VisiCompanion: Comparative Analysis of Yolov8 and Yolov9

There are approximately 21 million visually im-paired individuals who depend on other people for their basic work. This research adds to the current understanding of assistive technology by introducing a method for choosing and optimizing the best object detection models suited for accessi-bility environments. This research enhances the Visicompanion functions and assists visually impaired individuals in doing crucial daily tasks independently by selecting a suitable model. This research compares the analysis of two models i.e. Y oLov8 [1] and YOLOV9 [2] and identifies which algorithm is best for the application. YOLOv8 is known for its rapid inference speed which is beneficial for real-time systems whereas YOLOv9 introduces advanced detection capability that improves accuracy but may increase problems for processing time and computational resource requirements. This research uses evaluation metrics like precision, recall, size of model, and resource utilization across different hardware configurations. The results showed thatYOLOv9 is slightly better than YOLOv8 with mAP reaching 95% and precision 96.8%.