Klette, R.: Quantitative color optical flow. In: Proceedings of 16th ICPR, vol.聽4, pp. 251鈥?55 (2002)
  8. Heigl, B., Paulus, D., Niemann, H.: Tracking points in sequences of color images. In: Proceedings 5th German-Russian Workshop on Pattern Analysis, pp. 70鈥?7 (1998)
  9. Mileva, Y., Bruhn, A., Weickert, J.: Illumination-robust variational optical flow with photometric invariants. In: Hamprecht, F.A., Schn枚rr, C., J盲hne, B. (eds.) DAGM 2007. LNCS, vol.聽4713, pp. 152鈥?62. Springer, Heidelberg (2007) CrossRef
  10. Shi, J., Tomasi, C.: Good features to track. In: CVPR 1994, pp. 593鈥?00 (1994)
  
• 作者单位：Ming-Ying Fan (17)
  Atsushi Imiya (18)
  Kazuhiko Kawamoto (19)
  Tomoya Sakai (20)
  
  17. School of Advanced Integration Science, Chiba University, Japan
  18. Institute of Management and Information Technologies, Chiba University, Japan
  19. Academic Link Center, Chiba University, Yayoicho 1-33, Inage-ku, Chiba, 263-8522, Japan
  20. Department of Computer and Information Sciences, Nagasaki University, Bunkyo-cho 1-14, Nagasaki, 852-8521, Japan
  

文摘

The purpose of this paper is three-fold. First, we develop an algorith for the computation a locally affine optical flow field from multichannel images as an extension of the Lucus-Kanade (LK) method. The classical LK method solves a system of linear equations assuming that the flow field is locally constant. Our method solves a collection of systems of linear equations assuming the flow field is locally affine. For autonomous navigation in a real environment, the adaptation of the motion and image analysis algorithm to illumination changes is a fundamental problem, because illumination changes in an image sequence yield counterfeit obstacles. Second, we evaluate the colour channel selection of colour optical flow computation. By selecting an appropriate colour channel, it is possible to avoid these counterfeit obstacle regions in the snapshot image in front of a vehicle. Finally, we introduce an evaluation criterion for the computed optical flow field without ground truth.