Infrared small target discrimination using sequential forward feature selection with AUC mettric

Author

Sungho Kim ; Kyung-Tae Kim ; Sohyun Kim

Author_Institution

Adv. Visual Intell. Lab., Yeungnam Univ., Yeungnam, South Korea

fYear

2014

fDate

Feb. 26 2014-March 1 2014

Firstpage

641

Lastpage

644

Abstract

Infrared search and track (IRST) is an important research topic in military applications in surveillance and precise guided missiles. The bottleneck of IRST algorithm is huge number of false alarms in real world applications due to sky cloud, sea-glints, and ground clutters. This paper presents a novel target discrimination method using forward feature selection with area under ROC curve (AUC) metric. Experimental results on real target sequences validate the feasibility of the proposed method.

Keywords

feature selection; military computing; missiles; object detection; optical tracking; surveillance; AUC metric; IRST algorithm; area under ROC curve metric; forward feature selection; ground clutters; infrared search and track; infrared small target discrimination; military applications; precise guided missiles; sea-glints; sequential forward feature selection; sky cloud; surveillance missiles; Clutter; Feature extraction; Image sequences; Neural networks; Object detection; Target tracking; Small target; false alarm; feature selection; sequential forward;

fLanguage

English

Publisher

ieee

Conference_Titel

Industrial Technology (ICIT), 2014 IEEE International Conference on

Conference_Location

Busan

Type

conf

DOI

10.1109/ICIT.2014.6895005

Filename

6895005