Performing LiDAR data point cloud reduction using hyperspectral imaging

Authors: Bingqing Liang, Mentor from REU IDREHSI, Clarice Norton*, University of Texas at Austin
Topics: Geographic Information Science and Systems
Keywords: GIS, LiDAR, Hyperspectral, Point Cloud, Data reduction
Session Type: Poster
Day: 4/4/2019
Start / End Time: 9:55 AM / 11:35 AM
Room: Lincoln 2, Marriott, Exhibition Level
Presentation File: Download


High resolution LiDAR data is becoming an important component of answering complex environmental questions. However, the size of the files can make it very difficult to work with. Raw LiDAR data is often composed of millions or even billions of points that make up the point cloud. The sheer volume of the point cloud makes file sizes very large, resulting in long runtimes for associated operations. Reducing the number of points in each file is a proven method of decreasing file size and runtimes. We seek to address this issue, thereby increasing the broad utility of LiDAR data, by seeking a method to filter the points in a guided way while maintaining the accuracy of generated products. We are expanding upon these methods, incorporating hyperspectral imagery into the file reduction process by creating an artificial neural network landuse/landcover classification to guide the filtering by terrain complexity.

Abstract Information

This abstract is already part of a session. View the session here.

To access contact information login