Using Binocular Stereopsis for Vision-based Vehicle Control

Dieter Koller, Quang-Tuan Luong, and Jitendra Malik

In Proc. of the Intelligent Vehicles Symposium 1994, pp. 237-242, October 24-26, 1994, Paris, France

Abstract

We propose a new approach for vision based longitudinal and lateral vehicle control which makes extensive use of binocular stereopsis. Longitudinal control -- i.e. maintaining a safe, constant distance from the vehicle in front -- is supported by detecting and measuring the distances to leading vehicles using binocular stereo. A known camera geometry with respect to the locally planar road is used to map the images of the road plane in the two camera views into alignment. Any significant residual image disparity then indicates an object not lying in the road plane and hence a potential obstacle. This approach allows us to separate image features into those lying in the road plane, e.g. lane markers, and those due to other objects. The features which lie on the road are stationary in the scene and appear to move only because of the egomotion of the vehicle. Measurements on these features allow (a) a dynamic camera calibration update and (b) support the search for lane marker, which are used for lateral control.

The document is available online in application/postscript (1032811 Bytes)


Last modified on Tuesday, November 20, 1996, Dieter Koller (koller@vision.caltech.edu)