A study of high-resolution remote sensing image landslide detection with optimized anchor boxes and edge enhancement

This paper takes landslide as a special research object. For the problems of landslide detection in remote sensing images, deep learning and playback method is adopted. Using the You Only Look Once v5 network (YOLOv5) in combination with the Gabor filter, its edge detection, detection anchor frame a...

Full description

Saved in:
Bibliographic Details
Main Authors: Kun Wang, Ling Han, Juan Liao
Format: Article
Language:English
Published: Taylor & Francis Group 2024-12-01
Series:European Journal of Remote Sensing
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/22797254.2023.2289616
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850247425620443136
author Kun Wang
Ling Han
Juan Liao
author_facet Kun Wang
Ling Han
Juan Liao
author_sort Kun Wang
collection DOAJ
description This paper takes landslide as a special research object. For the problems of landslide detection in remote sensing images, deep learning and playback method is adopted. Using the You Only Look Once v5 network (YOLOv5) in combination with the Gabor filter, its edge detection, detection anchor frame and small object detection scale are improved and optimized. The YOLOv5(ISODATA) model was finally established for landslide image detection by incorporating the edge control factor and four clustering algorithms (K-means, K-means + +, k-medoid, and Iterative Self-Organizing Data Analysis Techniques Algorithm (ISODATA) to evaluate the accuracy of the detection anchor frame and add small target large-scale sampling. Three target identification models – YOLOv5, Region Convolution Neural Network (R-CNN), and Fast R-CNN – are experimentally compared in order to assess the effectiveness of the proposed method. According to the results of experiments, the proposed method outperforms the other three detection models with an AUC of 0.921, a recall of 86.14%, and an MCC of 0.887. It further demonstrates the method’s positive impact on landslide remote sensing image recognition and its ability to solve related issues.
format Article
id doaj-art-9d85c9dbb7a84aa2b4406fd73db6d470
institution OA Journals
issn 2279-7254
language English
publishDate 2024-12-01
publisher Taylor & Francis Group
record_format Article
series European Journal of Remote Sensing
spelling doaj-art-9d85c9dbb7a84aa2b4406fd73db6d4702025-08-20T01:58:55ZengTaylor & Francis GroupEuropean Journal of Remote Sensing2279-72542024-12-0157110.1080/22797254.2023.2289616A study of high-resolution remote sensing image landslide detection with optimized anchor boxes and edge enhancementKun Wang0Ling Han1Juan Liao2College of Earth Science and Resources, Chang’an University, Xi’an, ChinaCollege of Land Engineering, Chang’an University, Xi’an, ChinaCollege of Geography and Tourism, Hengyang Normal University, Heng Yang, ChinaThis paper takes landslide as a special research object. For the problems of landslide detection in remote sensing images, deep learning and playback method is adopted. Using the You Only Look Once v5 network (YOLOv5) in combination with the Gabor filter, its edge detection, detection anchor frame and small object detection scale are improved and optimized. The YOLOv5(ISODATA) model was finally established for landslide image detection by incorporating the edge control factor and four clustering algorithms (K-means, K-means + +, k-medoid, and Iterative Self-Organizing Data Analysis Techniques Algorithm (ISODATA) to evaluate the accuracy of the detection anchor frame and add small target large-scale sampling. Three target identification models – YOLOv5, Region Convolution Neural Network (R-CNN), and Fast R-CNN – are experimentally compared in order to assess the effectiveness of the proposed method. According to the results of experiments, the proposed method outperforms the other three detection models with an AUC of 0.921, a recall of 86.14%, and an MCC of 0.887. It further demonstrates the method’s positive impact on landslide remote sensing image recognition and its ability to solve related issues.https://www.tandfonline.com/doi/10.1080/22797254.2023.2289616Landslide1edge detection2detection anchor frame3YOLOv5 (ISODATA) model4remote sensing intelligence5
spellingShingle Kun Wang
Ling Han
Juan Liao
A study of high-resolution remote sensing image landslide detection with optimized anchor boxes and edge enhancement
European Journal of Remote Sensing
Landslide1
edge detection2
detection anchor frame3
YOLOv5 (ISODATA) model4
remote sensing intelligence5
title A study of high-resolution remote sensing image landslide detection with optimized anchor boxes and edge enhancement
title_full A study of high-resolution remote sensing image landslide detection with optimized anchor boxes and edge enhancement
title_fullStr A study of high-resolution remote sensing image landslide detection with optimized anchor boxes and edge enhancement
title_full_unstemmed A study of high-resolution remote sensing image landslide detection with optimized anchor boxes and edge enhancement
title_short A study of high-resolution remote sensing image landslide detection with optimized anchor boxes and edge enhancement
title_sort study of high resolution remote sensing image landslide detection with optimized anchor boxes and edge enhancement
topic Landslide1
edge detection2
detection anchor frame3
YOLOv5 (ISODATA) model4
remote sensing intelligence5
url https://www.tandfonline.com/doi/10.1080/22797254.2023.2289616
work_keys_str_mv AT kunwang astudyofhighresolutionremotesensingimagelandslidedetectionwithoptimizedanchorboxesandedgeenhancement
AT linghan astudyofhighresolutionremotesensingimagelandslidedetectionwithoptimizedanchorboxesandedgeenhancement
AT juanliao astudyofhighresolutionremotesensingimagelandslidedetectionwithoptimizedanchorboxesandedgeenhancement
AT kunwang studyofhighresolutionremotesensingimagelandslidedetectionwithoptimizedanchorboxesandedgeenhancement
AT linghan studyofhighresolutionremotesensingimagelandslidedetectionwithoptimizedanchorboxesandedgeenhancement
AT juanliao studyofhighresolutionremotesensingimagelandslidedetectionwithoptimizedanchorboxesandedgeenhancement