APPLICATION OF NEURAL NETWORKS TO VEHICLE RECOGNITION AND TRACKING
暂无分享,去创建一个
Three aspects of the application of neural networks to object recognition and tracking from a moving camera are evaluated on real data. The combination of a correlator with a Kalman filter and a neural network embedded within the tracking loop is shown to increase true recognitions and decrease false recognitions. Large training sets may be reduced by condensing via a k-nearest-neighbour algorithm without significant loss of network performance. Preprocessing the data using a self-adapting layer of discrete wavelet nodes yields performance that is comparable to a multilayer perceptron net.
[1] David Casasent,et al. Neural net design of macro Gabor wavelet filters for distortion-invariant object detection in clutter , 1994 .
[2] Farid Amoozegar,et al. Neural-network-based target tracking state-of-the-art survey , 1998 .
[3] Steven K. Rogers,et al. COMPLETE AUTOMATIC TARGET CUER/RECOGNITION SYSTEM FOR TACTICAL FORWARD-LOOKING INFRARED IMAGES , 1997 .