Co-difference based object tracking algorithm for infrared videos
Date
2016Source Title
Proceedings of the IEEE International Conference on Image Processing, ICIP 2016
Print ISSN
1522-4880
Publisher
IEEE
Pages
434 - 438
Language
English
Type
Conference PaperItem Usage Stats
235
views
views
383
downloads
downloads
Abstract
This paper presents a novel infrared (IR) object tracking algorithm based on the co-difference matrix. Extraction of co-difference features is similar to the well known covariance method except that the vector product operator is redefined in a multiplication-free manner. The new operator yields a computationally efficient implementation for real time object tracking applications. Experiments on an extensive set of IR image sequences indicate that the new method performs better than covariance tracking and other tracking algorithms without requiring any multiplication operations.
Keywords
Co-difference matrixCovariance features
Infrared band
Object tracking
Surveillance
Space surveillance
Computationally efficient
Multiplication operations
Object tracking algorithm
Real-time object tracking