Advanced methods for sub-pixel anomaly detection

被引：3

作者：

Cohen, Y ^{[1
]}

Rotman, SR ^{[1
]}

机构：

[1] Ben Gurion Univ Negev, Electroopt Unit, IL-84105 Beer Sheva, Israel

来源：

2004 23RD IEEE CONVENTION OF ELECTRICAL AND ELECTRONICS ENGINEERS IN ISRAEL, PROCEEDINGS | 2004年

关键词：

D O I：

10.1109/EEEI.2004.1361184

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A new sub-pixel target detection algorithm is developed, integrating the powerful "RX" anomaly detector of Reed and Yu (1990) [1], with segmentation and post-processing filters. The integrated method consistently outperforms spectral anomaly detectors based on RX alone, A novel approach is presented to deal with false alarms caused by edges.

引用

页码：432 / 435

页数：4

共 5 条

[1] Performance measurement in point source target detection
BarTal, M
Rotman, SR
[J]. INFRARED PHYSICS & TECHNOLOGY, 1996, 37 (02) : 231 - 238
[2] Algorithms for point target detection in hyperspectral imagery
Caefer, CE
Rotman, SR
Silverman, J
Yip, PW
[J]. IMAGING SPECTROMETRY VIII, 2002, 4816 : 242 - 257
[3] CAEFER CE, IN PRESS SPIE P, V5546
[4] RAVIV O, P SPIE, V5204
[5] ADAPTIVE MULTIPLE-BAND CFAR DETECTION OF AN OPTICAL-PATTERN WITH UNKNOWN SPECTRAL DISTRIBUTION
REED, IS
YU, XL
[J]. IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING, 1990, 38 (10): : 1760 - 1770

← 1 →