Multi-sensor registration via fuzzy c-mean cluster

A new multi-sensor registration algorithm via fuzzy c-mean cluster is presented after analyzing some previous multi-sensor data registrations. In the case of multi-target the same frame measure data from multi-sensor are clustered via fuzzy c-mean algorithm to get the cluster centers as the ideal positions of targets. Then the certain sensor's error estimation value for this frame is obtained by averaging this sensor's errors corresponding to these ideal positions of targets. Finally these error estimations of certain sensor from each frame are averaged to accomplish the multi-sensor registration. The advantage of this algorithm are better real-timely and having nothing with the registration model. In the end the simulation result and analysis are given.