2021 IEEE International Conference on Image Processing

19-22 September 2021 • Anchorage, Alaska, USA

Imaging Without Borders

2021 IEEE International Conference on Image Processing

19-22 September 2021 • Anchorage, Alaska, USA

Login Paper Search My Schedule Paper Index Help

My ICIP 2021 Schedule

Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
  1. Create a login based on your email (takes less than one minute)
  2. Perform 'Paper Search'
  3. Select papers that you desire to save in your personalized schedule
  4. Click on 'My Schedule' to see the current list of selected papers
  5. Click on 'Printable Version' to create a separate window suitable for printing (the header and menu will appear, but will not actually print)

Paper Detail

Paper IDMLR-APPL-IP-2.11
Paper Title ROBUST TRACKING FOR MOTION BLUR VIA CONTEXT ENHANCEMENT
Authors Zhongjie Mao, Xi Chen, Yucheng Wang, Jia Yan, Wuhan University, China
SessionMLR-APPL-IP-2: Machine learning for image processing 2
LocationArea E
Session Time:Monday, 20 September, 15:30 - 17:00
Presentation Time:Monday, 20 September, 15:30 - 17:00
Presentation Poster
Topic Applications of Machine Learning: Machine learning for image processing
IEEE Xplore Open Preview  Click here to view in IEEE Xplore
Abstract Motion blur is pervasive in object tracking, especially in applications such as unmanned aerial vehicles or pods. However, the focus of tracking research has been on generic visual tracking rather than specific scenarios, such as motion blur, which degrades the performance in these scenarios. In this work, we propose an effective method for tracking in motion blur by employing the framework of D3S (a discriminative single shot segmentation tracker). IQA (image quality assessment) and deblurring components are both introduced into the basic D3S framework to enhance context patch, which improves the tracking accuracy in blurred target tracking. Extensive experiments demonstrate that our tracker can robustly track objects, not only in blurred videos but also in other challenging scenes.