Multilayer Perceptron-Based Phenological and Radiometric Normalization for High-Resolution Satellite Imagery

Abstract

Radiometric normalization is an essential preprocessing step that must be performed to detect changes in multi-temporal satellite images and, in general, relative radiometric normalization is utilized. However, most relative radiometric normalization methods assume a linear relationship and they cannot take into account nonlinear properties, such as the distribution of the earth's surface or phenological differences that are caused by the growth of vegetation. Thus, this paper proposes a novel method that assumes a nonlinear relationship and it uses a representative nonlinear regression model-multilayer perceptron (MLP). The proposed method performs radiometric resolution compression while considering both the complexity and time cost, and radiometric control set samples are extracted based on a no-change set method. Subsequently, the spectral index is selected for each band to compensate for the phenological properties, phenological normalization is performed based on MLP, and the global radiometric properties are adjusted through postprocessing. Finally, a performance evaluation is conducted by comparing the results herein with those from conventional relative radiometric normalization algorithms. The experimental results show that the proposed method outperforms conventional methods in terms of both visual inspection and quantitative evaluation. In other words, the applicability of the proposed method to the normalization of multi-temporal images with nonlinear properties is confirmed. Relative radiometric normalization, on the other hand, is an image-based normalization method that selects one image as a reference and matches the radiometric characteristics of a subject image [13,14]. That is, relative radiometric normalization is generally utilized since the multi-temporal images are normalized into common scales without extra parameters [12,15].Relative radiometric normalization can be classified into two categories: a global statistics-based method and a radiometric control set sample (RCSS)-based method. The former is performed by using statistical values of all pixels in the image, which includes histogram matching, minimum-maximum (MM), mean-standard deviation (MS), and simple regression (SR) [15,16]. In contrast, the latter is based on invariant pixels, known as RCSSs, which include dark set-bright set (DB), pseudo invariant features (PIF), and no-change sets (NC) [17][18][19][20]. At this time, except for histogram matching, normalization is performed through regression equations, while assuming a linear relationship between the pixels at the same position in each band [21]. However, most remote sensing data are nonlinearly distributed, and the surface of the earth is composed of a complex mixture of natural and man-made features that exhibit nonlinear characteristics [22][23][24]. Changes that are caused by vegetation in particular have the most typical characteristics, including nonlinearity, which induces serious disturbances when change detection is performed [25,26]. In addition, since optical sa...

Performance Evaluation of Two Machine Learning Techniques in Heating and Cooling Loads Forecasting of Residential Buildings

“…The schematic of the MLP structure is shown in Figure 1, which illustrates a nonlinear mapping between the input vector and the output vector [35]. The neurons are connected through weights, and output signals are generated by a nonlinear transfer function [36].…”

A Learning-Based Image Fusion for High-Resolution SAR and Panchromatic Imagery

“…Conventional image-fusion methods use only the pixel values of SAR and panchromatic images. However, in general, the gray level of single pixels is not informative; therefore, additional information other than the pixel values is necessary [38,39]. To ensure that abundant information is considered, this study uses texture information.…”

Integrated Preprocessing of Multitemporal Very-High-Resolution Satellite Images via Conjugate Points-Based Pseudo-Invariant Feature Extraction

“…In general, RRN is classified into global statistical (GS) and radiometric control set sample (RCSS) methods [36,42]. The GS method uses the brightness value of all the pixels in the image [36,42], whereas the RCSS method uses the selected invariant features between images [8,39].…”

“…In general, RRN is classified into global statistical (GS) and radiometric control set sample (RCSS) methods [36,42]. The GS method uses the brightness value of all the pixels in the image [36,42], whereas the RCSS method uses the selected invariant features between images [8,39]. When the images exhibit similar radiometric characteristics, the GS method can rapidly and simply minimize the difference in brightness values between images [43,44].…”