Cross-correlation-based robust object tracking in aerial videos
Paper
Paper/Presentation Title | Cross-correlation-based robust object tracking in aerial videos |
---|---|
Presentation Type | Paper |
Authors | Perera, Asanka G, Law, Yee Wei and Chahl, Javaan |
Journal or Proceedings Title | Proceedings of the 18th Australian International Aerospace Congress (AIAC18) |
Journal Citation | pp. 222-228 |
Number of Pages | 7 |
Year | 2019 |
Place of Publication | Australia |
ISBN | 9781925627213 |
Web Address (URL) of Paper | https://search.informit.org/doi/10.3316/informit.321573522790602 |
Web Address (URL) of Conference Proceedings | https://search.informit.org/doi/10.3316/INFORMIT.9781925627213 |
Conference/Event | 18th Australian International Aerospace Congress (AIAC18) |
Event Details | 18th Australian International Aerospace Congress (AIAC18) Parent Australian International Aerospace Congress Delivery In person Event Date 24 to end of 26 Feb 2019 Event Location Melbourne, Australia |
Abstract | Normalized cross-correlation (NCC) is a well-known technique in visual feature tracking. However, it is sensitive to the scale, rotation and warping differences in the target object. In this work, we propose a method to use with the NCC filter for rotation- and scale-invariant object tracking. The proposed solution consists of three modules: (i) multiple appearance generation in the search image at different rotation angles and scales, (ii) bounding box drift correction by a re-initialization step, and (iii) failure handling by tracker combination. A point tracker that uses the Kanade-Lucas-Tomasi feature-tracking algorithm and a histogram-based tracker that uses the continuously adaptive mean shift (CAMShift) algorithm are used as supporting trackers. A "Faster R-CNN" detector is used to adjust the estimated bounding boxes. The proposed combined tracker is evaluated using the VisDrone2018 and VOT2018 datasets and compared with five recently published trackers. |
Keywords | Aerial video; scale-invariant; rotation-invariant; normalized cross-correlation; object tracking |
Contains Sensitive Content | Does not contain sensitive content |
ANZSRC Field of Research 2020 | 4007. Control engineering, mechatronics and robotics |
Public Notes | Files associated with this item cannot be displayed due to copyright restrictions. |
Byline Affiliations | University of South Australia |
Defence Science and Technology Group, Australia |
https://research.usq.edu.au/item/z77y3/cross-correlation-based-robust-object-tracking-in-aerial-videos
32
total views0
total downloads0
views this month0
downloads this month