On statistical approaches to target silhouette classification in difficult conditions

Sanderson, Conrad, Gibbons, Danny and Searle, Stephen (2008) On statistical approaches to target silhouette classification in difficult conditions. Digital Signal Processing, 18 3: 375-390. doi:10.1016/j.dsp.2007.05.008

Author Sanderson, Conrad
Gibbons, Danny
Searle, Stephen
Title On statistical approaches to target silhouette classification in difficult conditions
Journal name Digital Signal Processing   Check publisher's open access policy
ISSN 1051-2004
Publication date 2008-05
Sub-type Article (original research)
DOI 10.1016/j.dsp.2007.05.008
Volume 18
Issue 3
Start page 375
End page 390
Total pages 16
Place of publication Maryland Heights, MO, United States
Publisher Academic Press
Language eng
Subject 280204 Signal Processing
280203 Image Processing
280207 Pattern Recognition
Abstract In this paper we present a methodical evaluation of the performance of a new and two traditional approaches to automatic target recognition (ATR) based on silhouette representation of objects. Performance is evaluated under the simulated conditions of imperfect localization by a region of interest (ROI) algorithm (resulting in clipping and scale changes) as well as occlusions by other silhouettes, noise and out-of-plane rotations. The two traditional approaches are holistic in nature and are based on moment invariants and principal component analysis (PCA), while the proposed approach is based on local features (object parts) and is comprised of a block-by-block 2D Hadamard transform (HT) coupled with a Gaussian mixture model (GMM) classifier. Experiments show that the proposed approach has good robustness to clipping and, to a lesser extent, robustness to scale changes. The moment invariants based approach achieves poor performance in advantageous conditions and is easily affected by clipping and occlusions. The PCA based approach is highly affected by scale changes and clipping, while being relatively robust to occlusions and noise. Furthermore, we show that the performance of a silhouette recognition system subject to mismatches between training and test angles of silhouettes (caused by an out-of-plane rotation) can be considerably improved by extending the training set using only a few angles which are widely spaced apart. The improvement comes without affecting the performance at “side-on” views.
Keyword Automatic target recognition
Silhouette classification
Adverse conditions
Statistical models
Local features
Object parts
Q-Index Code C1
Q-Index Status Provisional Code
Institutional Status Non-UQ
Additional Notes Available online 6 June 2007.

Document type: Journal Article
Sub-type: Article (original research)
Collections: Security and Surveillance Collection
School of Information Technology and Electrical Engineering Publications
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 7 times in Thomson Reuters Web of Science Article | Citations
Scopus Citation Count Cited 8 times in Scopus Article | Citations
Google Scholar Search Google Scholar
Created: Fri, 20 Jun 2008, 16:51:04 EST by Anne Draper on behalf of School of Information Technol and Elec Engineering