Title :
Small targets in LADAR images using fuzzy clustering
Author :
Lim, Gek ; Bezdek, James C.
Author_Institution :
Div. of Comput. Sci., Univ. of West Florida, Pensacola, FL, USA
Abstract :
We describe an automatic target recognition system for detecting targets in temporal sequences of intensity LADAR images. The system first finds all objects in the images using a method that finds blobs and curves. Then features of the objects are extracted. Next fuzzy c-means (FCM) is used to cluster the objects. Finally, FCM prototypes for each class of objects are relabeled with the training data and used to classify unknown objects using a nearest prototype classifier
Keywords :
feature extraction; fuzzy set theory; image sequences; object detection; object recognition; optical radar; pattern classification; LADAR images; automatic target recognition system; blobs; curves; fuzzy c-means; fuzzy clustering; nearest prototype classifier; small targets; temporal sequences; training data; unknown objects; Computer science; Data mining; Feature extraction; Fuzzy logic; Laser radar; Object detection; Pixel; Prototypes; Speckle; Target recognition;
Conference_Titel :
Fuzzy Systems Proceedings, 1998. IEEE World Congress on Computational Intelligence., The 1998 IEEE International Conference on
Conference_Location :
Anchorage, AK
Print_ISBN :
0-7803-4863-X
DOI :
10.1109/FUZZY.1998.687459