Citation

Lee J, Roh S, Shin J, Sohn K. Sensors (Basel) 2019; 19(5): s19051227.

Affiliation

Department of Urban Engineering, Chung-Ang University, 84 Heukseok-ro, Dongjak-gu, Seoul 156-756, Korea. kmsohn@cau.ac.kr.

Copyright

(Copyright © 2019, MDPI: Multidisciplinary Digital Publishing Institute)

DOI

10.3390/s19051227

PMID

30862042

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.

Language: en

Keywords

convolutional neural network (CNN); cycle-consistent adversarial network (CycleGAN); space mean speed; traffic prediction; traffic surveillance