Superpixel-Based Stripe Noise Removal for Satellite Imageries
Abstract
This work introduces a novel noise removal algorithm for satellite imageries based on superpixel segmentation followed by statistics-based filtering. The algorithm worked in three main steps. First, the noisy input image was divided into subregions by employing simple linear iterative clustering (SLIC)-based superpixel segmentation. Then, the statistical property of each subregion was calculated, including their standard deviations and maximum values. Last, an adaptive statistics-based stripe noise removal was performed for each subregion by constructing adaptive filter sizes according to calculated properties. The algorithm was tested using real satellite imageries taken by the LAPAN-A2 and LAPAN-A3 satellites. Its performance was then compared to three existing methods in terms of image quality and computation speed. Extensive experiments on two datasets of 3-channel images captured by the LAPAN-A2 satellite showed that the algorithm was capable of reducing the stripe pattern as measured using the peak-signal-to-noise-ratio (PSNR) metric without introducing additional artifacts, which commonly appeared on over-corrected regions. Moreover, compared to existing methods, the proposed algorithm ran 42 to 103 times faster and provided better image quality by 2.46%, measured using the structural similarity metric (SSIM). The code of this work and the datasets used for the testing are publicly available on www.github.com/dancingpixel/SPSNR.
References
D. Wang et al., “SSRNet: In-Field Counting Wheat Ears Using Multi-Stage Convolutional Neural Network,” IEEE Trans. Geosci., Remote Sens., Vol. 60, pp. 1–11, 2022, doi: 10.1109/TGRS.2021.3093041.
X. Zhang et al., “Convective Clouds Extraction From Himawari–8 Satellite Images Based on Double-Stream Fully Convolutional Networks,” IEEE Geosc., Remote Sens. Lett., Vol. 17, No. 4, pp. 553–557, Apr. 2020, doi: 10.1109/LGRS.2019.2926402.
S. Lee and D. Shin, “On-Orbit Camera Misalignment Estimation Framework and Its Application to Earth Observation Satellite,” Remote Sens., Vol. 7, No. 3, pp. 3320–3346, Mar. 2015, doi:10.3390/rs70303320.
F.J. Meyer, J.B. Nicoll, and A.P. Doulgeris, “Correction and Characterization of Radio Frequency Interference Signatures in L-Band Synthetic Aperture Radar Data,” IEEE Trans. Geosci. Remote Sens., Vol. 51, No. 10, pp. 4961–4972, Oct. 2013, doi: 10.1109/TGRS.2013.2252469.
L. Zhuang and M.K. Ng, “Cross-Track Illumination Correction for Hyperspectral Pushbroom Sensors Using Total Variation and Sparsity Regularization,” 2020 IEEE 11th Sensor Array, Multichannel Signal Process. Workshop (SAM), 2020, pp. 1–5, doi: 10.1109/SAM48682.2020.9104285.
M. Amrouche, H. Carfantan, J. Idier, and V. Martin, “Statistical Destriping of Pushbroom-Type Images Based on an Affine Detector Response,” IEEE Trans. Geosci., Remote Sens., Vol. 60, pp. 1¬–14, Jul. 2022, doi: 10.1109/TGRS.2022.3195092.
B. Zhang et al., “Hyperspectral Image Stripe Detection and Correction Using Gabor Filters and Subspace Representation,” IEEE Geosci. Remote Sens. Lett., Vol. 19, pp. 1–5, 2022, doi: 10.1109/LGRS.2021.3061541.
Q. Wang, X. Ding, X. Tong, and P. M. Atkinson, “Real-Time Spatiotemporal Spectral Unmixing of MODIS Images,” ,” IEEE Trans. Geosci., Remote Sens., Vol. 60, pp. 1–16, 2022, doi: 10.1109/TGRS.2021.3108540.
W. Teng et al., “Classifier-Constrained Deep Adversarial Domain Adaptation for Cross-Domain Semisupervised Classification in Remote Sensing Images,” IEEE Geosci. Remote Sens. Lett., Vol. 17, No. 5, pp. 789¬–793, May 2020, doi: 10.1109/LGRS.2019.2931305.
Y. Chang, L. Yan, T. Wu, and S. Zhong, “Remote Sensing Image Stripe Noise Removal: From Image Decomposition Perspective,” IEEE Geosci. Remote Sens. Lett., Vol. 54, No. 12, pp. 7018–7031, Dec. 2016, doi: 10.1109/TGRS.2016.2594080.
Q. Zeng, H. Qin, X. Yan, and H. Zhou, “Fourier Spectrum Guidance for Stripe Noise Removal in Thermal Infrared Imagery,” IEEE Geosci. Remote Sens. Lett., Vol. 17, No. 6, pp. 1072–1076, Jun. 2020, doi: 10.1109/LGRS.2019.2938822.
M. Li et al., “A Novel Stripe Noise Removal Model for Infrared Images,” Sensors, Vol. 22, No. 8, pp.1–22, Apr. 2022, doi: 10.3390/s22082971.
J. Lin, H. Zuo, Y. Ye, and X. Liao, “Histogram-Based Autoadaptive Filter for Destriping NDVI Imagery Acquired by UAV-Loaded Multispectral Camera,” IEEE Geosci. Remote Sens. Lett., Vol. 16, No. 4, pp. 648–652, Apr. 2019, doi: 10.1109/LGRS.2018.2877728.
S. Banerjee and P. Shanmugam, “An Improved Method for Destriping of VIIRS Day/Night Band Images,” IEEE Access, Vol. 10, pp. 82164–82184, Jul. 2022, doi: 10.1109/ACCESS.2022.3194053.
Kamirul, P.R. Hakim, and S. Salaswati, “Statistical-based Stripe Noise Correction on LAPAN Microsatellite Imagery,” 2018 IEEE Int. Conf. Aerosp. Electron. Remote Sens. Technol. (ICARES), 2018, pp. 72–77, doi: 10.1109/ICARES.2018.8547079.
Kamirul, P.R. Hakim, and W. Hasbi, “An Adaptive Stripe Noise Removal Algorithm for Optical Satellite Imagery,” 2019 IEEE Int. Conf. Aerosp. Electron., Remote Sens. Technol. (ICARES), 2019, pp. 1–7, doi: 10.1109/ICARES.2019.8914344.
S. Subudhi, R.N. Patro, P.K. Biswal, and F. Dell’Acqua, “A Survey on Superpixel Segmentation as a Preprocessing Step in Hyperspectral Image Analysis,” IEEE J. Sel. Topics Appl. Earth Observ., Remote Sens., Vol. 14, pp. 5015–5035, Apr. 2021, doi: 10.1109/JSTARS.2021.3076005.
L. Yang et al., “Semisupervised Hyperspectral Image Classification via Superpixel-Based Graph Regularization with Local and Nonlocal Features,” IEEE J. Sel. Topics Appl. Earth Observ., Remote Sens., Vol. 15, pp. 6645–6658, Jul. 2022, doi: 10.1109/JSTARS.2022.3191692.
T. Ince, “Superpixel-Based Graph Laplacian Regularization for Sparse Hyperspectral Unmixing,” IEEE Geosci. Remote Sens. Lett., Vol. 19, pp. 1–5, 2022, doi: 10.1109/LGRS.2020.3027055.
M.-Y. Liu, O. Tuzel, S. Ramalingam and R. Chellappa, “Entropy-Rate Clustering: Cluster Analysis via Maximizing a Submodular Function Subject to a Matroid Constraint,” IEEE Trans. Pattern Anal., Mach. Intell., Vol. 36, No. 1, pp. 99–112, Jan. 2014, doi: 10.1109/TPAMI.2013.107.
J. Shen, Y. Du, W. Wang, and X. Li, “Lazy Random Walks for Superpixel Segmentation,” IEEE Trans. Image Process., Vol. 23, No. 4, pp. 1451–1462, Apr. 2014, doi: 10.1109/TIP.2014.2302892.
A. Levinshtein et al., “TurboPixels: Fast Superpixels Using Geometric Flows,” IEEE Trans. Pattern Anal., Mach. Intell., Vol. 31, No. 12, pp. 2290–2297, Dec. 2009, doi: 10.1109/TPAMI.2009.96.
Y. Yuan, Z. Zhu, H. Yu and W. Zhang, “Watershed-Based Superpixels with Global and Local Boundary Marching,” IEEE Trans. Image Process., Vol. 29, pp. 7375–7388, Jun. 2020, doi: 10.1109/TIP.2020.3002078.
R. Achanta et al., “SLIC Superpixels Compared to State-of-the-Art Superpixel Methods,” IEEE Trans. Pattern Anal., Mach. Intell., Vol. 34, No. 11, pp. 2274–2282, Nov. 2012, doi: 10.1109/TPAMI.2012.120.
Y.-J. Liu, M. Yu, B.-J. Li and Y. He, “Intrinsic Manifold SLIC: A Simple and Efficient Method for Computing Content-Sensitive Superpixels,” IEEE Trans. Pattern Anal., Mach. Intell., Vol. 40, No. 3, pp. 653–666, Mar. 2018, doi: 10.1109/TPAMI.2017.2686857.
Y. Zhou, L. Ju, and S. Wang, “Multiscale Superpixels and Supervoxels Based on Hierarchical Edge-Weighted Centroidal Voronoi Tessellation,” 2015 IEEE Winter Conf. Appl. Comput. Vis., 2015, pp. 1076–1083, doi: 10.1109/WACV.2015.148.
J. Wang et al., “A Sheared Low-Rank Model for Oblique Stripe Removal,” Appl. Math. Comput., Vol. 360, pp. 167–180, Nov. 2019, doi: 10.1016/j.amc.2019.03.066.
© Jurnal Nasional Teknik Elektro dan Teknologi Informasi, under the terms of the Creative Commons Attribution-ShareAlike 4.0 International License.
1.png)
