[论文解读] Online Multi-Object Tracking and Segmentation with GMPHD Filter and Simple Affinity Fusion

Young-Min Song, Moongu Jeon|arXiv (Cornell University)|Aug 31, 2020

Video Surveillance and Tracking Methods参考文献 45被引用 8

一句话总结

本文提出了一种完全在线的多目标跟踪与实例分割（MOTS）方法，结合高斯混合概率假设密度（GMPHD）滤波器、分层数据关联（HDA）和基于掩码的亲和力融合（MAF）。通过在分数级别归一化下融合运动与外观亲和力，并应用基于掩码IoU的合并策略，该方法在极少超参数调优和仅使用CPU并行执行的情况下，实现了最先进的MOTS性能。

ABSTRACT

In this paper, we propose a highly practical fully online multi-object tracking and segmentation (MOTS) method that uses instance segmentation results as an input. The proposed method is based on the Gaussian mixture probability hypothesis density (GMPHD) filter, a hierarchical data association (HDA), and a mask-based affinity fusion (MAF) model to achieve high-performance online tracking. The HDA consists of two associations: segment-to-track and track-to-track associations. One affinity, for position and motion, is computed by using the GMPHD filter, and the other affinity, for appearance is computed by using the responses from a single object tracker such as a kernalized correlation filter. These two affinities are simply fused by using a score-level fusion method such as min-max normalization referred to as MAF. In addition, to reduce the number of false positive segments, we adopt mask IoU-based merging (mask merging). The proposed MOTS framework with the key modules: HDA, MAF, and mask merging, is easily extensible to simultaneously track multiple types of objects with CPU only execution in parallel processing. In addition, the developed framework only requires simple parameter tuning unlike many existing MOTS methods that need intensive hyperparameter optimization. In the experiments on the two popular MOTS datasets, the key modules show some improvements. For instance, ID-switch decreases by more than half compared to a baseline method in the training sets. In conclusion, our tracker achieves state-of-the-art MOTS performance in the test sets.

研究动机与目标

• 开发一种完全在线的MOTS系统，实现实时高效地跟踪和分割多个对象。
• 减少对大量超参数调优的依赖，以缓解现有许多MOTS方法所面临的问题。
• 通过有效融合运动与外观亲和力，提升跟踪精度。
• 通过基于掩码IoU的合并策略，最小化误检分割。
• 实现并行、仅CPU的执行，以支持实际部署。

提出的方法

• 该方法采用高斯混合概率假设密度（GMPHD）滤波器来建模对象状态并估计后验密度。
• 分层数据关联（HDA）执行两阶段关联：基于运动与外观亲和力的“实例到轨迹”关联和“轨迹到轨迹”关联。
• 运动亲和力由GMPHD滤波器计算，外观亲和力由核化相关滤波跟踪器计算。
• 基于掩码的亲和力融合（MAF）通过分数级别归一化（如最小-最大归一化）融合两种亲和力，以增强跟踪鲁棒性。
• 应用基于掩码IoU的合并策略，通过合并重叠或高度相似的掩码预测，减少误检分割。
• 该框架设计为可扩展，支持多类目标跟踪，并支持在CPU上并行处理。

实验结果

研究问题

• RQ1 完全在线的MOTS系统是否能在极少超参数调优下实现高性能？
• RQ2 运动与外观亲和力的融合在多大程度上能有效提升跟踪精度？
• RQ3 基于掩码IoU的合并是否能显著减少误检分割预测？
• RQ4 HDA框架在复杂跟踪场景下是否优于标准关联方法？
• RQ5 系统是否能在仅使用CPU并行处理的情况下保持高性能？

主要发现

• 与基线相比，该方法在训练集上将ID切换错误减少了超过一半。
• 该框架在两个主流MOTS数据集的测试集上均实现了最先进性能。
• 采用MAF进行分数级别融合，通过平衡运动与外观线索，提升了跟踪鲁棒性。
• 基于掩码IoU的合并策略有效减少了误检分割，提升了分割精度。
• 该系统仅需简单参数调优，而不同于许多现有MOTS方法所要求的密集超参数优化。
• 该框架支持并行、仅CPU的执行，使其在实际部署中更具可行性。