Improving the accuracy of random forest‐based land‐use classification using fused images and digital surface models produced via different interpolation methods

Abstract

Land-use maps produced with high accuracy are extremely important as a basis for better use of the land as they are widely utilized in many areas such as agricultural policies, natural resources management, and environmental operations. This study aimed to produce a high accuracy land-use map using digital surface models (DSMs) produced using different interpolation methods and a random forest (RF) classifier. High spatial resolution Triplesat-2 images, Worldview-2 (WV-2) images, and unmanned aerial vehicle (UAV) images were used in this study. First, DSMs were produced from the point cloud using different interpolation methods. The image fusion process was applied and these fused images were classified using an RF classifier together with the DSMs. Overall results showed that the DSM obtained by the kriging method yielded better results than the other methods by increasing the classification accuracy by 7%-13%. In addition, the McNemar test was applied to the images resulting from the classification of fused images with and without using DSMs to investigate the statistical significance of the differences. McNemar test demonstrated that the 𝜒 2 values were greater than 3.84, which revealed that the DSM produced via kriging interpolation had significantly increased the classification accuracy at a 95% confidence interval.

Semantic segmentation of very-high spatial resolution satellite images: A comparative analysis of 3D-CNN and traditional machine learning algorithms for automatic vineyard detection

“…As an alternative, they proposed the utilization of allocation and quantity disagreements, which leverage the distinctions between a reference map and a comparison map. The quantity disagreement focuses on disparities in the category proportions between the reference and comparison maps, while the allocation disagreement addresses differences in the spatial distribution of categories between the reference and comparison maps [70]. In light of this suggestion, allocation and quantification values were calculated in addition to the kappa coefficient for each image's postclassification accuracy assessment.…”

Creating orthophotos with unmanned aerial vehicles and examining its accuracy and usability in geodetic applications

“…Pilot-assisted mapping systems have begun to lose their importance compared to UAV systems due to the low resolution of aerial photographs taken from high altitude flight heights and the high cost of the system. UAV systems, which can meet the accuracy needed in many engineering projects and scientific studies, [1][2][3][4][5][6][7][8][9][10][11] such as disaster management, agricultural and forestry activities, monitoring deformations, planning and architecture of cities, offer users the opportunity to collect data and produce maps for various purposes from this data. 12 Orthophoto maps are one of the products that emerged as a result of the use of the UAV system.…”