Karst Sinkhole Detecting and Mapping Using Airborne LiDAR - A Conceptual Framework

Abstract

Sinkholes cause subsidence and collapse problems for many transportation infrastructure assets. Subsequently, transportation infrastructure management agencies dedicate a considerable amount of time and money to detect and map sinkholes as part of their asset management programs. Traditionally, sinkholes are detected through area reconnaissance, which includes visual inspection of a site to locate existing sinkholes or device inspection of a site to locate potential sinkholes or previously filled sinkholes. Another method for sinkhole detection is through a review of maps such as geological maps. These methods are expensive, time-consuming, and labor-intensive. Recent advances in remote sensing, especially airborne light detection and ranging (LiDAR), allows for the examination of the change in the Earth's surface elevation accurately and rapidly. The focus of this study is to develop a conceptual framework for sinkhole detection and mapping with airborne LiDAR. This conceptual framework lays the foundation for the future application of airborne LiDAR for sinkhole detection and mapping.

Detecting and Tracking Sinkholes Using Multi-Level Convolutional Neural Networks and Data Association

“…The model first creates a digital elevation model (DEM), fills the depressions in the DEM, extracts the depressions with DEM differences, and converts the depressions to a polygon shape file. The system in [7] utilized airborne LiDAR data in combination with context information to improve the accuracy of sinkhole detection. [8] proposed a conceptual framework for detecting sinkholes by airborne LiDAR that consists of three steps: data prepossessing, preliminary sinkhole map development, and final sinkhole map development.…”

“…The system in [7] utilized airborne LiDAR data in combination with context information to improve the accuracy of sinkhole detection. [8] proposed a conceptual framework for detecting sinkholes by airborne LiDAR that consists of three steps: data prepossessing, preliminary sinkhole map development, and final sinkhole map development. Airborne LiDAR can provide a solution to identify subsidence areas by using ground object temperature, which cannot be determined using traditional photography.…”