论文标题
RSINET：用于在线视觉跟踪的旋转尺度不变网络
RSINet: Rotation-Scale Invariant Network for Online Visual Tracking
论文作者
论文摘要
大多数基于暹罗网络的跟踪器无需模型更新即可执行跟踪过程，并且无法自适应地学习目标特定的变化。此外，基于暹罗的跟踪器通过生成包含额外背景噪声的轴对准对象的新状态，并且无法准确估计移动对象的旋转和比例变换，从而有可能降低跟踪性能。在本文中，我们提出了一个新颖的旋转尺度不变网络（RSINET）来解决上述问题。我们的RSINET跟踪器由目标分散器歧视分支和旋转尺度估计分支组成，旋转和规模知识可以通过多任务学习方法以端到端的方式明确学习。另外，在时空能量控制下，跟踪模型被自适应优化和更新，从而确保模型稳定性和可靠性以及高跟踪效率。与最近的跟踪器相比，OTB-100，DOCT2018和LASOT基准的全面实验表明，我们提议的RSINET跟踪器可产生新的最先进性能，而以实时速度运行约45 fps。
Most Siamese network-based trackers perform the tracking process without model update, and cannot learn targetspecific variation adaptively. Moreover, Siamese-based trackers infer the new state of tracked objects by generating axis-aligned bounding boxes, which contain extra background noise, and are unable to accurately estimate the rotation and scale transformation of moving objects, thus potentially reducing tracking performance. In this paper, we propose a novel Rotation-Scale Invariant Network (RSINet) to address the above problem. Our RSINet tracker consists of a target-distractor discrimination branch and a rotation-scale estimation branch, the rotation and scale knowledge can be explicitly learned by a multi-task learning method in an end-to-end manner. In addtion, the tracking model is adaptively optimized and updated under spatio-temporal energy control, which ensures model stability and reliability, as well as high tracking efficiency. Comprehensive experiments on OTB-100, VOT2018, and LaSOT benchmarks demonstrate that our proposed RSINet tracker yields new state-of-the-art performance compared with recent trackers, while running at real-time speed about 45 FPS.
