Multi-Frame Attention with Feature-Level Warping for Drone Crowd Tracking
Multi-Frame Attention with Feature-Level Warping for Drone Crowd Tracking
复制标题
DOI：
10.1109/wacv56688.2023.00171
复制
发表时间：
2023-01
期刊：
影响因子：
--
通讯作者：
Takanori Asanomi;Kazuya Nishimura;Ryoma Bise
中科院分区：
文献类型：
--
作者：
Takanori Asanomi;Kazuya Nishimura;Ryoma Bise
无人机人群跟踪有各种各样的应用，如人群管理和视频监控。与一般的多目标跟踪不同，被跟踪对象的大小较小，并且地面真实值由点级注释给出，该注释不包含区域信息。这导致缺乏从许多相似对象中找到相同对象的判别特征。因此，基于相似度的跟踪技术在多目标边界盒跟踪中应用比较困难。为了解决这个问题，我们考虑了当地的时间背景。为了聚合局部区域的时间上下文，我们提出了具有特征级扭曲的多帧关注。特征级扭曲可以在多个帧中对齐同一对象的特征，然后多帧关注可以有效地从扭曲的特征中聚合时间上下文。实验结果表明了该方法的有效性。我们的方法在DroneCrowd数据集中优于最先进的方法。该代码可在https://github.com/asanomitakanori/mfa-feature-warping上公开获得。
Drone crowd tracking has various applications such as crowd management and video surveillance. Unlike in general multi-object tracking, the size of the objects to be tracked are small, and the ground truth is given by a point-level annotation, which has no region information. This causes the lack of discriminative features for finding the same objects from many similar objects. Thus, similarity-based tracking techniques, which are widely used for multi-object tracking with bounding-box, are difficult to use. To deal with this problem, we take into account the temporal context of the local area. To aggregate temporal context in a local area, we propose a multi-frame attention with feature-level warping. The feature-level warping can align the features of the same object in multiple frames, and then multi-frame attention can effectively aggregate the temporal context from the warped features. The experimental results show the effectiveness of our method. Our method outperformed the state-of-the-art method in DroneCrowd dataset. The code is publicly available in https://github.com/asanomitakanori/mfa-feature-warping.