Abstract LiDAR point clouds contain measurements of complicated natural scenes and can be used to update digital elevation models, glacial monitoring, detecting faults and measuring uplift detecting, forest inventory, detect shoreline and beach volume changes, landslide risk analysis, habitat mapping, and urban development, among others. A very important application is the classification of the 3D cloud into elementary classes. For example, it can be used to differentiate between vegetation, man-made structures, and water. Our goal is to present a preliminary comparison study for the classification of 3D point cloud LiDAR data that includes several types of feature engineering. In particular, we demonstrate that providing context by augmenting each point in the LiDAR point cloud with information about its neighboring points can improve the performance of downstream learning algorithms. We also experiment with several dimension reduction strategies, ranging from Principal Component Analysis (PCA) to neural network-based auto-encoders, and demonstrate how they affect classification performance in LiDAR point clouds. For instance, we observe that by combining feature engineering with a dimension reduction method such as PCA, there is an improvement in the accuracy of the classification with respect to doing a straightforward classification with the raw data.
BIO: F. Patricia Medina receivd PhD in Mathematics from Oregon State in 2014. She is an Assistant Professor at the Computer Science Department at Yeshiva College. She is a member of the Women in Data Science and Mathematics (current list server webmaster). Her current research focus is on machine learning and she is the PI of a Microsoft computing grant-AI for Earth and a Google Explore grant for funding undergraduate research. Prior to joining Yeshiva University, she was a postdoctoral scholar at Worcester Polytechnic Institute (Mathematics Department and Data Science program) and a visiting scholar at ICERM, Brown University. She also held academic positions at Oregon State University, Universidad Simon Bolivar, and Universidad Central de Venezuela. Dr. Medina has training in pure mathematics, applied and computational mathematics, and data science.