Measuring traffic volumes using an autoencoder with no need to tag images with labelsopen access
- Authors
- Roh, Seungbin; Shin, Johyun; Sohn, Keemin
- Issue Date
- May-2020
- Publisher
- MDPI AG
- Keywords
- Autoencoder; CycleGAN; Deep learning; Traffic volume; Vehicle counting
- Citation
- Electronics (Switzerland), v.9, no.5
- Journal Title
- Electronics (Switzerland)
- Volume
- 9
- Number
- 5
- URI
- https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/52005
- DOI
- 10.3390/electronics9050702
- ISSN
- 2079-9292
2079-9292
- Abstract
- Almost all vision technologies that are used to measure traffic volume use a two-step procedure that involves tracking and detecting. Object detection algorithms such as YOLO and Fast-RCNN have been successfully applied to detecting vehicles. The tracking of vehicles requires an additional algorithm that can trace the vehicles that appear in a previous video frame to their appearance in a subsequent frame. This two-step algorithm prevails in the field but requires substantial computation resources for training, testing, and evaluation. The present study devised a simpler algorithm based on an autoencoder that requires no labeled data for training. An autoencoder was trained on the pixel intensities of a virtual line placed on images in an unsupervised manner. The last hidden node of the former encoding portion of the autoencoder generates a scalar signal that can be used to judge whether a vehicle is passing. A cycle-consistent generative adversarial network (CycleGAN) was used to transform an original input photo of complex vehicle images and backgrounds into a simple illustration input image that enhances the performance of the autoencoder in judging the presence of a vehicle. The proposed model is much lighter and faster than a YOLO-based model, and accuracy of the proposed model is equivalent to, or better than, a YOLO-based model. In measuring traffic volumes, the proposed approach turned out to be robust in terms of both accuracy and efficiency. © 2020 by the authors. Licensee MDPI, Basel, Switzerland.
- Files in This Item
-
- Appears in
Collections - College of Engineering > ETC > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/52005)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.