Machine learning mask R-CNN for GPR B-scans

Ground Penetrating Radar (GPR) is a commonly used technology to detect underground objects and environments for different purposes. The output generated from moving GPR across the ground surface is called the GPR scan. Realistic subsurface surroundings can be visualized, mapped, and monitored...

Full description

Saved in:
Bibliographic Details
Main Author: Wu, Yi Xuan
Other Authors: Abdulkadir C. Yucel
Format: Final Year Project
Language:English
Published: Nanyang Technological University 2022
Subjects:
Online Access:https://hdl.handle.net/10356/158075
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-158075
record_format dspace
spelling sg-ntu-dr.10356-1580752023-07-07T19:05:18Z Machine learning mask R-CNN for GPR B-scans Wu, Yi Xuan Abdulkadir C. Yucel Lee Yee Hui School of Electrical and Electronic Engineering EYHLee@ntu.edu.sg, acyucel@ntu.edu.sg Engineering::Electrical and electronic engineering Ground Penetrating Radar (GPR) is a commonly used technology to detect underground objects and environments for different purposes. The output generated from moving GPR across the ground surface is called the GPR scan. Realistic subsurface surroundings can be visualized, mapped, and monitored with these data. In B-scans, underground objects are represented in hyperbolic signatures. However, the process of manual recognition of hyperbolas presented in the B-scan is difficult and tedious due to the noisy and complex nature of subterranean environments. Mask R-CNN will be implemented to perform object detection and instance segmentation with supervised learning. The procedures include data preparation, training, testing and evaluation of prediction results. Bachelor of Engineering (Information Engineering and Media) 2022-05-29T06:52:38Z 2022-05-29T06:52:38Z 2022 Final Year Project (FYP) Wu, Y. X. (2022). Machine learning mask R-CNN for GPR B-scans. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/158075 https://hdl.handle.net/10356/158075 en B3113-211 application/pdf Nanyang Technological University
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering::Electrical and electronic engineering
spellingShingle Engineering::Electrical and electronic engineering
Wu, Yi Xuan
Machine learning mask R-CNN for GPR B-scans
description Ground Penetrating Radar (GPR) is a commonly used technology to detect underground objects and environments for different purposes. The output generated from moving GPR across the ground surface is called the GPR scan. Realistic subsurface surroundings can be visualized, mapped, and monitored with these data. In B-scans, underground objects are represented in hyperbolic signatures. However, the process of manual recognition of hyperbolas presented in the B-scan is difficult and tedious due to the noisy and complex nature of subterranean environments. Mask R-CNN will be implemented to perform object detection and instance segmentation with supervised learning. The procedures include data preparation, training, testing and evaluation of prediction results.
author2 Abdulkadir C. Yucel
author_facet Abdulkadir C. Yucel
Wu, Yi Xuan
format Final Year Project
author Wu, Yi Xuan
author_sort Wu, Yi Xuan
title Machine learning mask R-CNN for GPR B-scans
title_short Machine learning mask R-CNN for GPR B-scans
title_full Machine learning mask R-CNN for GPR B-scans
title_fullStr Machine learning mask R-CNN for GPR B-scans
title_full_unstemmed Machine learning mask R-CNN for GPR B-scans
title_sort machine learning mask r-cnn for gpr b-scans
publisher Nanyang Technological University
publishDate 2022
url https://hdl.handle.net/10356/158075
_version_ 1772826572676399104