eduzhai > Applied Sciences > Engineering >

Vulnerable Road User Detection Using Smartphone Sensors and Recurrence Quantification Analysis

  • Save

... pages left unread,continue reading

Document pages: 6 pages

Abstract: With the fast advancements of the Autonomous Vehicle (AV) industry, detectionof Vulnerable Road Users (VRUs) using smartphones is critical for safetyapplications of Cooperative Intelligent Transportation Systems (C-ITSs). Thisstudy explores the use of low-power smartphone sensors and the RecurrenceQuantification Analysis (RQA) features for this task. These features arecomputed over a thresholded similarity matrix extracted from nine channels:accelerometer, gyroscope, and rotation vector in each direction (x, y, and z).Given the high-power consumption of GPS, GPS data is excluded. RQA features areadded to traditional time domain features to investigate the classificationaccuracy when using binary, four-class, and five-class Random Forestclassifiers. Experimental results show a promising performance when only usingRQA features with a resulted accuracy of 98. 34 and a 98. 79 by adding timedomain features. Results outperform previous reported accuracy, demonstratingthat RQA features have high classifying capability with respect to VRUdetection.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×