Faculty of Space, Xi'an Institute of Optics and Precision Mechanics of CAS, Xi'an 710119, China.
School of Astronautics, Northwestern Polytechnical Universty, Xi'an 710072, China.
Sensors (Basel). 2020 Aug 26;20(17):4810. doi: 10.3390/s20174810.
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).
基于区域提议网络（RPN）的跟踪器使用分类和回归块来生成提议，具有最高相似度得分的提议被制定为下一个帧的地面真实候选者。然而，基于区域提议网络的跟踪器无法充分利用来自不同卷积层的特征，并且原始的损失函数无法缓解训练过程中的数据不平衡问题。我们提出了空间级联变换 RPN，将 RPN 和 STN（空间变换网络）结合在一起，以成功获得高质量的提议，同时提高鲁棒性。STN 可以通过不同的阶段传输空间变换特征，从而扩展了这些网络处理复杂场景（如尺度变化和仿射变换）的空间表示能力。我们通过简单的样本惩罚损失（收缩损失）而不是平滑 L1 函数来打破这种限制。此外，我们执行多线索提议重新排序，以保证所提出的跟踪器的准确性。我们在跟踪数据集的消融研究中广泛证明了我们提出的方法的有效性，包括 OTB-2015（Object Tracking Benchmark 2015）、VOT-2018（Visual Object Tracking 2018）、LaSOT（大规模单目标跟踪）、TrackingNet（野外目标跟踪的大规模数据集和基准）和 UAV123（UAV 跟踪数据集）。
