1 March 1998 Three-dimensional recognition and tracking using neural networks trained on optimal views
Author Affiliations +
Optical Engineering, 37(3), (1998). doi:10.1117/1.601915
We describe a general approach to the representation and recognition of 3-D objects as it applies to automatic target recognition (ATR) tasks. The method is based on locally adaptive target segmentation, neural network classifier design, and a novel view selection mechanism that develops ‘‘visual filters’’ responsive to specific target classes that encode the complete viewing sphere with a small number of prototypical examples. The optimal set of visual filters is found via a crossvalidation-like data reduction algorithm used to train banks of backpropagation (BP) neural networks. To improve recognition accuracy under noisy or occluded conditions, as well as to eliminate false alarms, the proposed recognition system employs a temporal evidence integration technique that enables tracking and lock-on even when both targets and camera move. Experimental results on synthetic and real-world imagery demonstrate the feasibility of our approach.
Barnabas Takacs, Lev S. Sadovnik, "Three-dimensional recognition and tracking using neural networks trained on optimal views," Optical Engineering 37(3), (1 March 1998). https://doi.org/10.1117/1.601915


A color fusion method of infrared and low light level...
Proceedings of SPIE (November 24 2014)
3D target recognition using quasi-optimal visual filters
Proceedings of SPIE (September 18 1998)
Analysis of probe methodologies for target recognition
Proceedings of SPIE (June 14 1996)
Robust automatic target recognition in FLIR imagery
Proceedings of SPIE (May 02 2012)
An approach to target detection in forested scenes
Proceedings of SPIE (April 16 2008)

Back to Top