Normandie University, UNIROUEN, ESIGELEC, IRSEEM, 76000 Rouen, France.
Sensors (Basel). 2020 Jan 18;20(2):532. doi: 10.3390/s20020532.
In core computer vision tasks, we have witnessed significant advances in object detection, localisation and tracking. However, there are currently no methods to detect, localize and track objects in road environments, and taking into account real-time constraints. In this paper, our objective is to develop a deep learning multi object detection and tracking technique applied to road smart mobility. Firstly, we propose an effective detector-based on YOLOv3 which we adapt to our context. Subsequently, to localize successfully the detected objects, we put forward an adaptive method aiming to extract 3D information, i.e., depth maps. To do so, a comparative study is carried out taking into account two approaches: Monodepth2 for monocular vision and MADNEt for stereoscopic vision. These approaches are then evaluated over datasets containing depth information in order to discern the best solution that performs better in real-time conditions. Object tracking is necessary in order to mitigate the risks of collisions. Unlike traditional tracking approaches which require target initialization beforehand, our approach consists of using information from object detection and distance estimation to initialize targets and to track them later. Expressly, we propose here to improve SORT approach for 3D object tracking. We introduce an extended Kalman filter to better estimate the position of objects. Extensive experiments carried out on KITTI dataset prove that our proposal outperforms state-of-the-art approches.
在核心计算机视觉任务中，我们已经见证了物体检测、定位和跟踪方面的重大进展。然而，目前还没有方法可以在道路环境中并考虑到实时约束条件下检测、定位和跟踪物体。在本文中，我们的目标是开发一种应用于道路智能移动性的深度学习多目标检测和跟踪技术。首先，我们提出了一种基于 YOLOv3 的有效检测器，我们对其进行了适应我们上下文的调整。随后，为了成功定位检测到的物体，我们提出了一种旨在提取 3D 信息（即深度图）的自适应方法。为此，我们进行了一项考虑两种方法的比较研究：用于单目视觉的 Monodepth2 和用于立体视觉的 MADNEt。然后，在包含深度信息的数据集上对这些方法进行评估，以确定在实时条件下表现更好的最佳解决方案。为了减轻碰撞风险，需要进行目标跟踪。与需要事先进行目标初始化的传统跟踪方法不同，我们的方法包括使用来自物体检测和距离估计的信息来初始化目标，然后跟踪它们。具体来说，我们在这里提出了一种改进 3D 目标跟踪的 SORT 方法。我们引入了一个扩展卡尔曼滤波器来更好地估计物体的位置。在 KITTI 数据集上进行的广泛实验证明，我们的提议优于最先进的方法。
