<![CDATA[Deforestation has caused significant ecosystem degradation and increased the need for more accurate and efficient monitoring systems and reforestation planning. This study develops an integrated system combining YOLOv8 and Internet of Things (IoT)-based LiDAR sensors on a drone platform to detect deforested areas and generate 3D mapping to support reforestation efforts. The dataset consists of 1,822 aerial images collected from public datasets and drone-mounted cameras under various lighting conditions and flight altitudes. The YOLOv8 model was trained using transfer learning with an input size of 640 × 640, a batch size of 16, a learning rate of 0.001, and 100 training epochs. The results demonstrate that the model achieved a precision of 93%, a recall of 90%, and an mAP@0.5 of 94%, while successfully performing real-time deforestation area detection on the drone platform. Integration with the LiDAR sensor produced 3D point cloud visualizations with mapping deviations of less than 2 meters. The developed system effectively supports the identification of priority areas for reforestation more rapidly, accurately, and efficiently than conventional manual survey methods.]]>
Copyrights © 2026
