Joint Scale-Spatial Correlation Tracking with Adaptive Rotation Estimation

Zhang, Mengdan; Xing, Junliang; Gao, Jin; Shi, Xinchu; Wang, Qiang; Hu, Weiming

doi:10.1109/iccvw.2015.81

Cited by 48 publications

(29 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The seminal work by Bolme et al [3] introduces the Convolution Theorem from the signal processing field into visual tracking and transforms the object template matching problem into a correlation operation in the frequency domain. Own to this transformation, the correlation filter based trackers gain not only highly efficient running speed, but also increase accuracy if proper features are used [16,50,51,8,6]. With the wide adoption of deep learning models in visual tracking, tracking algorithms based on correlation filter with deep feature representations [9,5] have obtained the state-of-the-art accuracy in popular tracking benchmarks [45,46] and challenge [22,19,20].…”

Section: Related Workmentioning

confidence: 99%

SiamRPN++: Evolution of Siamese Visual Tracking With Very Deep Networks

Wang

et al. 2019

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

Self Cite

1,958

1,926

View full text Add to dashboard Cite

Siamese network based trackers formulate tracking as convolutional feature cross-correlation between a target template and a search region. However, Siamese trackers still have an accuracy gap compared with state-of-theart algorithms and they cannot take advantage of features from deep networks, such as ResNet-50 or deeper. In this work we prove the core reason comes from the lack of strict translation invariance. By comprehensive theoretical analysis and experimental validations, we break this restriction through a simple yet effective spatial aware sampling strategy and successfully train a ResNet-driven Siamese tracker with significant performance gain. Moreover, we propose a new model architecture to perform layer-wise and depthwise aggregations, which not only further improves the accuracy but also reduces the model size. We conduct extensive ablation studies to demonstrate the effectiveness of the proposed tracker, which obtains currently the best results on five large tracking benchmarks, including OTB2015, VOT2018, UAV123, LaSOT, and TrackingNet. Our model will be released to facilitate further researches. * The first three authors contributed equally. Work done at SenseTime. Project page: https://lb1100.github.io/SiamRPN++. Recently, the Siamese network based trackers [40,1,15,42,41,24,43,52,44] have drawn much attention in the community. These Siamese trackers formulate the visual object tracking problem as learning a general similarity map by cross-correlation between the feature representations learned for the target template and the search region. To ensure tracking efficiency, the offline learned Siamese similarity function is often fixed during the running time [40,1,15]. The CFNet tracker [41] and DSiam tracker [11] update the tracking model via a running average template and a fast transformation module, respectively. The SiamRNN tracker [24] introduces the region proposal network [24] after the Siamese network and performs joint classification and regression for tracking. The DaSiamRPN tracker [52] further introduces a distractor-aware module and improves the discrimination power of the model.

show abstract

Section: Related Workmentioning

confidence: 99%

SiamRPN++: Evolution of Siamese Visual Tracking With Very Deep Networks

Wang

et al. 2019

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

Self Cite

1,958

1,926

View full text Add to dashboard Cite

show abstract

“…SAMF [19] uses a scale pyramid to search corresponding target scale. Recently, RAJSSC [31] proposes to perform both scale and angle estimation in a unified correlation tracking framework by using the Log-Polar transformation. In SiamFC-based trackers, while the scale estimation has been considered in the original SiamFC tracker, angle estimation has not been considered before.…”

Section: Related Workmentioning

confidence: 99%

Towards a Better Match in Siamese Network Based Visual Object Tracker

Luo

Tian

et al. 2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Recently, Siamese network based trackers have received tremendous interest for their fast tracking speed and high performance. Despite the great success, this tracking framework still suffers from several limitations. First, it cannot properly handle large object rotation. Second, tracking gets easily distracted when the background contains salient objects. In this paper, we propose two simple yet effective mechanisms, namely angle estimation and spatial masking, to address these issues. The objective is to extract more representative features so that a better match can be obtained between the same object from different frames. The resulting tracker, named Siam-BM, not only significantly improves the tracking performance, but more importantly maintains the realtime capability. Evaluations on the VOT2017 dataset show that Siam-BM achieves an EAO of 0.335, which makes it the best-performing realtime tracker to date.

show abstract

“…Zhang et al [40] propose a rotation estimation method using Log-Polar transformation. In Log-Polar coordinate, a set of 36 rotation sample are chosen on every ∆ = 2π R , where R = 36.…”

Section: Rotated Bounding Boxesmentioning

confidence: 99%

Fast Visual Object Tracking using Ellipse Fitting for Rotated Bounding Boxes

Chen

Tsotsos

2019

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

View full text Add to dashboard Cite

In this paper, we demonstrate a novel algorithm that uses ellipse fitting to estimate the bounding box rotation angle and size with the segmentation(mask) on the target for online and real-time visual object tracking. Our method, SiamMask E, improves the bounding box fitting procedure of the state-of-the-art object tracking algorithm SiamMask and still retains a fast-tracking frame rate (80 fps) on a system equipped with GPU (GeForce GTX 1080 Ti or higher). We tested our approach on the visual object tracking datasets (VOT2016, VOT2018, and VOT2019) that were labeled with rotated bounding boxes. By comparing with the original SiamMask, we achieved an improved Accuracy of 65.2% and 30.9% EAO on VOT2019, which is 5.6% and 2.6% higher than the original SiamMask.The implementation is available on GitHub: https://github.com/ baoxinchen/siammask_e.

show abstract

Joint Scale-Spatial Correlation Tracking with Adaptive Rotation Estimation

Cited by 48 publications

References 15 publications

SiamRPN++: Evolution of Siamese Visual Tracking With Very Deep Networks

SiamRPN++: Evolution of Siamese Visual Tracking With Very Deep Networks

Towards a Better Match in Siamese Network Based Visual Object Tracker

Fast Visual Object Tracking using Ellipse Fitting for Rotated Bounding Boxes

Contact Info

Product

Resources

About