<![CDATA[Artificial intelligence (AI), especially computer vision, has made rapid progress in recent years. One of the rapidly developing fields in computer vision is object detection. The ability to detect objects accurately and quickly is essential for the development of autonomous driving technology or vehicles that can operate automatically without human intervention. However, the development of autonomous driving technology is still facing various challenges, especially related to the accuracy and speed of object detection by the system. The purpose of this study is to analyze the performance based on the mean average precision (mAP) value of the results of adjusting the number of epochs, batch size, and image size on one of the emerging object detection methods, YOLOv8, in the context of autonomous driving. The analysis focuses on the batch size hyperparameter on the object detection performance of YOLOv8. The research was conducted with an experimental approach where the YOLOv8 hyperparameters were modified and their performance was evaluated using the driver simulation dataset from the CARLA simulator. Object detection performance was evaluated using the mean average precision (mAP) metric. The research results with the highest mAP value are found in scheme VIII with an mAP value of 98.2% and a training time of 59.45 minutes. For scheme III, it gets the fastest training time of 36.25 minutes. Based on the mAP results, modifications to the number of batch sizes and the use of high image sizes can affect the performance and performance of object detection for autonomous driving.]]>
Copyrights © 2024
