Evaluation of LiDAR and image segmentation based classification techniques for automatic building footprint extraction for a segment of Atlantic County, New Jersey

Abstract

Extracting high-quality building footprints is a basic requirement in multiple sectors of town planning, disaster management, 3D visualization, etc. In the current study, we compare three different techniques for acquiring building footprints using (i) LiDAR, (ii) object-oriented classification (OOC) applied on high-resolution aerial photographs and (iii) digital surface models generated from interpolated LiDAR point cloud data. The three outputs were compared with a digitized sample of building polygons quantitatively by computing the errors of commission and omission, and qualitatively using statistical operations. These findings showed that building footprints derived from OOC gave highest regression and correlation values with least commission error. The R² and R values (0.86 and 0.92, respectively) imply that the footprint areas derived by OOC matched more closely with the actual area of buildings, while a low commission error of 24.7% represented a higher number of footprints as correctly classified.

Keywords:

• LiDAR
• building footprints
• object-oriented classification
• image segmentation
• DSM

Acknowledgement

The authors acknowledge the USGS for providing LiDAR data-sets, duly acquired under the Accessibility Policy (Section 508). We would also like to thank the New Jersey Geographic Information Network developed and maintained by the NJ Office of Information Technology (Office of GIS) for providing high-resolution aerial photographs of the study area. Further, we would like to extend our sincere gratitude to Ms Paige Parker from the GeoCue Corporation for equipping us with LP360 QCoherent Software (Advanced version) which immensely aided in putting this work in its current form.

Disclosure statement

No potential conflict of interest was reported by the authors.