Supervised spatio-spectral classification of fused images using superpixels

Karen Sanchez; Carlos Hinojosa; Henry Arguello

doi:10.1364/AO.58.0000B9

Applied Optics
Vol. 58,
Issue 7,
pp. B9-B18
(2019)
•https://doi.org/10.1364/AO.58.0000B9

Supervised spatio-spectral classification of fused images using superpixels

Karen Sanchez, Carlos Hinojosa, and Henry Arguello

Not Accessible

Your library or personal account may give you access

Get PDF
Email
Share
Get Citation
Copy Citation Text
Karen Sanchez, Carlos Hinojosa, and Henry Arguello, "Supervised spatio-spectral classification of fused images using superpixels," Appl. Opt. 58, B9-B18 (2019)

Export Citation
- BibTex
- Endnote (RIS)
- HTML
- Plain Text
Citation alert
Save article

Check for updates

Abstract

The low spatial resolution of hyperspectral (HS) images generally limits the classification accuracy. Therefore, different multiresolution data fusion techniques have been proposed in the literature. In this paper, a method for supervised classification of spectral images from data fusion measurements is proposed. Specifically, the proposed approach exploits the spatial information of an RGB image by grouping pixels with similar characteristics into superpixels and fuses such features with the spectral information of an HS image. Simulations results on three datasets show that the proposed classification method improves the overall accuracy and reduces the computational complexity compared to the traditional approach that first performs the fusion followed by the classification.

Full Article | PDF Article

More Like This

C-3SPCD: coded aperture similarity constrained design for spatio-spectral classification of single-pixel measurements

Carlos Hinojosa, Karen Sanchez, Hans Garcia, and Henry Arguello
Appl. Opt. 61(8) E21-E32 (2022)

Multifocus image fusion using superpixel segmentation and superpixel-based mean filtering

Junwei Duan, Long Chen, and C. L. Philip Chen
Appl. Opt. 55(36) 10352-10362 (2016)

Context guided belief propagation for remote sensing image classification

Tiancan Mei, Le An, and Bir Bhanu
Appl. Opt. 54(11) 3372-3382 (2015)

Previous Article Next Article

Cited By

You do not have subscription access to this journal. Cited by links are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access Optica Member Subscription

Figures (7)

You do not have subscription access to this journal. Figure files are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access Optica Member Subscription

Tables (4)

You do not have subscription access to this journal. Article tables are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access Optica Member Subscription

Equations (19)

You do not have subscription access to this journal. Equations are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access Optica Member Subscription

Class	FULL		GSA		MAP-SMM		PROPOSED
Class	SVM	KNN	SVM	KNN	SVM	KNN	SVM	KNN
Asphalt	86.41	76.48	97.04	81.00	94.94	82.40	96.10	96.28
Meadows	95.75	94.74	98.89	95.47	97.79	94.28	99.04	99.60
Gravel	69.18	62.34	87.34	66.72	82.93	70.83	90.40	96.61
Trees	91.51	83.74	94.07	85.96	91.91	74.66	74.39	77.81
Metal sheets	99.40	99.43	99.87	99.92	99.00	98.90	99.16	99.27
Bare soil	61.19	55.81	87.59	70.90	82.13	66.00	92.46	99.44
Bitumen	72.41	79.02	94.73	76.27	95.08	80.56	98.70	98.06
Bricks	76.53	77.89	93.03	76.58	91.60	79.32	93.34	93.39
Shadows	95.81	94.91	97.56	98.89	95.73	94.02	95.80	96.60
AA	83.13	80.48	94.46	83.52	92.34	82.33	93.27	95.23
OA	86.24	83.01	95.69	86.11	93.68	84.85	95.00	96.66
Kappa	0.8164	0.7731	0.9429	0.8158	0.9162	0.7985	0.9337	0.9559
Time	16.7052	23.9618	16.5859	25.1008	27.0535	38.1522	10.8399	6.8039

Class	FULL		GSA		MAP-SMM		PROPOSED
Class	SVM	KNN	SVM	KNN	SVM	KNN	SVM	KNN
Water	99.97	99.97	99.98	99.99	99.98	99.98	99.96	100
Trees	93.75	89.98	97.54	94.25	95.15	93.41	97.27	98.56
Meadows	86.27	87.58	95.95	92.02	87.16	87.27	93.07	97.37
Bricks	77.20	74.01	92.45	89.97	91.01	82.88	99.48	97.55
Bare soil	95.94	94.87	97.23	97.50	97.34	92.92	99.38	98.85
Asphalt	91.69	86.24	97.40	94.34	95.39	90.30	97.13	99.29
Bitumen	92.54	90.46	97.59	93.89	87.43	92.02	99.07	98.56
Tile	99.63	99.15	99.67	99.85	99.58	99.20	99.57	99.93
Shadows	96.70	94.32	98.32	99.55	90.97	98.29	90.68	99.10
AA	92.63	90.73	97.35	95.71	93.78	92.92	97.29	98.80
OA	97.74	96.84	99.11	98.54	98.00	97.51	99.13	99.62
Kappa	0.9680	0.9552	0.9874	0.9794	0.9716	0.9647	0.9877	0.9946
Time	35.5553	180.1488	54.4082	359.6640	58.2847	353.3343	10.9937	7.3261

Class	FULL		GSA		MAP-SMM		PROPOSED
Class	SVM	KNN	SVM	KNN	SVM	KNN	SVM	KNN
Broccoli-green-1	98.83	99.00	99.48	98.13	99.47	99.74	100	99.86
Broccoli-green-2	99.23	99.10	99.91	99.78	99.33	99.12	99.80	99.60
Fallow	99.24	97.07	99.76	95.07	99.91	93.85	99.78	99.78
Fallow-rough-plow	98.86	99.52	98.09	98.39	98.58	98.87	99.65	99.57
Fallow-smooth	99.35	96.59	98.98	95.63	98.19	93.10	98.90	98.95
Stubble	99.83	99.70	99.99	99.86	99.86	99.50	99.92	99.79
Celery	99.47	99.41	99.48	98.96	99.08	98.61	99.75	99.60
Grapes-untrained	83.21	76.73	92.60	77.52	90.71	73.89	91.51	99.72
Soil-vineyard-develop	99.50	98.77	99.99	99.46	99.82	98.96	99.94	99.80
Corn-senesced-green-weeds	96.29	93.34	98.32	91.73	97.71	90.53	98.28	98.67
Lettuce-romaine-4wk	97.80	98.25	97.88	89.79	97.45	88.56	97.95	98.93
Lettuce-romaine-5wk	99.83	99.65	99.97	98.42	99.90	98.65	98.72	99.49
Lettuce-romaine-6wk	98.01	97.74	98.67	97.93	97.38	96.59	96.56	92.35
Lettuce-romaine-7wk	96.63	94.51	98.90	94.92	96.80	93.27	95.63	90.88
Vineyard-untrained	66.45	67.07	78.71	66.90	76.90	65.61	78.98	99.28
Vineyard-vertical-trellis	98.76	97.63	97.90	96.38	98.86	95.99	99.02	98.88
AA	95.71	94.63	97.42	93.68	96.87	92.80	97.15	98.45
OA	91.29	89.47	95.17	89.20	94.34	87.86	94.93	99.21
Kappa	0.9030	0.8828	0.9462	0.8797	0.9369	0.8649	0.9435	0.9912
Time	33.4255	17.9035	34.4387	18.8947	35.4682	18.4208	5.4616	1.4140

Class	FULL		GSA		MAP-SMM		PROPOSED
Class	SVM	KNN	SVM	KNN	SVM	KNN	SVM	KNN
Asphalt	86.41	76.48	97.04	81.00	94.94	82.40	96.10	96.28
Meadows	95.75	94.74	98.89	95.47	97.79	94.28	99.04	99.60
Gravel	69.18	62.34	87.34	66.72	82.93	70.83	90.40	96.61
Trees	91.51	83.74	94.07	85.96	91.91	74.66	74.39	77.81
Metal sheets	99.40	99.43	99.87	99.92	99.00	98.90	99.16	99.27
Bare soil	61.19	55.81	87.59	70.90	82.13	66.00	92.46	99.44
Bitumen	72.41	79.02	94.73	76.27	95.08	80.56	98.70	98.06
Bricks	76.53	77.89	93.03	76.58	91.60	79.32	93.34	93.39
Shadows	95.81	94.91	97.56	98.89	95.73	94.02	95.80	96.60
AA	83.13	80.48	94.46	83.52	92.34	82.33	93.27	95.23
OA	86.24	83.01	95.69	86.11	93.68	84.85	95.00	96.66
Kappa	0.8164	0.7731	0.9429	0.8158	0.9162	0.7985	0.9337	0.9559
Time	16.7052	23.9618	16.5859	25.1008	27.0535	38.1522	10.8399	6.8039

Class	FULL		GSA		MAP-SMM		PROPOSED
Class	SVM	KNN	SVM	KNN	SVM	KNN	SVM	KNN
Water	99.97	99.97	99.98	99.99	99.98	99.98	99.96	100
Trees	93.75	89.98	97.54	94.25	95.15	93.41	97.27	98.56
Meadows	86.27	87.58	95.95	92.02	87.16	87.27	93.07	97.37
Bricks	77.20	74.01	92.45	89.97	91.01	82.88	99.48	97.55
Bare soil	95.94	94.87	97.23	97.50	97.34	92.92	99.38	98.85
Asphalt	91.69	86.24	97.40	94.34	95.39	90.30	97.13	99.29
Bitumen	92.54	90.46	97.59	93.89	87.43	92.02	99.07	98.56
Tile	99.63	99.15	99.67	99.85	99.58	99.20	99.57	99.93
Shadows	96.70	94.32	98.32	99.55	90.97	98.29	90.68	99.10
AA	92.63	90.73	97.35	95.71	93.78	92.92	97.29	98.80
OA	97.74	96.84	99.11	98.54	98.00	97.51	99.13	99.62
Kappa	0.9680	0.9552	0.9874	0.9794	0.9716	0.9647	0.9877	0.9946
Time	35.5553	180.1488	54.4082	359.6640	58.2847	353.3343	10.9937	7.3261

Abstract

Cited By

Figures (7)

Tables (4)

Equations (19)

Applied Optics