Feature space trajectory for distorted-object classification and pose estimation in synthetic aperture radar

被引:29
作者
Casasent, D
Shenoy, R
机构
[1] Carnegie Mellon University, Dept. of Elec. and Comp. Engineering, Pittsburgh
[2] Indian Institute of Technology, Madras
[3] Carnegie Mellon University, Pittsburgh, PA
[4] Indian Space Research Organization, Trivandrum
关键词
correlation pattern recognition; automatic target recognition; classification; clutter rejection; distortion invariance; feature space trajectory; pose estimation; synthetic aperture radar;
D O I
10.1117/1.601520
中图分类号
O43 [光学];
学科分类号
070207 ; 0803 ;
摘要
Classification and pose estimation of distorted input objects are considered. The feature space trajectory representation of distorted views of an object is used with a new eigenfeature space. For a distorted input object, the closest trajectory denotes the class of the input and the closest line segment on it denotes its pose. If an input point is too far from a trajectory, it is rejected as clutter. New methods for selecting Fukunaga-Koontz discriminant vectors, the number of dominant eigenvectors per class al-td for determining training, and test set compatibility are presented. (C) 1997 Society of Photo-Optical Instrumentation Engineers.
引用
收藏
页码:2719 / 2728
页数:10
相关论文
共 23 条
[1]   What Size Net Gives Valid Generalization? [J].
Baum, Eric B. ;
Haussler, David .
NEURAL COMPUTATION, 1989, 1 (01) :151-160
[2]   Space object identification - Using spatio-temporal pattern recognition [J].
Brandstrom, GW ;
Ruck, DW ;
Rogers, S ;
Stribling, B .
APPLICATIONS AND SCIENCE OF ARTIFICIAL NEURAL NETWORKS II, 1996, 2760 :475-486
[3]   Synthetic Aperture Radar detection and clutter rejection MINACE filters [J].
Casasent, D ;
Shenoy, R .
PATTERN RECOGNITION, 1997, 30 (01) :151-161
[4]   Feature space trajectory representation and processing for active vision [J].
Casasent, D ;
Sipe, MA .
INTELLIGENT ROBOTS AND COMPUTER VISION XV: ALGORITHMS, TECHNIQUES, ACTIVE VISION, AND MATERIALS HANDLING, 1996, 2904 :390-401
[5]   Nonlinear fusion of Gabor wavelet filters for locating objects, edges and clutter [J].
Casasent, D ;
Weber, D ;
Sipe, M .
WAVELET APPLICATIONS III, 1996, 2762 :232-243
[6]   Classifier and shift-invariant automatic target recognition neural networks [J].
Casasent, DP ;
Neiberg, LM .
NEURAL NETWORKS, 1995, 8 (7-8) :1117-1129
[7]   INITIALIZING BACK PROPAGATION NETWORKS WITH PROTOTYPES [J].
DENOEUX, T ;
LENGELLE, R .
NEURAL NETWORKS, 1993, 6 (03) :351-363
[8]  
Duda R. O., 1973, PATTERN CLASSIFICATI, V3
[9]   APPLICATION OF KARHUNEN-LOEVE EXPANSION TO FEATURE SELECTION AND ORDERING [J].
FUKUNAGA, K ;
KOONTZ, WLG .
IEEE TRANSACTIONS ON COMPUTERS, 1970, C 19 (04) :311-&
[10]  
Jain AK., 1989, FUNDAMENTALS DIGITAL