Pothole Detection Using Deep Learning And Image Processing

Prashant Solanki , Sushila Palwe

Yolov3 Algorithm, Roads, Cameras

Pothole location is one of the main errands for street support. PC vision approaches are by and large in light of either street picture investigation or street surface displaying. In any case, these two classifications are constantly utilized freely. Besides, the pothole recognition precision is still a long way from good. Along these lines, for current framework, we provide a powerful pothole discovery calculation which is exact and computably productive. A thick difference map is primarily changed to more readily recognize harmed and whole street regions. To accomplish more noteworthy difference change effectiveness, brilliant segment search and dynamic writing computer programs are used to assess the change boundaries. This strategy is then used to separate potential flawless street regions from the changed difference map naturally recognize pot opening on street utilizing YOLOv3 engineering with darknet system and profound learning. This framework likewise investigates the chance of custom preparation of YOLOv3 based recognition models utilizing pot opening pictures Knowledge dataset.

Published Paper   E-Certificate

"Pothole Detection Using Deep Learning And Image Processing", IJSDR - International Journal of Scientific Development and Research (www.IJSDR.org), ISSN:2455-2631, Vol.7, Issue 12, page no.1114 - 1120, December-2022, Available :https://ijsdr.org/papers/IJSDR2212179.pdf

Volume 7 Issue 12, December-2022

Pages : 1114 - 1120

Paper Reg. ID: IJSDR_203270

Published Paper Id: IJSDR2212179

Downloads: 000347438

Research Area: Science

Country: Pune, Maharashtra, India

Published Paper PDF: https://ijsdr.org/papers/IJSDR2212179

Published Paper URL: https://ijsdr.org/viewpaperforall?paper=IJSDR2212179

DOI: http://doi.one/10.1729/Journal.32517

ISSN: 2455-2631 | IMPACT FACTOR: 9.15 Calculated By Google Scholar | ESTD YEAR: 2016

An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 9.15 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator

Publisher: IJSDR(IJ Publication) Janvi Wave

This work is licensed under a Creative Commons Attribution 4.0 International License and The Open Definition