Efficient pothole detection using smartphone sensors

Pawar, Kshitij; Jagtap, Siddhi; Bhoir, Smita

doi:10.1051/itmconf/20203203013

Cited by 13 publications

(4 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The GSM at the server part takes that locations and indicate pothole or hump on the map of that area. KshitijPawar et.al., [8] proposed a solution to recognize and detect a pothole on the road. The data was acquired from the smart phone sensors, making the approach costeffective.…”

Section: Literature Reviewmentioning

confidence: 99%

Road Pothole Detection System

Lincy,

Dhanarajan,

Sanjay Kumar

et al. 2023

ITM Web Conf.

View full text Add to dashboard Cite

A pothole is an open crack developed on roads owing to varied climatic situations and exposure to heavy-load trucks. Potholes are acting as one of the major causes of accidents and economic loss in the repair of vehicles. Hence this paper proposes a pothole detection system that assists drivers in avoiding potholes on the road by providing prior warnings using the YOLOV7 machine learning technique. The warning can be like a buzzer while the vehicle approaches a pothole. This concept can be expanded to create vehicles that detect humps and other road irregularities. The application depicted in this work effectively reduces the problem of increasing accidents caused by potholes by ensuring accuracy in real-time of about 94.5% at efficient complexity than state-of-art approaches.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Road Pothole Detection System

Lincy,

Dhanarajan,

Sanjay Kumar

et al. 2023

ITM Web Conf.

View full text Add to dashboard Cite

show abstract

“…Road condition: 93.4% accuracy, Pothole detection: 78% accuracy and 42% recall [35] Pothole occurrences Use of a Neural network based on ReLU activation function.…”

Section: Approach Challengesmentioning

confidence: 99%

Pothole and Plain Road Classification Using Adaptive Mutation Dipper Throated Optimization and Transfer Learning for Self Driving Cars

et al. 2022

View full text Add to dashboard Cite

Self-driving car plays a crucial role in implementing traffic intelligence. Road smoothness in front of self-driving cars has a significant impact on the car's driving safety and comfort. Having potholes on the road may lead to several problems, including car damage and the occurrence of collisions. Therefore, self-driving cars should be able to change their driving behavior based on the real-time detection of road potholes. Various methods are followed to address this problem, including reporting to authorities, employing vibration-based sensors, and 3D laser imaging. However, limitations, such as expensive setup costs and the danger of discovery, affected these methods. Therefore, it is necessary to automate the process of potholes identification with sufficient precision and speed. A novel method based on adaptive mutation and dipper throated optimization (AMDTO) for feature selection and optimization of the random forest (RF) classifier is presented in this paper. In addition, we propose a new adaptive method for dataset balancing, referred to as optimized hashing SMOTE, to boost the performance of the optimized model. Data on potholes in different weather conditions and circumstances were collected and augmented before training the proposed model. The effectiveness of the proposed method is shown in experiments in classifying road potholes accurately. Eleven feature selection methods, including WOA, GWO, and PSO, and three machine learning classifiers were included in the conducted experiments to measure the superiority of the proposed method. The proposed method, AMDTO+RF, achieved a pothole classification accuracy of (99.795%), which outperforms the accuracy achieved by the other approaches, WOA+RF of 97.5%, GWO+RF of 98.6%, PSO+RF of 98.1%, and transfer learning approaches, AlexNet of 86.8%, VGG-19 of 87.3%, GoogLeNet of 90.4%, and ResNet-50 of 93.8%. In addition, an in-depth statistical analysis is performed on the recorded results to study the significance and stability of the proposed method.

show abstract

“…Por lo tanto, se aplica un nuevo paso que suaviza los datos. Esta suavización, normalizado al eje vertical (z) (Pawar et al, 2020), se realiza con la siguiente ecuación:…”

Section: Suavizado En La Aceleración Verticalunclassified

Detección de baches y su severidad usando el Video VBOX Lite y teléfonos inteligentes

et al. 2022

View full text Add to dashboard Cite

Los baches son un problema común en pavimentos deteriorados. Estos desniveles disminuyen la comodidad de conducción y pueden llegar a causar siniestros viales. El geolocalizar los baches y su grado severidad permitirán a los usuarios ajustar su velocidad y trayectoria en la vía deteriorada. Además, las entidades del Estado pueden planificar las intervenciones de mantenimiento en los sitios con más deterioro. Esto se podría resolver utilizando sensores como los que tienen los teléfonos celulares o el Video VBOX Lite, que tiene mayor precisión. La información recolectada por estos equipos por sí sola, no permite la geolocalización del bache o determinar su severidad; es necesario entender, procesar y evaluar esos datos para lograrlo. Por lo tanto, el objetivo de este estudio es proponer un procedimiento para detectar baches y su severidad usando el Video VBOX Lite y dos teléfonos inteligentes. Para ello, la recolección de datos se hizo en dos fases. En la fase 1, se recolectaron los baches de manera manual (posición, profundidad y diámetro). Mientras que en la fase 2 se recolectaron los datos de los sensores de los equipos colocados en un vehículo liviano. Se circuló a velocidades entre 20 a 50 km/h. Basado en estos datos, se propuso dos procedimientos uno para el Video VBOX Lite y otro para los teléfonos celulares. La precisión de los procedimientos llegó a detectar entre 71-90 % de los baches. Este procedimiento se puede adaptar como crowdsourcing para generar datos de las redes viales locales.

show abstract

Efficient pothole detection using smartphone sensors

Cited by 13 publications

References 2 publications

Road Pothole Detection System

Road Pothole Detection System

Pothole and Plain Road Classification Using Adaptive Mutation Dipper Throated Optimization and Transfer Learning for Self Driving Cars

Detección de baches y su severidad usando el Video VBOX Lite y teléfonos inteligentes

Contact Info

Product

Resources

About