Multi-Hierarchical Independent Correlation Filters For Visual Tracking

Bai, Song; He, Zhiqun; Dong, Yuan; Bai, Hongliang

doi:10.1109/icme46284.2020.9102759

Cited by 34 publications

(26 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The EAO score of the proposed Anti-occlusion-SiamRPN is 0.404, which is significantly higher than the peer trackers and outperforms the baseline (SiamRPN++) by 1.1. Anti-occlusion-SiamRPN tracker is also compared with all the 73 trackers on VOT2018, as shown in Fig.11, our tracker ranked sixth, which also achieves good performance on VOT2018, Table 3 reports the details of the comparison with LADCF [48], MFT [49], DaSiamRPN [38], UPDT [50], RCO [51], DRT [52], SiamRPN++ [1], DeepSTRCF [51], and CPT [51] on VOT2018. The EAO score of the proposed Antiocclusion-SiamRPN is 0.364, which is significantly outperforms the baseline (SiamRPN++) by 1.2.…”

Section: ) Experiments On Otb Benchmarksmentioning

confidence: 99%

Stably Adaptive Anti-Occlusion Siamese Region Proposal Network for Real-Time Object Tracking

Zhang

2020

IEEE Access

View full text Add to dashboard Cite

Siamese region proposal network has made remarkable achievements in visual object tracking because of its balanced accuracy and speed. However, it regards tracking as a local one-shot detection task, which lose the power of updating the appearance model online thereby cannot handle the object-occlusion, fast motion and out-of-view situations. To tackle this problem, we propose a method that combines adaptive Kalman filter with Siamese region proposal network (Anti-occlusion-SiamRPN) to make full use of the object spatial-temporal information. Specifically we first extract target features through deep network and then uses adaptive Kalman filter to predict target trajectory in these difficult scenarios. Further this trajectory is used to select the candidate area of the next frame for Siamese region proposal network, which improve the searching mechanism. In this way, the introduction of adaptive Kalman filter makes the tracking process online learning which makes up for the disadvantage that Siamese region proposal network can only track offline. In addition, a hard example discrimination method (HEDM) is proposed to estimate whether the occlusion occurs and how seriously it is, which also improve Kalman filtering mechanism to make it update adaptively. Our method being evaluated with the speed of 80 FPS on five widely-applied challenging benchmarks including OTB2013, OTB2015, OTB50, VOT2016 and VOT2018. The extensive experimental results demonstrate our method achieves state-of-the-art effects and great improvement in comparison to other trackers. INDEX TERMS Visual tracking, Siamese region proposal network, Kalman filter, occlusion judgment, real-time tracker.

show abstract

Section: ) Experiments On Otb Benchmarksmentioning

confidence: 99%

Stably Adaptive Anti-Occlusion Siamese Region Proposal Network for Real-Time Object Tracking

Zhang

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Some approaches improve the trackers by leveraging some stronger features extracted from neural network for a richer representation of the tracking target. As we know, CNN feature is more powerful for tracking task comparing to traditional handcraft features such as HOG [23], SIFI and CN [24,25]. So many trackers follow the idea that combines deep features with correlation filters like C-COT [22], ECO [26] and CF2.…”

Section: Related Tracking Algorithmsmentioning

confidence: 99%

High-speed tracking based on multi-CF filters and attention mechanism

Fan

Wang

et al. 2019

SIViP

View full text Add to dashboard Cite

Recently, correlation filters and deep convolutional network show good performance for visual tracking. Many real-time and high accuracy tracking algorithms are realized; however, there are still some challenges to build a robust tracker. In this paper, we present a novel tracking framework named multi-attention filter (MAF) to solve some challenges for tracking like object drift in a long time, lack of training samples and fast motion. Our framework consists of two components, a basic CNN network to extract feature maps and a set of classifiers to distinguish between the target and the background. First, to solve the problem of object drift in a long time, a simple but effective evaluation mechanism is proposed to the framework, the evaluation mechanism checks the tracking results and corrects it when needed. In addition, the results from different classifiers are fused to predict the object location according to intersection over union. Second, to overcome the lack of training samples, MAF stores some positive and negative samples in two queues, one named long-term queue and another named short-term queue. Third, to deal with fast motion of the target, attention mechanisms including channel attention and location attention are added to the tracker. In our experiments on the popular benchmarks including OTB-2013 and OTB-2015. MFA achieves state of the art among trackers, and as a correlation filter framework, MAF is very flexible and has great rooms for improvement and generalization.

show abstract

“…The accuracy is about 1.3% short of the baseline, but also higher than any other state-of-the-art. The robustness is 1.1% higher than the baseline, but unfortunately still lower than the VOT-2018 [ 9 ] challenge winner MFT [ 39 ], mostly because the latter is armed with Multi-hierarchical independent correlation filters, a close technology to our algorithm. Notice that we outperform it in the rest of the metrics.…”

Section: Resultsmentioning

confidence: 99%

“…Siamese–based results—We present results from evaluating the proposed algorithm with respect to VOT-2018 [ 9 ] and LaSOT [ 21 ] benchmarks. First, we start from VOT-2018 [ 9 ] and test our tracker SNS-CF against 7 state-of-the-art methods containing either correlation filters or Siamese networks or both [ 2 , 6 , 35 , 36 , 37 , 38 , 39 , 40 , 41 , 42 ]. We follow its evaluation protocol and present results in the following Table 2 .…”

Section: Resultsmentioning

confidence: 99%

SNS-CF: Siamese Network with Spatially Semantic Correlation Features for Object Tracking

Ntwari

Park

Shin

et al. 2020

Sensors

View full text Add to dashboard Cite

Recent advances in object tracking based on deep Siamese networks shifted the attention away from correlation filters. However, the Siamese network alone does not have as high accuracy as state-of-the-art correlation filter-based trackers, whereas correlation filter-based trackers alone have a frame update problem. In this paper, we present a Siamese network with spatially semantic correlation features (SNS-CF) for accurate, robust object tracking. To deal with various types of features spread in many regions of the input image frame, the proposed SNS-CF consists of—(1) a Siamese feature extractor, (2) a spatially semantic feature extractor, and (3) an adaptive correlation filter. To the best of authors knowledge, the proposed SNS-CF is the first attempt to fuse the Siamese network and the correlation filter to provide high frame rate, real-time visual tracking with a favorable tracking performance to the state-of-the-art methods in multiple benchmarks.

show abstract

Multi-Hierarchical Independent Correlation Filters For Visual Tracking

Cited by 34 publications

References 21 publications

Stably Adaptive Anti-Occlusion Siamese Region Proposal Network for Real-Time Object Tracking

Stably Adaptive Anti-Occlusion Siamese Region Proposal Network for Real-Time Object Tracking

High-speed tracking based on multi-CF filters and attention mechanism

SNS-CF: Siamese Network with Spatially Semantic Correlation Features for Object Tracking

Contact Info

Product

Resources

About