论文标题
端到端的深度对象跟踪具有旋转边界框的圆损耗功能
End-to-end Deep Object Tracking with Circular Loss Function for Rotated Bounding Box
论文作者
论文摘要
在众多应用程序中，任务对象跟踪至关重要，例如自动驾驶，智能监视，机器人技术等。此任务需要将边界框分配给视频流中的对象，仅给出了第一个帧上该对象的边界框。在2015年，创建了一种新型的视频对象跟踪（fot）数据集，该数据集引入了旋转的边界框，作为轴对齐的框的扩展。在这项工作中，我们介绍了一种基于变压器多头注意体系结构的新型端到端深度学习方法。我们还提出了一种新型的损失功能，该功能考虑了边界框的重叠和方向。 我们具有循环损耗函数（DOTCL）的深度对象跟踪模型在鲁棒性方面与当前最新的端到端深度学习模型有关。就预期的平均重叠（EAO）度量而言，它还优于vot2018数据集上最先进的对象跟踪方法。
The task object tracking is vital in numerous applications such as autonomous driving, intelligent surveillance, robotics, etc. This task entails the assigning of a bounding box to an object in a video stream, given only the bounding box for that object on the first frame. In 2015, a new type of video object tracking (VOT) dataset was created that introduced rotated bounding boxes as an extension of axis-aligned ones. In this work, we introduce a novel end-to-end deep learning method based on the Transformer Multi-Head Attention architecture. We also present a new type of loss function, which takes into account the bounding box overlap and orientation. Our Deep Object Tracking model with Circular Loss Function (DOTCL) shows an considerable improvement in terms of robustness over current state-of-the-art end-to-end deep learning models. It also outperforms state-of-the-art object tracking methods on VOT2018 dataset in terms of expected average overlap (EAO) metric.
