Mapping of land cover with open‐source software and ultra‐high‐resolution imagery acquired with unmanned aerial vehicles

Abstract

The use of unmanned aerial vehicles (UAVs) to map and monitor the environment has increased sharply in the last few years. Many individuals and organizations have purchased consumer-grade UAVs, and commonly acquire aerial photographs to map land cover. The resulting ultra-high-resolution (subdecimeter-resolution) imagery has high information content, but automating the extraction of this information to create accurate, wall-to-wall land-cover maps is quite difficult. We introduce image-processing workflows that are based on open-source software and can be used to create land-cover maps from ultra-high-resolution aerial imagery. We compared four machine-learning workflows for classifying images. Two workflows were based on random forest algorithms. Of these, one used a pixel-by-pixel approach available in ilastik, and the other used image segments and was implemented with R and the Orfeo ToolBox. The other two workflows used fully connected neural networks and convolutional neural networks implemented with Nenetic. We applied the four workflows to aerial photographs acquired in the Great Basin (western USA) at flying heights of 10 m, 45 m and 90 m above ground level. Our focal cover type was cheatgrass (Bromus tectorum), a non-native invasive grass that changes regional fire dynamics. The most accurate workflow for classifying ultra-highresolution imagery depends on diverse factors that are influenced by image resolution and land-cover characteristics, such as contrast, landscape patterns and the spectral texture of the land-cover types being classified. For our application, the ilastik workflow yielded the highest overall accuracy (0.82-0.89) as assessed by pixel-based accuracy.

Monitoring Invasive Plant Species Using Hyperspectral Remote Sensing Data

“…Although mapping milkweed based on airborne hyperspectral data through supervised classification techniques has been described previously, SVM and ANN have not been applied to classify milkweed in high-resolution hyperspectral unmanned aerial vehicle (UAV) data. The use of UAV based remote sensing makes it possible to generate aerial data about specific areas with higher spatial resolution compared to manned aerial platforms or satellite based sensors [7,[55][56][57].…”

UAV-Based Land Cover Classification for Hoverfly (Diptera: Syrphidae) Habitat Condition Assessment: A Case Study on Mt. Stara Planina (Serbia)

“…However, not every remote sensing instrument has been able to provide high-resolution data that meet the requirements of spatial ecology. Unmanned aerial vehicles (UAVs) have become one of the most promising toolkits for ecological studies capturing landscape habitats from a bird's eye view [12][13][14][15][16][17]. Compared to satellite techniques, the advantage of these systems is their ability to deliver data quickly in a very high spatial and temporal resolution.…”

“…Nowadays, the ecology community is relying on newer technologies to complete its goals of detailed land cover analysis: (UAVs). Recently, a growing number of studies have focused on using UAVs for land cover classification [8,16,[38][39][40][41][42][43]. However, most image classification methods rely on pixel-based techniques that have limitations when it comes to high-resolution satellite data and UAV imagery [16,43,44].…”

Portable LiDAR-Based Method for Improvement of Grass Height Measurement Accuracy: Comparison with SfM Methods

“…Researchers have also used this method to determine tree height [ 2 , 3 ], wheat height [ 4 ], pasture height [ 5 , 6 , 7 , 8 ], and reconstruct three-dimensional structures of legumes and carrots [ 9 ]. Vegetation classification can also be performed, using aerial images captured by an unmanned aerial vehicle (UAV) [ 10 , 11 ]. However, plant measurement using SfM has limitations, e.g., difficulties in reconstructing fine shapes, such as branches in three dimensions [ 2 ], insufficient reconstruction of canopy top [ 1 ], and inability to use on windy days [ 1 , 9 ].…”