DocumentCode :
1984429
Title :
Advanced methods for sub-pixel anomaly detection
Author :
Cohen, Y. ; Rotman, S.R.
Author_Institution :
Electro-optics Unit, Ben-Gurion Univ. of the Negev, Beer-Sheva, Israel
fYear :
2004
fDate :
6-7 Sept. 2004
Firstpage :
432
Lastpage :
435
Abstract :
A new sub-pixel target detection algorithm is developed, integrating the powerful "RX" anomaly detector of Reed and Yu (1990), 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.
Keywords :
adaptive filters; feature extraction; image segmentation; probability; RX anomaly detector; edge false alarms; post-processing filters; segmentation; sub-pixel anomaly detection; target detection; Covariance matrix; Detectors; Filtering algorithms; Filters; Histograms; Hyperspectral imaging; Image edge detection; Image segmentation; Object detection; Pixel;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Electrical and Electronics Engineers in Israel, 2004. Proceedings. 2004 23rd IEEE Convention of
Print_ISBN :
0-7803-8427-X
Type :
conf
DOI :
10.1109/EEEI.2004.1361184
Filename :
1361184
Link To Document :
بازگشت