DeepWiTraffic: Low Cost WiFi-Based Traffic Monitoring System Using Deep Learning

A traffic monitoring system (TMS) is an integral part of Intelligent Transportation Systems (ITS). It is an essential tool for traffic analysis and planning. One of the biggest challenges is, however, the high cost especially in covering the huge rural road network. In this paper, we propose to address the problem by developing a novel TMS called DeepWiTraffic. DeepWiTraffic is a low-cost, portable, and non-intrusive solution that is built only with two WiFi transceivers. It exploits the unique WiFi Channel State Information (CSI) of passing vehicles to perform detection and classification of vehicles. Spatial and temporal correlations of CSI amplitude and phase data are identified and analyzed using a machine learning technique to classify vehicles into five different types: motorcycles, passenger vehicles, SUVs, pickup trucks, and large trucks. A large amount of CSI data and ground-truth video data are collected over a month period from a real-world two-lane rural roadway to validate the effectiveness of DeepWiTraffic. The results validate that DeepWiTraffic is an effective TMS with the average detection accuracy of 99.4% and the average classification accuracy of 91.1% in comparison with state-of-the-art non-intrusive TMSs.

[1]  Hazem H. Refai,et al.  Intelligent Vehicle Counting and Classification Sensor for Real-Time Traffic Surveillance , 2018, IEEE Transactions on Intelligent Transportation Systems.

[2]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[3]  Muhammed Gökhan Cinsdikici,et al.  Vehicle-Classification Algorithm Based on Component Analysis for Single-Loop Inductive Detector , 2010, IEEE Transactions on Vehicular Technology.

[4]  Kaishun Wu,et al.  WiFall: Device-free fall detection by wireless networks , 2017, IEEE INFOCOM 2014 - IEEE Conference on Computer Communications.

[5]  Parth H. Pathak,et al.  Your AP knows how you move: fine-grained device motion recognition through WiFi , 2014, HotWireless@MobiCom.

[6]  Hazem H. Refai,et al.  Vehicle classification and accurate speed calculation using multi-element piezoelectric sensor , 2014, 2014 IEEE Intelligent Vehicles Symposium Proceedings.

[7]  Alade O. Tokuta,et al.  Counting and Classification of Highway Vehicles by Regression Analysis , 2015, IEEE Transactions on Intelligent Transportation Systems.

[8]  Shin-Ting Jeng,et al.  A high-definition traffic performance monitoring system with the Inductive Loop Detector signature technology , 2014, 17th International IEEE Conference on Intelligent Transportation Systems (ITSC).

[9]  Zezhi Chen,et al.  Vehicle detection, tracking and classification in urban traffic , 2012, 2012 15th International IEEE Conference on Intelligent Transportation Systems.

[10]  Lajos Hanzo,et al.  Coherent versus Non-coherent and Cooperative Turbo Transceivers , 2010 .

[11]  Wei Wang,et al.  Keystroke Recognition Using WiFi Signals , 2015, MobiCom.

[12]  Chang Xu,et al.  Vehicle Classification Using an Imbalanced Dataset Based on a Single Magnetic Sensor , 2018, Sensors.

[13]  Lawrence A Klein,et al.  SUMMARY OF VEHICLE DETECTION AND SURVEILLANCE TECHNOLOGIES USED IN INTELLIGENT TRANSPORTATION SYSTEMS , 2000 .

[14]  Xiaohui Liang,et al.  When CSI Meets Public WiFi: Inferring Your Mobile Phone Password via WiFi Signals , 2016, CCS.

[15]  Moustafa Youssef,et al.  RF-Based Vehicle Detection and Speed Estimation , 2012, 2012 IEEE 75th Vehicular Technology Conference (VTC Spring).

[16]  Jeff S. Shamma,et al.  Vehicle Classification and Speed Estimation Using Combined Passive Infrared/Ultrasonic Sensors , 2018, IEEE Transactions on Intelligent Transportation Systems.

[17]  Tom Minka,et al.  You are facing the Mona Lisa: spot localization using PHY layer information , 2012, MobiSys '12.

[18]  Li Cui,et al.  EasiSee: Real-Time Vehicle Classification and Counting via Low-Cost Collaborative Sensing , 2014, IEEE Transactions on Intelligent Transportation Systems.

[19]  Francesco Paolo Deflorio,et al.  Wireless sensor networks for traffic monitoring in a logistic centre , 2013 .

[20]  Wei Wang,et al.  Understanding and Modeling of WiFi Signal Based Human Activity Recognition , 2015, MobiCom.

[21]  Gellért Máttyus,et al.  Fast Multiclass Vehicle Detection on Aerial Images , 2015, IEEE Geoscience and Remote Sensing Letters.

[22]  Mauno Rönkkö,et al.  Situational Knowledge Representation for Traffic Observed by a Pavement Vibration Sensor Network , 2014, IEEE Transactions on Intelligent Transportation Systems.

[23]  Mingyan Liu,et al.  PhaseU: Real-time LOS identification with WiFi , 2015, 2015 IEEE Conference on Computer Communications (INFOCOM).

[24]  Bo Yang,et al.  Vehicle Detection and Classification for Low-Speed Congested Traffic With Anisotropic Magnetoresistive Sensor , 2015, IEEE Sensors Journal.

[25]  Bertrand Le Saux,et al.  Segment-before-Detect: Vehicle Detection and Classification through Semantic Segmentation of Aerial Images , 2017, Remote. Sens..

[26]  Ho Lee.  Side-Fire LIDAR Based Vehicle Classification , 2012 .

[27]  Pravin Varaiya,et al.  A Wireless Accelerometer-Based Automatic Vehicle Classification Prototype System , 2014, IEEE Transactions on Intelligent Transportation Systems.

[28]  Ho Lee,et al.  Using LIDAR to Validate the Performance of Vehicle Classification Stations , 2015, J. Intell. Transp. Syst..

[29]  Christian Wietfeld,et al.  Radio-Based Traffic Flow Detection and Vehicle Classification for Future Smart Cities , 2017, 2017 IEEE 85th Vehicular Technology Conference (VTC Spring).

[30]  Lin Lei,et al.  Arbitrary-Oriented Vehicle Detection in Aerial Imagery with Single Convolutional Neural Networks , 2017, Remote. Sens..

[31]  Boris Jutzi,et al.  INVESTIGATIONS ON THE POTENTIAL OF CONVOLUTIONAL NEURAL NETWORKS FOR VEHICLE CLASSIFICATION BASED ON RGB AND LIDAR DATA , 2017 .

[32]  Sang Hyuk Son,et al.  WiTraffic: Low-Cost and Non-Intrusive Traffic Monitoring System Using WiFi , 2017, 2017 26th International Conference on Computer Communication and Networks (ICCCN).

[33]  Moustafa Youssef,et al.  RF-Based Traffic Detection and Identification , 2012, 2012 IEEE Vehicular Technology Conference (VTC Fall).

[34]  Leena Mary,et al.  Vehicle detection and classification from acoustic signal using ANN and KNN , 2013, 2013 International Conference on Control Communication and Computing (ICCC).

[35]  Macario Cordel,et al.  Convolutional neural network for vehicle detection in low resolution traffic videos , 2016, 2016 IEEE Region 10 Symposium (TENSYMP).