论文标题
使用板载摄像头了解鸟类的道路语义的视图
Understanding Bird's-Eye View of Road Semantics using an Onboard Camera
论文作者
论文摘要
自主导航需要场景对动作空间的了解才能移动或预测事件。对于在地面飞机上行驶的策划者（例如自动驾驶汽车），这转化为鸟眼观察（BEV）中的场景。但是，自动驾驶汽车的车载摄像头通常可以水平安装，以更好地欣赏周围环境。在这项工作中，我们使用单个板载摄像头的视频输入以在线估算语义BEV图的形式研究场景理解。我们研究此任务的三个关键方面，图像级的理解，BEV级别的理解以及时间信息的聚集。基于这三个支柱，我们提出了一种结合这三个方面的新型建筑。在我们的广泛实验中，我们证明了所考虑的方面是相互互补的，以了解BEV。此外，拟议的建筑显着超过了当前的最新。代码：https：//github.com/ybarancan/bev_feat_stitch。
Autonomous navigation requires scene understanding of the action-space to move or anticipate events. For planner agents moving on the ground plane, such as autonomous vehicles, this translates to scene understanding in the bird's-eye view (BEV). However, the onboard cameras of autonomous cars are customarily mounted horizontally for a better view of the surrounding. In this work, we study scene understanding in the form of online estimation of semantic BEV maps using the video input from a single onboard camera. We study three key aspects of this task, image-level understanding, BEV level understanding, and the aggregation of temporal information. Based on these three pillars we propose a novel architecture that combines these three aspects. In our extensive experiments, we demonstrate that the considered aspects are complementary to each other for BEV understanding. Furthermore, the proposed architecture significantly surpasses the current state-of-the-art. Code: https://github.com/ybarancan/BEV_feat_stitch.
