Abstract
Congestion is a common problem that occurs in big cities. It is necessary to make an ITS (Intelligent Transportation System) using computer vision to monitor street density by counting the number of passing vehicles. The basis of vehicle counting is vehicle detection. This study will compare the performance of vehicle detection models in order to make it easier to determine which model is suitable for implementation. The dataset used is the Vehicle Detection Image Set. The models used are InceptionV3, Xception, MobileNet, MobileNet V2, VGG 16, VGG 19, Efficientnet (B7), and Efficientnet V2 (L). The results show that Inception, Xception, Mobilenet, and VGG19 are the models with the highest test accuracy. The VGG 16 model has the shortest training duration while the Efficientnet V2 (L) has the longest training duration.
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call