Occlusion handling method for object tracking using RGB-D data

Author

Benou, Ariel ; Benou, Itay ; Hagage, Rami

Author_Institution

Dept. of Electr. Eng., Ben Gurion Univ. of the Negev, Beer-Sheva, Israel

fYear

2014

fDate

3-5 Dec. 2014

Firstpage

1

Lastpage

5

Abstract

We propose a novel method for occlusion handling in object tracking using RGB-D sequences. The proposed method is designed as a stand-alone system which can be integrated into any 2D tracker, and consists of three stages: 1) Occlusion detection by fitting a Gaussian Mixture Model (GMM) to the depth distribution of the targets bounding box. 2) Reliable tracking during partial and full occlusions by incorporating RGB and depth segmentation of the scene. 3) Target recovery using depth information and motion estimation. We carry out a quantitative evaluation which shows a significant improvement in performance of state of the art RGB trackers, and also in comparison to another RGB-D tracker.

Keywords

Gaussian processes; image segmentation; mixture models; motion estimation; object tracking; 2D tracker; Gaussian mixture model; RGB-D data; RGB-D sequences; RGB-D tracker; depth distribution; depth information; depth segmentation; full occlusions; motion estimation; object tracking; occlusion detection; occlusion handling method; partial occlusions; reliable tracking; stand-alone system; target recovery; targets bounding box; Computer vision; Conferences; Histograms; Motion segmentation; Object tracking; Target tracking; Kinect; Occlusion Handling; RGB-D; Tracking;

fLanguage

English

Publisher

ieee

Conference_Titel

Electrical & Electronics Engineers in Israel (IEEEI), 2014 IEEE 28th Convention of

Conference_Location

Eilat

Print_ISBN

978-1-4799-5987-7

Type

conf

DOI

10.1109/EEEI.2014.7005857

Filename

7005857