Abstract
No feature-based vision system can work unless good features can be identified and tracked from frame to frame. Although tracking itself is by and large a solved problem, selecting features that can be tracked well and correspond to physical points in the world is still hard. We propose a feature selection criterion that is optimal by construction because it is based on how the tracker works, and a feature monitoring method that can detect occlusions, disocclusions, and features that do not correspond to points in the world. These methods are based on a new tracking algorithm that extends previous Newton-Raphson style search methods to work under affine image transformations. We test performance with several simulations and experiments.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">></ETX>
Keywords
Frame (networking)Computer scienceFeature (linguistics)Artificial intelligenceAffine transformationTracking (education)Computer visionFeature selectionFeature extractionPattern recognition (psychology)Mathematics
Affiliated Institutions
Related Publications
3-D surface description from binocular stereo
A stereo vision system that attempts to achieve robustness with respect to scene characteristics, from textured outdoor scenes to environments composed of highly regular man-mad...
Extracting affine deformations from image patches. I. Finding scale and rotation
Image deformations due to relative motion between an observer and an object may be used to infer 3-D structure. Up to the first order, these deformations can be written in terms...
Textural features corresponding to textural properties
Five properties of texture, namely, coarseness, contrast, business, complexity, and texture strength, are given conceptual definitions in terms of spatial changes in intensity. ...
Affine invariant model-based object recognition
New techniques are described for model-based recognition of the objects in 3-D space. The recognition is performed from single gray-scale images taken from unknown viewpoints. T...
Comparing images using the Hausdorff distance
The Hausdorff distance measures the extent to which each point of a model set lies near some point of an image set and vice versa. Thus, this distance can be used to determine t...
Publication Info
- Year
- 1994
- Type
- article
- Pages
- 593-600
- Citations
- 6842
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
6842
OpenAlex
Cite This
Jianbo Shi,
Tomasi
(1994).
Good features to track.
, 593-600.
https://doi.org/10.1109/cvpr.1994.323794
Identifiers
- DOI
- 10.1109/cvpr.1994.323794