4 October 2017 Multi-object tracking via tracklet confidence-aided relative motion analysis
Author Affiliations +
J. of Electronic Imaging, 26(5), 050501 (2017). doi:10.1117/1.JEI.26.5.050501
Abstract
Applications for tracking multiple objects in an image sequence are frequently challenged by various uncertainties, such as occlusion, misdetection, and abrupt camera motion. In practical environments, these uncertainties may occur simultaneously and with no pattern so that they must be jointly considered to achieve reliable tracking. We propose a two-step online multi-object tracking framework that incorporates a confidence-aided relative motion network (RMN) to jointly consider various difficulties. Because of the framework’s two-step data association process and the similarity function using RMNs, the proposed method achieves robust performance in the presence of most kinds of uncertainties. In our experiments, the proposed method exhibits a very robust and efficient performance compared with other state-of-the-art algorithms.
© 2017 SPIE and IS&T
Han-Mu Park, Se-Hoon Park, Kuk-Jin Yoon, "Multi-object tracking via tracklet confidence-aided relative motion analysis," Journal of Electronic Imaging 26(5), 050501 (4 October 2017). http://dx.doi.org/10.1117/1.JEI.26.5.050501 Submission: Received 18 May 2017; Accepted 11 September 2017
Submission: Received 18 May 2017; Accepted 11 September 2017
JOURNAL ARTICLE
4 PAGES


SHARE
KEYWORDS
Detection and tracking algorithms

Cameras

Motion analysis

Motion models

Image filtering

Motion measurement

Performance modeling

Back to Top