Extracted Features from ISPRS Vaihingen 3D Dataset

This dataset contains 3D point cloud data from the Vaihingen dataset, enriched with newly introduced Inner-Cube and Outer-Cube geometric features. It has been used for semantic labeling and classification tasks using various machine learning models, including Support Vector Machine (SVM), Random Forest (RF), Deep Neural Networks (DNN), PointNet++, and their combinations with Conditional Random Fields (CRF).Key Features: Original Vaihingen 3D Point Cloud Data, Inner-Cube and Outer-Cube Features for geometric property extraction, Labeled Data for Semantic Labeling, Compatible with ML and Deep Learning ModelsUsed in "Enhancing 3D Point Cloud Semantic Labeling by Introducing Innovative Cubic Neighborhoods" (This paper has been submitted and is awaiting review.)This dataset is publicly available for research purposes, particularly for point cloud classification, LiDAR data analysis, and ML-based 3D data processingFor more details, refer to the GitHub repository: https://github.com/FarzanehAghighi/InnerOuterCube-CRF-ML. (It will be uploaded soon)

本数据集包含源自韦欣根数据集（Vaihingen dataset）的3D点云数据，并通过新引入的立方体内（Inner-Cube）与立方体外（Outer-Cube）几何特征完成了特征增强。该数据集已被用于结合多种机器学习模型开展语义标注与分类任务，所涉模型包括支持向量机（Support Vector Machine, SVM）、随机森林（Random Forest, RF）、深度神经网络（Deep Neural Networks, DNN）、PointNet++，以及上述模型与条件随机场（Conditional Random Fields, CRF）的组合架构。
核心特性：原始韦欣根3D点云数据、用于提取几何属性的立方体内与立方体外特征、面向语义标注的标注数据集、兼容机器学习与深度学习模型。
本数据集已应用于论文《基于创新立方邻域的3D点云语义标注优化》（该论文已提交待审）。本数据集可公开用于科研用途，尤其适用于点云分类、激光雷达（LiDAR）数据分析以及基于机器学习的3D数据处理任务。如需获取更多详情，请参阅该GitHub仓库：https://github.com/FarzanehAghighi/InnerOuterCube-CRF-ML（该仓库即将上传）。