Fuzzy Dynamic Matching Approach for Multi-Feature Tracking

Lopes, Nuno Vieira; Couto, Pedro A.; Bustince, Humberto; Melo-Pinto, Pedro

http://hdl.handle.net/10400.8/3552

Use this identifier to reference this record.

Name:	Description:	Size:	Format:
eurofuse(2009).pdf		906.33 KB	Adobe PDF	Download

Send Feedback

Authors

Abstract(s)

Feature tracking is one of the most challenging and important tasks in computer vision playing an important role in several areas. In this paper, a new approach for multi feature tracking is presented. Information from the image gray levels and the features movement model is aggregated through the use of fuzzy sets with a fuzzy inference engine to give the final output. Experimental results are presented showing that the approach successfully copes with usual difficulties within this problem.