Classifying Road Conditions using Transfer Learning and Convolutional Neural Networks for Potholes and Smooth Surfaces

Registration ID: IJNRD_190230

Published ID: IJNRD2304051

DOI: Click Here to Get

B. Praneetha , K. Sirisha , B. Navyashree

CNN, Deep Learning, SVM, VGG, Pathole Detection

Pavement potholes pose a threat to both drivers and pedestrians. In many third world nations, it is a significant contributor to the tragedy that is traffic accidents, which often results in the loss of lives and property. So that vehicles may be alerted to alternative routes and the appropriate public authority can swiftly act to eliminate potholes for the advantage of travelers, it is necessary to regularly gather & refresh information on current road surfaces. Determine the proportion of road damage utilising the given factors: How deep the crater is. The highway has a lot of holes. To scare the government into action, rank the roads in order of importance, depending on which ones need fixing first. After signing up for an account on our hub, the user may submit a picture showing the location of a road along with some other metadata. When we have enough information, we'll create a database table that lists every street name and stores any user-submitted photos of that street. The ML model then makes a prediction of the percentage of damage. When calculating the proportion of damages to each indicated road, we will use an aggregate of the proportions shown in all linked pictures. A proportion of damage typical for that road type will be the end consequence. A straightforward and effective method for locating potholes on roadways is to use object identification techniques on photographs taken with a phone's cam. This project takes as its foundation a model of neural networks that has already been trained on a different set of data and then adapts it to perform the job of classifying road conditions. In order to improve performance and decrease the quantity of labelled data needed, models might transfer what they've learned from one job to another, a technique known as transfer learning. Image classification methods, such as the detection of potholes in road photographs, are ideally adapted for the convolutional network design.

Published Paper   E-Certificate

B. Praneetha, K. Sirisha , & B. Navyashree (April-2023). Classifying Road Conditions using Transfer Learning and Convolutional Neural Networks for Potholes and Smooth Surfaces . INTERNATIONAL JOURNAL OF NOVEL RESEARCH AND DEVELOPMENT, 8(4), a418-a426. https://ijnrd.org/papers/IJNRD2304051.pdf

Volume 8 Issue 4, April-2023

Pages : a418-a426

Paper Reg. ID: IJNRD_190230

Published Paper Id: IJNRD2304051

Downloads: 000121983

Research Area: Computer Science & Technology 

Country: Visakhapatnam, Andhra Pradesh, India

Published Paper PDF: https://ijnrd.org/papers/IJNRD2304051.pdf

Published Paper URL: https://ijnrd.org/viewpaperforall?paper=IJNRD2304051

Journal Name: INTERNATIONAL JOURNAL OF NOVEL RESEARCH AND DEVELOPMENT(IJNRD)

ISSN: 2456-4184 | IMPACT FACTOR: 8.76 Calculated By Google Scholar | ESTD YEAR: 2016

An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.76 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator

Publisher: IJNRD (IJ Publication) Janvi Wave | IJNRD.ORG | IJNRD.COM | IJPUB.ORG

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

Call For Paper - Volume 10 | Issue 10 | October 2025

IJNRD is a Scholarly Open Access, Peer-reviewed, and Refereed Journal with a High Impact Factor of 8.76 (calculated by Google Scholar & Semantic Scholar | AI-Powered Research Tool). It is a Multidisciplinary, Monthly, Low-Cost Journal that follows UGC CARE 2025 Peer-Reviewed Journal Policy norms, Scopus journal standards, and Transparent Peer Review practices to ensure quality and credibility. IJNRD provides indexing in all major databases & metadata repositories, a citation generator, and Digital Object Identifier (DOI) for every published article with full open-access visibility.

The INTERNATIONAL JOURNAL OF NOVEL RESEARCH AND DEVELOPMENT (IJNRD) aims to advance applied, theoretical, and experimental research across diverse fields. Its goal is to promote global scientific information exchange among researchers, developers, engineers, academicians, and practitioners. IJNRD serves as a platform where educators and professionals can share research evidence, models of best practice, and innovative ideas, contributing to academic growth and industry relevance.

Indexing Coverage includes Google Scholar, SSRN, ResearcherID-Publons, Semantic Scholar (AI-Powered Research Tool), Microsoft Academic, Academia.edu, arXiv.org, ResearchGate, CiteSeerX, ResearcherID (Thomson Reuters), Mendeley, DocStoc, ISSUU, Scribd, and many more recognized academic repositories.

How to submit the paper?

By Our website

Click Here to Submit Paper Online

By Mail

Send your paper to editor@ijnrd.org

Important Dates for Current issue

Paper Submission Open For: October 2025

Current Issue: Volume 10 | Issue 10 | October 2025

Impact Factor: 8.76

Last Date for Paper Submission: Till 31-Oct-2025

Notification of Review Result: Within 1-2 Days after Submitting paper.

Publication of Paper: Within 01-02 Days after Submititng documents.

Frequency: Monthly (12 issue Annually).

Journal Type: IJNRD is an International Peer-reviewed, Refereed, and Open Access Journal with Transparent Peer Review as per the new UGC CARE 2025 guidelines, offering low-cost multidisciplinary publication with Crossref DOI and global indexing.

Subject Category: Research Area

Call for Paper: More Details