A novel image-based convolutional neural network approach for traffic congestion estimation. (15th October 2021)

• Record Type: Journal Article
• Authors: Gao, Ying; Li, Jinlong; Xu, Zhigang; Liu, Zhangqi; Zhao, Xiangmo; Chen, Jianhua
• Is Part Of: Expert systems with applications. Volume 180(2021)
• Publication Date: 2021-10-15
• Subjects: Traffic congestion -- Convolutional neural network -- Vehicle detection -- Deep learning -- Traffic flow parameter; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2021.115037
• Languages: English
• ISSNs: 0957-4174

Abstract

Highlights: A specific and accurate traffic congestion definition is proposed. Addressing the well-concerned issues on low estimation accuracy in bad conditions. A traffic congestion estimation method via Convolutional Neural Network is devised. Our Proposed Method estimates traffic congestion directly once the model trained. Traffic congestion estimation in free and congested conditions is evaluated. Abstract: Traditional image-based traffic congestion estimation methods generally include two steps, which first extract the vehicles from the surveillance images, then calculate the congestion index using the vehicle counts. When working with vast amount of video frames, these approaches are time-consuming and hardly guarantee the real time detection of traffic congestion. In this study, firstly a specific and accurate definition of traffic congestion is proposed to quantify the level of traffic congestion. Then we construct an image-based traffic congestion estimation framework, in which a traffic parameter layer is integrated to the basic convolutional neural network (CNN) model. The proposed framework can directly perform traffic congestion calculation and estimation, which shortens the processing time and avoids the complicated postprocessing. A dataset of 1400 traffic images including 66, 890 vehicles is collected for training the proposed CNN model. Another new dataset of 2400 traffic images including 113, 516 vehicles is collected to test the proposed method on estimating traffic congestion. Experimental results show that our proposed approach has better efficiency and stability in both free flow and congested traffic conditions, as well as sunny and rainy scenes.