PotNet: Pothole detection for autonomous vehicle system using convolutional neural network
Abstract Advancement in vision‐based techniques has enabled the autonomous vehicle system (AVS) to understand the driving scene in depth. The capability of autonomous vehicle system to understand the scene, and detecting the specific object depends on the strong feature representation of such object...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-01-01
|
| Series: | Electronics Letters |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/ell2.12062 |
| _version_ | 1797894114857975808 |
|---|---|
| author | Deepak Kumar Dewangan Satya Prakash Sahu |
| author_facet | Deepak Kumar Dewangan Satya Prakash Sahu |
| author_sort | Deepak Kumar Dewangan |
| collection | DOAJ |
| description | Abstract Advancement in vision‐based techniques has enabled the autonomous vehicle system (AVS) to understand the driving scene in depth. The capability of autonomous vehicle system to understand the scene, and detecting the specific object depends on the strong feature representation of such objects. However, pothole objects are difficult to identify due to their non‐uniform structure in challenging, and dynamic road environments. Existing approaches have shown limited performance for the precise detection of potholes. The study on the detection of potholes, and intelligent driving behaviour of autonomous vehicle system is little explored in existing articles. Hence, here, an improved prototype model, which is not only truly capable of detecting the potholes but also shows its intelligent driving behaviour when any pothole is detected, is proposed. The prototype is developed using a convolutional neural network with a vision camera to explore, and validates the potential, and autonomy of its driving behaviour in the prepared road environment. The experimental analysis of the proposed model on various performance measures have obtained accuracy, sensitivity, and F‐measure of 99.02%, 99.03%, and 98.33%, respectively, which are comparable with the available state‐of‐art techniques. |
| first_indexed | 2024-04-10T07:03:42Z |
| format | Article |
| id | doaj.art-3e8099d3ef224721a32420581c11a79c |
| institution | Directory Open Access Journal |
| issn | 0013-5194 1350-911X |
| language | English |
| last_indexed | 2024-04-10T07:03:42Z |
| publishDate | 2021-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Electronics Letters |
| spelling | doaj.art-3e8099d3ef224721a32420581c11a79c2023-02-27T12:06:15ZengWileyElectronics Letters0013-51941350-911X2021-01-01572535610.1049/ell2.12062PotNet: Pothole detection for autonomous vehicle system using convolutional neural networkDeepak Kumar Dewangan0Satya Prakash Sahu1Department of Information Technology National Institute of Technology Raipur IndiaDepartment of Information Technology National Institute of Technology Raipur IndiaAbstract Advancement in vision‐based techniques has enabled the autonomous vehicle system (AVS) to understand the driving scene in depth. The capability of autonomous vehicle system to understand the scene, and detecting the specific object depends on the strong feature representation of such objects. However, pothole objects are difficult to identify due to their non‐uniform structure in challenging, and dynamic road environments. Existing approaches have shown limited performance for the precise detection of potholes. The study on the detection of potholes, and intelligent driving behaviour of autonomous vehicle system is little explored in existing articles. Hence, here, an improved prototype model, which is not only truly capable of detecting the potholes but also shows its intelligent driving behaviour when any pothole is detected, is proposed. The prototype is developed using a convolutional neural network with a vision camera to explore, and validates the potential, and autonomy of its driving behaviour in the prepared road environment. The experimental analysis of the proposed model on various performance measures have obtained accuracy, sensitivity, and F‐measure of 99.02%, 99.03%, and 98.33%, respectively, which are comparable with the available state‐of‐art techniques.https://doi.org/10.1049/ell2.12062Optical, image and video signal processingRoad-traffic system controlMobile robotsComputer vision and image processing techniquesControl engineering computingTraffic engineering computing |
| spellingShingle | Deepak Kumar Dewangan Satya Prakash Sahu PotNet: Pothole detection for autonomous vehicle system using convolutional neural network Electronics Letters Optical, image and video signal processing Road-traffic system control Mobile robots Computer vision and image processing techniques Control engineering computing Traffic engineering computing |
| title | PotNet: Pothole detection for autonomous vehicle system using convolutional neural network |
| title_full | PotNet: Pothole detection for autonomous vehicle system using convolutional neural network |
| title_fullStr | PotNet: Pothole detection for autonomous vehicle system using convolutional neural network |
| title_full_unstemmed | PotNet: Pothole detection for autonomous vehicle system using convolutional neural network |
| title_short | PotNet: Pothole detection for autonomous vehicle system using convolutional neural network |
| title_sort | potnet pothole detection for autonomous vehicle system using convolutional neural network |
| topic | Optical, image and video signal processing Road-traffic system control Mobile robots Computer vision and image processing techniques Control engineering computing Traffic engineering computing |
| url | https://doi.org/10.1049/ell2.12062 |
| work_keys_str_mv | AT deepakkumardewangan potnetpotholedetectionforautonomousvehiclesystemusingconvolutionalneuralnetwork AT satyaprakashsahu potnetpotholedetectionforautonomousvehiclesystemusingconvolutionalneuralnetwork |