Comparative Analysis of YOLOv8 and YOLOv11 for Wildlife Detection in Natural Habitats

FELIX CORPUTTY (Telkom University)
AHMAD SULTHON JAUHARI (Telkom University)
DARIELE ZEBADA SANUWU GEA (Telkom University)
IVAN FEBRIANTO LALO (Telkom University)
RIFKI RAHMAN NUR IKHSAN (Telkom University)
ADE ADITYA RAMADHA (Telkom University)

ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika
Vol 14, No 3: Published July 2026

Wildlife monitoring in natural habitats remains difficult due to occlusion, camouflage, and varying illumination, which limit the performance of conventional object detection systems. Although recent YOLO-based models have shown strong potential, systematic comparisons between newer architectures in real ecological environments are still limited. This study evaluates YOLOv8 and YOLOv11 using 6,165 images from 14 wildlife classes collected at Taman Buru Gunung Masigit Kareumbi, with data augmentation applied to improve robustness. Performance is evaluated using a quantitative comparative approach based on precision, recall, mAP 0.5, and mAP 0.5:0.95. The results indicate that YOLOv11 achieves higher detection accuracy with an mAP 0.5:0.95 of 0.894.