一种面向非结构化道路的点云语义分割方法  

A point cloud semantic segmentation method for unstructured roads

作　　者：王章宇 陈阳 周彬[1,2,3] 王杰[1,2] 段星集 赵忠山 WANG Zhangyu;CHEN Yang;ZHOU Bin;WANG Jie;DUAN Xingji;ZHAO Zhongshan(School of Transportation Science and Engineering,Beihang University,Beijing 100191,China;State Key Lab of Intelligent Transportation System,Beijing 100191,China;Hefei Innovation Research Institute of Beihang University,Hefei 230012,China;Key Laboratory of Special Vehicle Unmanned Transport Technology Ministry of Industry and Information Technology,Beijing 100191,China;Open-pit Mine Transportation Team,Guoneng Beidian Shengli Energy Co.,Ltd.,Xilinhot 026000,China)

机构地区：[1]北京航空航天大学交通工程与科学学院,北京100191 [2]车路一体智能交通全国重点实验室,北京100191 [3]北京航空航天大学合肥创新研究院,合肥230012 [4]特种车辆无人运输技术工业和信息化部重点实验室,北京100191 [5]国能北电胜利能源有限公司露天矿运输队,锡林浩特026000

出　　处：《北京航空航天大学学报》2025年第2期457-465,共9页Journal of Beijing University of Aeronautics and Astronautics

基　　金：国家重点研发计划(2020YFB1600301);国家自然科学基金青年基金(52102448)。

摘　　要：针对以露天矿区为代表的非结构化道路场景环境恶劣、道路边界模糊、障碍物尺寸差异较大等问题,提出一种面向非结构化道路的点云语义分割方法,包括预处理、特征提取网络及逆处理3部分。其中,预处理通过坐标转换将三维点云映射到二维Range View(RV)图上,以提高网络推理速度;特征提取网络包括卷积注意力模块及多尺度残差模块,卷积注意力模块用于细化分割边界,解决道路边界模糊问题,多尺度残差模块使用大卷积核扩大感受野并融合上下采样特征,以适应非结构化道路环境下障碍物尺寸变化较大的问题;逆处理通过K最邻近(KNN)算法修正语义标签并将点云映射回三维空间。在典型非结构化道路露天矿区数据集上对所提方法进行测试,平均交并比达到85.1%,推理速度达到6.423 ms,与主流的基于球面投影的语义分割网络相比整体精度提升了3%,此外,所提方法在非结构化道路场景下进行了实际应用。A point cloud semantic segmentation method for unstructured road scenes,represented by open-pit mining areas,is proposed to address issues such as harsh environmental conditions,blurred road boundaries,and significant differences in obstacle sizes.The method includes preprocessing,feature extraction networks,and inverse processing.Among them,preprocessing maps the three-dimensional point cloud to a two-dimensional Range View(RV)graph through coordinate transformation to improve network inference speed;The feature extraction network includes a convolutional attention module and a multi-scale residual module.The convolutional attention module is used to refine the segmentation boundaries and solve the problem of blurred road boundaries;The multi-scale residual module uses a large convolution kernel to expand the receptive field and fuse up and down sampling features to adapt to the problem of large changes in obstacle size in unstructured road environments;Inverse processing uses the Knearest neighbor(KNN)algorithm to correct semantic labels and map point clouds back to three-dimensional space.The proposed method was tested on a typical unstructured road open-pit mining dataset,with an average intersection to union ratio of 85.1%and an inference speed of 6.423 ms.Compared with mainstream semantic segmentation network based on spherical projection,the overall accuracy was improved by 3%.In addition,the proposed method has been practically applied in unstructured road scenarios.

关 键 词：三维点云 语义分割 非结构化道路 深度学习 注意力机制 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]