Accurate bounding-box regression with distance-IoU loss for visual tracking

Yuan, D; Shu, X; Fan, N; Chang, X; Liu, Q; He, Z

Accurate bounding-box regression with distance-IoU loss for visual tracking

Yuan, D Shu, X Fan, N Chang, X

Liu, Q He, Z

Permalink

Publisher:: ACADEMIC PRESS INC ELSEVIER SCIENCE
Publication Type:: Journal Article
Citation:: Journal of Visual Communication and Image Representation, 2022, 83
Issue Date:: 2022-02-01

Closed Access

	Filename	Description	Size
	Accurate bounding-box regression with distance-IoU loss for visual tracking.pdf	Published version	4.72 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Yuan, D
dc.contributor.author	Shu, X
dc.contributor.author	Fan, N
dc.contributor.author	Chang, X https://orcid.org/0000-0002-7778-8807
dc.contributor.author	Liu, Q
dc.contributor.author	He, Z
dc.date.accessioned	2023-03-20T00:00:27Z
dc.date.available	2023-03-20T00:00:27Z
dc.date.issued	2022-02-01
dc.identifier.citation	Journal of Visual Communication and Image Representation, 2022, 83
dc.identifier.issn	1047-3203
dc.identifier.issn	1095-9076
dc.identifier.uri	http://hdl.handle.net/10453/167639
dc.description.abstract	Most existing trackers are based on using a classifier and multi-scale estimation to estimate the target state. Consequently, and as expected, trackers have become more stable while tracking accuracy has stagnated. While trackers adopt a maximum overlap method based on an intersection-over-union (IoU) loss to mitigate this problem, there are defects in the IoU loss itself, that make it impossible to continue to optimize the objective function when a given bounding box is completely contained within/without another bounding box; this makes it very challenging to accurately estimate the target state. Accordingly, in this paper, we address the above-mentioned problem by proposing a novel tracking method based on a distance-IoU (DIoU) loss, such that the proposed tracker consists of target estimation and target classification. The target estimation part is trained to predict the DIoU score between the target ground-truth bounding-box and the estimated bounding-box. The DIoU loss can maintain the advantage provided by the IoU loss while minimizing the distance between the center points of two bounding boxes, thereby making the target estimation more accurate. Moreover, we introduce a classification part that is trained online and optimized with a Conjugate-Gradient-based strategy to guarantee real-time tracking speed. Comprehensive experimental results demonstrate that the proposed method achieves competitive tracking accuracy when compared to state-of-the-art trackers while with a real-time tracking speed.
dc.language	English
dc.publisher	ACADEMIC PRESS INC ELSEVIER SCIENCE
dc.relation	http://purl.org/au-research/grants/arc/DE190100626
dc.relation.ispartof	Journal of Visual Communication and Image Representation
dc.relation.isbasedon	10.1016/j.jvcir.2021.103428
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	0801 Artificial Intelligence and Image Processing, 1203 Design Practice and Management, 1905 Visual Arts and Crafts
dc.subject.classification	Artificial Intelligence & Image Processing
dc.title	Accurate bounding-box regression with distance-IoU loss for visual tracking
dc.type	Journal Article
utslib.citation.volume	83
utslib.for	0801 Artificial Intelligence and Image Processing
utslib.for	1203 Design Practice and Management
utslib.for	1905 Visual Arts and Crafts
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Strength - AAII - Australian Artificial Intelligence Institute
utslib.copyright.status	closed_access	*
dc.date.updated	2023-03-20T00:00:26Z
pubs.publication-status	Published
pubs.volume	83

Abstract:

Most existing trackers are based on using a classifier and multi-scale estimation to estimate the target state. Consequently, and as expected, trackers have become more stable while tracking accuracy has stagnated. While trackers adopt a maximum overlap method based on an intersection-over-union (IoU) loss to mitigate this problem, there are defects in the IoU loss itself, that make it impossible to continue to optimize the objective function when a given bounding box is completely contained within/without another bounding box; this makes it very challenging to accurately estimate the target state. Accordingly, in this paper, we address the above-mentioned problem by proposing a novel tracking method based on a distance-IoU (DIoU) loss, such that the proposed tracker consists of target estimation and target classification. The target estimation part is trained to predict the DIoU score between the target ground-truth bounding-box and the estimated bounding-box. The DIoU loss can maintain the advantage provided by the IoU loss while minimizing the distance between the center points of two bounding boxes, thereby making the target estimation more accurate. Moreover, we introduce a classification part that is trained online and optimized with a Conjugate-Gradient-based strategy to guarantee real-time tracking speed. Comprehensive experimental results demonstrate that the proposed method achieves competitive tracking accuracy when compared to state-of-the-art trackers while with a real-time tracking speed.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/167639