Performance evaluation of linear-feature-mapping detection/classification algorithms using large SAR clutter dataset

Lynne A. Tablewski; An Mei Chen; Clark R. Hendrickson; Xiaoli Yu; David L. Buck

doi:10.1117/12.210859

5 June 1995 Performance evaluation of linear-feature-mapping detection/classification algorithms using large SAR clutter dataset

Lynne A. Tablewski, An Mei Chen, Clark R. Hendrickson, Xiaoli Yu, David L. Buck

Author Affiliations +

Proceedings Volume 2487, Algorithms for Synthetic Aperture Radar Imagery II; (1995) https://doi.org/10.1117/12.210859
Event: SPIE's 1995 Symposium on OE/Aerospace Sensing and Dual Use Photonics, 1995, Orlando, FL, United States

Abstract

Using a linear feature mapping framework, a detector and classifier were developed for detecting and recognizing 2D target patterns in data collected by the SRI ultra wideband synthetic aperture radar (SAR), where limited prior knowledge of the target pattern and clutter statistics was known. Preliminary results on 0.1 square kilometers of the illustrative example site show that this linear feature mapping detector (LFMD) improves the receiver operating characteristic (ROC) curve by 1.5 orders of magnitude over the amplitude only 2-parameter constant false alarm rate (CFAR) detector, and the linear feature mapping classifier (LFMC) was able to classify 100% of the targets with no false alarms. In this report, the performances of both LFMD and LFMC are evaluated using ROC curves for 54 square kilometers of UHF SAR clutter data. Extensive experimental performance analysis using the large clutter data set shows that the LFMD and LFMC are very effective in detecting and classifying targets embedded in intense clutter background in UHF SAR data. Performance evaluation on 54 square kilometers of clutter data shows that the LFMD has only 0.3 false alarm per square kilometer and approximately 3 orders of magnitude improvement over the amplitude-only 2- parameter CFAR detector at probability of detection P_d equals 100%. The LFMC yields 100% correct classification by perfectly discriminating against the detected potential targets from the clutter data as nontargets.

Citation Download Citation

Lynne A. Tablewski, An Mei Chen, Clark R. Hendrickson, Xiaoli Yu, and David L. Buck "Performance evaluation of linear-feature-mapping detection/classification algorithms using large SAR clutter dataset", Proc. SPIE 2487, Algorithms for Synthetic Aperture Radar Imagery II, (5 June 1995); https://doi.org/10.1117/12.210859

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

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
10 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Target detection

Sensors

Synthetic aperture radar

Associative arrays

Detection and tracking algorithms

Target recognition

Algorithm development

Show All Keywords

Keywords/Phrases

Search In:

Publication Years