SiamCenter: An Anchor-free Siamese Network for Object Tracking

Object tracking had absorbed many beneficial practices from object detection. Recently, the anchor-free object detection algorithms have received more and more attention. Siamese network is the mainstream architecture for single object tracking because of its great balance on efficiency and effectiveness. In this paper, a new object tracking model is proposed which combining Siamese network and anchor-free object detection algorithm, named SiamCenter. It directly predicts center point location and size of object. Hourglass network is carefully selected as the feature extraction backbone network of Siamese network, and intermediate supervision is employed to improve the model's performance. Experiments have proved that SiamCenter is effective in solving object tracking problem on VOT and OTB datasets.

[1]  Luca Bertinetto,et al.  Fully-Convolutional Siamese Networks for Object Tracking , 2016, ECCV Workshops.

[2]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Jia Deng,et al.  Stacked Hourglass Networks for Human Pose Estimation , 2016, ECCV.

[4]  Michael Felsberg,et al.  ATOM: Accurate Tracking by Overlap Maximization , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Wei Wu,et al.  End-to-End Flow Correlation Tracking with Spatial-Temporal Attention , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[6]  Yi Wu,et al.  Online Object Tracking: A Benchmark , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[7]  Arnold W. M. Smeulders,et al.  UvA-DARE (Digital Academic Repository) Siamese Instance Search for Tracking , 2016 .

[8]  Wei Wu,et al.  Distractor-aware Siamese Networks for Visual Object Tracking , 2018, ECCV.

[9]  Tianzhu Zhang,et al.  Graph Convolutional Tracking , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Wei Wu,et al.  High Performance Visual Tracking with Siamese Region Proposal Network , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[11]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[12]  Pietro Perona,et al.  Microsoft COCO: Common Objects in Context , 2014, ECCV.

[13]  Zhenyu He,et al.  The Visual Object Tracking VOT2016 Challenge Results , 2016, ECCV Workshops.

[14]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[15]  Qiang Wang,et al.  Fast Online Object Tracking and Segmentation: A Unifying Approach , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Xingyi Zhou,et al.  Objects as Points , 2019, ArXiv.

[17]  Wei Wu,et al.  SiamRPN++: Evolution of Siamese Visual Tracking With Very Deep Networks , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  Hei Law,et al.  CornerNet: Detecting Objects as Paired Keypoints , 2018, ECCV.

[19]  Qi Tian,et al.  CenterNet: Keypoint Triplets for Object Detection , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[20]  Xingyi Zhou,et al.  Bottom-Up Object Detection by Grouping Extreme and Center Points , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  Jian Sun,et al.  Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).