Context-dependent feature selection for landmine detection with ground-penetrating radar
Publication
, Conference
Ratto, CR; Torrione, PA; Collins, LM
Published in: Proceedings of SPIE - The International Society for Optical Engineering
September 8, 2009
We present a novel method for improving landmine detection with ground-penetrating radar (GPR) by utilizing a priori knowledge of environmental conditions to facilitate algorithm training. The goal of Context-Dependent Feature Selection (CDFS) is to mitigate performance degradation caused by environmental factors. CDFS operates on GPR data by first identifying its environmental context, and then fuses the decisions of several classifiers trained on context-dependent subsets of features. CDFS was evaluated on GPR data collected at severaldistinct sites under a variety of weather conditions. Results show that using prior environmental knowledge in this fashion has the potential to improve landmine detection. © 2009 SPIE.
Duke Scholars
Published In
Proceedings of SPIE - The International Society for Optical Engineering
DOI
ISSN
0277-786X
Publication Date
September 8, 2009
Volume
7303
Related Subject Headings
- 5102 Atomic, molecular and optical physics
- 4009 Electronics, sensors and digital hardware
- 4006 Communications engineering
Citation
APA
Chicago
ICMJE
MLA
NLM
Ratto, C. R., Torrione, P. A., & Collins, L. M. (2009). Context-dependent feature selection for landmine detection with ground-penetrating radar. In Proceedings of SPIE - The International Society for Optical Engineering (Vol. 7303). https://doi.org/10.1117/12.817946
Ratto, C. R., P. A. Torrione, and L. M. Collins. “Context-dependent feature selection for landmine detection with ground-penetrating radar.” In Proceedings of SPIE - The International Society for Optical Engineering, Vol. 7303, 2009. https://doi.org/10.1117/12.817946.
Ratto CR, Torrione PA, Collins LM. Context-dependent feature selection for landmine detection with ground-penetrating radar. In: Proceedings of SPIE - The International Society for Optical Engineering. 2009.
Ratto, C. R., et al. “Context-dependent feature selection for landmine detection with ground-penetrating radar.” Proceedings of SPIE - The International Society for Optical Engineering, vol. 7303, 2009. Scopus, doi:10.1117/12.817946.
Ratto CR, Torrione PA, Collins LM. Context-dependent feature selection for landmine detection with ground-penetrating radar. Proceedings of SPIE - The International Society for Optical Engineering. 2009.
Published In
Proceedings of SPIE - The International Society for Optical Engineering
DOI
ISSN
0277-786X
Publication Date
September 8, 2009
Volume
7303
Related Subject Headings
- 5102 Atomic, molecular and optical physics
- 4009 Electronics, sensors and digital hardware
- 4006 Communications engineering