Distortion Robust Relative Radiometric Normalization of Multitemporal and Multisensor Remote Sensing Images Using Image Features

• Published in: IEEE transactions on geoscience and remote sensing Vol. 60; pp. 1 - 20
• Main Authors: Moghimi, Armin, Sarmadian, Amin, Mohammadzadeh, Ali, Celik, Turgay, Amani, Meisam, Kusetogullari, Huseyin
• Format: Journal Article
• Language: English
• Published: New York IEEE 2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Change detection; Conditional probabilities; Conditional probability; Data acquisition; feature detection; Feature extraction; feature matching; Histograms; Illumination invariant; Image enhancement; image matching; Image sensors; Interpolation; Land cover; Land use; Land use/land cover; Linear regression; Multi sensor images; Multi-temporal data; Multisensor remote sensing; Probability theory; Radiometry; Registration methods; relative radiometric normalization; Remote sensing; rotation invariant; Satellite broadcasting; scale invariant; Sensors; Statistical analysis; Textures
• ISSN: 0196-2892; 1558-0644; 1558-0644
• DOI: 10.1109/TGRS.2021.3063151

In this article, we propose a novel framework to radiometrically correct unregistered multisensor image pairs based on the extracted feature points with the KAZE detector and the conditional probability (CP) process in the linear model fitting. In this method, the scale, rotation, and illumination invariant radiometric control set samples (SRII-RCSS) are first extracted by the blockwise KAZE strategy. They are then distributed uniformly over both textured and texture-less land use/land cover (LULC) using grid interpolation and a set of nearest-neighbors. Subsequently, SRII-RCSS are scored by a similarity measure, and the histogram of the scores is then used to refine SRII-RCSS. The normalized subject image is produced by adjusting the subject image to the reference image using the CP-based linear regression (CPLR) based on the optimal SRII-RCSS. The registered normalized image is finally generated by registration of the normalized subject image to the reference image through a two-pass registration method, namely affine-B-spline and, then, it is enhanced by updating the normalization coefficient of CPLR based on the SRII-RCSS. In this study, eight multitemporal data sets acquired by inter/intra satellite sensors were used in tests to comprehensively assess the efficiency of the proposed method. Experimental results show that the proposed method outperforms the existing state-of-the-art relative radiometric normalization (RRN) methods both qualitatively and quantitatively, indicating its capability for RRN of unregistered multisensor image pairs.