当前位置: X-MOL 学术IEEE Trans. Fuzzy Syst. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Fuzzy Neighborhood Learning for Deep 3D Segmentation of Point Cloud
IEEE Transactions on Fuzzy Systems ( IF 11.9 ) Pub Date : 2020-12-01 , DOI: 10.1109/tfuzz.2020.2992611
Mingyang Zhong , Chaojie Li , Liangchen Liu , Jiahui Wen , Jingwei Ma , Xinghuo Yu

Semantic segmentation of point cloud data, an efficient 3-D scattered point representation, is a fundamental task for various applications, such as autonomous driving and 3-D telepresence. In recent years, deep learning techniques have achieved significant progress in semantic segmentation, especially in the 2-D image setting. However, due to the irregularity of point clouds, most of them cannot be applied to this special data representation directly. While recent works are able to handle the irregularity problem and maintain the permutation invariance, most of them fail to capture the valuable high-dimensional local feature in fine granularity. Inspired by fuzzy mathematical methods and the analysis on the drawbacks of current state-of-the-art works, in this article, we propose a novel deep neural model, Fuzzy3DSeg, that is able to directly feed in the point clouds while maintaining invariant to the permutation of the data feeding order. We deeply integrate the learning of the fuzzy neighborhood feature of each point into our network architecture, so as to perform operations on high-dimensional features. We demonstrate the effectiveness of this network architecture level integration, compared with methods of the fuzzy data preprocessing cascading neural network. Comprehensive experiments on two challenging datasets demonstrate that the proposed Fuzzy3DSeg significantly outperforms the state-of-the-art methods.

中文翻译:

用于点云深度 3D 分割的模糊邻域学习

点云数据的语义分割是一种高效的 3-D 散点表示,是各种应用(例如自动驾驶和 3-D 远程呈现)的基本任务。近年来,深度学习技术在语义分割方面取得了重大进展,尤其是在二维图像设置方面。然而,由于点云的不规则性,它们中的大多数不能直接应用于这种特殊的数据表示。虽然最近的工作能够处理不规则问题并保持排列不变性,但它们中的大多数未能以细粒度捕获有价值的高维局部特征。受模糊数学方法的启发和对当前最先进作品缺点的分析,在本文中,我们提出了一种新颖的深度神经模型 Fuzzy3DSeg,它能够直接输入点云,同时保持对数据输入顺序排列的不变。我们将每个点的模糊邻域特征的学习深度融入我们的网络架构中,从而对高维特征进行操作。与模糊数据预处理级联神经网络的方法相比,我们证明了这种网络架构级集成的有效性。在两个具有挑战性的数据集上进行的综合实验表明,所提出的 Fuzzy3DSeg 显着优于最先进的方法。从而对高维特征进行操作。与模糊数据预处理级联神经网络的方法相比,我们证明了这种网络架构级集成的有效性。在两个具有挑战性的数据集上进行的综合实验表明,所提出的 Fuzzy3DSeg 显着优于最先进的方法。从而对高维特征进行操作。与模糊数据预处理级联神经网络的方法相比,我们证明了这种网络架构级集成的有效性。在两个具有挑战性的数据集上进行的综合实验表明,所提出的 Fuzzy3DSeg 显着优于最先进的方法。
更新日期:2020-12-01
down
wechat
bug