光学学报, 2020, 40 (2): 0210001, 网络出版: 2020-01-02
基于Tikhonov正则化和细节重建的红外与可见光图像融合方法 
下载： 1633次
Infrared and Visible Image Fusion Method Based on Tikhonov Regularization and Detail Reconstruction
图 & 表
图 6. 不同分解方法对Smoke场景的分解效果。(a)原图像;(b)双边滤波;(c)引导滤波;(d)高斯金字塔;(e)小波变换;(f) Tikhonov正则化,α=2;(g) Tikhonov正则化,α=4;(h) Tikhonov正则化,α=8
Fig. 6. Comparison of decomposition effects of different decomposition algorithms for “Smoke” scene. (a) Original image; (b) bilateral filtering; (c) guided filtering; (d) Gaussian pyramid; (e) wavelet transform; (f) Tikhonov regularization, α=2; (g) Tikhonov regularization, α=4 ; (h) Tikhonov regularization, α=8
图 7. 不同分解方法对Heather场景的分解效果。(a)原图像;(b)双边滤波;(c)引导滤波;(d)高斯金字塔;(e)小波变换;(f) Tikhonov正则化,α=2;(g) Tikhonov正则化,α=4;(h) Tikhonov正则化,α=8
Fig. 7. Comparison of decomposition effects of different decomposition algorithms for “Heather” scene. (a) Original image; (b) bilateral filtering; (c) guided filtering; (d) Gaussian pyramid; (e) wavelet transform; (f) Tikhonov regularization, α=2; (g) Tikhonov regularization, α=4 ; (h) Tikhonov regularization, α=8
图 8. 不同算法对Quad场景的融合效果。(a)可见光图像;(b)红外图像; (c) DenseNet; (d) LatLRR; (e) VGG; (f) ResNet; (g) VSM; (h) QD; (i) GAN; (j)本文算法
Fig. 8. Fusion effects of different algorithms in “Quad” scene. (a) Visible image; (b) infrared image; (c) DenseNet; (d) LatLRR; (e) VGG; (f) ResNet; (g) VSM; (h) QD; (i) GAN; (j) proposed algorithm
图 9. 不同算法对Smoke场景的融合效果。(a)可见光图像;(b)红外图像;(c) DenseNet;(d) LatLRR;(e) VGG;(f) ResNet;(g) VSM;(h) QD;(i) GAN;(j)本文算法
Fig. 9. Fusion effects of different algorithms in “Smoke” scene. (a)Visible image; (b) infrared image; (c) DenseNet; (d) LatLRR; (e) VGG;(f) ResNet; (g) VSM; (h) QD; (i) GAN; (j) proposed algorithm
图 10. 不同算法对Nato_camp场景的融合效果。(a)可见光图像;(b)红外图像;(c) DenseNet;(d) LatLRR;(e) VGG;(f)ResNet;(g)VSM;(h)QD;(i)GAN;(j)本文算法
Fig. 10. Fusion effects of different algorithms in “Nato_camp” scene. (a) Visible image; (b) infrared image; (c) DenseNet; (d) LatLRR; (e) VGG; (f) ResNet; (g) VSM; (h) QD; (i) GAN; (j) proposed algorithm
图 11. 不同算法对模糊场景Kaptein_1123的融合效果。(a)可见光图像;(b)红外图像;(c) DenseNet; (d) LatLRR; (e) VGG; (f) ResNet; (g) VSM; (h) QD; (i) GAN; (j)本文算法
Fig. 11. Fusion effects of different algorithms in blurred “Kaptein_1123” scene. (a) Visible image; (b) infrared image; (c) DenseNet; (d) LatLRR; (e) VGG; (f) ResNet; (g) VSM; (h) QD; (i) GAN; (j) proposed algorithm
图 12. 不同算法对模糊场景Heather的融合效果。(a)可见光图像;(b)红外图像; (c) DenseNet; (d) LatLRR; (e) VGG; (f) ResNet; (g) VSM; (h) QD; (i) GAN; (j)本文算法
Fig. 12. Fusion effects of different algorithms in blurred “Heather” scene. (a) Visible image; (b) infrared image; (c) DenseNet; (d) LatLRR; (e) VGG; (f) ResNet; (g) VSM; (h) QD; (i) GAN; (j) proposed algorithm
图 13. 本文算法对其他场景的融合效果。(a) Steamer; (b) Bunker; (c) Street; (d) Jeep; (e) Soldier
Fig. 13. Fusion results of proposed algorithm in other scenes. (a) Steamer; (b) Bunker; (c) Street; (d) Jeep; (e) Soldier
表 1全卷积模块的参数信息
Table1. Parameter information of fully convolutional block
|
表 2不同融合方法的客观评价结果
Table2. Objective evaluation results of different fusion methods
|
卢鑫, 杨林, 李敏, 张学武. 基于Tikhonov正则化和细节重建的红外与可见光图像融合方法[J]. 光学学报, 2020, 40(2): 0210001. Xin Lu, Lin Yang, Min Li, Xuewu Zhang. Infrared and Visible Image Fusion Method Based on Tikhonov Regularization and Detail Reconstruction[J]. Acta Optica Sinica, 2020, 40(2): 0210001.
PDF全文
