Detecting and Tracking Sinkholes Using Multi-Level Convolutional Neural Networks and Data Association
Sinkholes can cause severe property damage and threaten public safety. Therefore, the early prediction and detection of sinkholes are important measures for protecting both citizenry and infrastructure. Although many studies have made significant progress on sinkhole detection, challenges remain, in...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9145527/ |
| _version_ | 1818734145087471616 |
|---|---|
| author | Hoai Nam Vu Cuong Pham Nguyen Manh Dung Soonghwan Ro |
| author_facet | Hoai Nam Vu Cuong Pham Nguyen Manh Dung Soonghwan Ro |
| author_sort | Hoai Nam Vu |
| collection | DOAJ |
| description | Sinkholes can cause severe property damage and threaten public safety. Therefore, the early prediction and detection of sinkholes are important measures for protecting both citizenry and infrastructure. Although many studies have made significant progress on sinkhole detection, challenges remain, including long-term data collection and the discovery of lightweight machine learning models that can be deployed to analyze sinkhole images. In this paper, we propose a method that takes advantage of the recent success of deep learning models to detect and track sinkholes via video streaming. Our system consists of two main stages: sinkhole detection with a cascaded convolutional neural network and sinkhole tracking with a data association algorithm. The experimental results show that a sinkhole can be tracked in real time using the dataset [1]. Furthermore, we implement the system on a Jetson TX2 embedded board (weighing 85 grams), which can operate at 13.2 FPS (frames per second). With an average IoU (intersection over union) score of 88% for sinkhole tracking and an accuracy of 97,6% for sinkhole detection on a 45-minute dataset, this study demonstrates the feasibility of sinkhole detection and tracking using IR images and their suitability for practical applications. |
| first_indexed | 2024-12-18T00:00:42Z |
| format | Article |
| id | doaj.art-15fe02281a60471ab1ae29951f2001a4 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-18T00:00:42Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-15fe02281a60471ab1ae29951f2001a42022-12-21T21:27:58ZengIEEEIEEE Access2169-35362020-01-01813262513264110.1109/ACCESS.2020.30108859145527Detecting and Tracking Sinkholes Using Multi-Level Convolutional Neural Networks and Data AssociationHoai Nam Vu0https://orcid.org/0000-0001-5290-2258Cuong Pham1Nguyen Manh Dung2https://orcid.org/0000-0001-6165-4137Soonghwan Ro3https://orcid.org/0000-0001-6091-796XDepartment of Computer Science, Posts and Telecommunications Institute of Technology, Hanoi, VietnamDepartment of Computer Science, Posts and Telecommunications Institute of Technology, Hanoi, VietnamDepartment of Electronic Engineering, Posts and Telecommunications Institute of Technology, Hanoi, VietnamDepartment of Information and Communication, Kongju National University, Cheonan, South KoreaSinkholes can cause severe property damage and threaten public safety. Therefore, the early prediction and detection of sinkholes are important measures for protecting both citizenry and infrastructure. Although many studies have made significant progress on sinkhole detection, challenges remain, including long-term data collection and the discovery of lightweight machine learning models that can be deployed to analyze sinkhole images. In this paper, we propose a method that takes advantage of the recent success of deep learning models to detect and track sinkholes via video streaming. Our system consists of two main stages: sinkhole detection with a cascaded convolutional neural network and sinkhole tracking with a data association algorithm. The experimental results show that a sinkhole can be tracked in real time using the dataset [1]. Furthermore, we implement the system on a Jetson TX2 embedded board (weighing 85 grams), which can operate at 13.2 FPS (frames per second). With an average IoU (intersection over union) score of 88% for sinkhole tracking and an accuracy of 97,6% for sinkhole detection on a 45-minute dataset, this study demonstrates the feasibility of sinkhole detection and tracking using IR images and their suitability for practical applications.https://ieeexplore.ieee.org/document/9145527/Sinkhole detectionconvolutional neural networkimagenetembedded systemdata association |
| spellingShingle | Hoai Nam Vu Cuong Pham Nguyen Manh Dung Soonghwan Ro Detecting and Tracking Sinkholes Using Multi-Level Convolutional Neural Networks and Data Association IEEE Access Sinkhole detection convolutional neural network imagenet embedded system data association |
| title | Detecting and Tracking Sinkholes Using Multi-Level Convolutional Neural Networks and Data Association |
| title_full | Detecting and Tracking Sinkholes Using Multi-Level Convolutional Neural Networks and Data Association |
| title_fullStr | Detecting and Tracking Sinkholes Using Multi-Level Convolutional Neural Networks and Data Association |
| title_full_unstemmed | Detecting and Tracking Sinkholes Using Multi-Level Convolutional Neural Networks and Data Association |
| title_short | Detecting and Tracking Sinkholes Using Multi-Level Convolutional Neural Networks and Data Association |
| title_sort | detecting and tracking sinkholes using multi level convolutional neural networks and data association |
| topic | Sinkhole detection convolutional neural network imagenet embedded system data association |
| url | https://ieeexplore.ieee.org/document/9145527/ |
| work_keys_str_mv | AT hoainamvu detectingandtrackingsinkholesusingmultilevelconvolutionalneuralnetworksanddataassociation AT cuongpham detectingandtrackingsinkholesusingmultilevelconvolutionalneuralnetworksanddataassociation AT nguyenmanhdung detectingandtrackingsinkholesusingmultilevelconvolutionalneuralnetworksanddataassociation AT soonghwanro detectingandtrackingsinkholesusingmultilevelconvolutionalneuralnetworksanddataassociation |