论文标题
实时跟踪的更快对象跟踪管道
Faster object tracking pipeline for real time tracking
论文作者
论文摘要
多对象跟踪（MOT）对于基于视觉的应用来说是一个具有挑战性的实际问题。 MOT的最新方法使用了从更快的RCNN等模型，对边界框进行微调和随后阶段的关联的预先计算检测。但是，由于检测不可用，这不适合实际的工业应用。 Wang等人在最近的工作中。提出了使用联合检测和嵌入模型并实时执行目标定位和关联的跟踪管道。在通过检测范式调查跟踪时，我们发现可以通过执行本地化和关联任务与模型预测相同，可以更快地进行跟踪管道。这以及其他计算优化（例如使用混合精度模型和执行二叶检测）会在FULLHD分辨率上加快跟踪管道的加速57.8 \％（19 fps至30 fps）。此外，速度与图像序列中的对象密度无关。本文的主要贡献是展示一条通用管道，该管道可用于加快基于检测的对象跟踪方法。考虑到GPU的内存使用和速度，我们还审查了不同的批次大小以获得最佳性能。
Multi-object tracking (MOT) is a challenging practical problem for vision based applications. Most recent approaches for MOT use precomputed detections from models such as Faster RCNN, performing fine-tuning of bounding boxes and association in subsequent phases. However, this is not suitable for actual industrial applications due to unavailability of detections upfront. In their recent work, Wang et al. proposed a tracking pipeline that uses a Joint detection and embedding model and performs target localization and association in realtime. Upon investigating the tracking by detection paradigm, we find that the tracking pipeline can be made faster by performing localization and association tasks parallely with model prediction. This, and other computational optimizations such as using mixed precision model and performing batchwise detection result in a speed-up of the tracking pipeline by 57.8\% (19 FPS to 30 FPS) on FullHD resolution. Moreover, the speed is independent of the object density in image sequence. The main contribution of this paper is showcasing a generic pipeline which can be used to speed up detection based object tracking methods. We also reviewed different batch sizes for optimal performance, taking into consideration GPU memory usage and speed.
