OBJECT TRACKING BY AN OPTOELECTRONIC INNER-PRODUCT COMPLEX NEURAL-NETWORK

A complex associative memory model based on a neural network architect ure is proposed for tracking three-dimensional objects in a dynamic en vironment. The storage representation of the complex associative memor y model is based on an efficient amplitude-modulated phase-only matche d filter. The input to the memory is derived from the discrete Fourier transform of the edge coordinates of the to-be-recognized moving obje ct, where the edges are obtained through motion-based segmentation of the image scene. An adaptive threshold is used during the decision-mak ing process to indicate a match or identify a mismatch. Computer simul ation on real-world data proves the effectiveness of the proposed mode l. The proposed scheme is readily amenable to optoelectronic implement ation.