Traffic Index Cloud Maps for Traffic Flow Analysis with Big Traffic Data

In this paper, we focus on traffic flow analysis in a visualization way. Classical methods visualize the traffic states by mapping the road section speed values into different colors. These classical methods have two defects need to be improved. Firstly, the traffic states computation process does not concern the effects arisen by different road types and time periods. Secondly, as these classical methods take the road sections as research objects, it can not evaluate the traffic states of areas with larger space scale. Thus, traffic index is adopted to evaluate the traffic states, which is a comprehensive criterion that it can both consider the effects arisen by different road types and time periods. A new traffic states visualization method, traffic index cloud maps, is proposed to visualize the traffic states for large road network areas. Real applications in Shanghai indicate that our method can present the traffic states of road network areas accurately and intuitively. Also, it can analyze the macroscopic traffic flow effectively and flexibly.

[1]  Alexandre M. Bayen,et al.  Traffic state estimation on highway: A comprehensive survey , 2017, Annu. Rev. Control..

[2]  Yan Song,et al.  An outlier detection algorithm based on the degree of sharpness and its applications on traffic big data preprocessing , 2017, 2017 IEEE 2nd International Conference on Big Data Analysis (ICBDA)(.

[3]  Chuan Zhou,et al.  Parameter k search strategy in outlier detection , 2018, Pattern Recognit. Lett..

[4]  Robert Pless,et al.  Deep Feature Interpolation for Image Content Changes , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Haris N. Koutsopoulos,et al.  Dynamic data-driven local traffic state estimation and prediction , 2013 .

[6]  J A Wattleworth,et al.  PEAK PERIOD ANALYSIS AND CONTROL OF A FREEWAY SYSTEM /WITH DISCUSSION/ , 1965 .

[7]  Thierry Blu,et al.  Linear interpolation revitalized , 2004, IEEE Transactions on Image Processing.

[8]  Hang Li,et al.  Traffic Peak Period Detection from an Image Processing View , 2018 .

[9]  Markus Friedrich,et al.  Generating Trajectories from Mobile Phone Data , 2010 .

[10]  C. Barrett,et al.  Using Weather Index Insurance to Improve Drought Response for Famine Prevention , 2007 .

[11]  Zhipeng Li,et al.  An Approach to Urban Traffic State Estimation by Fusing Multisource Information , 2009, IEEE Transactions on Intelligent Transportation Systems.

[12]  Henrique S. Malvar,et al.  High-quality linear interpolation for demosaicing of Bayer-patterned color images , 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[13]  Xue Xing,et al.  Classifying the traffic state of urban expressways: A machine-learning approach , 2020 .

[14]  Yuncai Liu,et al.  Speed estimation of traffic flow using multiple kernel support vector regression , 2018, Physica A: Statistical Mechanics and its Applications.

[15]  Wu Lei.  Traffic State Recognition and Dynamic EvaluationBased on VelocityStudy , 2012 .

[16]  Yun Fu,et al.  Consensus Regularized Multi-View Outlier Detection , 2018, IEEE Transactions on Image Processing.

[17]  Satish V. Ukkusuri,et al.  Mobility Pattern Identification Based on Mobile Phone Data , 2019 .

[18]  Jianli Xiao,et al.  SVM and KNN ensemble learning for traffic incident detection , 2019, Physica A: Statistical Mechanics and its Applications.

[19]  Stephen Shaoyi Liao,et al.  Aggregating and Sampling Methods for Processing GPS Data Streams for Traffic State Estimation , 2013, IEEE Transactions on Intelligent Transportation Systems.

[20]  Dimitri N. Mavris,et al.  Development of a Data Fusion Framework to support the Analysis of Aviation Big Data , 2019, AIAA Scitech 2019 Forum.

[21]  Hui Zhang,et al.  Statistical analysis of the stability of bus vehicles based on GPS trajectory data , 2019 .