Effect of combining algorithms in smartphone based pothole detection

Lekshmipathy, Janani; Sunitha, V.; Mathew, Samson

doi:10.1007/s42947-020-0033-0

Cited by 37 publications

(12 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Los resultados de este estudio, comparado con los resultados son bastante aceptables. Sin embargo, si se los compara con estudios basados con otro enfoque o combinación de técnicas de procesamiento de información, como inteligencia artificial, esta precisión aumenta considerablemente: 93,18 % (Lekshmipathy et al, 2021), 95,2 % (Chen et al, 2020), 97,6 % (Patra et al, 2021, 98,1 % (Aswath et al, 2022), 98,7 % (Fan et al, 2020), 99,6 % (Fan et al, 2020, incluso, algunos pocos han llegado al 100 % de detección. Desafortunadamente, para lograr estos valores de precisión es necesario mayores recursos, ya sea en adquirir equipos, personal calificado, mayor demanda computacional, etc., que algunos gobiernos no están dispuestos a invertir.…”

Section: Discussionunclassified

“…Para aplicar cualquier enfoque y el uso de la técnica es necesario recolectar información de la red vial. Esta recolección se ha hecho por medio de sensores a bordo vehículos o scooters (D. Gupta et al, 2021), sensores con GPS (Kempaiah et al, 2022;Pratama et al, 2021;Thakur et al, 2020), acelerómetros (Kempaiah et al, 2022;Kotha et al, 2020;Kumar et al, 2020;Yik et al, 2021), cámaras (Aswath et al, 2022;Muhammad Hanif et al, 2020;Pratama et al, 2021;Riedl et al, 2020;Tsai et al, 2020;Yik et al, 2021), estéreo cámara (Bangalore Ramaiah & Kundu, 2021), sensor ultrasónico (Arulananth et al, 2022;Ganesh Babu et al, 2020;Thakur et al, 2020), tabletas (Egaji et al, 2021), sensores móviles junto con sensores basados en imágenes (Kandoi et al, 2021), sensores de los teléfonos inteligentes (Ashwini et al, 2020;Kyriakou et al, 2019;Lekshmipathy et al, 2021;Mamatha et al, 2020;Ravi et al, 2020;Silvister et al, 2019;Thiruppathiraj et al, 2020;Van Khang & Renault, 2019), por citar algunos.…”

Section: Introductionunclassified

See 1 more Smart Citation

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

Section: Discussionunclassified

Section: Introductionunclassified

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

et al. 2022

View full text Add to dashboard Cite

show abstract

“…In addition to the computer vision-based methods, many researchers explored the use of the built-in accelerometers in the smartphones to analyze their response to the road surface profile (Sattar et al 2018). The research efforts in this area can be categorized in two groups: (1) roughness assessment of a stretch of a road (Yeganeh et al 2019;Souza et al 2018); (2) detection and geotagging of road surface defects, such as potholes and patches (Lekshmipathy et al 2020;Basavaraju et al 2019;Kyriakou et al 2019).…”

Section: R a F Tmentioning

confidence: 99%

“…(2) Methods were developed for analysis of the accelerometer data in a single direction (vertical) to detect anomalies (e.g., potholes, patches, and bumps) on the roads (Basavaraju et al 2019). Various machine learning and statistical methods, such as Random Forest (Wu et al 2020), neural networks (Basavaraju et al 2019;Kyriakou et al 2019), combined statistical and thresholding (Lekshmipathy et al 2020), Grubbs' test (Nguyen et al 2019), difference-and threshold-based detection algorithms (Mednis et al 2011), were used for this purpose.…”

Section: Acceleration-based Road Condition Assessmentmentioning

confidence: 99%

Integrating acceleration signal processing and image segmentation for condition assessment of asphalt roads

Sprague

Azar

2022

Can. J. Civ. Eng.

View full text Add to dashboard Cite

A proactive road maintenance system enables agencies to better allocate resources to manage their road networks. An inventory of the roads’ conditions is an essential component of such maintenance program. This research project proposes a hybrid system to asses the condition of the asphalt roads, which uses a dashboard-mounted smartphone to simultaneously collect the acceleration response of a vehicle and the video footage of the road surface while driving. The system analyzes acceleration data for anomalous events that could indicate a defect. Then the computer vision module of the system applies semantic segmentation in the corresponding frame to the detected anomaly to identify defects. This system demonstrated 84% recall and 88% precision rates in detection of anomalies in two road segments. Despite these promising results, the system can only detect the defects that are passed over and it could miss some defects with small acceleration responses, such as traverse cracks.

show abstract

“…To know the irregularities of the road surface most commonly used indicator is the Roughness index (RI). RI is the condition index obtained from the measurement of longitudinal road profiles with the measuring unit of slope (m/km, mm/m for instance) [1][2][3][4].…”

Section: Introductionmentioning

confidence: 99%

Assessment of Ride Quality and Road Roughness by Measuring the Response from a Vehicle Mounted Android Smartphone

Kumar¹,

Tallam²,

Kumar³

2022

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

Road surface roughness is considered as one of the most important aspect in functional condition of roads indicating to riding comfort in both transverse and longitudinal direction. For all highway projects maintaining proper surface evenness has been a mandatory requirement from the government of India. In this study, pavement unevenness was estimated using an android-based smartphone and system rely on the movement of a suspension system in response to the unevenness of the road surface travelled by a vehicle. Roughness index (RI) is an indicator to measure the standard road roughness. Conventional way of measuring RI involves usage of bump integrator, profilometer and roughometer. Present study proposes an alternative method to measure roughness using smartphones. The study was carried out in 2 different locations and 3 different smartphones to obtain the magnitude of deflections. Data collected using standard fifth wheel bump integrator is used for validation. Data collected through smartphone i.e., accelerometer sensor details was given as input to Fast Fourier transforms (FFT) to find the magnitude of deflection on the road. The results obtained from smartphones was then correlated with the existing roughness index data collected by standard fifth wheel bump integrator to establish an equation to predict RI using an android mobile.

show abstract

Effect of combining algorithms in smartphone based pothole detection

Cited by 37 publications

References 25 publications

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

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

Integrating acceleration signal processing and image segmentation for condition assessment of asphalt roads

Assessment of Ride Quality and Road Roughness by Measuring the Response from a Vehicle Mounted Android Smartphone

Contact Info

Product

Resources

About