Efficient detection of building in remote sensing images using an improved YOLOv10 network

Objectives. At present, rapid detection of the location and size of building objects from remote sensing images is important for scientific research value and has practical significance for urban planning, environmental monitoring and disaster management.Methods. This paper proposes an object detect...

Full description

Saved in:
Bibliographic Details
Main Authors: X. Wu, Se. V. Ablameyko
Format: Article
Language:Russian
Published: National Academy of Sciences of Belarus, the United Institute of Informatics Problems 2025-07-01
Series:Informatika
Subjects:
Online Access:https://inf.grid.by/jour/article/view/1351
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849335967238848512
author X. Wu
Se. V. Ablameyko
author_facet X. Wu
Se. V. Ablameyko
author_sort X. Wu
collection DOAJ
description Objectives. At present, rapid detection of the location and size of building objects from remote sensing images is important for scientific research value and has practical significance for urban planning, environmental monitoring and disaster management.Methods. This paper proposes an object detection method based on improved YOLOv10 network, which incorporates Super Token Attention, RepConv and Normalized Weighted Distance to more precisely detect buildings in remote sensing images. This method improves the detection accuracy and efficiency especially for small objects. The LEVIR-CD dataset is used for model training and testing.Results. The experimental results show that the method demonstrates better accuracy on the building detection task than the traditional YOLOv10 and other methods.Conclusion. The proposed method significantly enhances the accuracy and efficiency of building detection in remote sensing images
format Article
id doaj-art-1aa42679f1d840458e55f67dc1035513
institution Kabale University
issn 1816-0301
language Russian
publishDate 2025-07-01
publisher National Academy of Sciences of Belarus, the United Institute of Informatics Problems
record_format Article
series Informatika
spelling doaj-art-1aa42679f1d840458e55f67dc10355132025-08-20T03:45:07ZrusNational Academy of Sciences of Belarus, the United Institute of Informatics ProblemsInformatika1816-03012025-07-01222334710.37661/1816-0301-2025-22-2-33-471114Efficient detection of building in remote sensing images using an improved YOLOv10 networkX. Wu0Se. V. Ablameyko1Belarusian State UniversityThe United Institute of Informatics Problems of the National Academy of Sciences of BelarusObjectives. At present, rapid detection of the location and size of building objects from remote sensing images is important for scientific research value and has practical significance for urban planning, environmental monitoring and disaster management.Methods. This paper proposes an object detection method based on improved YOLOv10 network, which incorporates Super Token Attention, RepConv and Normalized Weighted Distance to more precisely detect buildings in remote sensing images. This method improves the detection accuracy and efficiency especially for small objects. The LEVIR-CD dataset is used for model training and testing.Results. The experimental results show that the method demonstrates better accuracy on the building detection task than the traditional YOLOv10 and other methods.Conclusion. The proposed method significantly enhances the accuracy and efficiency of building detection in remote sensing imageshttps://inf.grid.by/jour/article/view/1351yolov10remote sensing imagesattention mechanismbuilding detectionrepconvsuper token attention
spellingShingle X. Wu
Se. V. Ablameyko
Efficient detection of building in remote sensing images using an improved YOLOv10 network
Informatika
yolov10
remote sensing images
attention mechanism
building detection
repconv
super token attention
title Efficient detection of building in remote sensing images using an improved YOLOv10 network
title_full Efficient detection of building in remote sensing images using an improved YOLOv10 network
title_fullStr Efficient detection of building in remote sensing images using an improved YOLOv10 network
title_full_unstemmed Efficient detection of building in remote sensing images using an improved YOLOv10 network
title_short Efficient detection of building in remote sensing images using an improved YOLOv10 network
title_sort efficient detection of building in remote sensing images using an improved yolov10 network
topic yolov10
remote sensing images
attention mechanism
building detection
repconv
super token attention
url https://inf.grid.by/jour/article/view/1351
work_keys_str_mv AT xwu efficientdetectionofbuildinginremotesensingimagesusinganimprovedyolov10network
AT sevablameyko efficientdetectionofbuildinginremotesensingimagesusinganimprovedyolov10network