Multi-object tracking (MOT) has made great progress in recent years, but there are still some problems. Most MOT algorithms follow tracking-by-detection framework, which separates detection and tracking into two independent parts. Early tracking-by-detection algorithms need to do two feature extractions for detection and tracking. Recently, some algorithms make the feature extraction into one network, but the tracking part still relies on data association and needs complex post-processing for life cycle management. Those methods do not combine detection and tracking well. In this paper, we present a novel network to realize joint multi-object detection and tracking in an end-to-end way, called Global Correlation Network (GCNet). Different from most object detection methods, GCNet introduces the global correlation layer for regression of absolute size and coordinates of bounding boxes instead of offsets prediction. The pipeline of detection and tracking by GCNet is conceptually simple, which does not need non-maximum suppression, data association, and other complicated tracking strategies. GCNet was evaluated on a multi-vehicle tracking dataset, UA-DETRAC, and demonstrates promising performance compared to the state-of-the-art detectors and trackers.
翻译:多目标跟踪(MOT)近年来取得了很大进展,但仍有一些问题。大多数MOT算法都遵循了逐个检测跟踪框架,将检测和跟踪分为两个独立部分。早期逐个检测算法需要进行两种特征提取,以便检测和跟踪。最近,一些算法将特征提取成一个网络,但跟踪部分仍然依赖于数据关联,需要复杂的生命周期管理后处理。这些方法并不很好地结合探测和跟踪。在本文中,我们提出了一个新的网络,以最终到终端的方式实现多目标联合检测和跟踪,称为全球关联网络(GCNet)。与大多数对象检测方法不同,GCNet引入了绝对大小回归的全球相关层,并协调捆绑盒,而不是抵消预测。GCNet的检测和跟踪管道在概念上很简单,不需要非最大程度的抑制、数据关联和其他复杂的跟踪战略。GCNet在多车辆跟踪数据集、UA-DETRAC上进行了评估,并展示了与州级探测器和轨道相比有希望的业绩。