Catalogue of Artificial Intelligence Techniques
Author(s): R.M. Cameron-Jones
A method for calculating a (generally sparse) depth map for a scene by corresponding (features of) three intensity images taken from different viewpoints. The major advantages of using three images rather than two (as used in biologically motivated binocular stereo) are the rejection of many of the false correspondences which may arise in the two image case and the improvement in the accuracy of the estimated depth as a consequence of using the extra data.
- Ayache, N. and Lustman, F., Fast and reliable passive trinocular stereo-vision First International Conference on Computer Vision (1987), 422--427.