Andrew P. Witkin

ICRA Conference 1991 Conference Paper

Visual tracking with deformation models

• James M. Rehg
• Andrew P. Witkin

A novel solution to the 2-D tracking problem is presented. This solution has two major components: a deformation model that constrains the interpretation of motion, and a set of energy-based match criteria that specify image features to be used in tracking. The separation of the motion model from the match features is an advantage of this approach over previous tracking systems. An implementation of these ideas has been shown to exhibit fast and flexible operation over a wide class of image motions. Experimental results are given for two real-world image sequences. >

IJCAI Conference 1983 Conference Paper

Scale-Space Filtering

• Andrew P. Witkin

IJCAI Conference 1983 Conference Paper

What Is Perceptual Organization For?

• Andrew P. Witkin
• Jay M. Tenenbaum

AAAI Conference 1982 Conference Paper

Intensity-Based Edge Classification

• Andrew P. Witkin

A new intensity-based approach to the classification of edges was developed and implemented. Using basic continuity and independence properties of scenes and images, signatures were deduced for each of several edge types expressed in terms of correlational properties of the image intensities in the neighborhood of the edge. This procedure’s ability to discriminate occluding contours from cast shadow boundaries was demonstrated for cases where line junction cues are absent from the image.

AIJ Journal 1981 Journal Article

Recovering surface shape and orientation from texture

• Andrew P. Witkin

Texture provides an important source of information about the three-dimensional structure of visible surfaces, particularly for stationary monocular views. To recover 3d structure, the distorting effects of projection must be distinguished from properties of the texture on which the distortion acts. This requires that assumptions must be made about the texture, yet the unpredictability of natural textures precludes the use of highly restrictive assumptions. The recovery method reported in this paper exploits the minimal assumption that textures do not mimic projective effects. This assumption determines the strategy of attributing as much as possible of the variation observed in the image to projection. Equivalently, the interpretation is chosen for which the texture, prior to projection, is made as uniform as possible. This strategy was implemented using statistical methods, first for the restricted case of planar surfaces and then, by extension, for curved surfaces. The technique was applied successfully to natural images.

AAAI Conference 1980 Conference Paper

A Statistical Technique for Recovering Surface Orientation from Texture in Natural Imagery

• Andrew P. Witkin