Multistage infrared target detection

作     者：Chan, AL Der, SZ Nasrabadi, NM 

作者机构：USA Res Lab Attn AMSRL SE SE Adelphi MD 20783 USA 

出 版 物：《OPTICAL ENGINEERING》 (光学工程)

年 卷 期：2003年第42卷第9期

页      面：2746-2754页

核心收录：

学科分类：08[工学] 080401[工学-精密仪器及机械] 0804[工学-仪器科学与技术] 081102[工学-检测技术与自动化装置] 0811[工学-控制科学与工程] 0702[理学-物理学] 

基　　金：Army Research Laboratory  ARL  (DAAL01-96-C-0038) 

主　　题：target recognition target detection clutter rejection FLIR imagery feature extraction generalized Hebbian algorithm multilayer perceptron 

摘      要：Algorithms are considered for searching wide-area forward-looking infrared imagery for military vehicles. Wide-area search has typically been handled by using a simple detection algorithm with low computational cost to search the entire image or set of images, followed by a clutter rejection algorithm that analyzes only those portions of the image that are marked by the detection algorithm. We start with a feature-based detector and an eigen-neural-based clutter rejecter, and examine a number of architectures for combining these modules to maximize joint performance. The architectures considered include a clutter rejection threshold method and a nonlinear learning-based combination. The performance of the architectures is compared using a set of several thousand real images. (C) 2003 Society of Photo-Optical Instrumentation Engineers.