Share Email Print

Proceedings Paper

Scale-space features for object detection
Author(s): Bradley Pryor Kjell; Arun K. Sood; V. A. Topkar
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

In many applications, such as remote sensing or target detection, the target objects are small, compact blobs. In the images discussed in this paper these objects are only 6 or fewer pixels across, and the images contain noise and clutter which is similar in appearance to the targets. Since so few pixels comprise an object, the object shape is uncertain, so common shape features are unreliable. To distinguish targets from clutter, features which make use of scale-space have proven useful. The scale-space of an image is a sequence of Gauss-filtered versions of the image, using increasing scales from one image to the next. Experiments show that object features calculated at a single scale. Various moments of the value of the Laplacian at the centroid of a blob were particularly effective for some targets.

Paper Details

Date Published: 1 March 1991
PDF: 8 pages
Proc. SPIE 1468, Applications of Artificial Intelligence IX, (1 March 1991); doi: 10.1117/12.45461
Show Author Affiliations
Bradley Pryor Kjell, George Mason Univ. (United States)
Arun K. Sood, George Mason Univ. (United States)
V. A. Topkar, George Mason Univ. (United States)

Published in SPIE Proceedings Vol. 1468:
Applications of Artificial Intelligence IX
Mohan M. Trivedi, Editor(s)

© SPIE. Terms of Use
Back to Top