High-Speed Range Estimation Based on Intensity Gradient Analysis

  • Kurt D. Skifstad

Part of the Springer Series in Perception Engineering book series (SSPERCEPTION)

Table of contents

  1. Front Matter
    Pages i-x
  2. Kurt D. Skifstad
    Pages 1-4
  3. Kurt D. Skifstad
    Pages 5-23
  4. Kurt D. Skifstad
    Pages 25-33
  5. Kurt D. Skifstad
    Pages 35-44
  6. Kurt D. Skifstad
    Pages 45-54
  7. Kurt D. Skifstad
    Pages 55-86
  8. Kurt D. Skifstad
    Pages 87-110
  9. Kurt D. Skifstad
    Pages 111-144
  10. Kurt D. Skifstad
    Pages 171-174
  11. Back Matter
    Pages 175-182

About this book


A fast and reasonably accurate perception of the environment is essential for successful navigation of an autonomous agent. Although many modes of sensing are applicable to this task and have been used, vision remains the most appealing due to its passive nature, good range, and resolution. Most vision techniques to recover depth for navigation use stereo. In the last few years, researchers have started studying techniques to combine stereo with the motion of the camera. Skifstad's dissertation proposes a new approach to recover depth information using known camera motion. This approach results in a robust technique for fast estimation of distances to objects in an image using only one translating camera. A very interesting aspect of the approach pursued by Skifstad is the method used to bypass the most difficult and computationally expensive step in using stereo or similar approaches for the vision-based depth esti­ mation. The correspondence problem has been the focus of research in most stereo approaches. Skifstad trades the correspondence problem for the known translational motion by using the fact that it is easier to detect single pixel disparities in a sequence of images rather than arbitrary disparities after two frames. A very attractive feature of this approach is that the computations required to detect single pixel disparities are local and hence can be easily parallelized. Another useful feature of the approach, particularly in naviga­ tion applications, is that the closer objects are detected earlier.


algorithms calibration control high-speed range estimation intensity gradient analysis machine vision path planning sensor sensors stability uncertainty

Authors and affiliations

  • Kurt D. Skifstad
    • 1
  1. 1.Artificial Intelligence LaboratoryThe University of MichiganAnn ArborUSA

Bibliographic information

  • DOI
  • Copyright Information Springer-Verlag New York 1991
  • Publisher Name Springer, New York, NY
  • eBook Packages Springer Book Archive
  • Print ISBN 978-1-4612-7801-6
  • Online ISBN 978-1-4612-3112-7
  • Series Print ISSN 1431-858X
  • Buy this book on publisher's site