Data association for multiple target tracking using Hopfield neural network
Henry Leung, Martin Blanchette · 2002
Data association consists of assigning measurements to the predicted track positions in the multiple target tracking application. The data association problem can be structured in a basic framework very similar to that of the classic travelling salesman problem (TSP). The derivation of the energy function is presented, and the solution is based on a modified Hopfield network which uses the Runge-Kutta method and Aiyer (1990) network's structure. We demonstrate the feasibility of applying neural network technology to multitarget tracking using simulated and real-life radar data. The modified Hopfield tracker is also observed to have better performance than the original Hopfield network.>