Real-Time Detection of UAV Small Target’s Infrared Imaging via OSTD-YOLOv8
Fida Hussain Dahri, Asif Ali Laghari, Nisar Ahmed Dahri, Ghulam E Mustafa Abro, Vania V. Estrela, Gabriel Gomes de Oliveira, Yuzo Iano, Euclides Lourenço Chuma
Abstract
Unmanned aerial vehicles (UAVs) have boosted modern living. Tiny, frail high-density targets, low resolution, complicated backgrounds, noise, and poor real-time exposure performance have augmented due to UAV firms. Realtime recognition in high-altitude (HA) infrared thermal images is intricate. Our fresh OSTD-YOLOv8 is a multi-class target recognition tactic to tackle these issues and spot and classify objects on the HIT-UAV dataset. YOLOv8 is an effective advanced object detection model. Our OSTD-YOLOv8 model detects small objects in HA thermal images with ${90 \%}$ precision, ${91.5 \%}$ recall, ${90.5 \%}$ F1-score, ${89.1 \%}$ AP, and 98% mAP. Our unique approach delivers effective object recognition in difficult thermal imaging conditions. Consequently, this distinctive UAV-focused HA, thermal, target detection scheme can be used.