High-Performance Long-Term Tracking With Meta-Updater

Dai, Kenan; Zhang, Yunhua; Wang, Dong; Li, Jianhua; Lu, Huchuan; Yang, Xiaoyun

doi:10.1109/cvpr42600.2020.00633

Cited by 220 publications

(146 citation statements)

References 38 publications

Supporting

Mentioning

144

Contrasting

Order By: Relevance

“…Correlation filters are popular due to high tracking accuracy and high computational efficiency. The correlation filter by Bolme et al [40] has been extended to many variants such as kernel correlation filters [41,42], long-term memory [43][44][45], multi-dimensional features [46,47], part-based strategies [48][49][50], scale es-timation [51][52][53], context-aware filters [54][55][56], spatial-temporal regularization [57][58][59], deep learning [60,61], and multi-feature fusion [62][63][64]. Existing correlation filter-based trackers generally follow ridge regression models.…”

Section: Correlation Filter Trackingmentioning

confidence: 99%

Object Tracking in Hyperspectral-Oriented Video with Fast Spatial-Spectral Features

et al. 2021

View full text Add to dashboard Cite

This paper presents a correlation filter object tracker based on fast spatial-spectral features (FSSF) to realize robust, real-time object tracking in hyperspectral surveillance video. Traditional object tracking in surveillance video based only on appearance information often fails in the presence of background clutter, low resolution, and appearance changes. Hyperspectral imaging uses unique spectral properties as well as spatial information to improve tracking accuracy in such challenging environments. However, the high-dimensionality of hyperspectral images causes high computational costs and difficulties for discriminative feature extraction. In FSSF, the real-time spatial-spectral convolution (RSSC) kernel is updated in real time in the Fourier transform domain without offline training to quickly extract discriminative spatial-spectral features. The spatial-spectral features are integrated into correlation filters to complete the hyperspectral tracking. To validate the proposed scheme, we collected a hyperspectral surveillance video (HSSV) dataset consisting of 70 sequences in 25 bands. Extensive experiments confirm the advantages and the efficiency of the proposed FSSF for object tracking in hyperspectral video tracking in challenging conditions of background clutter, low resolution, and appearance changes.

show abstract

Section: Correlation Filter Trackingmentioning

confidence: 99%

Object Tracking in Hyperspectral-Oriented Video with Fast Spatial-Spectral Features

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Consequently, the MBMD [11] method begins to control local and global switching with an additional verifier, which is an online updated classifier. Recently, the LTMU [6] method improves the robustness by adding a meta-updater to guide the update of the online tracker. Nevertheless, several factors limiting the performance of long-term tracker remain; one is the poor discrimination ability of verifier, and the other is the risk of global tracker drifting to similar object when facing complex situations, such as out-of-view and full-occlusion.…”

Section: Related Workmentioning

confidence: 99%

“…Motivated by these analysis, we propose a long-term tracking framework, which owns a verifier that can effectively eliminate interferences and a robust global track strategy to cope with complex scenes, such as out-of-view and full-occlusion. Our tracker adopts the similar framework to LTMU [6], which owns a verifier to reidentify target and a global tracker to search target when it disappears. However, as shown in the first two sequences in Fig.…”

Section: Introductionmentioning

confidence: 99%

A Method of Stable Long-Term Single Object Tracking

Tong

Zhao

et al. 2021

2021 IEEE International Conference on Multimedia and Expo (ICME)

View full text Add to dashboard Cite

We propose a stable long-term tracking method to deal with visual tracking in multiple complex scenarios to solve the problem of frequent disappearance and reappearance of targets in long-term tracking. In our method, we do not blindly start the global tracker once the target disappears, but use it only when necessary and in reasonable scope with the assistance of localization module. In addition, we designed an FP-verifier based on feature pools to reevaluate the candidate bounding boxes given by our local tracker and global tracker to ensure that online learning local tracker can be updated stably. Our method outperforms the state-of-the-art results on the VOT2020LT challenge. In addition, the control experiments show that our FP-verifier is more effective than the RT-MDNet verifier used by the top three winners of VOT2020LT challenge.

show abstract

“…Siam R-CNN [202] − 0.648 Dimp50 [206] 0.564 0.568 LTMU [207] 0.572 0.572 GlobalTrack [208] 0.528 0.517 ATOM [209] 0.500 0.501 Best performance on VOT dataset Performance A R EAO AO Fig. 9 Historical results on the VOT datasets.…”

Section: Trackers Precision Successmentioning

confidence: 99%

Advances in Deep Learning Methods for Visual Tracking: Literature Review and Fundamentals

Zhang

Jiang

Fan

et al. 2021

Int. J. Autom. Comput.

View full text Add to dashboard Cite

Recently, deep learning has achieved great success in visual tracking tasks, particularly in single-object tracking. This paper provides a comprehensive review of state-of-the-art single-object tracking algorithms based on deep learning. First, we introduce basic knowledge of deep visual tracking, including fundamental concepts, existing algorithms, and previous reviews. Second, we briefly review existing deep learning methods by categorizing them into data-invariant and data-adaptive methods based on whether they can dynamically change their model parameters or architectures. Then, we conclude with the general components of deep trackers. In this way, we systematically analyze the novelties of several recently proposed deep trackers. Thereafter, popular datasets such as Object Tracking Benchmark (OTB) and Visual Object Tracking (VOT) are discussed, along with the performances of several deep trackers. Finally, based on observations and experimental results, we discuss three different characteristics of deep trackers, i.e., the relationships between their general components, exploration of more effective tracking frameworks, and interpretability of their motion estimation components.

show abstract

High-Performance Long-Term Tracking With Meta-Updater

Cited by 220 publications

References 38 publications

Object Tracking in Hyperspectral-Oriented Video with Fast Spatial-Spectral Features

Object Tracking in Hyperspectral-Oriented Video with Fast Spatial-Spectral Features

A Method of Stable Long-Term Single Object Tracking

Advances in Deep Learning Methods for Visual Tracking: Literature Review and Fundamentals

Contact Info

Product

Resources

About