论文标题
SimpleTrack：重新思考和改进用于多对象跟踪的JDE方法
SimpleTrack: Rethinking and Improving the JDE Approach for Multi-Object Tracking
论文作者
论文摘要
基于联合检测和嵌入方法（JDE）方法通常会在多对象跟踪（MOT）中估算具有单个网络的对象的边界框和嵌入特征。在跟踪阶段，基于JDE的方法通过应用相同的规则来融合目标运动信息和外观信息，当目标丢失或阻止目标时，这可能会失败。为了克服这个问题，我们提出了一个新的关联矩阵，嵌入式和GIOU矩阵，该矩阵结合了余弦距离和物体的giou距离。为了进一步提高数据关联的性能，我们开发了一个名为Simpletrack的简单，有效的跟踪器，该跟踪器设计了一种自下而上的融合方法，以重新认同，并根据我们的EG矩阵提出了一种新的跟踪策略。实验结果表明，SimpleTrack具有强大的数据关联能力，例如MOT17上的61.6 HOTA和76.3 IDF1。此外，我们将EG矩阵应用于5种不同的基于JDE的方法，并在IDF1，HOTA和IDSW指标上实现了显着改善，并将这些方法的跟踪速度提高约20％。
Joint detection and embedding (JDE) based methods usually estimate bounding boxes and embedding features of objects with a single network in Multi-Object Tracking (MOT). In the tracking stage, JDE-based methods fuse the target motion information and appearance information by applying the same rule, which could fail when the target is briefly lost or blocked. To overcome this problem, we propose a new association matrix, the Embedding and Giou matrix, which combines embedding cosine distance and Giou distance of objects. To further improve the performance of data association, we develop a simple, effective tracker named SimpleTrack, which designs a bottom-up fusion method for Re-identity and proposes a new tracking strategy based on our EG matrix. The experimental results indicate that SimpleTrack has powerful data association capability, e.g., 61.6 HOTA and 76.3 IDF1 on MOT17. In addition, we apply the EG matrix to 5 different state-of-the-art JDE-based methods and achieve significant improvements in IDF1, HOTA and IDsw metrics, and increase the tracking speed of these methods by about 20%.
