S
Sandor Z. Der
Researcher at United States Army Research Laboratory
Publications - 54
Citations - 782
Sandor Z. Der is an academic researcher from United States Army Research Laboratory. The author has contributed to research in topics: Automatic target recognition & Clutter. The author has an hindex of 15, co-authored 54 publications receiving 738 citations.
Papers
More filters
Journal ArticleDOI
Adaptive anomaly detection using subspace separation for hyperspectral imagery
TL;DR: Adaptive anomaly detectors that find materials whose spectral characteristics are substantially different from those of the neighboring materials are proposed and the detection performance for each method is evaluated.
Journal ArticleDOI
Automatic target recognition using a feature-decomposition and data-decomposition modular neural network
TL;DR: A modular neural network classifier applied to the problem of automatic target recognition using forward-looking infrared (FLIR) imagery results in performance superior to a fully connected network in terms of both network complexity and probability of classification.
Journal ArticleDOI
Simulation of error in optical radar range measurements
TL;DR: A computer simulation of atmospheric and target effects on the accuracy of range measurements using pulsed laser radars with p-i-n or avalanche photodiodes for direct detection and compares simulation results with actual range error data collected in field tests.
Journal ArticleDOI
Experimental Evaluation of FLIR ATR Approaches–A Comparative Study
Baoxin Li,Rama Chellappa,Qinfen Zheng,Sandor Z. Der,Nasser M. Nasrabadi,Lipchen Alex Chan,L Wang +6 more
TL;DR: An empirical evaluation of a number of recently developed Automatic Target Recognition algorithms for Forward-Looking Infrared (FLIR) imagery using a large database of real FLIR images shows that among the neural approaches, the LVQ- and MNN-based algorithms perform the best.
Journal ArticleDOI
Model-based temporal object verification using video
TL;DR: A generalized Hausdorff (1962) metric, which is more robust to noise and allows a confidence interpretation, is suggested for the matching procedure used for pose estimation as well as the identification and verification problem.