Neurofuzzy prediction for visual tracking

Real time visual tracking is a complicated problem due the different dynamic of the objects involved in the process. On one hand the algorithms for image processing usually consume a lot of time on the other hand the motors and mechanisms used for the camera movements are significantly slow. This work describes the use of ANFIS model to reduce the delay´s effects in the control for visual tracking and also explains how we resolved this problem by predicting the target movement using a neurofuzzy approach.