Paper
6 December 1989 Parallel Algorithms For Automatic Target Identification Using CO2 Laser Radar Imagery
Arthur V. Forman Jr., Daniel J. Sullivan
Author Affiliations +
Abstract
This paper describes a parallel implementation of algorithms for automatic target identification using a CO2 laser radar sensor, which provides pixel-registered visual, infrared, relative range and Doppler (motion) images. Images are preprocessed to remove artifacts and speckle and to detect edges. The processed images are then passed to a transformation which provides a representation independent of translation, rotation, and scaling of the input scene. The transformed image is designed to be input to a neural network to extract features representative of the targets. This paper also discusses three-dimensional transformation of range images for pattern matching and the implementation of algorithms in a single instruction, multiple data (SIMD) parallel architecture.
© (1989) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Arthur V. Forman Jr. and Daniel J. Sullivan "Parallel Algorithms For Automatic Target Identification Using CO2 Laser Radar Imagery", Proc. SPIE 1154, Real-Time Signal Processing XII, (6 December 1989); https://doi.org/10.1117/12.962382
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Target recognition

Doppler effect

Signal processing

Detection and tracking algorithms

Image segmentation

Image processing

Sensors

RELATED CONTENT

Very fast SAR detection
Proceedings of SPIE (June 14 1996)
Survey of radar-based target recognition techniques
Proceedings of SPIE (August 01 1991)
Comparison of features from SAR and GMTI imagery of ground...
Proceedings of SPIE (September 12 2003)
Radar waveform diversity for tracking
Proceedings of SPIE (August 05 2009)

Back to Top