Abstract: Optical flow estimation is oldest but still most active research domain in image processing. This method is used in motion estimation process. Here, we have discussed the Optical flow method to detect the moving object in video. We have also discussed object detection technique which is used in object detection for moving object. Thereafter, we have chosen optical flow method of detection for further improvement in object detection task. We have discussed different types of most popular techniques of optical flow and also recent survey paper and identified problems (research gaps) in the existing techniques. We found the most recent benchmark of optical flow MPI Sintel.............
Keywords: Object detection, Optical Flow, SURF Feature, Patch Matching, Near Neighbourhood Field (NNF), Sub-pixel Refinement.
[1]. Piccardi, Massimo. "Background subtraction techniques: a review." InSystems, man and cybernetics, 2004 IEEE international conference on, vol. 4, pp. 3099-3104.IEEE, 2004.
[2]. Kulchandani, Jaya S., and Kruti J. Dangarwala. "Moving object detection: Review of recent research trends." In Pervasive Computing (ICPC), 2015 International Conference on, pp. 1-5. IEEE, 2015.
[3]. Beauchemin, Steven S., and John L. Barron. "The computation of optical flow." ACM computing surveys (CSUR) 27, no. 3, pp. 433-466, 1995.
[4]. Brox, Thomas, and Jitendra Malik. "Large displacement optical flow: descriptor matching in variational motion estimation." IEEE transactions on pattern analysis and machine intelligence 33, no. 3, pp. 500-513,2011.
[5]. Butler, Daniel J., Jonas Wulff, Garrett B. Stanley, and Michael J. Black. "A naturalistic open source movie for optical flow evaluation."In European Conference on Computer Vision, pp. 611-625.Springer Berlin Heidelberg, 2012.