Distractor-aware deep regression for visual tracking

Simple item page
dc.contributor.authorDu, Ming
dc.contributor.authorDing, Yang
dc.contributor.authorMeng, Xiuyun
dc.contributor.authorWei, Hua-Liang
dc.contributor.authorZhao, Yifan
dc.date.accessioned2019-02-05T15:04:47Z
dc.date.available2019-02-05T15:04:47Z
dc.date.issued2019-01-18
dc.description.abstractIn recent years, regression trackers have drawn increasing attention in the visual-object tracking community due to their favorable performance and easy implementation. The tracker algorithms directly learn mapping from dense samples around the target object to Gaussian-like soft labels. However, in many real applications, when applied to test data, the extreme imbalanced distribution of training samples usually hinders the robustness and accuracy of regression trackers. In this paper, we propose a novel effective distractor-aware loss function to balance this issue by highlighting the significant domain and by severely penalizing the pure background. In addition, we introduce a full differentiable hierarchy-normalized concatenation connection to exploit abstractions across multiple convolutional layers. Extensive experiments were conducted on five challenging benchmark-tracking datasets, that is, OTB-13, OTB-15, TC-128, UAV-123, and VOT17. The experimental results are promising and show that the proposed tracker performs much better than nearly all the compared state-of-the-art approaches.en_UK
dc.identifier.citationMing Du, Yan Ding, Xiuyun Meng, et al., Distractor-aware deep regression for visual tracking. Sensors, 2019, Volume 19, Issue 2, Article number 387en_UK
dc.identifier.issn1424-8220
dc.identifier.urihttps://doi.org/10.3390/s19020387
dc.identifier.urihttps://dspace.lib.cranfield.ac.uk/handle/1826/13882
dc.language.isoenen_UK
dc.publisherMDPIen_UK
dc.rightsAttribution 4.0 International*
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/*
dc.subjectobject trackingen_UK
dc.subjectdeep-regression networksen_UK
dc.subjectdata imbalanceen_UK
dc.subjectdistractor awareen_UK
dc.titleDistractor-aware deep regression for visual trackingen_UK
dc.typeArticleen_UK

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Distractor-aware_deep_regression_for_visual_tracking-2019.pdf
Size:
3.64 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.63 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Staff publications (SATM)