Joint Sparse Representation-based Single Image Super-Resolution for Remote Sensing Applications

被引:2
|
作者
Deka, Bhabesh [1 ]
Mullah, Helal Uddin [1 ]
Barman, Trishna [1 ]
Datta, Sumit [2 ]
机构
[1] Tezpur Univ, Dept Elect & Commun Engn, Tezpur 784028, India
[2] Digital Univ Kerala, Sch Elect Syst & Automat, Thiruvananthapuram 695317, India
关键词
Dictionaries; Image reconstruction; Training; Spatial resolution; Image restoration; Feature extraction; Sensors; Dictionary training; joint sparse representation ([!text type='JS']JS[!/text]R); parallel processing; remote sensing (RS); super-resolution; K-SVD; ALGORITHM; REGULARIZATION; RESTORATION;
D O I
10.1109/JSTARS.2023.3244069
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Sparse representation-based single image super-resolution (SISR) methods use a coupled overcomplete dictionary trained from high-resolution images/image patches. Since remote sensing (RS) satellites capture images of large areas, these images usually have poor spatial resolution and obtaining an effective dictionary as such would be very challenging. Moreover, traditional patch-based sparse representation models for reconstruction tend to give unstable sparse solution and produce visual artefact in the recovered images. To mitigate these problems, in this article, we have proposed an adaptive joint sparse representation-based SISR method that is dependent only on the input low-resolution image for dictionary training and sparse reconstruction. The new model combines patch-based local sparsity and group sparse representation-based nonlocal sparsity in a single framework, which helps in stabilizing the sparse solution and improve the SISR results. The experimental results are evaluated both visually and quantitatively for several RGB and multispectral RS datasets, where the proposed method shows improvements in peak signal-to-noise ratio by 1-4 dB and 2-3 dB over the state-of-the-art sparse representation- and deep learning-based SR methods, respectively. Land cover classification applied on the super-resolved images further validate the advantages of the proposed method. Finally, for practical RS applications, we have performed parallel implementation in general purpose graphics processing units and achieved significant speed ups (30-40x) in the execution time.
引用
收藏
页码:2352 / 2365
页数:14
相关论文
共 50 条
  • [1] Remote sensing image super-resolution based on improved sparse representation
    Zhu, Fu-Zhen
    Liu, Yue
    Huang, Xin
    Bai, Hong-Yi
    Wu, Hong
    [J]. Guangxue Jingmi Gongcheng/Optics and Precision Engineering, 2019, 27 (03): : 718 - 725
  • [2] Understanding Compressive Sensing and Sparse Representation-Based Super-Resolution
    Kulkarni, Naveen
    Nagesh, Pradeep
    Gowda, Rahul
    Li, Baoxin
    [J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2012, 22 (05) : 778 - 789
  • [3] A Single Image Compression Framework Combined with Sparse Representation-Based Super-Resolution
    He Xiaohai
    He Jingbo
    Huang Jianqiu
    Wu Di
    [J]. PROCEEDINGS OF THE 2015 INTERNATIONAL CONFERENCE ON ELECTRONIC SCIENCE AND AUTOMATION CONTROL, 2015, 20 : 292 - 296
  • [4] A super-resolution model and algorithm of remote sensing image based on sparse representation
    [J]. Zhong, J. (zhongjiusheng@sina.com), 1600, SinoMaps Press (43):
  • [5] Sparse representation-based MRI super-resolution reconstruction
    Wang, Yun-Heng
    Qiao, Jiaqing
    Li, Jun-Bao
    Fu, Ping
    Chu, Shu-Chuan
    Roddick, John F.
    [J]. MEASUREMENT, 2014, 47 : 946 - 953
  • [6] Remote Sensing Image Super-Resolution Using Sparse Representation and Coupled Sparse Autoencoder
    Shao, Zhenfeng
    Wang, Lei
    Wang, Zhongyuan
    Deng, Juan
    [J]. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2019, 12 (08) : 2663 - 2674
  • [7] A new framework for remote sensing image super-resolution: Sparse representation-based method by processing dictionaries with multi-type features
    Wu, Wei
    Yang, Xiaomin
    Liu, Kai
    Liu, Yiguang
    Yan, Binyu
    Hua, Hua
    [J]. JOURNAL OF SYSTEMS ARCHITECTURE, 2016, 64 : 63 - 75
  • [8] Sparse Representation-Based Multiple Frame Video Super-Resolution
    Dai, Qiqin
    Yoo, Seunghwan
    Kappeler, Armin
    Katsaggelos, Aggelos K.
    [J]. IEEE TRANSACTIONS ON IMAGE PROCESSING, 2017, 26 (02) : 765 - 781
  • [9] Sparse Representation-based Super-Resolution for Diffusion Weighted Images
    Afzali, Maryam
    Fatemizadeh, Emad
    Soltanian-Zadeh, Hamid
    [J]. 2014 21TH IRANIAN CONFERENCE ON BIOMEDICAL ENGINEERING (ICBME), 2014, : 12 - 16
  • [10] Sparse Representation-based Super-Resolution for Face Recognition At a Distance
    Bilgazyev, E.
    Efraty, B.
    Shah, S. K.
    Kakadiaris, I. A.
    [J]. PROCEEDINGS OF THE BRITISH MACHINE VISION CONFERENCE 2011, 2011,