Evaluating YOLO Object Detection Models Under Adverse Lighting Conditions

This research looks at the problems that You Only Look Once (YOLO) object recognition models have when they have to work in adverse lighting. Even though YOLO models are generally very good at finding items, they have shown that they are not very good at identifying things when the lighting is bright or changes. Most of the study that has been done so far has focused on finding the best conditions for object detection algorithms, which has left a major knowledge gap. In order to fill this gap, the main goal of this study is to carefully look at how well YOLO models work when lighting conditions aren't ideal. It is very important to understand these limits because they have big effects on real-world situations, like how safe self-driving cars are when the lighting changes and how well security systems work. The main objective of the study is to make object detection algorithms like YOLO more reliable and robust in a wide range of environmental situations.