蒋腾平, 杨必胜, 周雨舟, 朱润松, 胡宗田, 董震. 道路点云场景双层卷积语义分割[J]. 武汉大学学报 ( 信息科学版), 2020, 45(12): 1942-1948. DOI: 10.13203/j.whugis20200081
引用本文: 蒋腾平, 杨必胜, 周雨舟, 朱润松, 胡宗田, 董震. 道路点云场景双层卷积语义分割[J]. 武汉大学学报 ( 信息科学版), 2020, 45(12): 1942-1948. DOI: 10.13203/j.whugis20200081
JIANG Tengping, YANG Bisheng, ZHOU Yuzhou, ZHU Runsong, HU Zongtian, DONG Zhen. Bilevel Convolutional Neural Networks for 3D Semantic Segmentation Using Large-scale LiDAR Point Clouds in Complex Environments[J]. Geomatics and Information Science of Wuhan University, 2020, 45(12): 1942-1948. DOI: 10.13203/j.whugis20200081
Citation: JIANG Tengping, YANG Bisheng, ZHOU Yuzhou, ZHU Runsong, HU Zongtian, DONG Zhen. Bilevel Convolutional Neural Networks for 3D Semantic Segmentation Using Large-scale LiDAR Point Clouds in Complex Environments[J]. Geomatics and Information Science of Wuhan University, 2020, 45(12): 1942-1948. DOI: 10.13203/j.whugis20200081

道路点云场景双层卷积语义分割

Bilevel Convolutional Neural Networks for 3D Semantic Segmentation Using Large-scale LiDAR Point Clouds in Complex Environments

  • 摘要: 在大规模道路环境中,基于点的语义分割方法需要动态计算,而基于体素的方法权衡分辨率和性能导致损失大量信息。为了克服上述两类方法的缺陷,提出了一种通用的结合双层卷积和动态边缘卷积优化的网络架构来进行大型道路场景语义分割。该框架结合点与超体素两种不同域的卷积运算来避免冗余的计算和存储网络中的空间信息,并结合动态边缘卷积优化,使其端到端地一次性处理大规模点云。在不同场景的数据集上对该方法进行了测试与评估,结果表明,该方法能适应不同场景数据集并取得较高精度,优于现有方法。

     

    Abstract: In large-scale road environment, point-based methods require dynamic calculations, and voxel-based methods often lose a lot of information when balancing resolution and performance. To overcome the drawbacks of the above two classical methods, this paper proposes a general network architecture that combines bi-level convolution and dynamic graph edge convolution optimization for multi-object recognition of large-scale road scenes. The framework integrates the convolution operations of two different domains of points and supervoxels to avoid redundant calculations and storage of spatial information in the network. Coupled with the dynamic graph edge convolution optimization, our model enables it to process large-scale point clouds end-to-end at once. Our method was tested and evaluated on different datasets. The experimental results show that our method can achieve higher accuracy in complex road scenes, which is superior to the existing advanced methods.

     

/

返回文章
返回