Vehicle classification and detection aims to extract certain types of vehicle information from images or videos containing vehicles and is one of the important things in a smart transportation system. However, due to the different size of the vehicle, it became a challenge that directly and interested many researchers . In this paper, we compare YOLOv3's one-stage detection method with MobileNet-SSD for direct vehicle detection on a highway vehicle video dataset specifically recorded using two cellular devices on highway activities in Medan City, producing 42 videos, both methods evaluated based on Mean Average Precision (mAP) where YOLOv3 produces better accuracy of 81.9% compared to MobileNet-SSD at 67.9%, but the size of the resulting video file detection is greater. Mobilenet-SSD performs faster with smaller video output sizes, but it is difficult to detect small objects.
Deep Neural Networks Approach for Monitoring Vehicles on the Highway