Land Cover Classification of Multispectral LiDAR Data With an Efficient Self-Attention Capsule Network

被引:18
作者
Yu, Yongtao [1 ]
Liu, Chao [1 ]
Guan, Haiyan [2 ]
Wang, Lanfang [1 ]
Gao, Shangbing [1 ]
Zhang, Haiyan [1 ]
Zhang, Yahong [1 ]
Li, Jonathan [3 ]
机构
[1] Huaiyin Inst Technol, Fac Comp & Software Engn, Huaian 223003, Peoples R China
[2] Nanjing Univ Informat Sci & Technol, Sch Remote Sensing & Geomat Engn, Nanjing 210044, Peoples R China
[3] Univ Waterloo, Dept Geog & Environm Management, Waterloo, ON N2L 3G1, Canada
基金
中国国家自然科学基金;
关键词
Laser radar; Feature extraction; Remote sensing; Sensors; Task analysis; Labeling; Image sensors; Capsule feature attention; capsule network; land cover classification; land use mapping; multispectral light detection and ranging (LiDAR);
D O I
10.1109/LGRS.2021.3071252
中图分类号
P3 [地球物理学]; P59 [地球化学];
学科分类号
0708 ; 070902 ;
摘要
Periodically conducting land cover mapping plays a vital role in monitoring the status and changes of the land use. The up-to-date and accurate land use database serves importantly for a wide range of applications. This letter constructs an efficient self-attention capsule network (ESA-CapsNet) for land cover classification of multispectral light detection and ranging (LiDAR) data. First, formulated with a novel capsule encoder-decoder architecture, the ESA-CapsNet performs promisingly in extracting high-level, informative, and strong feature semantics for pixel-wise land cover classification by using the five types of rasterized feature images. Furthermore, designed with a novel capsule-based attention module, the channel and spatial feature encodings are comprehensively exploited to boost the feature saliency and robustness. The ESA-CapsNet is evaluated on two multispectral LiDAR data sets and achieves an advantageous performance with the overall accuracy, average accuracy, and kappa coefficient of over 98.42%, 95.15%, and 0.9776, respectively. Comparative experiments with the existing methods also demonstrate the effectiveness and applicability of the ESA-CapsNet in land cover classification tasks.
引用
收藏
页数:5
相关论文
共 50 条
[31]   A Novel Network-Level Fusion Architecture of Proposed Self-Attention and Vision Transformer Models for Land Use and Land Cover Classification From Remote Sensing Images [J].
Rubab, Saddaf ;
Khan, Muhammad Attique ;
Hamza, Ameer ;
Albarakati, Hussain Mobarak ;
Saidani, Oumaima ;
Alshardan, Amal ;
Alasiry, Areej ;
Marzougui, Mehrez ;
Nam, Yunyoung .
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2024, 17 :13135-13148
[32]   Optimization of the routing of capsule network based on multiscale information and self-attention mechanism [J].
Shang, Yunhao ;
Xu, Ning ;
Jin, Zhenzhou ;
Yao, Xiao .
JOURNAL OF ELECTRONIC IMAGING, 2022, 31 (02)
[33]   Urban land cover classification using airborne LiDAR data: A review [J].
Yan, Wai Yeung ;
Shaker, Ahmed ;
El-Ashmawy, Nagwa .
REMOTE SENSING OF ENVIRONMENT, 2015, 158 :295-310
[34]   Behind-the-Scenes: Multispectral imagery and land cover classification [J].
M'Closkey, Karen ;
VanDerSys, Keith .
JOURNAL OF LANDSCAPE ARCHITECTURE, 2022, 17 (01) :22-37
[35]   RADIOMETRIC CALIBRATION OF AIRBORNE LIDAR INTENSITY DATA FOR LAND COVER CLASSIFICATION [J].
Yan, Wai Yeung ;
Shaker, Ahmed .
2010 CANADIAN GEOMATICS CONFERENCE AND SYMPOSIUM OF COMMISSION I, ISPRS CONVERGENCE IN GEOMATICS - SHAPING CANADA'S COMPETITIVE LANDSCAPE, 2010, 38
[36]   MAGE: Multisource Attention Network With Discriminative Graph and Informative Entities for Classification of Hyperspectral and LiDAR Data [J].
Xiu, Di ;
Pan, Zongxu ;
Wu, Yirong ;
Hu, Yuxin .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2022, 60
[37]   Self-Attention Context Network: Addressing the Threat of Adversarial Attacks for Hyperspectral Image Classification [J].
Xu, Yonghao ;
Du, Bo ;
Zhang, Liangpei .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2021, 30 :8671-8685
[38]   Recursive Self-Attention Modules-Based Network for Panchromatic and Multispectral Image Fusion [J].
Liu, Chuang ;
Wei, Lu ;
Zhang, Zhiqi ;
Feng, Xiaoxiao ;
Xiang, Shao .
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2023, 16 :10067-10083
[39]   Separable Attention Capsule Network for Signal Classification [J].
Liu, Shaoqing ;
Liu, Huiling ;
Yang, Chen ;
Yang, Shuyuan ;
Wang, Min .
IEEE ACCESS, 2020, 8 (08) :181744-181750
[40]   Multibranch Feature Fusion Network With Self- and Cross-Guided Attention for Hyperspectral and LiDAR Classification [J].
Dong, Wenqian ;
Zhang, Tian ;
Qu, Jiahui ;
Xiao, Song ;
Zhang, Tongzhen ;
Li, Yunsong .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2022, 60