UAV images and deep learning improve measuring land sinking
Determining Vertical Displacement of Agricultural Areas Using UAV-Photogrammetry and a Heteroscedastic Deep Learning Model
Computer Vision and Pattern Recognition
Summary
Measuring how much the ground sinks in farm areas can be hard because plants and trees get in the way. The authors created a computer program that uses pictures taken from drones and a special type of machine learning called a U-Net to better guess the actual ground height changes. Their method also tells how sure it is about each guess. When tested on different land areas over time, this new way was a bit more accurate and reliable than older methods.
What this means in practice
- •For agricultural survey teams: Improve tracking of farmland sinking by analyzing drone images more accurately despite plant cover.
- •For environmental monitoring groups: Monitor land deformation over time using corrected elevation data with uncertainty estimates from drone surveys.
Authors
Wojciech Gruszczyński, Edyta Puniach, Paweł Ćwiąkała, Wojciech Matwij
Abstract
This article introduces an algorithm that uses a U-Net architecture to determine vertical ground surface displacements from unmanned aerial vehicle (UAV)-photogrammetry point clouds, offering an alternative to traditional ground filtering methods. Unlike con-ventional ground filters that rely on point cloud classification, the proposed approach em-ploys heteroscedastic regression. The U-Net model predicts the conditional expected val-ues of the elevation corrections, aiming to reduce the impact of vegetation on determined ground surface elevations. Concurrently, it estimates the logarithm of the elevation cor-rection variance, allowing for direct quantification of the uncertainty associated with each elevation correction value. The algorithm was evaluated using three metrics: the root mean square error (RMSE) of vertical displacements, the percentage of nodes with deter-mined displacement values, and the percentage of outliers among those values. Perfor-mance was assessed using the technique for order of preference by similarity to ideal so-lution (TOPSIS) method and compared against several ground-filter-based algorithms across four datasets, each including at least two time intervals. In most cases, the U-Net-based approach demonstrated a slight performance advantage over traditional ground filtering techniques. For example, for the U-Net-based algorithm, for one of the test da-tasets, the RMSE of the determined subsidences was 6.1 cm, the percentage of nodes with determined subsidences was 80.5%, and the percentage of outliers was 0.2%. For the same case, the algorithm based on the next best model (SMRF) allowed an RMSE of 7.7 cm to be obtained; for 77.3% of nodes, the subsidences were determined; and the percentage of outliers was 0.3%.