Ανίχνευση διαφορετικών αντικειμένων για αυτόνομες εφαρμογές οδήγησης
View/
Keywords
Μηχανική μάθηση ; Faster R-CNN ; YOLO ; Αυτόνομη οδήγησηAbstract
Object detection and tracking around an autonomous vehicle are essential for its safe operation. This thesis focuses on object detection and classification for autonomous driving applications. Specifically, two of the most advanced object detection models will be examined: YOLO (You Only Look Once) and Faster R-CNN (Region-Based Convolutional Neural Networks). The performance of these algorithms will be compared based on key evaluation metrics, including Mean Average Precision (mAP), precision, and recall. The dataset used for this study contains data relevant to the detection and recognition of vehicles, pedestrians, and traffic signs. It includes 22,241 images in .jpg format and 3 .csv files, which provide information for each image such as the image name, object category, and bounding box coordinates.