Detecting Vehicles using YOLOv8n in Edge Computing Dashcam

Dashcam is a camera placed on the dashboard of a vehicle. This device's function is to capture footage of all events in front of the vehicle. Security and safety have become a significant concern in various sectors, including transportation and public roads. Traffic accidents caused by drivers’ ignorance of objects around the vehicle are still a severe problem on the highway. In this study, a simple dashcam built from an edge computer was developed. By adding a camera, the dashcam is able to detect vehicles ahead. By the time, vehicles appear in the system, it will be detected using an object detection method called YOLOv8. This research is expected to be one step in a proof-of-concept of the development of an Intelligent Transportation System that is in accordance with traffic conditions in Indonesia. In this paper simulated and tested the usage of GPU from the edge computing device. Even though the YOLO8n has lower 6.29, 9.11, 6.05, and 0.24 points performances for its precision, recall, mAP50, and mAP50-95 respectively than YOLOv7-tiny, it only used half the computational cost than the YOLOv7-tiny. It shows the YOLOv8n is suitable as a detection method in an edge computing device. As the inference time testing, objects in an image can be detected from 65-500 ms based on the power supplied to the computer. It also means, in a second the system is able to infer objects for 2 to 15.38 frames.