摘要
提出一种基于深度信念网络(DBN)的车载激光点云路侧多目标提取方法。首先通过预处理对原始数据进行分段,并将地面和建筑物点云与路侧目标进行分离;然后利用连通分支聚类分析算法进行路侧点云聚类,并采用基于体素的归一化分割方法分割重叠点云,从而生成独立目标点云;在此基础上,生成基于多方向目标对象的二值图像并展开成二值向量作为独立目标点云的描述特征;最后构建并训练DBN,利用训练好的DBN提取行道树、车辆及杆状目标等3类路侧目标。试验采用两份不同城市道路场景的点云数据,行道树、车辆及杆状目标提取结果的准确率分别达97.31%、97.79%、92.78%,召回率分别达98.30%、98.75%和96.77%,精度分别达95.70%、93.81%和90.00%,F1值分别达97.80%、96.81%和94.73%。试验结果验证了本文的有效性。
This paper proposed an novel algorithm for exploring deep belief network(DBN)architectures to extract and recognize roadside facilities(trees,cars and traffic poles)from mobile laser scanning(MLS)point cloud.The proposed methods firstly partitioned the raw MLS point cloud into blocks and then removed the ground and building points.In order to partition the off-ground objects into individual objects,off-ground points were organized into an Octree structure and clustered into candidate objects based on connected component.To improve segmentation performance on clusters containing overlapped objects,a refining processing using a voxel-based normalized cut was then implemented.In addition,multi-view features descriptor was generated for each independent roadside facilities based on binary images.Finally,a deep belief network(DBN)was trained to extract trees,cars and traffic pole objects.Experiments are undertaken to evaluate the validities of the proposed method with two datasets acquired by Lynx Mobile Mapper System.The precision of trees,cars and traffic poles objects extraction results respectively was 97.31%,97.79% and 92.78%.The recall was 98.30%,98.75% and 96.77%respectively.The quality is 95.70%,93.81%and 90.00%.And the F1 measure was 97.80%,96.81%and 94.73%.
出处
《测绘学报》
EI
CSCD
北大核心
2018年第2期234-246,共13页
Acta Geodaetica et Cartographica Sinica
基金
国家自然科学基金(41501493)
福建省科技计划重点项目(2015H0015)
中国博士后科学基金(2017M610391)~~
关键词
车载激光点云
深度信念网络
深度学习
点云分割
路侧目标提取
MLS point cloud
deep belief network(DBN)
deep learning
point cloud segmentation
road side objects extraction