SiamCPN:Visual tracking with the Siamese center-prediction network

作     者：Dong Chen Fan Tang Weiming Dong Hanxing Yao Changsheng Xu Dong Chen;Fan Tang;Weiming Dong;Hanxing Yao;Changsheng Xu

作者机构：School of Artificial IntelligenceUniversity of Chinese Academy of SciencesBeijing 100040China NLPRInstitute of AutomationChinese Academy of SciencesBeijing 100190China School of Artificial IntelligenceJilin UniversityChangchun 130012China CASIA-LLVISION Joint LabBeijing 100190China LLVISION Technology Co.LTD.Beijing 100190China 

出 版 物：《Computational Visual Media》 (计算可视媒体（英文版）)

年 卷 期：2021年第7卷第2期

页      面：253-265页

核心收录：

学科分类：08[工学] 080203[工学-机械设计及理论] 0802[工学-机械工程] 

基　　金：supported by the National Key R&D Program of China(Grant No.2018YFC0807500) the National Natural Science Foundation of China(Grant Nos.U20B2070 and 61832016) 

主　　题：s Siamese network single object tracking anchor-free center point detection 

摘      要：Object detection is widely used in object tracking;anchor-free object tracking provides an end-to-end single-object-tracking *** this study,we propose a new anchor-free network,the Siamese center-prediction network(SiamCPN).Given the presence of referenced object features in the initial frame,we directly predict the center point and size of the object in subsequent frames in a Siamese-structure network without the need for perframe post-processing *** other anchor-free tracking approaches that are based on semantic segmentation and achieve anchor-free tracking by pixel-level prediction,SiamCPN directly obtains all information required for tracking,greatly simplifying the model.A center-prediction sub-network is applied to multiple stages of the backbone to adaptively learn from the experience of different branches of the Siamese *** model can accurately predict object location,implement appropriate corrections,and regress the size of the target bounding *** to other leading Siamese networks,SiamCPN is simpler,faster,and more efficient as it uses fewer *** demonstrate that our method outperforms other leading Siamese networks on GOT-10K and UAV123 benchmarks,and is comparable to other excellent trackers on LaSOT,VOT2016,and OTB-100 while improving inference speed 1.5 to 2 times.