Ground Fissure Identification in Mining Areas from UAV Images Based on DN-CAMSCBNet

The development and use of mine resources have had many adverse impacts on the environment of mining areas. Among them, ground fissures are the most serious. They not only threaten the ecological protection of mining areas but also hinder the sustainable exploitation of energy. To mitigate the damag...

Full description

Saved in:
Bibliographic Details
Main Authors: Haibin Hu, Xinhui Guo, Jie Xiao
Format: Article
Language:English
Published: Kaunas University of Technology 2025-02-01
Series:Elektronika ir Elektrotechnika
Subjects:
Online Access:https://eejournal.ktu.lt/index.php/elt/article/view/39481
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850040560408068096
author Haibin Hu
Xinhui Guo
Jie Xiao
author_facet Haibin Hu
Xinhui Guo
Jie Xiao
author_sort Haibin Hu
collection DOAJ
description The development and use of mine resources have had many adverse impacts on the environment of mining areas. Among them, ground fissures are the most serious. They not only threaten the ecological protection of mining areas but also hinder the sustainable exploitation of energy. To mitigate the damage to the ecological environment caused by mining areas and ensure sustainable long-term resource exploitation, it is of particular importance to identify ground fissures in mining areas efficiently. Therefore, this paper proposes a ground fissure identification model for UAV images in mining areas named DN-CAMSCBNet. This method integrates the channel attention mechanism and the dropout mechanism on the basis of the traditional U-Net. Meanwhile, it introduces the multiscale convolution block and Nesterov-accelerated adaptive moment estimation. These are used to enhance its ability to capture complex image features, expand the receptive field of the original model, reduce the number of parameters, and reduce computational complexity. To verify the segmentation performance of the model, it is compared with U-Net, D-CAMNet, and D-MSCBNet models. The experimental results show that the accuracy and precision of the DN-CAMSCBNet model can reach 99.47 % and 92.25 %, respectively, and the F1 score is 0.7699. All these are superior to comparison models and can provide strong support for the identification of ground fissures in mining areas.
format Article
id doaj-art-5daef461aaf2438d90e7f9caca20e0f1
institution DOAJ
issn 1392-1215
2029-5731
language English
publishDate 2025-02-01
publisher Kaunas University of Technology
record_format Article
series Elektronika ir Elektrotechnika
spelling doaj-art-5daef461aaf2438d90e7f9caca20e0f12025-08-20T02:56:03ZengKaunas University of TechnologyElektronika ir Elektrotechnika1392-12152029-57312025-02-01311394610.5755/j02.eie.3948144735Ground Fissure Identification in Mining Areas from UAV Images Based on DN-CAMSCBNetHaibin Hu0Xinhui Guo1Jie Xiao2School of Traffic Engineering, Shanxi Vocational University of Engineering Science and Technology, Jinzhong Shanxi, ChinaShanxi Institute of Surveying and Mapping Geographic Information, Taiyuan Shanxi, ChinaShanxi Institute of Surveying and Mapping Geographic Information, Taiyuan Shanxi, ChinaThe development and use of mine resources have had many adverse impacts on the environment of mining areas. Among them, ground fissures are the most serious. They not only threaten the ecological protection of mining areas but also hinder the sustainable exploitation of energy. To mitigate the damage to the ecological environment caused by mining areas and ensure sustainable long-term resource exploitation, it is of particular importance to identify ground fissures in mining areas efficiently. Therefore, this paper proposes a ground fissure identification model for UAV images in mining areas named DN-CAMSCBNet. This method integrates the channel attention mechanism and the dropout mechanism on the basis of the traditional U-Net. Meanwhile, it introduces the multiscale convolution block and Nesterov-accelerated adaptive moment estimation. These are used to enhance its ability to capture complex image features, expand the receptive field of the original model, reduce the number of parameters, and reduce computational complexity. To verify the segmentation performance of the model, it is compared with U-Net, D-CAMNet, and D-MSCBNet models. The experimental results show that the accuracy and precision of the DN-CAMSCBNet model can reach 99.47 % and 92.25 %, respectively, and the F1 score is 0.7699. All these are superior to comparison models and can provide strong support for the identification of ground fissures in mining areas.https://eejournal.ktu.lt/index.php/elt/article/view/39481mine ground fissuresuav imagesu-netmultiscale convolution blockchannel attention mechanism
spellingShingle Haibin Hu
Xinhui Guo
Jie Xiao
Ground Fissure Identification in Mining Areas from UAV Images Based on DN-CAMSCBNet
Elektronika ir Elektrotechnika
mine ground fissures
uav images
u-net
multiscale convolution block
channel attention mechanism
title Ground Fissure Identification in Mining Areas from UAV Images Based on DN-CAMSCBNet
title_full Ground Fissure Identification in Mining Areas from UAV Images Based on DN-CAMSCBNet
title_fullStr Ground Fissure Identification in Mining Areas from UAV Images Based on DN-CAMSCBNet
title_full_unstemmed Ground Fissure Identification in Mining Areas from UAV Images Based on DN-CAMSCBNet
title_short Ground Fissure Identification in Mining Areas from UAV Images Based on DN-CAMSCBNet
title_sort ground fissure identification in mining areas from uav images based on dn camscbnet
topic mine ground fissures
uav images
u-net
multiscale convolution block
channel attention mechanism
url https://eejournal.ktu.lt/index.php/elt/article/view/39481
work_keys_str_mv AT haibinhu groundfissureidentificationinminingareasfromuavimagesbasedondncamscbnet
AT xinhuiguo groundfissureidentificationinminingareasfromuavimagesbasedondncamscbnet
AT jiexiao groundfissureidentificationinminingareasfromuavimagesbasedondncamscbnet