Abstract
This paper summarizes a research effort to explore the use of neural networks for fusing information from multiple sensors in an automatic target recognition (ATR) scenario. Data from two sensors, forward-looking infrared (FLIR) and millimeter wave (MMW) radar, were collected on three ground targets: tank, truck, and armored personnel carrier (APC). Two different types of classifiers were developed and compared: a conventional statistical quadratic and a neural network consisting of a multilayer perceptron with a backpropagation of error training algorithm. Single sensor classifiers were developed for both FLIR and MMW radar data. In addition, multisensor classifiers were developed using merged FLIR and MMW radar features. The experimental results indicate that a backpropagation neural network (BPN) outperformed the conventional quadratic classifier. Neural networks may provide better solutions to the varying clutter problem found in ATR environments because neural networks can describe both linear and nonlinear boundaries required for complex decision surfaces.© (1991) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
