ShadowCam: Real-Time Detection of Moving Obstacles Behind A Corner For Autonomous Vehicles
ShadowCam: Real-Time Detection of Moving Obstacles Behind A Corner For Autonomous Vehicles
复制标题
DOI：
10.1109/itsc.2018.8569569
复制
发表时间：
2018-11
期刊：
影响因子：
--
通讯作者：
Felix Naser;Igor Gilitschenski;G. Rosman;Alexander Amini;F. Durand;A. Torralba;G. Wornell;W. Freeman;S. Karaman;D. Rus
中科院分区：
文献类型：
--
作者：
Felix Naser;Igor Gilitschenski;G. Rosman;Alexander Amini;F. Durand;A. Torralba;G. Wornell;W. Freeman;S. Karaman;D. Rus
在自动驾驶汽车等移动机器人应用中，被角落遮挡的移动障碍物是碰撞的潜在来源。在本文中，我们提出了一种基于视觉的检测算法，用于车辆直接视线之外的障碍物，从而解决了预测此类碰撞的问题。我们的方法检测隐藏在角落周围的障碍物的阴影，并自动将这些看不见的障碍物分类为“动态”或“静态”。我们在现实世界的角落和各种模拟环境中评估了我们提出的检测算法，以评估在不同具有挑战性的表面和照明条件下的泛化性。在模拟数据上的平均分类准确率约为80%，在真实世界的角落上约为70%。此外，我们将检测系统集成到全尺寸自动轮椅上，并通过现实世界的实验证明其作为额外安全机制的可行性。我们在开源许可下发布了ShadowCam算法的实时实现以及包含模拟和真实数据的数据集。
Moving obstacles occluded by corners are a potential source for collisions in mobile robotics applications such as autonomous vehicles. In this paper, we address the problem of anticipating such collisions by proposing a vision-based detection algorithm for obstacles which are outside of a vehicle's direct line of sight. Our method detects shadows of obstacles hidden around corners and automatically classifies these unseen obstacles as “dynamic” or “static”. We evaluate our proposed detection algorithm on real-world corners and a large variety of simulated environments to assess generalizability in different challenging surface and lighting conditions. The mean classification accuracy on simulated data is around 80% and on real-world corners approximately 70%. Additionally, we integrate our detection system on a full-scale autonomous wheelchair and demonstrate its feasibility as an additional safety mechanism through real-world experiments. We release our real-time-capable implementation of the proposed ShadowCam algorithm and the dataset containing simulated and real-world data under an open-source license.