Share Email Print

Proceedings Paper

Multiresolution Object Detection And Segmentation
Author(s): John A. Hird
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

The use of multiresolution methods for the detection and segmentation of objects in images has been widely examined in the literature. The approaches used have largely been concerned with computationally expensive iterative pyramid linking procedures, and it is only recently that less costly procedures have been investigated using, for instance, top-down tree-growing methods which are computationally more efficient than earlier techniques, and which provide comparable detection and segmentation performance. This paper is concerned with the use of computationally efficient hierarchical techniques for object detection and segmentation, and describes several such algorithms, both new and previously published, which exploit the pyramid structure using vertical interactions between levels. The algorithms use mainly top-down approaches to achieve good performance at a lower cost relative to earlier techniques. Specific problems associated with automatic initialisation and start node selection are also addressed. The algorithms are discussed and their performance on both synthetic images and real infra red images is compared in terms of segmentation quality and computational cost. Results using the earlier iterative linking procedures are also presented, and are compared with the present algorithms in terms of cost and performance.

Paper Details

Date Published: 26 September 1989
PDF: 14 pages
Proc. SPIE 1111, Acquisition, Tracking, and Pointing III, (26 September 1989); doi: 10.1117/12.977986
Show Author Affiliations
John A. Hird, Pilkington Optronics (Scotland)

Published in SPIE Proceedings Vol. 1111:
Acquisition, Tracking, and Pointing III
Sankaran Gowrinathan, Editor(s)

© SPIE. Terms of Use
Back to Top