Pothole Detection Using Advanced Neural Networks

Narayana Darapaneni, Naresh Suresh Reddy, Anitha Urkude, A. Paduri, Arati Alok Satpute, Aakash Yogi, Dilip Krishna Natesan, Sarang Surve, Utkarsh Srivastava
{"title":"Pothole Detection Using Advanced Neural Networks","authors":"Narayana Darapaneni, Naresh Suresh Reddy, Anitha Urkude, A. Paduri, Arati Alok Satpute, Aakash Yogi, Dilip Krishna Natesan, Sarang Surve, Utkarsh Srivastava","doi":"10.1109/iemcon53756.2021.9623237","DOIUrl":null,"url":null,"abstract":"A pothole is one among the first reasons for road accidents and is becoming increasingly important to detect while driving on roads. Detection and warning can significantly reduce accidents and damages caused to vehicles. Advanced neural networks process the pictures from the camera on a realtime basis to spot if there is a pothole within the image. Detection of potholes using neural networks will be time-consuming. Recently, the advances in artificial neural network have led to varied high-performance single-shot detection algorithms. These algorithms are especially useful in real-time applications. Hence, in this paper, we present a study of various object detection algorithms towards pothole detection with its speed and accuracy. The dataset comprises around 9000 training images with and without potholes. The article analyzes Yolo V3, Yolo V4, Yolo V5, and SSD algorithms to judge the results with the identical dataset for training and evaluation.","PeriodicalId":272590,"journal":{"name":"2021 IEEE 12th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 IEEE 12th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/iemcon53756.2021.9623237","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

Abstract

A pothole is one among the first reasons for road accidents and is becoming increasingly important to detect while driving on roads. Detection and warning can significantly reduce accidents and damages caused to vehicles. Advanced neural networks process the pictures from the camera on a realtime basis to spot if there is a pothole within the image. Detection of potholes using neural networks will be time-consuming. Recently, the advances in artificial neural network have led to varied high-performance single-shot detection algorithms. These algorithms are especially useful in real-time applications. Hence, in this paper, we present a study of various object detection algorithms towards pothole detection with its speed and accuracy. The dataset comprises around 9000 training images with and without potholes. The article analyzes Yolo V3, Yolo V4, Yolo V5, and SSD algorithms to judge the results with the identical dataset for training and evaluation.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
利用先进的神经网络进行坑穴检测
坑洼是交通事故的首要原因之一,在道路上驾驶时,探测坑洼变得越来越重要。探测和预警可以显著减少事故和对车辆造成的损害。先进的神经网络实时处理来自相机的照片,以发现图像中是否有坑洞。使用神经网络检测坑洞将是耗时的。近年来,随着人工神经网络的发展,出现了各种高性能的单镜头检测算法。这些算法在实时应用中特别有用。因此,在本文中,我们对各种目标检测算法进行了研究,以达到坑洞检测的速度和精度。该数据集包括大约9000张有坑洼和没有坑洼的训练图像。本文分析了Yolo V3、Yolo V4、Yolo V5和SSD算法,用相同的数据集来判断训练和评估的结果。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Maximization of the User Association of a Low-Power Tier Deploying Biased User Association Scheme in 5G Multi-Tier Heterogeneous Network A Deep Reinforcement Learning: Location-based Resource Allocation for Congested C-V2X Scenario A Deep Learning Approach to Predict Chronic Kidney Disease in Human Evaluation of a bio-socially inspired secure DSA scheme using testbed-calibrated hybrid simulations Siamese Network based Pulse and Signal Attribute Identification
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1