Online Graph-Based Change Point Detection in Multiband Image Sequences

被引:5
|
作者
Borsoi, R. A. [1 ,2 ]
Richard, C. [1 ]
Ferrari, A. [1 ]
Chen, J. [3 ]
Bermudez, J. C. M. [2 ,4 ]
机构
[1] Univ Cote dAzur, OCA, CNRS, Nice, France
[2] Univ Fed Santa Catarina, Florianopolis, SC, Brazil
[3] Northwestern Polytech Univ, Xian, Peoples R China
[4] Univ Catolica Pelotas, Pelotas, RS, Brazil
关键词
Hyperspectral images; change detection; graphs; multitemporal; superpixels; TIME-SERIES; FILTER; MAD;
D O I
10.23919/eusipco47968.2020.9287747
中图分类号
O42 [声学];
学科分类号
070206 ; 082403 ;
摘要
The automatic detection of changes or anomalies between multispectral and hyperspectral images collected at different time instants is an active and challenging research topic. To effectively perform change-point detection in multitemporal images, it is important to devise techniques that are computationally efficient for processing large datasets, and that do not require knowledge about the nature of the changes. In this paper, we introduce a novel online framework for detecting changes in multitemporal remote sensing images. Acting on neighboring spectra as adjacent vertices in a graph, this algorithm focuses on anomalies concurrently activating groups of vertices corresponding to compact, well-connected and spectrally homogeneous image regions. It fully benefits from recent advances in graph signal processing to exploit the characteristics of the data that lie on irregular supports. Moreover, the graph is estimated directly from the images using superpixel decomposition algorithms. The learning algorithm is scalable in the sense that it is efficient and spatially distributed. Experiments illustrate the detection and localization performance of the method.
引用
收藏
页码:850 / 854
页数:5
相关论文
共 50 条
  • [1] Online graph-based change point detection in multiband image sequences
    Borsoi, R.A.
    Richard, C.
    Ferrari, A.
    Chen, J.
    Bermudez, J.C.M.
    [J]. European Signal Processing Conference, 2021, 2021-January : 850 - 854
  • [2] GRAPH-BASED CHANGE-POINT DETECTION
    Chen, Hao
    Zhang, Nancy
    [J]. ANNALS OF STATISTICS, 2015, 43 (01): : 139 - 176
  • [3] A Graph-Based Method for Joint Instance Segmentation of Point Clouds and Image Sequences
    Abello, Montiel
    Mangelson, Joshua G.
    Kaess, Michael
    [J]. 2021 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2021), 2021, : 9565 - 9571
  • [4] Global and Local Graph-Based Difference Image Enhancement for Change Detection
    Zheng, Xiaolong
    Guan, Dongdong
    Li, Bangjie
    Chen, Zhengsheng
    Pan, Lefei
    [J]. REMOTE SENSING, 2023, 15 (05)
  • [5] Graph-Based Change-Point Analysis
    Chen, Hao
    Chu, Lynna
    [J]. ANNUAL REVIEW OF STATISTICS AND ITS APPLICATION, 2023, 10 : 475 - 499
  • [6] An online graph-based anomalous change detection strategy for unsupervised video surveillance
    Kim, Jongwon
    Cho, Jeongho
    [J]. EURASIP JOURNAL ON IMAGE AND VIDEO PROCESSING, 2019, 2019 (01)
  • [7] An online graph-based anomalous change detection strategy for unsupervised video surveillance
    Jongwon KIM
    Jeongho CHO
    [J]. EURASIP Journal on Image and Video Processing, 2019
  • [8] Graph-Based Malware Detection Using Opcode Sequences
    Gulmez, Sibel
    Sogukpinar, Ibrahim
    [J]. 9TH INTERNATIONAL SYMPOSIUM ON DIGITAL FORENSICS AND SECURITY (ISDFS'21), 2021,
  • [9] Graph-Based Place Recognition in Image Sequences with CNN Features
    Xiwu Zhang
    Lei Wang
    Yan Zhao
    Yan Su
    [J]. Journal of Intelligent & Robotic Systems, 2019, 95 : 389 - 403
  • [10] Graph-Based Place Recognition in Image Sequences with CNN Features
    Zhang, Xiwu
    Wang, Lei
    Zhao, Yan
    Su, Yan
    [J]. JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS, 2019, 95 (02) : 389 - 403