The possibility of using certain kinds of neural networks, shared weight neural networks, to recognizevehicles in IR images is investigated. We use the neural network as a preprocessor to find tank wheelsin the images, followed by a more specific traditional search in the region(s) of interest found by thenetwork; i.e., the neural network is used as a feature detector. In this way, although we train thenetworks on individual samples, we use the trained networks as nonlinear filters on entire images.The resulting system is tested on scale dependency and sensitivity to clutter in the background ofimages and performs adequately.
展开▼