Knowledge Commons of Institute of Automation,CAS
Fast Online Object Tracking and Segmentation: A Unifying Approach | |
Wang, Qiang1; Zhang, Li2; Luca Bertinetto3; Hu, Weiming1; Philip H.S. Torr2 | |
2019-06 | |
会议名称 | The IEEE Conference on Computer Vision and Pattern Recognition |
会议日期 | 2019-7 |
会议地点 | Long Beach, CA, USA |
摘要 | In this paper we illustrate how to perform both visual object tracking and semi-supervised video object segmentation, in real-time, with a single simple approach. Our method, dubbed SiamMask, improves the offline training procedure of popular fully-convolutional Siamese approaches for object tracking by augmenting their loss with a binary segmentation task. Once trained, SiamMask solely relies on a single bounding box initialisation and operates online, producing class-agnostic object segmentation masks and rotated bounding boxes at 55 frames per second. Despite its simplicity, versatility and fast speed, our strategy allows us to establish a new state of the art among real-time trackers on VOT-2018, while at the same time demonstrating competitive performance and the best speed for the semi-supervised video object segmentation task on DAVIS-2016 and DAVIS-2017. |
七大方向——子方向分类 | 目标检测、跟踪与识别 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/39072 |
专题 | 多模态人工智能系统全国重点实验室_视频内容安全 |
作者单位 | 1.CASIA 2.University of Oxford 3.Five AI |
第一作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Wang, Qiang,Zhang, Li,Luca Bertinetto,et al. Fast Online Object Tracking and Segmentation: A Unifying Approach[C],2019. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
王强_CVPR2019.pdf(2111KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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