Underwater Polarization Image Fusion Based on NSST and Adaptive SPCNN

Jinqiang Yu; Jin Duan; Weimin Chen; Suxin Mo; Yingchao Li; Yu Chen

doi:10.3788/LOP57.061006

Journals >Laser & Optoelectronics Progress >Volume 57 >Issue 6 >Page 061006 > Article

Laser & Optoelectronics Progress
Vol. 57, Issue 6, 061006 (2020)

Underwater Polarization Image Fusion Based on NSST and Adaptive SPCNN

Jinqiang Yu¹, Jin Duan^1、*, Weimin Chen¹, Suxin Mo¹, Yingchao Li², and Yu Chen¹

Author Affiliations

¹School of Electronic and Information Engineering, Changchun University of Science and Technology, Changchun, Jilin 130022, China

²Institute of Space Optoelectronic Technology, Changchun University of Science and Technology, Changchun, Jilin 130022, China

show less

DOI: 10.3788/LOP57.061006 Cite this Article Set citation alerts

Jinqiang Yu, Jin Duan, Weimin Chen, Suxin Mo, Yingchao Li, Yu Chen. Underwater Polarization Image Fusion Based on NSST and Adaptive SPCNN[J]. Laser & Optoelectronics Progress, 2020, 57(6): 061006 Copy Citation Text

show less

Fig. 1. NSST decomposition diagram

Download full size

Fig. 2. Architecture of the SPCNN model

Download full size

Fig. 3. Block diagram of polarization image fusion

Download full size

Fig. 4. Diagrams of collecting underwater polarization images. (a) Principle block diagram; (b) scene diagram

Download full size

Fig. 5. Polarization characteristic images of different objects. (a) I images; (b) Q images; (c) U images; (d) G images; (e) D images

Download full size

Fig. 6. Objective evaluation results of different decomposition layers in fusion based on NSST

Download full size

Fig. 7. Fused images of various algorithms in four sets of experiments. (a) Method 1; (b) method 2; (c) method 3; (d) method 4; (e) method 5; (f) method 6;(g) method 7; (h) method 8; (i) method 9; (j) method 10; (k) method 11; (l) proposed method

Download full size

Evaluation index	NSP	Group 1	Group 2	Group 3	Group 4
SD	‘9-7’	71.7938	53.1231	29.0225	66.9654
	‘maxflat’	71.8146	53.1387	29.0338	66.9632
	‘pyr’	71.8254	53.1452	29.0427	66.9846
	‘pyrexc’	71.8362	53.1464	29.0425	66.9828
EN	‘9-7’	7.2876	7.1927	6.6413	7.8472
	‘maxflat’	7.2989	7.1942	6.6427	7.8501
	‘pyr’	7.3034	7.1051	6.6453	7.8526
	‘pyrexc’	7.3065	7.1053	6.6484	7.8523
Q^abf	‘9-7’	0.6853	0.7615	0.7516	0.5803
	‘maxflat’	0.6726	0.7643	0.7527	0.5812
	‘pyr’	0.6878	0.7679	0.7531	0.5849
	‘pyrexc’	0.6876	0.7682	0.7548	0.5846
MI	‘9-7’	4.1395	4.0072	0.5815	4.2157
	‘maxflat’	4.1428	4.0096	0.5826	4.2213
	‘pyr’	4.1463	4.0117	0.5843	4.2391
	‘pyrexc’	4.1478	4.0128	0.5846	4.2387

Table 1. Objective evaluation results of different pyramid filters in fusion based on NSST

Evaluation index	Method 1	Method 2	Method 3	Method 4	Method 5	Method 6
SD	56.6778	44.3967	61.1142	45.0537	44.2578	57.4242
EN	6.7723	6.2663	6.8461	6.7132	6.3059	7.3089
Q^abf	0.5202	0.3804	0.5115	0.1963	0.3671	0.4375
MI	3.3614	3.2694	3.4411	2.1876	3.5395	3.7182
Evaluation index	Method 7	Method 8	Method 9	Method 10	Method 11	Proposed method
SD	71.0913	57.8436	52.8640	72.6199	60.6569	71.8362
EN	6.8551	6.8714	6.9262	6.3219	6.4077	7.3065
Q^abf	0.6160	0.5863	0.3488	0.5945	0.6720	0.6876
MI	3.6226	3.1841	3.2632	2.8624	4.0556	4.1478

Table 2. Evaluation index values of the fused images by various algorithms in the first group of experiments

Evaluation index	Method 1	Method 2	Method 3	Method 4	Method 5	Method 6
SD	40.1386	28.9578	50.9480	29.8781	28.8215	48.4425
EN	6.6281	6.1723	6.7663	6.4704	6.1589	7.1111
Q^abf	0.6534	0.4433	0.6009	0.1836	0.4233	0.5153
MI	3.1491	3.1427	3.2822	1.6791	3.7706	2.8008
Evaluation index	Method 7	Method 8	Method 9	Method 10	Method 11	Proposed method
SD	39.5314	39.5314	39.9533	51.6194	43.2425	53.1464
EN	6.7439	6.7439	6.6291	5.9156	6.7210	7.1053
Q^abf	0.7271	0.7271	0.7438	0.5964	0.7248	0.7682
MI	3.5081	3.1834	3.4180	2.6834	3.7238	4.0128

Table 3. Evaluation index values of the fused images by various algorithms in the second group of experiments

Evaluation index	Method 1	Method 2	Method 3	Method 4	Method 5	Method 6
SD	24.6030	15.8382	27.7079	19.9809	15.7362	28.4300
EN	5.9118	5.3973	6.1907	5.7575	5.4024	6.4786
Q^abf	0.7552	0.3946	0.7525	0.4961	0.3708	0.3936
MI	1.6614	3.3193	2.1569	1.4321	3.3528	3.5814
Evaluation index	Method 7	Method 8	Method 9	Method 10	Method 11	Proposed method
SD	25.6820	21.8504	24.4234	28.1476	26.8165	29.0425
EN	5.9289	5.7622	5.9289	6.0147	5.7960	6.6484
Q^abf	0.7664	0.7017	0.7491	0.6860	0.6930	0.7548
MI	1.8397	2.3353	1.6062	2.0746	3.5282	4.1863

Table 4. Evaluation index values of the fused images by various algorithms in the third group of experiments

Evaluation index	Method 1	Method 2	Method 3	Method 4	Method 5	Method 6
SD	47.4696	37.8272	66.4415	39.1870	37.7084	51.4002
EN	7.2589	6.8949	7.6891	7.0276	6.9039	7.5925
Q^abf	0.4720	0.3749	0.4455	0.2700	0.3707	0.3161
MI	2.8271	3.8016	3.3755	2.8460	3.8673	2.0153
Evaluation index	Method 7	Method 8	Method 9	Method 10	Method 11	Proposed method
SD	51.4296	46.4801	45.9618	65.3107	63.6552	66.9828
EN	7.4264	7.2903	7.2644	7.6795	6.9369	7.8523
Q^abf	0.4537	0.4673	0.4369	0.5242	0.3981	0.5846
MI	3.0410	3.0871	2.5922	3.2463	3.9800	4.2387

Table 5. Evaluation index values of the fused images by various algorithms in the fourth group of experiments

Jinqiang Yu, Jin Duan, Weimin Chen, Suxin Mo, Yingchao Li, Yu Chen. Underwater Polarization Image Fusion Based on NSST and Adaptive SPCNN[J]. Laser & Optoelectronics Progress, 2020, 57(6): 061006

Download Citation

Set citation alerts for the article

Tools

Set citation alerts for the article

Save the article for my favorites

Paper Information