Obstacle detection by evaluation of optical flow fields from image sequences

https://doi.org/10.1016/0262-8856(91)90010-MGet rights and content

Abstract

In comparison with single images, image sequences contain information about the dynamic aspects of the recorded scene. Dynamic aspects play a crucial role in traffic scenarios, especially for the guidance of an autonomous vehicle. In this contribution we present an approach for the detection of stationary obstacles and moving objects on the road of an autonomous vehicle by evaluation of optical flow fields from image sequences. It will be shown how two-dimensional optical flow fields can be interpreted to infer information about the three-dimensional environment if the camera is moving on a planar surface. Objects are detected by comparing calculated optical flow fields with a model vector field which explicitly expresses the image shift expectation resulting from the camera motion if the environment is free of obstacles. Until now, we had to determine the camera motion heuristically in order to estimate a model vector field. In this paper we evaluate additional velocity information from vehicle sensors. It will be shown that the obstacle detection procedure using velocity information from vehicle sensors yields results similar to the ones obtained by the heuristic velocity estimation. Results obtained from investigations with three different approaches for the estimation of optical flow vectors are used to test the obstacle algorithm.

References (32)

  • RC Nelson

    Visual navigation

  • HA Mallot et al.

    Neural network strategies for robot navigation

  • S Carlsson et al.

    Object detection using model based prediction and motion parallax

  • JK Aggarwal et al.

    On the computation of motion from sequences of images — a review

  • R Kories et al.

    A versatile method for the estimation of displacement vector fields from image sequences

  • N Rehfeld

    Dichte Verschiebungsvektorfelder entlang von Kantenzügen für zeitliche und stereoskopische Bildpaare

  • Cited by (69)

    • Mind the gap: Developments in autonomous driving research and the sustainability challenge

      2020, Journal of Cleaner Production
      Citation Excerpt :

      In 1985, a pioneering computer-vision system was built by the University of Maryland’s computer vision lab (Davis and Kushner, 1986) for AV’s road and road network navigation, wherein the image processing component along with the implementation of a set of algorithms were investigated. Inspired by this work, a cruise control system is created for AV guidance on the German highway system (Maurer et al., 1996) and image sequences techniques are implemented (Enkelmann, 1991; Suzuki et al., 1992), laying the foundations for AV detection and navigation studies. Equally important to road recognition, efficient obstacle detection on roads within a short time helps trigger appropriate reactions to road situations.

    • Optical flow modeling and computation: A survey

      2015, Computer Vision and Image Understanding
      Citation Excerpt :

      Autonomous car driving has received particular attention in recent years [94,98,235]. Obstacle detection and avoidance are the main tasks investigated for general robot control in real environment exploiting optical flow [57,67,82]. Automated video surveillance is another growing research field requiring motion analysis.

    • Independent components of optical flow in a multiresolution image sequence

      2008, International Journal of Pattern Recognition and Artificial Intelligence
    • Event-Based Time-To-Contact Estimation with Depth Image Fusion

      2023, Lecture Notes in Networks and Systems
    View all citing articles on Scopus
    View full text