An Effective Approach for Automatic River Features Extraction Using High-Resolution UAV Imagery

Abstract

The effects of climate change are causing an increase in the frequency and extent of natural disasters. Because of their morphological characteristics, rivers can cause major flooding events. Indeed, they can be subjected to variations in discharge in response to heavy rainfall and riverbank failures. Among the emerging methodologies that address the monitoring of river flooding, those that include the combination of Unmanned Aerial Vehicle (UAV) and photogrammetric techniques (i.e., Structure from Motion-SfM) ensure the high-frequency acquisition of high-resolution spatial data over wide areas and so the generation of orthomosaics, useful for automatic feature extraction. Trainable Weka Segmentation (TWS) is an automatic feature extraction open-source tool. It was developed to primarily fulfill supervised classification purposes of biological microscope images, but its usefulness has been demonstrated in several image pipelines. At the same time, there is a significant lack of published studies on the applicability of TWS with the identification of a universal and efficient combination of machine learning classifiers and segmentation approach, in particular with respect to classifying UAV images of riverine environments. In this perspective, we present a study comparing the accuracy of nine combinations, classifier plus image segmentation filter, using TWS, also with respect to human photo-interpretation, in order to identify an effective supervised approach for automatic river features extraction from UAV multi-temporal orthomosaics. The results, which are very close to human interpretation, indicate that the proposed approach could prove to be a valuable tool to support and improve the hydro-geomorphological and flooding hazard assessments in riverine environments.

Mapping Small Watercourses from DEMs with Deep Learning—Exploring the Causes of False Predictions

“…They found that depending on when the orthomosaic was collected, either the random forest or k-Nearest Neighbors performed the best in terms of the f1-score [3]. However, Noi and Kappas [4] showed that support vector machines outperformed both random forest and k-nearest neighbors when classifying features from Sentinel-2 imagery.…”

“…Existing datasets of small watercourses are often lacking in both completeness and accuracy. However, as new high-resolution remote-sensing datasets have emerged, there has been increased research on automated and semi-automatic methods for the extraction of watercourses [1][2][3][4][5]. Convolutional neural networks (CNNs) are state-of-the-art networks for computer vision tasks [6,7].…”

Mapping Social Vulnerability to Multi-Hazard Scenarios: A GIS-Based Approach at the Census Tract Level

“…Examples of significant events with a declared state of emergency that occurred in the Basilicata Region in the last ten years are listed in Table 1. These events led the scientific community to develop relevant research for landslide characterization [20,22,25,26] and flood monitoring, vulnerability and risk mapping [24,[27][28][29][30][31][32][33]. In terms of national and regional hazard data, Figure 1 shows the spatial distribution of the landslide and flood hazard in the Basilicata Region, derived from Italian Institute for Environmental Research and Protection (ISPRA) 2020-2021 mosaic layers.…”

Quantitative and Qualitative Analysis of Agricultural Fields Based on Aerial Multispectral Images Using Neural Networks

“…UAVs are especially vital in scenarios involving peril, such as natural disasters. Various solutions have been developed to aid in locating individuals affected by earthquakes, building collapses, or river floods [11][12][13][14][15][16]. While these solutions use cameras to detect specific objects, they primarily focus on object identification within images, which can vary in size depending on the object being sought.…”