Multiresolution Object Detection And Segmentation

John A. Hird

doi:10.1117/12.977986

26 September 1989 Multiresolution Object Detection And Segmentation

John A. Hird

Proceedings Volume 1111, Acquisition, Tracking, and Pointing III; (1989) https://doi.org/10.1117/12.977986
Event: SPIE 1989 Technical Symposium on Aerospace Sensing, 1989, Orlando, FL, United States

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.

Citation Download Citation

John A. Hird "Multiresolution Object Detection And Segmentation", Proc. SPIE 1111, Acquisition, Tracking, and Pointing III, (26 September 1989); https://doi.org/10.1117/12.977986

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available