Researching

Journals
  • Advanced Photonics
  • Photonics Insights
  • Advanced Photonics Nexus
  • Photonics Research
  • Advanced Imaging
  • View All Journals
  • Chinese Optics Letters
  • High Power Laser Science and Engineering
    • Articles
  • Optics
  • Physics
  • Geography
  • View All Subjects
    • Conferences
  • CIOP
  • HPLSE
  • AP
  • View All Events
    • News
    About CLP
    Search by keywords or author
    Journals >Acta Optica Sinica >Volume 37 >Issue 11 >Page 1110004 > Article
    • Acta Optica Sinica
    • Vol. 37, Issue 11, 1110004 (2017)
    Fusion of Infrared and Visible Images Based on Multi-Scale Directional Guided Filter and Convolutional Sparse Representation
    Xianhong Liu and Zhibin Chen*
    Author Affiliations
  • Mechanical Institute of Technology, Mechanical Engineering College, Shijiazhuang, Hebei 050003, China
    • show less
    DOI: 10.3788/AOS201737.1110004 Cite this Article Set citation alerts
    Xianhong Liu, Zhibin Chen. Fusion of Infrared and Visible Images Based on Multi-Scale Directional Guided Filter and Convolutional Sparse Representation[J]. Acta Optica Sinica, 2017, 37(11): 1110004 Copy Citation Text show less
    Decomposed results of low-frequency subband of UNcamp infrared source image via Gaussian filter. (a) Infrared source image; (b) low-frequency subband after filtering; (c) low-frequency approximate component; (d) strong edge component
    Fig. 1. Decomposed results of low-frequency subband of UNcamp infrared source image via Gaussian filter. (a) Infrared source image; (b) low-frequency subband after filtering; (c) low-frequency approximate component; (d) strong edge component
    Download full size
    Partial enlarged views of Fig.1. (a1)(a2) Infrared source image; (b1)(b2) low-frequency subband after filtering; (c1)(c2) low-frequency approximate component; (d1)(d2) strong edge component
    Fig. 2. Partial enlarged views of Fig.1. (a1)(a2) Infrared source image; (b1)(b2) low-frequency subband after filtering; (c1)(c2) low-frequency approximate component; (d1)(d2) strong edge component
    Download full size
    Saliency of UNcamp infrared source image obtained by different methods. (a) Infrared source image; (b) method of reference [5]; (c) method of reference [15]
    Fig. 3. Saliency of UNcamp infrared source image obtained by different methods. (a) Infrared source image; (b) method of reference [5]; (c) method of reference [15]
    Download full size
    Fused results of Quad source images. (a) Visible source image; (b) infrared source image; (c) DWT method; (d) NSCT+PCNN method; (e) GFF method; (f) SR method; (g) DWT+SR method; (h)proposed method
    Fig. 4. Fused results of Quad source images. (a) Visible source image; (b) infrared source image; (c) DWT method; (d) NSCT+PCNN method; (e) GFF method; (f) SR method; (g) DWT+SR method; (h)proposed method
    Download full size
    Fused results of Leaves source images. (a) Visible source image; (b) infrared source image; (c) DWT method; (d) NSCT+PCNN method; (e) GFF method; (f) SR method; (g) DWT+SR method; (h)proposed method
    Fig. 5. Fused results of Leaves source images. (a) Visible source image; (b) infrared source image; (c) DWT method; (d) NSCT+PCNN method; (e) GFF method; (f) SR method; (g) DWT+SR method; (h)proposed method
    Download full size
    Fused results of UNcamp source images. (a) Visible source image; (b) infrared source image; (c) DWT method; (d) NSCT+PCNN method; (e) GFF method; (f) SR method; (g) DWT+SR method; (h)proposed method
    Fig. 6. Fused results of UNcamp source images. (a) Visible source image; (b) infrared source image; (c) DWT method; (d) NSCT+PCNN method; (e) GFF method; (f) SR method; (g) DWT+SR method; (h)proposed method
    Download full size
    Partial enlarged views of advertising board in Quad fused images. (a) Visible source image; (b) infrared source image; (c) DWT method; (d) NSCT+PCNN method; (e) GFF method; (f) SR method; (g) DWT+SR method; (h) proposed method
    Fig. 7. Partial enlarged views of advertising board in Quad fused images. (a) Visible source image; (b) infrared source image; (c) DWT method; (d) NSCT+PCNN method; (e) GFF method; (f) SR method; (g) DWT+SR method; (h) proposed method
    Download full size
    Partial enlarged views of traffic light in Quad fused images. (a) Visible source image; (b) infrared source image; (c) DWT method; (d) NSCT+PCNN method; (e) GFF method; (f) SR method; (g) DWT+SR method; (h) proposed method
    Fig. 8. Partial enlarged views of traffic light in Quad fused images. (a) Visible source image; (b) infrared source image; (c) DWT method; (d) NSCT+PCNN method; (e) GFF method; (f) SR method; (g) DWT+SR method; (h) proposed method
    Download full size
    Partial enlarged views of object board in Leaves fused images. (a) Visible source image; (b) infrared source image; (c) DWT method; (d) NSCT+PCNN method; (e) GFF method; (f) SR method; (g) DWT+SR method; (h) proposed method
    Fig. 9. Partial enlarged views of object board in Leaves fused images. (a) Visible source image; (b) infrared source image; (c) DWT method; (d) NSCT+PCNN method; (e) GFF method; (f) SR method; (g) DWT+SR method; (h) proposed method
    Download full size
    Partial enlarged views of object in UNcamp fused images. (a) Visible source image; (b) infrared source image; (c) DWT method; (d) NSCT+PCNN method; (e) GFF method; (f) SR method; (g) DWT+SR method; (h) proposed method
    Fig. 10. Partial enlarged views of object in UNcamp fused images. (a) Visible source image; (b) infrared source image; (c) DWT method; (d) NSCT+PCNN method; (e) GFF method; (f) SR method; (g) DWT+SR method; (h) proposed method
    Download full size
    IndexDWTNSCT+PCNNGFFSRDWT+SRProposed method
    AGV51.891380.299470.863069.004169.967991.6608
    STD23.197634.379032.253436.840736.014740.6317
    IE6.02396.75396.53286.80636.83936.9126
    MI1.91463.03081.71462.74772.24963.4649
    SF11.983812.098212.014013.754212.603515.0227
    QAB/F0.49800.56460.57820.52430.58200.6111
    Table 1. Objective evaluation for Quad fused images
    IndexDWTNSCT+PCNNGFFSRDWT+SRProposed method
    AGV35.687432.852842.154840.528842.851351.2290
    STD34.836537.880838.829239.075641.602547.7524
    IE6.56826.41716.75426.61566.78826.9611
    MI3.45173.00773.82344.23953.65204.5171
    SF20.842319.219720.130920.531221.588429.3360
    QAB/F0.62890.57370.63830.63600.63120.6459
    Table 2. Objective evaluation for Leaves fused images
    IndexDWTNSCT+PCNNGFFSRDWT+SRProposed method
    AGV90.736195.169290.554491.355392.9005111.7959
    STD24.816027.558525.851628.569532.075933.8266
    IE6.40296.70796.42286.71126.84976.9260
    MI1.48721.85811.58781.85501.70422.0552
    SF10.71808.87979.115810.720611.380313.0813
    QAB/F0.41330.37680.42800.37110.40850.4455
    Table 3. Objective evaluation for UNcamp fused images
    Abstract
    Get PDF(in Chinese)
    Figures&Tables (13)
    Equations (0)
    References (19)
    Cited By (8)
    Get Citation
    Copy Citation Text
    Xianhong Liu, Zhibin Chen. Fusion of Infrared and Visible Images Based on Multi-Scale Directional Guided Filter and Convolutional Sparse Representation[J]. Acta Optica Sinica, 2017, 37(11): 1110004
    Download Citation
    Set citation alerts for the article
    Tools
    Share
    Set citation alerts for the article
    Save the article for my favorites
    Paper Information
    Recommended Topics
    laser devices and laser physics
    Lasers and Laser Optics
    Laser physics
    laser manufacturing
    Instrumentation, Measurement and Metrology