Skip to Content
You are currently on the new version of our website. Access the old version .

Journal of Imaging, Volume 8, Issue 3

2022 March - 32 articles

Cover Story: Visual tracking is still an open challenge in computer vision, especially with mobile cameras and in the wild. Errors in the target’s bounding-box estimations accumulate over time and yield to drifting of the tracker. Hence, bounding-box estimations must be as precise as possible in each frame. This article proposes a new iterative procedure to locate the target in the image by gradually refining its bounding box. It also introduces the idea of non-conflicting bounding-box transformations, which allows applying multiple refinements to the target’s bounding box without introducing ambiguities when learning parameters. The empirical results demonstrate that the proposed approach improves the single iterative refinement in terms of accuracy of tracking results. View this paper
  • Issues are regarded as officially published after their release is announced to the table of contents alert mailing list .
  • You may sign up for email alerts to receive table of contents of newly released issues.
  • PDF is the official format for papers published in both, html and pdf forms. To view the papers in pdf format, click on the "PDF Full-text" link, and use the free Adobe Reader to open them.

Articles

There are no articles in this issue yet.

Get Alerted

Add your email address to receive forthcoming issues of this journal.

XFacebookLinkedIn
J. Imaging - ISSN 2313-433X