Data used for detection and tracking of dynamic objects for visually impaired people

This paper presents in detail the methodology for the detection and tracking of dynamic objects from the article in press (A new methodology applied to dynamic object detection and tracking systems for visually impaired people [1]). In order to validate this methodology, four different architectures have been designed in this paper. These architectures have implemented the techniques of pattern recognition, optical flow, background subtraction and color tracking to enable comparison and to see which is the most appropriate in a given environment. In this paper we also present a method created to quantify the effectiveness of each architecture implemented.