Campus Units

Civil, Construction and Environmental Engineering, Mechanical Engineering, Institute for Transportation

Document Type

Article

Publication Version

Accepted Manuscript

Publication Date

12-1-2018

Journal or Book Title

Transportation Research Record

Volume

2672

Issue

45

First Page

222

Last Page

231

DOI

10.1177%2F0361198118777631

Abstract

Recent improvements in machine vision algorithms have led to closed-circuit television (CCTV) cameras emerging as an important data source for determining of the state of traffic congestion. In this study we used two different deep learning techniques, you only look once (YOLO) and deep convolution neural network (DCNN), to detect traffic congestion from camera images. The support vector machine (SVM), a shallow algorithm, was also used as a comparison to determine the improvements obtained using deep learning algorithms. Occupancy data from nearby radar sensors were used to label congested images in the dataset and for training the models. YOLO and DCCN achieved 91.5% and 90.2% accuracy, respectively, whereas SVM’s accuracy was 85.2%. Receiver operating characteristic curves were used to determine the sensitivity of the models with regard to different camera configurations, light conditions, and so forth. Although poor camera conditions at night affected the accuracy of the models, the areas under the curve from the deep models were found to be greater than 0.9 for all conditions. This shows that the models can perform well in challenging conditions as well.

Research Focus Area

Transportation Engineering

Comments

This is a manuscript of an article published as Chakraborty, Pranamesh, Yaw Okyere Adu-Gyamfi, Subhadipto Poddar, Vesal Ahsani, Anuj Sharma, and Soumik Sarkar. "Traffic congestion detection from camera images using deep convolution neural networks." Transportation Research Record 2672, no. 45 (2018): 222-231. DOI: 10.1177%2F0361198118777631. Posted with permission.

Copyright Owner

National Academy of Sciences: Transportation Research Board

Language

en

File Format

application/pdf

Published Version

Share

COinS