New technique for online object tracking‐by‐detection in video. Issue 12 (1st December 2014)

• Record Type: Journal Article
• Authors: Azab, Maha M.; Shedeed, Howida A.; Hussein, Ashraf S.
• Is Part Of: IET image processing. Volume 8:Issue 12(2014)
• Page Start: 794
• Page End: 803
• Publication Date: 2014-12-01
• Subjects: object tracking -- object detection -- video signal processing -- computer vision -- image motion analysis -- particle filtering (numerical methods) -- image colour analysis -- feature extraction -- image texture -- image classification -- edge detection; online object tracking‐by‐detection -- computer vision -- video surveillance -- automated video analysis -- motion tracking -- stationary camera -- particle filtering framework -- local binary pattern texture feature -- RGB colour feature -- Sobel edge feature extraction -- Choquet fuzzy integral -- texture confidence map -- continuous confidence detectors -- classifier confidence maps -- online boosting classifier extraction -- particle filtering framework -- indoor dataset sequences -- outdoor dataset sequences -- illumination variation -- scene motion; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2014.0238
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : Object detection and tracking is an important task within the field of computer vision, because of its promising application in many areas, such as video surveillance. The need for automated video analysis has generated a great deal of interest in the area of motion tracking. A new technique is proposed for online object tracking‐by‐detection capable of achieving high detection and tracking rates, using a stationary camera, in a particle filtering framework. The fundamental innovation is that the detection technique integrates the local binary pattern texture feature, the red green blue (RGB) colour feature and the Sobel edge feature, using 'Choquet' fuzzy integral to avoid uncertainty in the classification. This is performed by extracting the colour and edge grey scale confidence maps and introducing the texture confidence map. Then, the tracking technique makes use of the continuous confidence detectors, extracted from those confidence maps, along with another three introduced classifier confidence maps, extracted from an online boosting classifier. Finally, both the confidence detectors and the classifier maps are integrated in the particle filtering framework, using the Choquet integral. Experimental results for both indoor and outdoor dataset sequences confirmed the robustness of the proposed technique against illumination variation and scene motion.