融合车载影像与点云的道路边界提取与矢量化

Fusion of Vehicle-Mounted Imagery and Point Cloud for Road Boundary Extraction and Vectorization

车载激光点云的数据不完整和影像连续帧之间的地物重影现象给提取连续、完整的道路边界带来了巨大挑战。提出了一种融合点云与全景影像的道路边界提取与矢量化方法。首先,分别从点云和全景影像中提取初始道路边界点,然后基于非闭合Snake模型融合两种数据源中的道路边界点,实现结构化和非结构化道路边界的准确提取与矢量化。该融合过程首先基于点云中的道路边界构建特征图,并以车载影像中的道路边界提取结果为初始轮廓,然后基于道路边界的几何特性构建非闭合Snake模型,最后通过求解该模型实现多源道路边界点的融合,并完成道路边界线的矢量化。将该方法应用于2个城市场景数据集,结果表明:该方法可有效提取形状多样的结构化和非结构化道路边界,对由于遮挡导致的数据不完整和多帧影像中的地物重影具有较强的鲁棒性,对城区道路边界提取的精度、召回率、F1值分别优于95.43%、89.27%、93.38%。

Objectives:The incomplete data in vehicle-mounted laser point clouds and the large number of overlapping objects among consecutive frames of images have brought great challenges to the extraction of continuous and complete road boundaries.Methods:To address the above challenges,we propose a road boundary extraction and vectorization method that takes the full advantage of point clouds and panoramic images.First,initial road boundaries are extracted from point clouds and panoramic images respectively.Then,the extracted road boundaries are accurately fused at the result level based on an improved Snake model.The fusion procedure includes three main steps:Feature map generation,mathematical model for⁃mulation,and the model solver.With the successful fusion of road boundaries from two modal data,the model finally generates complete and continuous vectorized road boundaries.Results:Additionally,the ef⁃fectiveness of the proposed method is demonstrated on two typical urban scene datasets.Experiments elabo⁃rate that the proposed method can effectively extract complete and continuous vectorized road boundaries with diverse structures and shapes,in terms of precision,recall,and F1 score better than 95.43%,89.27%,and 93.38%,respectively.Conclusions:Compared to the single data source based method,the proposed multimodal data fusion method fully leverages the advantages of 3D point clouds with precise geo⁃metrical features and panoramic images with rich textures.The method is robust to data incompleteness due to occlusion and overlapping objects in multi-frame images.Consequently,the extracted vectorized road boundaries are more accurate,complete,and smoother compared to the sole source data based methods,which can support downstream applications such as high definition maps generation,directly.