Traffic Analytics With Low-Frame-Rate Videos

• Published in: IEEE transactions on circuits and systems for video technology Vol. 28; no. 4; pp. 878 - 891
• Main Authors: Luo, Zhiming, Jodoin, Pierre-Marc, Su, Song-Zhi, Li, Shao-Zi, Larochelle, Hugo
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.04.2018; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial neural networks; Automobiles; Cameras; Convolutional neural network (CNN); Driving conditions; Image classification; Image segmentation; Motion perception; Neural networks; Roads; Traffic; traffic density; Traffic models; Traffic volume; transfer learning; video surveillance; Videos
• ISSN: 1051-8215; 1558-2205
• DOI: 10.1109/TCSVT.2016.2632439

In this paper, we investigate the possibility of monitoring highway traffic based on videos whose frame rate is too low to accurately estimate motion features. The goal of the proposed method is to recognize traffic conditions instead of measuring them, as is usually the case. The main advantage of our approach comes from its ability to process low-frame-rate videos for which motion features cannot be estimated. Our method takes advantage of the highly redundant nature of traffic scenes that are pictured from a top-down perspective showing vehicles on a predominant asphalted road surrounded by background objects. Due to the limited variety of objects pictured in traffic scenes, our method gets to learn features that are specific to such images. With these features, our method is able to segment traffic images, classify traffic scenes, and estimate traffic density without requiring motion features. Different convolutional neural network models are proposed to segment traffic images in three different classes ( Road , Car , and Background ), classify traffic images into different categories ( Empty , Fluid , Heavy , and Jam ), and predict traffic density. We also propose a procedure to perform transfer learning of any of these models to new traffic scenes.