skip to main content
10.1145/2683405.2683454acmotherconferencesArticle/Chapter ViewAbstractPublication PagesivcnzConference Proceedingsconference-collections
research-article

Compensated Rotational-Invariant Fast Motion Tracking with Collateral Trajectory Guess

Published: 19 November 2014 Publication History

Abstract

In this paper we introduce a method to track the motion of a fast moving objects, in a video with blurred background images being captured by a rotating camera. When tracking motion of a fast-moving object like a car, we need to find solutions basically for two issues. Firstly, to eliminate the rotational effect of the camera we need to find a method of matching two given consecutive frames in the sequence. Because of the fast rotation of the camera that follows the moving vehicles, the use of feature points (i.e. detection and matching) is of little value as we get blurred background (and possibly blurred foreground objects as well). Secondly, it is necessary to identify a fast-processing method either to develop a reference background for an indirect method, or to detect fast-moving objects in direct processing for motion tracking.
Instead of applying blind search for whole image frames, we derive an Progressively Optimized Representative Scanning Window (PORSW) method for the sake of high efficiency. The method limits the region of interest, that is initially determined in a training phase and is progressively updated with our proposed progressive random walk algorithm. The initial window is obtained by applying an adaptive Lucas Kanade method to determine the direction of the movement of the pixels in each scan line, running towards the trailing end from the starting boundary. Unusual pixel behaviour, i.e. when pixels do not comply with expected direction and magnitude of the flow given by background pixels, is categorized as the motion of foreground pixels.
Our evaluation shows that the estimation result is more stable even for significant angular error, as we propose to employ the variation in the flow vector of image data for the control functions at different image sequences.

References

[1]
L. Alvarez, J. Weickert, and J. Sanchez. Reliable estimation of dense optical flow fields with large displacements. Int. J. Computer Vision, 39:41--56, 2000.
[2]
P. Anandan. A computational framework and an algorithm for the measurement of visual motion. Int. J. Computer Vision, 2:283--310, 1989.
[3]
J. L. Barron, D. J. Fleet, and S. S. Beauchemin. Systems and experiment performance of optical flow techniques. Int. J. Computer Vision, 12:43--77, 1994.
[4]
J. R. Bergen, P. Anandan, T. J. Hanna, R. Hingorani. Hierarchical model-based motion estimation. In Proc. European Conf. Computer Vision, pages 237 --252, 1992
[5]
T. Brox, C. Bregler, and J. Malik. Large displacement optical flow. In Proc. IEEE Conf. Computer Vision Pattern Recognition, 2009
[6]
T. Brox, A. Bruhn, N. Papenberg, and J. Weickert. High accuracy optical flow estimation based on a theory for warping In Proc. ECCV, Springer LNCS 3024, pages 25--36, 2004.
[7]
B. K. P. Horn and B. G. Schunck. Determining optical flow. Artificial Intelligence, pages 185--203, 1981
[8]
B. Lucas and T. Kanade. An iterative image registration technique with an application to stereo vision. In Proc. Int. Joint Conf. Artificial Intelligence, pages 674--679, 1981
[9]
E. Memin and P. Perez. A multigrid approach for hierarchical motion estimation. In Proc. Int. Conf. Computer Vision, pages 933--938, 1998.
[10]
J. Serrat, F. Diego, F. Lumbreras, J. M. Alvarez. Alignment of videos recorded from moving vehicles. In Proc. Int. Conf. Image Analysis Processing, pages 512--517, 2007
[11]
F. Steinbruecker, T. Pock, and D. Cremers. Large displacement optical flow computation without warping. In Proc. Int. Conf. Computer Vision, 2009
[12]
T. Svoboda and T. Pajdla. Matching in catadioptric images with appropriate windows, and outliers removal. In Proc. Int. Conf. Computer Analysis Images and Patterns, pages 733--740, 2001
[13]
J.M. Geusebroek, R. van den Boomgaard, A.W.M. Smeulders, and A. Dev, Color and Scale: The Spatial Structure of Color Images, Proc. Sixth European Conf. Computer Vision, vol. 1, pages. 331--341, 2000.
[14]
J. Weber and J. Malik. Robust computation of optical flow in a multiscale differential framework. Int. J. Computer Vision, pages 67--81, 1995.
[15]
J. van de Weijer, T. Gevers, Robust optical flow from photometric invariants Int. Conf. on Image Processing, ICIP V(3), pages 1835--1838, 2004
[16]
M. Proesmans, L. van Gool, E. Pauwels, A. Oosterlinck Determination of optical flow and its discontinuities using non-linear diffusion Proc. of European conf. on Computer Vision-ECCV V(1) pages 295--304, 1994
[17]
J. L. Barron, D.J. Fleet, S.S. Beauchemin, T.A. Burkitt, Performance of optical flow techniques Conf. on Computer Vision and Pattern Recognition-CVPR, pages 236--242, 1992

Index Terms

  1. Compensated Rotational-Invariant Fast Motion Tracking with Collateral Trajectory Guess

      Recommendations

      Comments

      Information & Contributors

      Information

      Published In

      cover image ACM Other conferences
      IVCNZ '14: Proceedings of the 29th International Conference on Image and Vision Computing New Zealand
      November 2014
      298 pages
      ISBN:9781450331845
      DOI:10.1145/2683405
      Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

      In-Cooperation

      • The University of Waikato

      Publisher

      Association for Computing Machinery

      New York, NY, United States

      Publication History

      Published: 19 November 2014

      Permissions

      Request permissions for this article.

      Check for updates

      Author Tags

      1. Fast motion tracking
      2. Image correspondence
      3. Motion detection
      4. Random walk
      5. Rotational invariant motion detection

      Qualifiers

      • Research-article
      • Research
      • Refereed limited

      Conference

      IVCNZ '14

      Acceptance Rates

      IVCNZ '14 Paper Acceptance Rate 55 of 74 submissions, 74%;
      Overall Acceptance Rate 55 of 74 submissions, 74%

      Contributors

      Other Metrics

      Bibliometrics & Citations

      Bibliometrics

      Article Metrics

      • 0
        Total Citations
      • 37
        Total Downloads
      • Downloads (Last 12 months)0
      • Downloads (Last 6 weeks)0
      Reflects downloads up to 23 Feb 2025

      Other Metrics

      Citations

      View Options

      Login options

      View options

      PDF

      View or Download as a PDF file.

      PDF

      eReader

      View online with eReader.

      eReader

      Figures

      Tables

      Media

      Share

      Share

      Share this Publication link

      Share on social media