6802 IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, VOL. 53, NO. 12, DECEMBER 2015
However, we are aware that the EBSPTM and EBSCDL
methods, by addressing the dictionary perturbation with an
error bound regularization, consistently outperform their
counterparts, which confirms the superiority of the proposed
methods. Moreover, we have also validated that the error-
bound-regularized method is effective for natural image
super-resolution, which we will discuss in another paper. Other
applications with this technique, such as image classification
and imag e detection, will also be attempted in the future.
A
CKNOWL EDGMENT
The authors would like to thank the anonymous reviewers
for their insightful comments that have been very helpful in
improving this paper.
R
EFERENCES
[1] S. Li, “Multisensor remote sensing image fusion using stationary wavelet
transform: Effects of basis and depth,” Int. J. Wavelets Multir esol. Inf.
Process., vol. 6, no. 1, pp. 37–50, Jan. 2008.
[2] B. Huang, J. Wang, H. Song, D. Fu, and K. Wong, “Generating high spa-
tiotemporal resolution land surface temperature for urban heat island mon-
itoring,” IEEE Geosci. Remote Sens. Lett., vol. 10, no. 5, pp.1011–1015,
Sep. 2013.
[3] J. G. Masek et al., “North American forest disturbance mapped from
a decadal landsat record,” Remote Sens. Environ., vol. 112, no. 6,
pp. 2914–2926, Jun. 2008.
[4] C. E. Woodcock and M. Ozdogan, “Trends in land cover mapping and
monitoring,” in Land Change Science, G. Gutman, Ed. New York,
NY, USA: Springer-Verlag, 2004, pp. 367–377.
[5] D. Lu, P. Mausel, E. Brondízio, and E. Moran, “Change detection tech-
niques,” Int. J . Remote Sens., vol. 25, no. 12, pp. 2365–2407, Jun. 2004.
[6] F. Gao, J. Masek, M. Schwaller, and F. Hall, “On the blending of
the landsat and modis surface reflectance: Predicting daily landsat sur-
face reflectance,” IEEE Trans. Geosci. Remote Sens., vol. 44, no. 8,
pp. 2207–2218, Aug. 2006.
[7] T. Hilker et al., “Generation of dense time series synthetic landsat data
through data blending with MODIS using a spatial and temporal adap-
tive reflectance fusion model,” Remote Sens. Environ., vol. 113, no. 8,
pp. 1988–1999, Sep. 2009.
[8] H. Shen et al., “A spatial and temporal reflectance fusion model consider-
ing sensor observation differences,” Int. J. Remote Sens., vol. 34, no. 12,
pp. 4367–4383, Jun. 2013.
[9] X. Zhu, J. Chen, F. Gao, X. H. Chen, and J. G. Masek, “An enhanced spa-
tial and temporal adaptive reflectance fusion model for complex heteroge-
neous regions,” Remote Sens. Environ., vol. 114, no. 11, pp. 2610–2623,
Nov. 2010.
[10] B. Huang and H. Song, “Spatiotemporal reflectance fusion via sparse
representation,” IEEE Trans. Geosci. Remote Sens., vol. 50, no. 10,
pp. 3707–3716, Oct. 2012.
[11] S. Shekhar, V. M. Patel, H. V. Nguyen, and R. Chellappa, “Gen-
eralized domain-adapti ve dictionaries,” in Proc. IEEE CVPR, 2013,
pp. 361–368.
[12] J. Quiñonero-Candela, M. Sugiyama, A. Schwaighofer, and
N. D. Lawrence, Dataset Shift in Machine Learning. Cambridge, MA,
USA: MIT Press, 2009.
[13] M. Sugiyama, M. Krauledat, and K. R. Müller, “Covariate shift adaptation
by importance weighted cross validation,” J. Mach. Learn. Res.,vol.8,
pp. 985–1005, Dec. 2007.
[14] D. Tuia, E. Pasolli, and W. J. Emery, “Using acti ve learning to adapt
remote sensing image classifiers,” Remote Sens. Environ., vol. 115,
no. 9, pp. 2232–2242, Sep. 2010.
[15] S. Chandrasekaran, B. G. Golub, M. Gu, and A. H. Sayed, “Parameter
estimation in the presence of bounded data uncertainties,” SIAM J. Matrix
Anal. A., vol. 19, no. 1, pp. 235–252, 1998.
[16] H. Zhou and T. Hastie, “Regularization and variable selection via the
elastic net,” J. R. Stat. Soc. B., vol. 57, Part 2, pp. 301–320, 2005.
[17] K. Kavukcuoglu, M. Ranzato, R. Fergus, and Y. Le-Cun, “Learning in-
variant features through topographic filter maps,” in
Proc. IEEE Conf.
Compute. Vis. Pattern Recog., 2009, pp. 1605–1612.
[18] J. Yang, J. Wright, T. Huang, and Y. Ma, “Image super-resolution via
sparse representation,” IEEE Trans. Image Process., vol. 19, no. 11,
pp. 2861–2873, Nov. 2010.
[19] S. Wang, L. Zhang, Y. Liang, and Q. Pan, “Semi-coupled dictionary
learning with applications to image super-resolution and photo-sketch
synthesis,” in Proc. IEEE Conf. CVPR, 2012, pp. 2216–2223.
[20] M. Aharon, M. Elad, and A. Bruckstein, “K-SVD: An algorithm for de-
signing overcomplete dictionaries for sparse representation,” IEEE Trans.
Signal Process., vol. 54, no. 11, pp. 4311–4322, Nov. 2006.
[21] A. Beck and M. Teboulle, “A fast iterative shrinkage-thresholding al-
gorithm for linear inverse problems,” SIAM J. Image Sci., vol. 2, no. 1,
pp. 183–202, Mar. 2009.
[22] B. Efron, T. Hastie, I. Johnstone, and R. Tibshirani, “Least angle regres-
sion,” Ann. Stat., vol. 32, no. 2, pp. 407–499, 2004.
[23] J. Mairal, SPAMS: A SPArse Modeling Software, v2.4. [Online].
Av ailable: http://spams-devel.gforge.inria.fr/doc/doc_spams.pdf
[24] A. Gretton, K. M. Borgwardt, M. J. Rasch, B. Scholkopf, and A. A. Smola,
“A kernel two-sample test,” J. Mach. Learn. Res., vol. 13, no. 3,
pp. 727–773, Mar. 2012.
[25] B. Gong, K. Grauman, and F. Sha, “Connecting the dots with landmarks:
Discriminativ ely learning domain invariant features for unsupervised do-
main adaptation,” in Proc. 30th Int. Conf. Mach. Learn., Atlanta, GA,
USA, 2013, pp. 222–230.
[26] B. K. Sriperumbudur, A. Gretton, K. Fukumizu, B. Scholkopf, and
G. R. G. Lanckriet, “Hilbert space embeddings and metrics on proba-
bility measures,” J. Mach. Learn. Res., vol. 11, no. 4, pp. 1517–1561,
Apr. 2010.
[27] A. Gretton, K. M. Borgwardt, M. J. Rasch, B. Scholkopf, and
A. A. Smola, “A kernel method for the two-sample-problem,” in Proc.
Adv. NIPS, Vancouver, BC, Canada, 2006, pp. 513–520.
[28] Z. Wang, A. C. Bovik, and H. R. Sheikh, “Image quality assessment:
From error visibility to structural similarity,” IEEE Trans. Image Process.,
vol. 13, no. 4, pp. 600–612, Apr. 2004.
[29] A. C. Brooks, X. Zhao, and T. N. Pappas, “Structural similarity quality
metrics in a coding context: Exploring the space of realistic distortions,”
IEEE Trans. Image Process., vol. 17, no. 8, pp. 1261–1273, Aug. 2008.
[30] D. W. Zimmerman, “Teachers corner: A note on interpretation of the
paired-samples t test,” J. Educ. Behav. Stat., vol. 22, no. 3, pp. 349–360,
Autumn 1997.
Bo Wu received the Ph.D. degree in photogrammetry
and remote sensing from Wuhan University, Wuhan,
China, in 2006.
From 2007 to 2008, he was a Postdoctoral Re-
search Fellow with The Chinese University of Hong
Kong, Shatin, Hong Kong. In September 2008, he
joined the Ministry of Education Key Laboratory
of Spatial Data Mining and Information Sharing,
Fuzhou Univ ersity, Fuzhou, China, as an Associate
Professor. He is currently a Full T ime Professor with
Fuzhou University. He is the author of more than
40 research papers. His current research interests include image processing,
spatiotemporal statistics, and machine learning, with applications in remote
sensing.
Bo Huang (A’12–M’13) From 2001 to 2004,
he held a faculty position with the Department of
Ci vil Engineering, National University of Singapore,
Singapore, and from 2004 to 2006, with the Schulich
School of Engineering, Uni versity of Calgary ,
Calgary, AB, Canada. He is currently a Professor
with the Department of Geography and Resource
Management and the Associate Director of the In-
stitute of Space and Earth Information Science, The
Chinese Uni versity of Hong Kong, Shatin, Hong
Kong. His research interests include most aspects
of geoinformation science, specifically spatiotemporal image fusion for envi-
ronmental monitoring, spatial/spatiotemporal statistics for land cover/land use
change modeling, and spatial optimization for sustainable urban and land use
planning.