Object tracking framework with Siamese network and re-detection mechanism

Li, Daqun; Yu, Yi; Chen, Xiaolin

doi:10.1186/s13638-019-1579-x

Cited by 11 publications

(16 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We do consider their elaboration important to our research. Various Siamese trackers utilize some of those methods (e.g., optical flow in [28], GMM in [29]), apart from deep learning. One of the leading causes of difficulties for VOT is a variation of object appearance [6].…”

Section: Related Workmentioning

confidence: 99%

“…Authors of [12] were also the first to train a tracker on ILSVRC dataset. Many newer trackers followed their path later on [16], [29], [40], [41]. This dataset is suitable for pre-training, and it seems like it has become a standard.…”

Section: Siamese Trackingmentioning

confidence: 99%

“…Li et al [29] pointed out that the size of the response map in the SiamFC architecture was relatively small (just 17 × 17). As a result, it is not suitable for precise positioning.…”

Section: ) Spatial Granularitymentioning

confidence: 99%

“…Siamese tracking is essentially a template matching problem, and most template-based trackers generally fail to track an object that undergoes significant changes in appearance [29]. This flaw is primarily caused by a misalignment between the general domain and the specific target domain [40].…”

Section: Similar Interference 1) Distractor Awarenessmentioning

confidence: 99%

See 3 more Smart Citations

Siamese Visual Object Tracking: A Survey

Ondrašovič

Tarábek

2021

IEEE Access

View full text Add to dashboard Cite

Object tracking belongs to active research areas in computer vision. We are interested in matching-based trackers exploiting deep machine learning known as Siamese trackers. Their powerful capabilities stem from similarity learning. This tracking paradigm is promising due to its inherent balance between performance and efficiency, so trackers of this type are suitable for real-time generic object tracking. There is an upsurge in research interest in Siamese trackers and the lack of available specialized surveys in this category. In this survey, we aim to identify and elaborate on the most significant challenges the Siamese trackers face. Our goal is to answer what design decisions the authors made and what problems they attempted to solve in the first place. We thus perform an in-depth analysis of the core principles on which Siamese trackers operate with a discussion of incentives behind them. Besides, we provide an up-todate qualitative and quantitative comparison of the prominent Siamese trackers on established benchmarks. Among other things, we discuss current trends in developing Siamese trackers. Our survey could help absorb the details about the underlying principles of Siamese trackers and the challenges they face.INDEX TERMS visual object tracking, deep learning, Siamese neural networks, similarity learning, fully convolutional networks

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Siamese Trackingmentioning

confidence: 99%

“…Li et al [29] pointed out that the size of the response map in the SiamFC architecture was relatively small (just 17 × 17). As a result, it is not suitable for precise positioning.…”

Section: ) Spatial Granularitymentioning

confidence: 99%

Section: Similar Interference 1) Distractor Awarenessmentioning

confidence: 99%

See 2 more Smart Citations

Siamese Visual Object Tracking: A Survey

Ondrašovič

Tarábek

2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Wang et al [24] presented a long-term target tracking method by combining adaptive discriminative correlation filters with a support vector machine-based component. Siam-RM [25] has an object-tracking framework that uses the Siamese network and adopts the Siamese instance search tracker as the re-detection network. Zhang et al [26] deployed local-global multiple correlation filters for tracking and a Kalman filter re-detection model for re-detection when the correlation filters are unreliable.…”

Section: Related Workmentioning

confidence: 99%

Multi-Templates Based Robust Tracking for Robot Person-Following Tasks

Cao

Wang

2021

Applied Sciences

View full text Add to dashboard Cite

While the robotics techniques have not developed to full automation, robot following is common and crucial in robotic applications to reduce the need for dedicated teleoperation. To achieve this task, the target must first be robustly and consistently perceived. In this paper, a robust visual tracking approach is proposed. The approach adopts a scene analysis module (SAM) to identify the real target and similar distractors, leveraging statistical characteristics of cross-correlation responses. Positive templates are collected based on the tracking confidence constructed by the SAM, and negative templates are gathered by the recognized distractors. Based on the collected templates, response fusion is performed. As a result, the responses of the target are enhanced and the false responses are suppressed, leading to robust tracking results. The proposed approach is validated on an outdoor robot-person following dataset and a collection of public person tracking datasets. The results show that our approach achieved state-of-the-art tracking performance in terms of both the robustness and AUC score.

show abstract