A new model for automatic normalization of multitemporal satellite images using Artificial Neural Network and mathematical methods

• Published in: Applied mathematical modelling Vol. 37; no. 9; pp. 6437 - 6445
• Main Authors: Sadeghi, Vahid, Ebadi, Hamid, Ahmadi, Farshid Farnood
• Format: Journal Article
• Language: English
• Published: Elsevier Inc 01.05.2013
• Subjects: Adjustment; Architecture; Artificial Neural Network; Artificial neural networks; Change Vector Analysis (CVA); Learning theory; Mathematical models; Multi-temporal satellite images; Neural networks; Pixels; Principal Component Analysis (PCA); Relative Radiometric Normalization; Change Vector Analysis (CVA); Relative Radiometric Normalization; Principal Component Analysis (PCA); Artificial Neural Network; Multi-temporal satellite images
• DOI: 10.1016/j.apm.2013.01.006
• ISSN: 0307-904X

Relative Radiometric Normalization is often required in remote sensing image analyses particularly in the land cover change detection process. Normalization process minimizes the radiometric differences between two images caused by inequalities in the acquisition conditions rather than changes in surface reflectance. A wide range of RRN methods have been developed to adjust linear models. This paper proposes an automated Relative Radiometric Normalization (RRN) method to adjust a non-linear model based on an Artificial Neural Network (ANN) and unchanged pixels. The proposed method includes the following stages: (1) automatic detection of unchanged pixels based on a new idea that uses CVA (Change Vector Análysis) method, PCA (Principal Component Analysis) transformation and K-means clustering technique, (2) evaluation of different architectures of perceptron neural networks to find the best architecture for this specific task and (3) use of the aforementioned network for normalizing the subject image. The method has been implemented on two images taken by the TM sensor. Experimental results confirm the effectiveness of the presented technique in the automatic detection of unchanged pixels and minimizing imaging condition effects (i.e., atmosphere and other effective parameters).