Vehicle Detection and Classification using Vibration Sensor and Machine Learning

• Main Authors: Okuro, Tomoki, Nakayama, Yumiko, Takeshima, Yoshitada, Kondo, Yusuke, Tachimori, Nobuya, Yoshida, Makoto, Yoshihara, Hiromu, Suwa, Hirohiko, Yasumoto, Keiichi
• Format: Conference Proceeding
• Language: English
• Subjects: machine learning; Privacy; Random forests; Research and development; Roads; Support vector machines; traffic census; Vehicle detection; vehicle type classification; vibration sensors; Vibrations
• ISSN: 2472-7571
• DOI: 10.1109/IE54923.2022.9826783

Road traffic censuses have been carried out manually for many years since measurements by machines were not widely spread due to the difficulty of installation. To solve installation difficulty, the size issues of the necessary equipment, and privacy issues of the existing traffic counter, we are conducting research and development of portable traffic counters using a vibration sensor and machine learning. However, vehicle type classification was not realized in the previous work, hence it was not possible to survey traffic volume by vehicle types. In addition, to the best of our knowledge, there is no existing study that can detect and classify vehicles based on road vibrations with a single sensor. In this paper, we propose a method of vehicle type classification that is capable of binary classification of small and large vehicles by machine learning combined with Support Vector Machine and Random Forest for vibrations of passing vehicles. We evaluated the proposed method by conducting measurements for up to 12 hours at two actual road locations. We tested over 5 hours of data and confirmed that small vehicles classified with the F-measure of 0.96 and large vehicles with the F-measure of 0.83.