作者：Yu-Hsiang Wang, Jun-Wei Hsieh, Ping-Yang Chen, Ming-Ching Chang

作者单位：

台湾国立阳明交通大学人工智能与绿色能源学院

台湾国立阳明交通大学计算机学系

美国纽约州立大学奥尔巴尼分校人工智能与绿色能源学院

发布时间：2022

发布期刊/会议：Arxiv

出版商：

论文全称：SMILEtrack: SiMIlarity LEarning for Multiple Object Tracking

论文地址：

SMILEtrack: SiMIlarity LEarning for Multiple Object Tracking

论文代码：

https://github.com/WWangYuHsiang/SMILEtrack

地位：

一、摘要

Multiple Object Tracking (MOT) is widely investigated in computer vision with many applications. Tracking-By-Detection (TBD) is a popular multiple-object tracking paradigm. TBD consists of the first step of object detection and the subsequent of data association, tracklet generation, and update. We propose a Similarity Learning Module (SLM) motivated from the Siamese network to extract important object appearance features and a procedure to combine object motion and appearance features effectively. This design strengthens the modeling of object motion and appearance features for data association. We design a Similarity Matching Cascade (SMC) for the data association of our SMILEtrack tracker. SMILEtrack achieves 81.06 MOTA and 80.5 IDF1 on the MOTChallenge and the MOT17 test set, respectively.

• 多目标跟踪（MOT）在计算机视觉领域上有广泛的应用，大多数算法都是遵循 Tracking-By-Detection 范式（该范式主要包括：detection，data association， tracklet generation， tracklet update），本文所提的 SMILETrack 也是遵循该范式
• SMILETrack
  • 受孪生网络（Siamese network）的启发，设计了一个 **Similarity Learning Module （SLM）**来提取目标外观特征，并把目标的运动特征和外观特征进行有效的融合。
  • 设计了 **Similarity Matching Cascade Module（SMC）**用于data association

二、研究背景