In this paper, a new multicriterion segmentation method has been proposed to be applied to satellite image of very high spatial resolution (VHSR). It is consisted of the following process: For each region of the grayscale image, a center of gravity has been calculated and it has been also selected a threshold for its histogram. According to a certain criteria, this approach has been based on the separation of the different classes of grayscale in an optimal way. The proposed approach has been tested on synthetic images, and then has applied to an urban environment for the classification of data in Quickbird images. The selected zone of study has been laid in Skhirate-Témara province, northwest of Morocco. Which is based on the Levine and Nazif criterion, this segmentation technique has given promising results compared those obtained using OTSU and K-means methods.

The article describes a new method of threshold satellite image, based on the optimization multi-objective for segmentation of Worldview images and funded on the Tsallis and the Rényi entropies, allowing the evolution of the satellite image classification. Owing to the goal of achieving a large classifying all unclassified pixels by the previous method in 2017 in our research laboratory. An improved analysis and a multi-objective optimized thresholding method was proposed. Firstly, we are calculate the optimal thresholds with respect to the criteria retained such as the Tsallis criterion and the Rényi criterion. Lastly, we are challenging the performance of our method to that developed previously in 2017. The new method effectiveness evaluation confirmed by the calculation of the evaluation criterion related on both the Levine and Nazif criterion and the Mean Squared Error criterion. The results obtained by our approach were very satisfactory. It was been shown that the method overcomes the difficulties of the method previously developed in 2017 and obtained results that are more precise. In particular, for synthetic images, the segmentation accuracy increases by 81.16% and for the satellite images, the segmentation also improves enormously, and the accuracy of the overall classification of Worldview images increases by 97.21%. Therefore, the new method based on multi-objective optimization contribute significantly to performance.

No abstract