论文标题
用于绘制人行横道的端到端的深层结构化模型
End-to-End Deep Structured Models for Drawing Crosswalks
论文作者
论文摘要
在本文中，我们解决了从激光雷达和相机图像中检测人行横道的问题。朝向这个目标，鉴于多个LIDAR扫描和相应的图像，我们将两个输入投影到地面上，以产生场景的自上而下的视图。然后，我们利用卷积神经网络提取有关人类人行横道位置的语义提示。然后将它们与可自由可用的地图（例如OpenStreetMaps）的道路中心线结合使用，以解决一个结构化的优化问题，该问题绘制了最终的人行横道边界。我们在大型城市地区进行人行横道的实验表明，可以实现96.6％的自动化。
In this paper we address the problem of detecting crosswalks from LiDAR and camera imagery. Towards this goal, given multiple LiDAR sweeps and the corresponding imagery, we project both inputs onto the ground surface to produce a top down view of the scene. We then leverage convolutional neural networks to extract semantic cues about the location of the crosswalks. These are then used in combination with road centerlines from freely available maps (e.g., OpenStreetMaps) to solve a structured optimization problem which draws the final crosswalk boundaries. Our experiments over crosswalks in a large city area show that 96.6% automation can be achieved.
