Object Detection in Low Light using YOLOv11

Object detection refers to the identification of objects where the presence, location, and size are determined while putting on the corresponding class labels. Object detection is sensitive to challenges that may arise during low-light illumination, since it entails the absence of light surrounding the object, thereby hindering view. This paper discusses the viability of the YOLOv11 model for detecting objects under low light illumination. The datasets used for this research contain low-light images acquired from the openly accessible Roboflow dataset, which contains three object classes: a person, a car, and a bicycle. The performance of YOLOv11 is to be evaluated using precision, recall, F1-score, and mAP values. YOLOv11 will surpass the former versions based on the comparison of performance. The results regarding the precision, recall, F1Score, and mAP values demonstrate tremendous improvement in the accuracy and reliability capabilities of YOLOv11 compared to previous models.