A Fast Point Cloud Ground Segmentation Approach Based on Coarse-To-Fine Markov Random Field
文献类型:期刊论文
作者 | Huang WX(黄伟鑫)1,4; Liang HW(梁华为)1,2,3; Lin LL(林玲龙)1,2,3; Wang ZL(王智灵)1,2,3; Wang SB(王少博)1,4; Yu B(余彪)1,2,3; Niu RX(牛润新)1,2,3 |
刊名 | IEEE Transactions on Intelligent Transportation Systems |
出版日期 | 2021-04-21 |
英文摘要 | Ground segmentation is an important preprocessing task for autonomous vehicles (AVs) with 3D LiDARs. However, the existing ground segmentation methods are very difficult to balance accuracy and computational complexity. This paper proposes a fast point cloud ground segmentation approach based on a coarse-to-fine Markov random field (MRF) method. The method uses the coarse segmentation result of an improved local feature extraction algorithm instead of prior knowledge to initialize an MRF model. It provides an initial value for the fine segmentation and dramatically reduces the computational complexity. The graph cut method is then used to minimize the proposed model to achieve fine segmentation. Experiments on two public datasets and field tests show that our approach is more accurate than both methods based on features and MRF and faster than graph-based methods. It can process Velodyne HDL-64E data frames in real-time (24.86 ms, on average) with only one thread of the I7-8700 CPU. Compared with methods based on deep learning, it has better environmental adaptability. |
语种 | 英语 |
WOS记录号 | WOS:000732221600001 |
源URL | [http://ir.hfcas.ac.cn:8080/handle/334002/125910] |
专题 | 合肥物质科学研究院_中科院合肥智能机械研究所 |
通讯作者 | Yu B(余彪); Niu RX(牛润新) |
作者单位 | 1.中科学院合肥物质科学研究院 2.中国科学院机器人与智能制造创新研究院 3.安徽省智能驾驶技术及应用工程实验室 4.中国科学技术大学 |
推荐引用方式 GB/T 7714 | Huang WX,Liang HW,Lin LL,et al. A Fast Point Cloud Ground Segmentation Approach Based on Coarse-To-Fine Markov Random Field[J]. IEEE Transactions on Intelligent Transportation Systems,2021. |
APA | Huang WX.,Liang HW.,Lin LL.,Wang ZL.,Wang SB.,...&Niu RX.(2021).A Fast Point Cloud Ground Segmentation Approach Based on Coarse-To-Fine Markov Random Field.IEEE Transactions on Intelligent Transportation Systems. |
MLA | Huang WX,et al."A Fast Point Cloud Ground Segmentation Approach Based on Coarse-To-Fine Markov Random Field".IEEE Transactions on Intelligent Transportation Systems (2021). |
入库方式: OAI收割
来源:合肥物质科学研究院
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。