Sökning: id:"swepub:oai:DiVA.org:liu-163194" >
ATOM: Accurate trac...
ATOM: Accurate tracking by overlap maximization
-
- Danelljan, Martin, 1989- (författare)
- Linköpings universitet,Datorseende,Tekniska fakulteten,Swiss Fed Inst Technol, Switzerland
-
- Bhat, Goutam (författare)
- Linköpings universitet,Datorseende,Tekniska fakulteten,Swiss Fed Inst Technol, Switzerland
-
- Khan, Fahad Shahbaz, 1983- (författare)
- Linköpings universitet,Datorseende,Tekniska fakulteten,Incept Inst Artificial Intelligence, U Arab Emirates
-
visa fler...
-
- Felsberg, Michael, 1974- (författare)
- Linköpings universitet,Datorseende,Tekniska fakulteten
-
visa färre...
-
(creator_code:org_t)
- IEEE, 2019
- 2019
- Engelska.
-
Ingår i: 2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019). - : IEEE. - 9781728132938 ; , s. 4655-4664
- Relaterad länk:
-
https://urn.kb.se/re...
-
visa fler...
-
https://doi.org/10.1...
-
visa färre...
Abstract
Ämnesord
Stäng
- While recent years have witnessed astonishing improvements in visual tracking robustness, the advancements in tracking accuracy have been limited. As the focus has been directed towards the development of powerful classifiers, the problem of accurate target state estimation has been largely overlooked. In fact, most trackers resort to a simple multi-scale search in order to estimate the target bounding box. We argue that this approach is fundamentally limited since target estimation is a complex task, requiring highlevel knowledge about the object. We address this problem by proposing a novel tracking architecture, consisting of dedicated target estimation and classification components. High level knowledge is incorporated into the target estimation through extensive offline learning. Our target estimation component is trained to predict the overlap between the target object and an estimated bounding box. By carefully integrating targetspecific information, our approach achieves previously unseen bounding box accuracy. We further introduce a classification component that is trained online to guarantee high discriminative power in the presence of distractors. Our final tracking framework sets a new state-of-the-art on five challenging benchmarks. On the new large-scale TrackingNet dataset, our tracker ATOM achieves a relative gain of 15% over the previous best approach, while running at over 30 FPS. Code and models are available at https://github.com/visionml/pytracking.
Ämnesord
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datorseende och robotik (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Vision and Robotics (hsv//eng)
Publikations- och innehållstyp
- ref (ämneskategori)
- kon (ämneskategori)
Hitta via bibliotek
Till lärosätets databas