| 超体素随机森林与LSTM神经网络联合优化的室内点云高精度分类方法 |
| |
| 引用本文： | 汤圣君,张韵婕,李晓明,姚萌萌,叶致煌,李亚鑫,郭仁忠,王伟玺.超体素随机森林与LSTM神经网络联合优化的室内点云高精度分类方法[J].武汉大学学报(信息科学版),2023,48(4):525-533. |
| |
| 作者姓名： | 汤圣君 张韵婕 李晓明 姚萌萌 叶致煌 李亚鑫 郭仁忠 王伟玺 |
| |
| 作者单位： | 1.深圳大学建筑与城市规划学院智慧城市研究院&自然资源部城市自然资源监测与仿真重点实验室, 广东 深圳, 518061 |
| |
| 基金项目： | 深圳市科技计划JCYJ20210324093012033广东省自然科学基金2121A1515012574自然资源部城市国土资源监测与仿真重点实验室开放基金KF-2021-06-1252020年佛山市促进高校科技成果服务产业发展扶持项目2020DZXX04国家自然科学基金71901147国家自然科学基金41901329国家自然科学基金41971354国家自然科学基金41971341深圳大学新入职教师项目2019056 |
| |
| 摘 要： | 针对现有三维点云数据分割分类方法存在分类目标内部不一致的问题，提出一种超体素随机森林与长短期记忆神经网络（long short-term memory,LSTM）联合优化的室内点云高精度分类方法。该方法根据超体素结构具备内部特征一致性的特点，对原始点云进行超体素划分，并以超体素为基本单元进行多元特征计算，搭建室内点云超体素随机森林分类模型，实现点云数据的粗分类。在此基础上，引入LSTM对粗分类的超体素邻域连接关系进行神经网络模型训练与预测，实现超体素粗分类结果的优化。基于开放数据集对所提分类方法进行有效性和精度验证，结果显示，该方法在公开数据集中对13类要素的分类精度可达到83.2%；与经典的深度学习框架相比，该方法在小样本训练时可以达到更优的分类精度。
|
| 关 键 词： | 超体素 随机森林 LSTM 点云分类 室内建模 |
| 收稿时间： | 2022-03-09 |
A High-Precision Indoor Point Cloud Classification Method Jointly Optimized by Super Voxel Random Forest and LSTM Neural Network |
| |
| Affiliation: | 1.School of Architecture and Urban Planning, Shenzhen University & Key Laboratory of Urban Natural Resources Monitoring and Simulation, MNR, Shenzhen 518061, China2.Department of Architecture and Civil Engineering, City University of Hong Kong, Hong Kong 999077, China3.Shenzhen Research Institute, Hong Kong Polytechnic University, Shenzhen 518061, China |
| |
| Abstract: | Objectives To address the problem of internal inconsistency of classification targets in existing three dimensional(3D) point cloud data segmentation and classification methods. we propose a high-precision classification method for indoor point cloud jointly optimized by super voxel random forest and long short-term memory (LSTM) neural network. Methods The method takes into account that the super voxel structure has the characteristics of internal feature consistency, divides the original point cloud into super voxels, and uses super voxels as the basic unit for multivariate feature calculation to build a super voxel random forest classification model for indoor point cloud to achieve coarse classification of point cloud data. On this basis, LSTM is introduced to train and predict the neural network model for the hyper voxel neighborhood connectivity of coarse classification to achieve the optimization of hyper voxel coarse classification results. The validity and accuracy of the proposed classification method are verified based on the open dataset. Results The results show that the classification accuracy of the proposed classification method can reach 83.2% for 13 types of elements in the open dataset. The training data of the LSTM optimization network proposed in this paper used only the label information of region 1 for model training, while other deep learning frameworks used regions 1-5 for model training, so from the perspective of training data requirements, the point cloud data classification framework proposed in this paper can achieve a relatively better prediction result with a small portion of the training data set. The super voxel-based LSTM optimization method approach has high classification accuracy on objects with obvious set features such as ceiling, floor and wall, however, it is inferior to the deep learning algorithm RandLA-Net in classifying objects with complex structures such as chair, sofa and bookcase. Conclusions In this paper, we consider the association characteristics between different types of elements embedded in the connection relations among super voxels, and introduce LSTM to train and predict the model for the coarse classification of super voxel neighborhood connection relations to achieve the optimization of coarse classification results of super voxels. The proposed method can achieve better classification accuracy when trained with small samples compared with the classical deep learning framework. |
| |
| Keywords: | |
|
| 点击此处可从《武汉大学学报(信息科学版)》浏览原始摘要信息 |
|
点击此处可从《武汉大学学报(信息科学版)》下载全文 |
|
