Computing multiple aggregation levels and contextual features for road facilities recognition using mobile laser scanning data
Computing multiple aggregation levels and contextual features for road facilities recognition using mobile laser scanning data
复制标题
使用移动激光扫描数据计算道路设施识别的多个聚合级别和上下文特征
DOI：
10.1016/j.isprsjprs.2017.02.014
复制
发表时间：
2017-04
影响因子：
12.7
通讯作者：
Wang Yongjun
中科院分区：
文献类型：
--
作者：
Yang Bisheng;Dong Zhen;Liu Yuan;Liang Fuxun;Wang Yongjun
近年来，基于实地工作更新道路基础设施的库存是劳动密集型的、耗时的并且成本高。幸运的是，基于车辆的移动的激光扫描（MLS）系统提供了一种高效的解决方案，以高灵活性和精度快速捕获道路环境的三维（3D）点云。然而，从大量的三维点云的道路设施的鲁棒识别仍然是一个具有挑战性的问题，因为复杂和不完整的结构，闭塞和不同的点密度。现有的方法大多利用基于点或对象的特征来识别候选对象，并且只能提取有限类型的对象，识别率相对较低，特别是对于不完整和小的对象。为了克服这些缺点，本文提出了一个语义标注框架，结合多个聚合层次（点段对象）的功能和上下文特征识别道路设施，如路面，道路边界，建筑物，护栏，路灯，交通标志，路边树，电力线，和汽车，公路基础设施库存。该方法首先识别地面点和非地面点，并从地面点提取路面设施。提出了一种基于多规则区域生长的非地面点分割方法。然后，计算与每个候选对象相关联的特征和上下文特征（相对位置、相对方向和空间模式）的多个聚合水平，并将其馈送到SVM分类器中以标记对应的候选对象。结合多个聚合水平和上下文功能的识别性能进行了比较，单级（点，段，或对象）为基础的功能，使用大规模的高速公路场景点云。对比研究表明，所提出的语义标注框架显着提高道路设施识别的准确率（90.6%）和召回率（91.2%），特别是对不完整和小的对象。
In recent years, updating the inventory of road infrastructures based on field work is labor intensive, time consuming, and costly. Fortunately, vehicle-based mobile laser scanning (MLS) systems provide an efficient solution to rapidly capture three-dimensional (3D) point clouds of road environments with high flexibility and precision. However, robust recognition of road facilities from huge volumes of 3D point clouds is still a challenging issue because of complicated and incomplete structures, occlusions and varied point densities. Most existing methods utilize point or object based features to recognize object candidates, and can only extract limited types of objects with a relatively low recognition rate, especially for incomplete and small objects. To overcome these drawbacks, this paper proposes a semantic labeling framework by combing multiple aggregation levels (point-segment-object) of features and contextual features to recognize road facilities, such as road surfaces, road boundaries, buildings, guardrails, street lamps, traffic signs, roadside-trees, power lines, and cars, for highway infrastructure inventory. The proposed method first identifies ground and non-ground points, and extracts road surfaces facilities from ground points. Non-ground points are segmented into individual candidate objects based on the proposed multi-rule region growing method. Then, the multiple aggregation levels of features and the contextual features (relative positions, relative directions, and spatial patterns) associated with each candidate object are calculated and fed into a SVM classifier to label the corresponding candidate object. The recognition performance of combining multiple aggregation levels and contextual features was compared with single level (point, segment, or object) based features using large-scale highway scene point clouds. Comparative studies demonstrated that the proposed semantic labeling framework significantly improves road facilities recognition precision (90.6%) and recall (91.2%), particularly for incomplete and small objects.
登录
查看更多内容
影响因子：
4.5
作者：
Fischer, A;Kolbe, TH;Steinhage, V
通讯作者：
Steinhage, V
使用彩色移动激光雷达点云对道路场景进行基于补丁的语义标记
DOI：
10.1109/tits.2015.2499196
发表时间：
2016
影响因子：
8.5
作者：
Luo Huan;Wang Cheng;Wen Chenglu;Cai Zhipeng;Chen Ziyi;Wang Hanyun;Yu Yongtao;Li Jonathan
通讯作者：
Li Jonathan
影响因子：
6.2
作者：
Osada, R;Funkhouser, T;Dobkin, D
通讯作者：
Dobkin, D
DOI：
10.1007/978-3-540-24672-5_18
发表时间：
2004-05
期刊：
--
影响因子：
--
作者：
Andrea Frome;Daniel F. Huber;R. Kolluri;Thomas Bülow;Jitendra Malik
通讯作者：
Andrea Frome;Daniel F. Huber;R. Kolluri;Thomas Bülow;Jitendra Malik
影响因子：
5
作者：
Wai Yeung Yan;S. Morsy;A. Shaker;M. Tulloch
通讯作者：
Wai Yeung Yan;S. Morsy;A. Shaker;M. Tulloch