Neural network target identification system for false alarm reduction

David Ye; Weston Edens; Thomas T. Lu; Tien-Hsin Chao

doi:10.1117/12.820949

Translator Disclaimer

13 April 2009 Neural network target identification system for false alarm reduction

David Ye, Weston Edens, Thomas T. Lu, Tien-Hsin Chao

Author Affiliations +

Proceedings Volume 7340, Optical Pattern Recognition XX; 73400K (2009) https://doi.org/10.1117/12.820949
Event: SPIE Defense, Security, and Sensing, 2009, Orlando, Florida, United States

Abstract

A multi-stage automated target recognition (ATR) system has been designed to perform computer vision tasks with adequate proficiency in mimicking human vision. The system is able to detect, identify, and track targets of interest. Potential regions of interest (ROIs) are first identified by the detection stage using an Optimum Trade-off Maximum Average Correlation Height (OT-MACH) filter combined with a wavelet transform. False positives are then eliminated by the verification stage using feature extraction methods in conjunction with neural networks. Feature extraction transforms the ROIs using filtering and binning algorithms to create feature vectors. A feed forward back propagation neural network (NN) is then trained to classify each feature vector and remove false positives. This paper discusses the test of the system performance and parameter optimizations process which adapts the system to various targets and datasets. The test results show that the system was successful in substantially reducing the false positive rate when tested on a sonar image dataset.

Citation Download Citation

David Ye, Weston Edens, Thomas T. Lu, and Tien-Hsin Chao "Neural network target identification system for false alarm reduction", Proc. SPIE 7340, Optical Pattern Recognition XX, 73400K (13 April 2009); https://doi.org/10.1117/12.820949

ACCESS THE FULL ARTICLE