Jenkin, M., Jepson, A., and Tsotsos, J. K., Local surface structure from disparity measurements. Proc. SPIE Vol 850 Optics, Illumination and Image Sensing, 140-145,1987.
Current theories of stereopsis involve three distinct stages: First, the two images of a stereo pair are processed separately to extract monocular features. Once common choice of feature is the presence of a zero-crossing in a bandpassed version of the image. Second, the monocular features in one image are matched with corresponding features found in the other image. In practice this second stage cannot be expected to produce only the correct machines and a third stage must be considered in order to remove the incorrect matches ("false targets"). There are therefore three main issues in the design of such a traditional algorithm for stereopsis, namely i) the choice of image features; ii) the choice of matching criteria; and iii) the way false targets are avoided or eliminated.In this paper we introduce a different approach. We propose that symbolic features should not be extracted from the monocular images in the first stage of processing. Rather we examine a technique for measuring the local phase differrence between the two images. We show how local phase difference in a bandpassed version of the image can be interpreted as disparity. This essentially combines the first two stages of the traditional approach. These disparity measurements may contain "false targets" which must be eliminated.Building upon the results of these disparity detectors, we show that a simple surface model based on object cohesiveness and local surface planarity across a range of spatial-frequency tuned channels can be used to reduce false matches. The resulting local planar surface support can be used to segment the image into planar regsion in depth. Due to the independent nature of both the disparity detection and local planar support mechanism, this method is capable of dealing with both opaque and transparent stimuli.
Jenkin, M. R.M., Jepson, A. and Tsotsos, J. K., Techniques for disparity measurement, RBCV-TR-86-16, Techinical Report on Research in Biological and Computational Vision, Department of Computer Science, University of Toronto, 1987.
Many different approaches have been suggested for the measurement of structure in space from spatially separated cameras. IN this report we will critically examine some of these techniques. Through a series of well-chosen examples we will show that none of the current mechanisms of disparity measurement are particularly robust. By considering some of the implications of disparity in the frequency domain, we present a new definition of disparity that is tied to the inter-ocular phase difference in band-pass versino fo the monocular images. Finally, we present a new technique for measuring disparity as the local phase difference betwen band-pass versions of the two images, and we show how this technique surmounts some of the difficulties encountered by current disparity detection mechanisms.
