<![CDATA[This study is a Systematic Literature Review (SLR) that comprehensively reviews the recent advances in YOLOv8-based object detection models and their implementations in various application fields, such as UAV aerial photography, fruit ripeness identification, road defect detection, forest fire smoke detection, and medical imaging. This study evaluates the performance of YOLOv8 based on precision, recall, F1-score, and mean average precision (mAP) metrics, and compares its advantages and limitations with previous YOLO versions and other object detection algorithms. Improvements in the YOLOv8 architecture, including attention mechanisms, improved feature extraction, and hyperparameter optimization, enable significant improvements in accuracy and computational efficiency, especially for small objects and low-light conditions. In addition, the integration of image enhancement techniques strengthens the model's performance in challenging environmental conditions. This study is expected to be an important reference for researchers and practitioners in developing YOLOv8-based object detection models for real-world applications.]]>
Copyrights © 2025
