Spatial and Cluster Structural Prior-Guided Subspace Clustering for Hyperspectral Image

高光谱成像 聚类分析 计算机科学 子空间拓扑 人工智能 模式识别(心理学) 星团(航天器) 图像(数学) 遥感 计算机视觉 地质学 程序设计语言
作者
Shaoguang Huang,Haijin Zeng,Hongyu Chen,Hongyan Zhang
出处
期刊:IEEE Transactions on Geoscience and Remote Sensing [Institute of Electrical and Electronics Engineers]
卷期号:62: 1-15
标识
DOI:10.1109/tgrs.2024.3375922
摘要

Subspace clustering has achieved remarkable performance for hyperspectral image (HSI). However, existing methods are often computationally expensive and have limited ability to capture the intrinsic structural information of HSI. In this paper, we propose a structural prior-guided subspace clustering method, which simultaneously incorporates the local and non-local spatial information and the cluster prior information. Accordingly, three efficient regularizations are developed. Considering the local connectivity of pixels, we propose an ℓ 2,1 norm based constraint on the representation difference matrix to improve the homogeneity of clustering result. Next, to capture the non-local geometric structure of HSI, we propose a manifold-based regularization with an adaptively learned landmark graph. Furthermore, we explore the block-diagonal cluster structure of HSI and develop a landmark-based clustering constraint, which makes the representations more favorable for clustering. Our local constraint is imposed on all the data points due to its efficiency and the latter two are solely imposed on landmarks, leading to computationally efficient regularizations. Due to the local constraint, the manifold and cluster structure of the landmarks can be effectively propagated to all the data points. To make our model scalable to large-scale data, we learn a compact dictionary with an orthogonal constraint, significantly reducing the number of parameters. In addition, we propose a novel landmark selection method to support our landmark-based constraints using multi-scale super-pixel segmentation and clustering, which improves the uniformity and diversity of landmarks. We also develop an efficient algorithm to solve the proposed model. Experimental results demonstrate that our model outperforms the state-of-the-art.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
大幅提高文件上传限制,最高150M (2024-4-1)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
cinn完成签到 ,获得积分10
刚刚
今后应助an采纳,获得10
1秒前
CipherSage应助Qiang采纳,获得10
3秒前
li完成签到,获得积分10
3秒前
流水不腐发布了新的文献求助10
3秒前
温婉的初南完成签到,获得积分10
3秒前
FashionBoy应助洪洪1采纳,获得10
4秒前
huajinoob发布了新的文献求助10
4秒前
5秒前
5秒前
帕克发布了新的文献求助10
6秒前
大个应助Jjj采纳,获得10
9秒前
9秒前
Sprinkle发布了新的文献求助10
10秒前
我是老大应助烂漫的草莓采纳,获得10
10秒前
11秒前
12秒前
科研通AI2S应助TOPLi采纳,获得10
12秒前
阿斯蒂和琴酒完成签到,获得积分10
13秒前
13秒前
14秒前
14秒前
biotnt完成签到,获得积分10
14秒前
乐乐应助Sprinkle采纳,获得10
14秒前
14秒前
萧暖发布了新的文献求助10
15秒前
留胡子的书桃完成签到 ,获得积分10
15秒前
16秒前
16秒前
传奇3应助翻翻CHEN采纳,获得10
17秒前
18秒前
KK关注了科研通微信公众号
19秒前
小西发布了新的文献求助10
19秒前
wanci应助蛋炒饭不加蛋采纳,获得10
19秒前
沉静的函发布了新的文献求助10
20秒前
Sprinkle完成签到,获得积分10
20秒前
cookie发布了新的文献求助10
21秒前
JamesPei应助露露采纳,获得10
21秒前
VV发布了新的文献求助10
21秒前
sugarxy应助Strike采纳,获得150
22秒前
高分求助中
Sustainability in Tides Chemistry 2000
Bayesian Models of Cognition:Reverse Engineering the Mind 800
Essentials of thematic analysis 700
A Dissection Guide & Atlas to the Rabbit 600
Very-high-order BVD Schemes Using β-variable THINC Method 568
Mantiden: Faszinierende Lauerjäger Faszinierende Lauerjäger 500
PraxisRatgeber: Mantiden: Faszinierende Lauerjäger 500
热门求助领域 (近24小时)
化学 医学 生物 材料科学 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3124688
求助须知:如何正确求助?哪些是违规求助? 2775052
关于积分的说明 7725125
捐赠科研通 2430553
什么是DOI,文献DOI怎么找? 1291228
科研通“疑难数据库(出版商)”最低求助积分说明 622091
版权声明 600323