Scribd
Upload
13 views

CNN Based Crack Detection in Concrete Structures

Uploaded by

Gedum Lego
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
13 views

CNN Based Crack Detection in Concrete Structures

Uploaded by

Gedum Lego
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 2

CNN Based Crack Detection in Concrete Structures

Gedum Lego
21CE10024

Introduction:
Crack detection in concrete is essential for maintaining infrastructure safety. Traditional manual
methods are error-prone and inefficient. The project aims to develop a simplified CNN model for
automated crack detection, offering a more accurate and efficient solution. With India's aging
infrastructure and rapid urbanization, such systems are crucial for preventing failures and reducing
maintenance costs. Implementing CNN-based detection can enhance public safety and ensure
sustainable infrastructure management.

Objective:
1.Develop a system for detecting and monitoring cracks in concrete structures.
2.Collect a comprehensive dataset of concrete images with annotated cracks.
3.Implement and test machine learning algorithms for crack detection.
4.Create a user-friendly interface for real-time analysis.
5.Evaluate the system's performance for accuracy and reliability.

Scope:
The project aims to develop a system using image processing and machine learning for detecting and
monitoring cracks in concrete structures. It includes data collection, algorithm development,
interface integration, and performance evaluation.

Literature review:
1. DEEP LEARNING FOR ANOMALY DETECTION: A SURVEY
The paper discusses the application of deep learning, specifically Convolutional Neural Networks
(CNNs), in object detection. It highlights the evolution of object detection models, including R-CNN
and Faster R-CNN, which have significantly improved detection speed and accuracy.
2. Deep Learning-Based Crack Damage Detection Using CNNs:
This study explores the use of CNNs for object detection, highlighting improvements over traditional
methods. It details the evolution of models like R-CNN, Fast R-CNN, and Faster R-CNN, which
enhance detection speed and accuracy.
3. Damage Detection and Localization in Masonry Structures Using FRCNN:
This report focuses on detecting damage in masonry structures using Faster Region Convolutional
Neural Networks (FRCNN). It highlights the advantages of this method over manual inspections,
including higher accuracy and efficiency. The study demonstrates the use of UAVs and FRCNN for
real-time damage detection in heritage sites.

References:
1. Zhou, X., Gong, W., Fu, W., & Du, F. (2017). Application of Deep Learning in Object Detection.
Proceedings of the 2017 IEEE International Conference on Imaging Systems and Techniques (ICIS),
631-634.
2. Cha, Y.-J., Choi, W., & Büyüköztürk, O. (2017). Application of Deep Learning in Object Detection.
Computer-Aided Civil and Infrastructure Engineering, 32(5), 361-378.
3. Luqman, July (2019). Damage Detection in Heritage Masonry Structures Using Deep Learning
Techniques.

You might also like