Deep Learning Based Vehicle Detection From Aerial Images
Hüseyin Seçkin Dikbayir, Halil İbrahim Bülbül
Abstract
With the help of today's developing technology; many applications such as traffic monitoring, target detection, empty parking lot assignment etc. have become applicable with machine learning and deep learning methods. These applications are aimed to determine the desired object from the photographs. In this study, it is aimed to develop an approach that able to identify the vehicles through aerial images by using the YOLO (You Only Look Once) algorithm, feeding it with a trained convolutional neural network structure. As a result of the study, an application that can detect vehicles was developed, increased the performance rate of the YOLO algorithm by 3.2%.
Topics & Concepts
Object detectionDeep learningComputer scienceConvolutional neural networkArtificial intelligenceComputer visionArtificial neural networkMachine learningPattern recognition (psychology)Advanced Neural Network ApplicationsVehicle License Plate RecognitionVideo Surveillance and Tracking Methods