Adaptive artificial bee colony based parameter selection for subpixel mapping multiagent system in remote-sensing imagery

Abstract

Remote sensing has become an important source of land use/cover information at a range of spatial and temporal scales. The existence of mixed pixels is a major problem in remote-sensing image classification. Although the soft classification and spectral unmixing techniques can obtain an abundance of different classes in a pixel to solve the mixed pixel problem, the subpixel spatial attribution of the pixel will still be unknown. The subpixel mapping technique can effectively solve this problem by providing a fine-resolution map of class labels from coarser spectrally unmixed fraction images. However, most traditional subpixel mapping algorithms treat all mixed pixels as an identical type, either boundary-mixed pixel or linear subpixel, leading to incomplete and inaccurate results. To improve the subpixel mapping accuracy, this paper proposes an adaptive subpixel mapping framework based on a multiagent system for remote sensing imagery. In the proposed multiagent subpixel mapping framework, three kinds of agents, namely, feature detection agents, subpixel mapping agents and decision agents, are designed to solve the subpixel mapping problem. This confirms that MASSM is appropriate for the subpixel mapping of remote-sensing images. But the major problem is that the selection of the parameters becomes assumption in order to overcome these problems proposed work focus on adaptive selection of parameters based on the optimization methods, it automatically selects the parameters value in the classification, and it improves the classification results in the remote-sensing imagery. Experiments with artificial images and synthetic remote-sensing images were performed to evaluate the performance of the proposed artificial bee colony based optimization subpixel mapping algorithm in comparison with the hard classification method and other subpixel mapping algorithms: subpixel mapping based on a back-propagation neural network and the spatial attraction model. The experimental results indicate that the proposed algorithm outperforms the other two subpixel mapping algorithms in reconstructing the different structures in mixed pixels.