Remote drain inspection framework using the convolutional neural network and re-configurable robot Raptor

Abstract Drain blockage is a crucial problem in the urban environment. It heavily affects the ecosystem and human health. Hence, routine drain inspection is essential for urban environment. Manual drain inspection is a tedious task and prone to accidents and water-borne diseases. This work presents...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Lee Ming Jun Melvin, Rajesh Elara Mohan, Archana Semwal, Povendhan Palanisamy, Karthikeyan Elangovan, Braulio Félix Gómez, Balakrishnan Ramalingam, Dylan Ng Terntzer
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/7958d0f6fd4b4d489bd94d3cf8b6a4a7
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:7958d0f6fd4b4d489bd94d3cf8b6a4a7
record_format dspace
spelling oai:doaj.org-article:7958d0f6fd4b4d489bd94d3cf8b6a4a72021-11-21T12:20:27ZRemote drain inspection framework using the convolutional neural network and re-configurable robot Raptor10.1038/s41598-021-01170-02045-2322https://doaj.org/article/7958d0f6fd4b4d489bd94d3cf8b6a4a72021-11-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-01170-0https://doaj.org/toc/2045-2322Abstract Drain blockage is a crucial problem in the urban environment. It heavily affects the ecosystem and human health. Hence, routine drain inspection is essential for urban environment. Manual drain inspection is a tedious task and prone to accidents and water-borne diseases. This work presents a drain inspection framework using convolutional neural network (CNN) based object detection algorithm and in house developed reconfigurable teleoperated robot called ‘Raptor’. The CNN based object detection model was trained using a transfer learning scheme with our custom drain-blocking objects data-set. The efficiency of the trained CNN algorithm and drain inspection robot Raptor was evaluated through various real-time drain inspection field trial. The experimental results indicate that our trained object detection algorithm has detect and classified the drain blocking objects with 91.42% accuracy for both offline and online test images and is able to process 18 frames per second (FPS). Further, the maneuverability of the robot was evaluated from various open and closed drain environment. The field trial results ensure that the robot maneuverability was stable, and its mapping and localization is also accurate in a complex drain environment.Lee Ming Jun MelvinRajesh Elara MohanArchana SemwalPovendhan PalanisamyKarthikeyan ElangovanBraulio Félix GómezBalakrishnan RamalingamDylan Ng TerntzerNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-15 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Lee Ming Jun Melvin
Rajesh Elara Mohan
Archana Semwal
Povendhan Palanisamy
Karthikeyan Elangovan
Braulio Félix Gómez
Balakrishnan Ramalingam
Dylan Ng Terntzer
Remote drain inspection framework using the convolutional neural network and re-configurable robot Raptor
description Abstract Drain blockage is a crucial problem in the urban environment. It heavily affects the ecosystem and human health. Hence, routine drain inspection is essential for urban environment. Manual drain inspection is a tedious task and prone to accidents and water-borne diseases. This work presents a drain inspection framework using convolutional neural network (CNN) based object detection algorithm and in house developed reconfigurable teleoperated robot called ‘Raptor’. The CNN based object detection model was trained using a transfer learning scheme with our custom drain-blocking objects data-set. The efficiency of the trained CNN algorithm and drain inspection robot Raptor was evaluated through various real-time drain inspection field trial. The experimental results indicate that our trained object detection algorithm has detect and classified the drain blocking objects with 91.42% accuracy for both offline and online test images and is able to process 18 frames per second (FPS). Further, the maneuverability of the robot was evaluated from various open and closed drain environment. The field trial results ensure that the robot maneuverability was stable, and its mapping and localization is also accurate in a complex drain environment.
format article
author Lee Ming Jun Melvin
Rajesh Elara Mohan
Archana Semwal
Povendhan Palanisamy
Karthikeyan Elangovan
Braulio Félix Gómez
Balakrishnan Ramalingam
Dylan Ng Terntzer
author_facet Lee Ming Jun Melvin
Rajesh Elara Mohan
Archana Semwal
Povendhan Palanisamy
Karthikeyan Elangovan
Braulio Félix Gómez
Balakrishnan Ramalingam
Dylan Ng Terntzer
author_sort Lee Ming Jun Melvin
title Remote drain inspection framework using the convolutional neural network and re-configurable robot Raptor
title_short Remote drain inspection framework using the convolutional neural network and re-configurable robot Raptor
title_full Remote drain inspection framework using the convolutional neural network and re-configurable robot Raptor
title_fullStr Remote drain inspection framework using the convolutional neural network and re-configurable robot Raptor
title_full_unstemmed Remote drain inspection framework using the convolutional neural network and re-configurable robot Raptor
title_sort remote drain inspection framework using the convolutional neural network and re-configurable robot raptor
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/7958d0f6fd4b4d489bd94d3cf8b6a4a7
work_keys_str_mv AT leemingjunmelvin remotedraininspectionframeworkusingtheconvolutionalneuralnetworkandreconfigurablerobotraptor
AT rajeshelaramohan remotedraininspectionframeworkusingtheconvolutionalneuralnetworkandreconfigurablerobotraptor
AT archanasemwal remotedraininspectionframeworkusingtheconvolutionalneuralnetworkandreconfigurablerobotraptor
AT povendhanpalanisamy remotedraininspectionframeworkusingtheconvolutionalneuralnetworkandreconfigurablerobotraptor
AT karthikeyanelangovan remotedraininspectionframeworkusingtheconvolutionalneuralnetworkandreconfigurablerobotraptor
AT brauliofelixgomez remotedraininspectionframeworkusingtheconvolutionalneuralnetworkandreconfigurablerobotraptor
AT balakrishnanramalingam remotedraininspectionframeworkusingtheconvolutionalneuralnetworkandreconfigurablerobotraptor
AT dylanngterntzer remotedraininspectionframeworkusingtheconvolutionalneuralnetworkandreconfigurablerobotraptor
_version_ 1718419073590624256