Building Change Detection in Remote Sensing Images Based on Dual Multi-Scale Attention

被引:14
|
作者
Zhang, Jian [1 ]
Pan, Bin [1 ]
Zhang, Yu [2 ]
Liu, Zhangle [1 ]
Zheng, Xin [1 ]
机构
[1] Wuhan Univ, Sch Remote Sensing & Informat Engn, Wuhan 430061, Peoples R China
[2] Yangtze River Sci Res Inst, Inst Spatial Informat Technol Applicat, Wuhan 430014, Peoples R China
关键词
building change detection; multi-scale attention module; optical remote sensing images; NETWORK; CNN;
D O I
10.3390/rs14215405
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Accurate change detection continues to pose challenges due to the continuous renovation of old urban areas and the emergence of cloud cover in coastal areas. There have been numerous methods proposed to detect land-cover changes from optical images. However, there are still many flaws in many existing deep learning methods. In response to the problems of unpredictable change details and the lack of global semantic information in deep learning-based change detection models, a change detection model based on multi-scale and attention is proposed. Firstly, a multi-scale attention module is proposed to effectively obtain multi-scale semantic information to build an end-to-end dual multi-scale attention building change detection model. Secondly, an efficient double-threshold automatic data equalization rule is proposed to address the imbalance of data categories existing in the building change detection dataset, which effectively alleviates the severely skewed data distribution and facilitates the training and convergence of the model. The validation experiments are conducted on three open-source high-resolution building change detection datasets. The experimental results show that the proposed method in this paper can detect the location and area of the actual building changes more accurately and has better results in the detail detection part. This verifies the effectiveness and accuracy of the proposed method.
引用
收藏
页数:15
相关论文
共 50 条
  • [1] Multi-scale Cross Dual Attention Network for Building Change Detection in Remote Sensing Images
    Zhang J.
    Yan Z.
    Ma S.
    [J]. Journal of Geo-Information Science, 2023, 25 (12) : 2487 - 2500
  • [2] Building detection algorithm in multi-scale remote sensing images based on attention mechanism
    Wei Ding
    Li Zhang
    Guangliang Yang
    [J]. Evolutionary Intelligence, 2023, 16 : 1717 - 1728
  • [3] Building detection algorithm in multi-scale remote sensing images based on attention mechanism
    Ding, Wei
    Zhang, Li
    Yang, Guangliang
    [J]. EVOLUTIONARY INTELLIGENCE, 2023, 16 (05) : 1717 - 1728
  • [4] Multi-scale Contrastive Learning for Building Change Detection in Remote Sensing Images
    Xue, Mingliang
    Huo, Xinyuan
    Lu, Yao
    Niu, Pengyuan
    Liang, Xuan
    Shang, Hailong
    Jia, Shucai
    [J]. PATTERN RECOGNITION AND COMPUTER VISION, PRCV 2023, PT IV, 2024, 14428 : 318 - 329
  • [5] GCN-based multi-scale dual fusion for remote sensing building change detection
    Liang, Shike
    Hua, Zhen
    Li, Jinjiang
    [J]. INTERNATIONAL JOURNAL OF REMOTE SENSING, 2023, 44 (03) : 953 - 980
  • [6] Multi-Attention Object Detection Model in Remote Sensing Images Based on Multi-Scale
    Ying, Xiang
    Wang, Qiang
    Li, Xuewei
    Yu, Mei
    Jiang, Han
    Gao, Jie
    Liu, Zhiqiang
    Yu, Ruiguo
    [J]. IEEE ACCESS, 2019, 7 : 94508 - 94519
  • [7] Change Detection for High-Resolution Remote Sensing Images Based on a Multi-Scale Attention Siamese Network
    Li, Jiankang
    Zhu, Shanyou
    Gao, Yiyao
    Zhang, Guixin
    Xu, Yongming
    [J]. REMOTE SENSING, 2022, 14 (14)
  • [8] Semantic Segmentation of Remote Sensing Images Based on Dual Attention and Multi-scale Feature Fusion
    Weng, Mengqian
    Hu, Zhibo
    Xie, Xiaopeng
    Li, Yunhong
    Hu, Lei
    [J]. TWELFTH INTERNATIONAL CONFERENCE ON GRAPHICS AND IMAGE PROCESSING (ICGIP 2020), 2021, 11720
  • [9] MSGATN: A Superpixel-Based Multi-Scale Siamese Graph Attention Network for Change Detection in Remote Sensing Images
    Shuai, Wenjing
    Jiang, Fenlong
    Zheng, Hanhong
    Li, Jianzhao
    [J]. APPLIED SCIENCES-BASEL, 2022, 12 (10):
  • [10] Multi-Scale Feature Fusion Attention Network for Building Extraction in Remote Sensing Images
    Liu, Jia
    Gu, Hang
    Li, Zuhe
    Chen, Hongyang
    Chen, Hao
    [J]. ELECTRONICS, 2024, 13 (05)