Review of Deep Learning Algorithms for Urban Remote Sensing Using Unmanned Aerial Vehicles (UAVs)

Abstract

This study conducts a comprehensive review of Deep Learning-based approaches for accurate object segmentation and detection in high-resolution imagery captured by Unmanned Aerial Vehicles (UAVs). The methodology employs three different existing algorithms tailored to detect roads, buildings, trees, and water bodies. These algorithms include Res-UNet for roads and buildings, DeepForest for trees, and WaterDetect for water bodies. To evaluate the effectiveness of this approach, the performance of each algorithm is compared with state-of-the-art (SOTA) models for each class. The results of the study demonstrate that the methodology outperforms SOTA models in all three classes, achieving an accuracy of 93% for roads and buildings using Res-U-Net, 95% for trees using DeepForest, and an impressive 98% for water bodies using WaterDetect. The paper utilizes a Deep Learning-based approach for accurate object segmentation and detection in high-resolution UAV imagery, achieving superior performance to SOTA models, with reduced overfitting and faster training by employing three smaller models for each task