Object Tracking by Reconstruction With View-Specific Discriminative Correlation Filters

Kart, Ugur; Lukežič, Alan; Kristan, Matej; Kämäräinen, Joni-Kristian; Matas, Jiřı́

doi:10.1109/cvpr.2019.00143

Cited by 92 publications

(55 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The top tracker according to the EAO is mfDiMP (C.6) and is thus the VOT-RGBT2019 challenge winner. , OTR [45], SiamFC [7], CSRDCF-D [44], ECO [15] and CADMS [64]; thus 12 trackers were considered in the challenge. In the following we briefly overview the entries and provide the references to the original papers in Appendix D where available.…”

Section: The Vot-rgbt2019 Challenge Winnermentioning

confidence: 99%

The Seventh Visual Object Tracking VOT2019 Challenge Results

Kristan

Berg

Zheng

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)

Self Cite

382

359

View full text Add to dashboard Cite

The Visual Object Tracking challenge VOT2019 is the seventh annual tracker benchmarking activity organized by the VOT initiative. Results of 81 trackers are presented; many are state-of-the-art trackers published at major computer vision conferences or in journals in the recent years. The evaluation included the standard VOT and other popular methodologies for short-term tracking analysis as well as the standard VOT methodology for long-term tracking analysis. The VOT2019 challenge was composed of five challenges focusing on different tracking domains: (i) VOT-ST2019 challenge focused on short-term tracking in RGB, (ii) VOT-RT2019 challenge focused on "real-time" shortterm tracking in RGB, (iii) VOT-LT2019 focused on longterm tracking namely coping with target disappearance and reappearance. Two new challenges have been introduced: (iv) VOT-RGBT2019 challenge focused on short-term tracking in RGB and thermal imagery and (v) VOT-RGBD2019 challenge focused on long-term tracking in RGB and depth imagery. The VOT-ST2019, VOT-RT2019 and VOT-LT2019 datasets were refreshed while new datasets were introduced for VOT-RGBT2019 and VOT-RGBD2019. The VOT toolkit has been updated to support both standard shortterm, long-term tracking and tracking with multi-channel imagery. Performance of the tested trackers typically by far exceeds standard baselines. The source code for most of the trackers is publicly available from the VOT page. The dataset, the evaluation kit and the results are publicly available at the challenge website 1 .

show abstract

Section: The Vot-rgbt2019 Challenge Winnermentioning

confidence: 99%

The Seventh Visual Object Tracking VOT2019 Challenge Results

Kristan

Berg

Zheng

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)

Self Cite

382

359

View full text Add to dashboard Cite

show abstract

“…Hannuna et al [14], An et al formulation, Kart et al [20] adopted Gaussian foreground masks on depth images in CSRDCF [32] training. 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.…”

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)

Self Cite

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

“…A popular method for visual object tracking is learning Discriminative Correlation Filters (DCF) to predict the location of the tracked object in a patch [65][66][67][68][69][70][71][72][73][74][75][76][77][78][79]. A basic correlation filter based tracking framework is shown in Figure 3.…”

Section: Cf-based Trackersmentioning

confidence: 99%

Benchmarking Deep Trackers on Aerial Videos

Taufique

Minnehan

Savakis

2020

Sensors

View full text Add to dashboard Cite

In recent years, deep learning-based visual object trackers have achieved state-of-the-art performance on several visual object tracking benchmarks. However, most tracking benchmarks are focused on ground level videos, whereas aerial tracking presents a new set of challenges. In this paper, we compare ten trackers based on deep learning techniques on four aerial datasets. We choose top performing trackers utilizing different approaches, specifically tracking by detection, discriminative correlation filters, Siamese networks and reinforcement learning. In our experiments, we use a subset of OTB2015 dataset with aerial style videos; the UAV123 dataset without synthetic sequences; the UAV20L dataset, which contains 20 long sequences; and DTB70 dataset as our benchmark datasets. We compare the advantages and disadvantages of different trackers in different tracking situations encountered in aerial data. Our findings indicate that the trackers perform significantly worse in aerial datasets compared to standard ground level videos. We attribute this effect to smaller target size, camera motion, significant camera rotation with respect to the target, out of view movement, and clutter in the form of occlusions or similar looking distractors near tracked object.

show abstract

Object Tracking by Reconstruction With View-Specific Discriminative Correlation Filters

Cited by 92 publications

References 38 publications

The Seventh Visual Object Tracking VOT2019 Challenge Results

The Seventh Visual Object Tracking VOT2019 Challenge Results

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

Benchmarking Deep Trackers on Aerial Videos

Contact Info

Product

Resources

About