Proposal-based visual tracking using spatial cascaded transformed region proposal network | |
Zhang, Ximing1; Luo, Shujuan2; Fan, Xuewu1 | |
作者部门 | 空间光学技术研究室 |
2020-09-01 | |
发表期刊 | Sensors (Switzerland) |
ISSN | 14248220 |
卷号 | 20期号:17页码:1-20 |
产权排序 | 1 |
摘要 | Region proposal network (RPN) based trackers employ the classification and regression block to generate the proposals, the proposal that contains the highest similarity score is formulated to be the groundtruth candidate of next frame. However, region proposal network based trackers cannot make the best of the features from different convolutional layers, and the original loss function cannot alleviate the data imbalance issue of the training procedure. We propose the Spatial Cascaded Transformed RPN to combine the RPN and STN (spatial transformer network) together, in order to successfully obtain the proposals of high quality, which can simultaneously improves the robustness. The STN can transfer the spatial transformed features though different stages, which extends the spatial representation capability of such networks handling complex scenarios such as scale variation and affine transformation. We break the restriction though an easy samples penalization loss (shrinkage loss) instead of smooth L1 function. Moreover, we perform the multi-cue proposals re-ranking to guarantee the accuracy of the proposed tracker. We extensively prove the effectiveness of our proposed method on the ablation studies of the tracking datasets, which include OTB-2015 (Object Tracking Benchmark 2015), VOT-2018 (Visual Object Tracking 2018), LaSOT (Large Scale Single Object Tracking), TrackingNet (A Large-Scale Dataset and Benchmark for Object Tracking in the Wild) and UAV123 (UAV Tracking Dataset). © 2020 by the authors. Licensee MDPI, Basel, Switzerland. |
关键词 | visual tracking spatial cascaded networks shrinkage loss multi-cue proposals re-ranking region proposals networks |
DOI | 10.3390/s20174810 |
收录类别 | SCI ; EI |
语种 | 英语 |
WOS记录号 | WOS:000569711300001 |
出版者 | MDPI AG, Postfach, Basel, CH-4005, Switzerland |
EI入藏号 | 20203509110028 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.opt.ac.cn/handle/181661/93675 |
专题 | 空间光学技术研究室 |
作者单位 | 1.Faculty of Space, Xi’an Institute of Optics and Precision Mechanics of CAS, Xi’an; 710119, China; 2.School of Astronautics, Northwestern Polytechnical Universty, Xi’an; 710072, China |
推荐引用方式 GB/T 7714 | Zhang, Ximing,Luo, Shujuan,Fan, Xuewu. Proposal-based visual tracking using spatial cascaded transformed region proposal network[J]. Sensors (Switzerland),2020,20(17):1-20. |
APA | Zhang, Ximing,Luo, Shujuan,&Fan, Xuewu.(2020).Proposal-based visual tracking using spatial cascaded transformed region proposal network.Sensors (Switzerland),20(17),1-20. |
MLA | Zhang, Ximing,et al."Proposal-based visual tracking using spatial cascaded transformed region proposal network".Sensors (Switzerland) 20.17(2020):1-20. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Proposal-based visua(8427KB) | 期刊论文 | 出版稿 | 限制开放 | CC BY-NC-SA | 请求全文 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论