This paper is published in Volume-5, Issue-3, 2019
Area
IoT
Author
Pruthvi Gowda R., Ankith A. S., Hari Prabhanjan L., Kiran Acharya, Dr. K. N. Rama Mohan Babu
Org/Univ
Dayanand Sagar College of Engineering, Bengaluru, Karnataka, India
Pub. Date
20 May, 2019
Paper ID
V5I3-1462
Publisher
Keywords
Neural networks, Machine Learning, Android, Raspberry Pi MicroController

Citationsacebook

IEEE
Pruthvi Gowda R., Ankith A. S., Hari Prabhanjan L., Kiran Acharya, Dr. K. N. Rama Mohan Babu. Intelligent pothole detection via deep learning using Raspberry-Pi microcontroller, International Journal of Advance Research, Ideas and Innovations in Technology, www.IJARIIT.com.

APA
Pruthvi Gowda R., Ankith A. S., Hari Prabhanjan L., Kiran Acharya, Dr. K. N. Rama Mohan Babu (2019). Intelligent pothole detection via deep learning using Raspberry-Pi microcontroller. International Journal of Advance Research, Ideas and Innovations in Technology, 5(3) www.IJARIIT.com.

MLA
Pruthvi Gowda R., Ankith A. S., Hari Prabhanjan L., Kiran Acharya, Dr. K. N. Rama Mohan Babu. "Intelligent pothole detection via deep learning using Raspberry-Pi microcontroller." International Journal of Advance Research, Ideas and Innovations in Technology 5.3 (2019). www.IJARIIT.com.

Abstract

Bad road conditions are public trouble, causing passenger discomfort, damage to vehicles, and accidents. In India, 9300 deaths and over 25000 injured in 3 years due to potholes according to Ministry of road transport and Highways. Often we complain about bad roads, we have no proper way to detect or report them at scale. To address this issue, we have developed a system to detect potholes and assess road conditions on the go. Our solution is a raspberry pi that captures data on a car’s movement from gyroscope and accelerometer sensors in the Sense Hat sensor. To assess roads using this sensor data, we trained SVM model and Multi layer Perceptron Neural Network to classify road conditions with 97% accuracy. As the user drives, the models use the accelerometer and gyroscope sensor data to classify whether or not pothole is present. Then, the classification results are given to the public to drive by looking at the Potholes in map. Our system will empower civic officials to identify and repair damaged roads which inconvenience passengers and cause accidents