1 September 2003 Multistage infrared target detection
Author Affiliations +
Algorithms are considered for searching wide-area forward-looking infrared imagery for military vehicles. Wide-area search has typically been handled by using a simple detection algorithm with low computational cost to search the entire image or set of images, followed by a clutter rejection algorithm that analyzes only those portions of the image that are marked by the detection algorithm. We start with a feature-based detector and an eigen-neural-based clutter rejecter, and examine a number of architectures for combining these modules to maximize joint performance. The architectures considered include a clutter rejection threshold method and a nonlinear learning-based combination. The performance of the architectures is compared using a set of several thousand real images.
© (2003) Society of Photo-Optical Instrumentation Engineers (SPIE)
Alex Lipchen Chan, Alex Lipchen Chan, Sandor Z. Der, Sandor Z. Der, Nasser M. Nasrabadi, Nasser M. Nasrabadi, } "Multistage infrared target detection," Optical Engineering 42(9), (1 September 2003). https://doi.org/10.1117/1.1593038 . Submission:


Back to Top