A Superpixel-Based Dual Window RX for Hyperspectral Anomaly Detection

被引：35
|
作者：
Ren, Lang [1 ]
Zhao, Liaoying [1 ]
Wang, Yulei [2 ]
机构：
[1] Hangzhou Dianzi Univ, Dept Comp Sci, Hangzhou 310018, Zhejiang, Peoples R China
[2] Dalian Maritime Univ, Informat & Technol Coll, Ctr Hyperspectral Imaging Remote Sensing, Dalian 116026, Peoples R China
来源：
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS | 2020年 / 17卷 / 07期
关键词：
Hyperspectral imaging; Image segmentation; Erbium; Anomaly detection; Object detection; Microsoft Windows; Correlation; Anomaly detection (AD); dual window; hyperspectral image (HSI); superpixel segmentation (SPS);
D O I：
10.1109/LGRS.2019.2942949
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：
This letter presents a superpixel-based dual window RX (SPDWRX) anomaly detection (AD) algorithm that uses superpixel segmentation (SPS) to adaptively determine the dual window for local RX (LRX) detection, rather than using a fixed dual window. The main premise of SPDWRX is to first divide the hyperspectral image into multiple superpixels and then extend the minimum bounding rectangle to determine the background of each superpixel. Finally, LRX AD is conducted on each pixel in the same superpixel using the same background. Furthermore, a fine SPS method is proposed based on the entropy rate superpixel to quickly obtain uniform superpixels. The experimental results show that the proposed SPDWRX method can significantly improve the detection speed and slightly improve the detection performance, and the modified SPS can further improve the detection performance of SPDWRX.
引用
收藏
页码：1233 / 1237
页数：5
相关论文
共 50 条
  • [1] SUPERPIXEL-BASED STATISTICAL ANOMALY DETECTION FOR SENSE AND AVOID
    Pappas, Odysseas A.
    Achim, Alin M.
    Bull, David R.
    [J]. 2015 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2015, : 2229 - 2233
  • [2] Dual window-based anomaly detection for hyperspectral imagery
    Kwon, H
    Der, SZ
    Nasrabadi, NM
    [J]. AUTOMATIC TARGET RECOGNITION XIII, 2003, 5094 : 148 - 158
  • [3] SUPERPIXEL-BASED HYPERSPECTRAL UNMIXING WITH REGIONAL SEGMENTATION
    Alkhatib, Mohammed Q.
    Velez-Reyes, Miguel
    [J]. IGARSS 2018 - 2018 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, 2018, : 6384 - 6387
  • [4] Hyperspectral Anomaly Detection Using Dual Window Density
    Tu, Bing
    Yang, Xianchang
    Zhou, Chengle
    He, Danbing
    Plaza, Antonio
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2020, 58 (12): : 8503 - 8517
  • [5] SUPERPIXEL-BASED SALIENCY DETECTION
    Liu, Zhi
    Le Meur, Olivier
    Luo, Shuhua
    [J]. 2013 14TH INTERNATIONAL WORKSHOP ON IMAGE ANALYSIS FOR MULTIMEDIA INTERACTIVE SERVICES (WIAMIS), 2013,
  • [6] Hyperspectral anomaly detection via combining adaptive window saliency detection and improved superpixel segmentation
    Qian, Xiaoliang
    Zeng, Yinfeng
    Lin, Sheng
    Zhang, Bo
    Ren, Hangli
    Wang, Wei
    [J]. National Remote Sensing Bulletin, 2023, 27 (12) : 2748 - 2761
  • [7] Superpixel-based spectral classification for the detection of head and neck cancer with hyperspectral imaging
    Chung, Hyunkoo
    Lu, Guolan
    Tian, Zhiqiang
    Wang, Dongsheng
    Chen, Zhuo Georgia
    Fei, Baowei
    [J]. MEDICAL IMAGING 2016-BIOMEDICAL APPLICATIONS IN MOLECULAR, STRUCTURAL, AND FUNCTIONAL IMAGING, 2016, 9788
  • [8] SUPERPIXEL-BASED NONNEGATIVE TENSOR FACTORIZATION FOR HYPERSPECTRAL UNMIXING
    Xiong, Fengchao
    Chen, Jingzhou
    Zhou, Jun
    Qian, Yuntao
    [J]. IGARSS 2018 - 2018 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, 2018, : 6392 - 6395
  • [9] SUPERPIXEL-BASED COMPOSITE KERNEL FOR HYPERSPECTRAL IMAGE CLASSIFICATION
    Duan, Wuhui
    Li, Shutao
    Fang, Leyuan
    [J]. 2015 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS), 2015, : 1698 - 1701
  • [10] Hyperspectral anomaly detection: Beyond RX
    Schaum, A.
    [J]. Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XIII, 2007, 6565 : COVER1 - +
12345