Effect of Gaussian filtered images on Mask RCNN in detection and segmentation of potholes in smart cities
Accidents have contributed a lot to the loss of lives of motorists and serious damage to vehicles around the globe. Potholes are the major cause of these accidents. It is very important to build a model that will help in recognizing these potholes on vehicles. Several object detection models based o...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
AIMS Press
2023-01-01
|
Series: | Mathematical Biosciences and Engineering |
Subjects: | |
Online Access: | https://www.aimspress.com/article/doi/10.3934/mbe.2023013?viewType=HTML |
_version_ | 1811237733421547520 |
---|---|
author | Auwalu Saleh Mubarak Zubaida Said Ameen Fadi Al-Turjman |
author_facet | Auwalu Saleh Mubarak Zubaida Said Ameen Fadi Al-Turjman |
author_sort | Auwalu Saleh Mubarak |
collection | DOAJ |
description | Accidents have contributed a lot to the loss of lives of motorists and serious damage to vehicles around the globe. Potholes are the major cause of these accidents. It is very important to build a model that will help in recognizing these potholes on vehicles. Several object detection models based on deep learning and computer vision were developed to detect these potholes. It is very important to develop a lightweight model with high accuracy and detection speed. In this study, we employed a Mask RCNN model with ResNet-50 and MobileNetv1 as the backbone to improve detection, and also compared the performance of the proposed Mask RCNN based on original training images and the images that were filtered using a Gaussian smoothing filter. It was observed that the ResNet trained on Gaussian filtered images outperformed all the employed models. |
first_indexed | 2024-04-12T12:29:27Z |
format | Article |
id | doaj.art-2a5eb993c2c54fbfab4ff4d47b4a92eb |
institution | Directory Open Access Journal |
issn | 1551-0018 |
language | English |
last_indexed | 2024-04-12T12:29:27Z |
publishDate | 2023-01-01 |
publisher | AIMS Press |
record_format | Article |
series | Mathematical Biosciences and Engineering |
spelling | doaj.art-2a5eb993c2c54fbfab4ff4d47b4a92eb2022-12-22T03:33:04ZengAIMS PressMathematical Biosciences and Engineering1551-00182023-01-0120128329510.3934/mbe.2023013Effect of Gaussian filtered images on Mask RCNN in detection and segmentation of potholes in smart citiesAuwalu Saleh Mubarak0Zubaida Said Ameen1Fadi Al-Turjman21. Artificial Intelligence Engineering Dept., AI and Robotics Institute, Near East University, Mersin 10, Turkey 2. Electrical Engineering Dept., Kano University of Science and Technology, Wudil, Kano, Nigeria1. Artificial Intelligence Engineering Dept., AI and Robotics Institute, Near East University, Mersin 10, Turkey3. Biochemistry Dept., Maitama Sule University, Kano, Nigeria1. Artificial Intelligence Engineering Dept., AI and Robotics Institute, Near East University, Mersin 10, Turkey4. Research Center for AI and IoT, Faculty of Engineering, University of Kyrenia, Kyrenia, Mersin 10, TurkeyAccidents have contributed a lot to the loss of lives of motorists and serious damage to vehicles around the globe. Potholes are the major cause of these accidents. It is very important to build a model that will help in recognizing these potholes on vehicles. Several object detection models based on deep learning and computer vision were developed to detect these potholes. It is very important to develop a lightweight model with high accuracy and detection speed. In this study, we employed a Mask RCNN model with ResNet-50 and MobileNetv1 as the backbone to improve detection, and also compared the performance of the proposed Mask RCNN based on original training images and the images that were filtered using a Gaussian smoothing filter. It was observed that the ResNet trained on Gaussian filtered images outperformed all the employed models.https://www.aimspress.com/article/doi/10.3934/mbe.2023013?viewType=HTMLmask rcnnpotholecomputer visionsmart citiesobject detectiongaussian filter |
spellingShingle | Auwalu Saleh Mubarak Zubaida Said Ameen Fadi Al-Turjman Effect of Gaussian filtered images on Mask RCNN in detection and segmentation of potholes in smart cities Mathematical Biosciences and Engineering mask rcnn pothole computer vision smart cities object detection gaussian filter |
title | Effect of Gaussian filtered images on Mask RCNN in detection and segmentation of potholes in smart cities |
title_full | Effect of Gaussian filtered images on Mask RCNN in detection and segmentation of potholes in smart cities |
title_fullStr | Effect of Gaussian filtered images on Mask RCNN in detection and segmentation of potholes in smart cities |
title_full_unstemmed | Effect of Gaussian filtered images on Mask RCNN in detection and segmentation of potholes in smart cities |
title_short | Effect of Gaussian filtered images on Mask RCNN in detection and segmentation of potholes in smart cities |
title_sort | effect of gaussian filtered images on mask rcnn in detection and segmentation of potholes in smart cities |
topic | mask rcnn pothole computer vision smart cities object detection gaussian filter |
url | https://www.aimspress.com/article/doi/10.3934/mbe.2023013?viewType=HTML |
work_keys_str_mv | AT auwalusalehmubarak effectofgaussianfilteredimagesonmaskrcnnindetectionandsegmentationofpotholesinsmartcities AT zubaidasaidameen effectofgaussianfilteredimagesonmaskrcnnindetectionandsegmentationofpotholesinsmartcities AT fadialturjman effectofgaussianfilteredimagesonmaskrcnnindetectionandsegmentationofpotholesinsmartcities |