@article{ref1,
title="Image-based learning to measure the space mean speed on a stretch of road without the need to tag images with labels",
journal="Sensors (Basel)",
year="2019",
author="Lee, Jincheol and Roh, Seungbin and Shin, Johyun and Sohn, Keemin",
volume="19",
number="5",
pages="s19051227-s19051227",
abstract="Space mean speed cannot be directly measured in the field, although it is a basic parameter that is used to evaluate traffic conditions. An end-to-end convolutional neural network (CNN) was adopted to measure the space mean speed based solely on two consecutive road images. However, tagging images with labels (=true space mean speeds) by manually positioning and tracking every vehicle on road images is a formidable task. The present study was focused on naïve animation images provided by a traffic simulator, because these contain perfect information concerning vehicle movement to attain labels. The animation images, however, seem far-removed from actual photos taken in the field. A cycle-consistent adversarial network (CycleGAN) bridged the reality gap by mapping the animation images into seemingly realistic images that could not be distinguished from real photos. A CNN model trained on the synthesized images was tested on real photos that had been manually labeled. The test performance was comparable to those of state-of-the-art motion-capture technologies. The proposed method showed that deep-learning models to measure the space mean speed could be trained without the need for time-consuming manual annotation.<p /> <p>Language: en</p>",
language="en",
issn="1424-8220",
doi="10.3390/s19051227",
url="http://dx.doi.org/10.3390/s19051227"
}