Advertisement

Moving vehicle detection and tracking in image sequences

  • Yi Lu
  • Jason Miller
  • Tie Qui Chen
Poster Session III
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1352)

Abstract

This paper presents an algorithm that tracks moving vehicles in an outdoor environment. The algorithm was developed based on four heuristics derived from the properties of moving vehicles, maximum velocity, small velocity changes, coherent motion, and continuous motion. The algorithm was developed based on four heuristics on moving vehicles, namely maximum velocity, small velocity change, coherent motion and continuous motion. The algorithm has three major computational components, compute pixel motion vectors using a search window and a matching window, eliminate irrelevant moving pixels using a proximity filter and directional filters, and track the moving vehicles through multiple image frames using a proximity filter. The algorithm has been implemented and tested on image sequences taking in outdoor environments. The test results are presented in the paper.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Reference

  1. [GaL96]
    Warren F. Gardner and D. T. Lawton, “Interactive Model-Based Vehicle Tracking,” IEEE Transaction on Patern Analysis and Machine Intelligence, Vol. 18, No. 11, PP. 1115–1121, Nov. 1996Google Scholar
  2. [HuT81]
    T. S. Hung and R. Y. Tsai, “Image Sequence Analysis: Motion Estimation,” Image Sequence Analysis, Edited T. S. Huang, Springer-Verlag, 1981Google Scholar
  3. [LiH93]
    Y. Liu and T. S. Huang, “Vehicle-Type Motion Estimation from Multi-Frame Images,” IEEE Transaction on Patern Analysis and Machine Intelligence, PP. 802–808, Vol. 15, No. 8, Aug. 1993Google Scholar
  4. [OkK93]
    M. Okutomi and T. Kanade, “A Multiple Baseline Stereo,” IEEE Transaction on Pattern Analysis and Machine intelligence, Vol. 15, No. 4, pp. 353–363, April, 1993Google Scholar
  5. [SzS96]
    Richard Szeliski and Huang-yeung Sham, “Motion Estimation with Quadtree Splines,” IEEE Transaction on Pattern Analysis and Machine intelligence, Vol. 18, No. 12, pp. 1199–1210, 1996Google Scholar
  6. [WHA93]
    Juyang Weng, Thomas S. Huang, Narendra Ahuja, Motion and Structure from Image Sequences, Springer-Verlag, 1993.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • Yi Lu
    • 1
  • Jason Miller
    • 1
  • Tie Qui Chen
    • 1
  1. 1.Department of Electrical and Computer EngineeringThe University of Michigan-DearbornDearbornUSA

Personalised recommendations