当前位置: X-MOL 学术IEEE Signal Process. Lett. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Template Enhancement and Mask Generation for Siamese Tracking
IEEE Signal Processing Letters ( IF 3.2 ) Pub Date : 2020-12-31 , DOI: 10.1109/lsp.2020.3048638
Xiao Ke , Yuezhou Li , Yu Ye , Wenzhong Guo

Siamese tracking methods have become the focus of visual tracking in recent years. Advanced Siamese trackers perform well on certain benchmarks, but there are still some limitations. First, most Siamese trackers adopt the initial frame as a single template, which leads to underfitting and reduces the ability to predict instances. Second, mainstream trackers report a rectangular bounding box as a prediction, resulting in poor accuracy of non-rigid objects. Therefore, we propose the template enhancement and mask generation for Siamese tracking. Given that the essence of Siamese trackers is instance learning, we propose constructing an alternative template explicitly to address the underfitting of the instance space. Moreover, in order to improve the tracking accuracy, we obtain the descriptor aggregation to transform the semantic segmentation outputs for mask prediction. Finally, we propose the SiamEM through the fusion of the above approaches. Comprehensive experiments show that template enhancement and mask generation significantly improve Siamese trackers on benchmarks.

中文翻译:

暹罗跟踪的模板增强和掩码生成

近年来,暹罗跟踪方法已经成为视觉跟踪的焦点。先进的暹罗跟踪器在某些基准上表现良好,但仍然存在一些局限性。首先,大多数暹罗跟踪器将初始框架用作单个模板,这会导致拟合不足并降低了预测实例的能力。其次,主流追踪器将矩形边界框作为预测,导致非刚性对象的准确性较差。因此,我们提出了用于暹罗跟踪的模板增强和掩码生成。鉴于暹罗跟踪器的本质是实例学习,我们建议显式构造一个替代模板来解决实例空间的不足。而且,为了提高跟踪精度,我们获得描述符聚合以转换语义分割输出以进行掩码预测。最后,我们通过上述方法的融合提出SiamEM。全面的实验表明,模板增强和蒙版生成可以显着提高基准上的暹罗跟踪器。
更新日期:2021-02-12
down
wechat
bug