Context-Aware Three-Dimensional Mean-Shift With Occlusion Handling for Robust Object Tracking in RGB-D Videos

Liu, Ye; Jing, Xiao‐Yuan; Nie, Jianhui; Gao, Hao; Li, Jun; Jiang, Guoping

doi:10.1109/tmm.2018.2863604

Cited by 97 publications

(60 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Results are reported in Table 1. OTR convincingly sets the new state-of-the-art in terms of both overall ranking and the average success by a large margin compared to the next-best trackers ( Table 1). In terms of average success, OTR obtains a 4.3% gain compared to the second ranking tracker ca3dms+toh [26], which tracks the target in 3D as well, but without reconstruction. This result speaks in favour of our 3D-based pre-image construction and its superiority for RGB-D tracking.…”

Section: Performance On Ptb Benchmark [35]mentioning

confidence: 98%

“…The OTR tracker is compared to all trackers available on the PTB leaderboard: ca3dms+toh [26], CSR-rgbd++ [19], 3D-T [3], PT [35], OAPF [31], DM-DCF [20], DS-KCF-Shape [16], DS-KCF [6], DS-KCF-CPP [16], hiob lc2 [36] and we added two recent trackers STC [40] and DLST [1]. Results are reported in Table 1. OTR convincingly sets the new state-of-the-art in terms of both overall ranking and the average success by a large margin compared to the next-best trackers ( Table 1).…”

Section: Performance On Ptb Benchmark [35]mentioning

confidence: 99%

“…The OTR tracker is compared to the following trackers: CSR-rgbd++ [19], ca3dms+toh [26], STC [40], DS-KCF-Shape [16], PT [35], DS-KCF [6] and OAPF [31]. The results are presented in Table 2 and Figure 4.…”

Section: Performance On Stc Benchmark [40]mentioning

confidence: 99%

“…The proposed OTR tracker confidently tracks the target undergoing a substantial pose change. Two state-of-the-art RGB-D trackers (CSR-rgbd++ [19] and cs3dms+toh [26]), that do not apply the multi-view DCFs nor target 3D pre-image, result in less accurate localization or failure.…”

Section: Ablation Studiesmentioning

confidence: 99%

See 3 more Smart Citations

Object Tracking by Reconstruction With View-Specific Discriminative Correlation Filters

Kart

Lukežič

Kristan

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

Standard RGB-D trackers treat the target as an inherently 2D structure, which makes modelling appearance changes related even to simple out-of-plane rotation highly challenging. We address this limitation by proposing a novel long-term RGB-D tracker -Object Tracking by Reconstruction (OTR). The tracker performs online 3D target reconstruction to facilitate robust learning of a set of viewspecific discriminative correlation filters (DCFs). The 3D reconstruction supports two performance-enhancing features: (i) generation of accurate spatial support for constrained DCF learning from its 2D projection and (ii) pointcloud based estimation of 3D pose change for selection and storage of view-specific DCFs which are used to robustly localize the target after out-of-view rotation or heavy occlusion. Extensive evaluation of OTR on the challenging Princeton RGB-D tracking and STC Benchmarks shows it outperforms the state-of-the-art by a large margin.

show abstract

Section: Performance On Ptb Benchmark [35]mentioning

confidence: 98%

Section: Performance On Ptb Benchmark [35]mentioning

confidence: 99%

Section: Performance On Stc Benchmark [40]mentioning

confidence: 99%

Section: Ablation Studiesmentioning

confidence: 99%

See 2 more Smart Citations

Object Tracking by Reconstruction With View-Specific Discriminative Correlation Filters

Kart

Lukežič

Kristan

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

show abstract

“…They later extended their work by using a graph cut method with color and depth priors for the foreground mask segmentation [19] and more recently proposed a view-specific DCF using object's 3D structure based masks [21]. Liu et al [30] proposed a 3D mean-shift tracker with occlusion handling. Xiao et al [45] introduced a two-layered representation of the target by adopting a spatio-temporal consistency constraints.…”

Section: Related Workmentioning

confidence: 99%

CDTB: A Color and Depth Visual Object Tracking Dataset and Benchmark

Lukežič

Kart

Käpylä

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

We propose a new color-and-depth general visual object tracking benchmark (CDTB). CDTB is recorded by several passive and active RGB-D setups and contains indoor as well as outdoor sequences acquired in direct sunlight. The CDTB dataset is the largest and most diverse dataset for RGB-D tracking, with an order of magnitude larger number of frames than related datasets. The sequences have been carefully recorded to contain significant object pose change, clutter, occlusion, and periods of long-term target absence to enable tracker evaluation under realistic conditions. Sequences are per-frame annotated with 13 visual attributes for detailed analysis. Experiments with RGB and RGB-D trackers show that CDTB is more challenging than previous datasets. State-of-the-art RGB trackers outperform the recent RGB-D trackers, indicating a large gap between the two fields, which has not been detected by the prior benchmarks. Based on the results of the analysis we point out opportunities for future research in RGB-D tracker design.

show abstract

Facilitating 3D Object Tracking in Point Clouds with Image Semantics and Geometry

Wang

Hui

Xie

2021

Pattern Recognition and Computer Vision

View full text Add to dashboard Cite

Context-Aware Three-Dimensional Mean-Shift With Occlusion Handling for Robust Object Tracking in RGB-D Videos

Cited by 97 publications

References 43 publications

Object Tracking by Reconstruction With View-Specific Discriminative Correlation Filters

Object Tracking by Reconstruction With View-Specific Discriminative Correlation Filters

CDTB: A Color and Depth Visual Object Tracking Dataset and Benchmark

Facilitating 3D Object Tracking in Point Clouds with Image Semantics and Geometry

Contact Info

Product

Resources

About