Visible to the public Adaptive Subpixel Mapping Based on a Multiagent System for Remote-Sensing Imagery

TitleAdaptive Subpixel Mapping Based on a Multiagent System for Remote-Sensing Imagery
Publication TypeJournal Article
Year of Publication2014
AuthorsXiong Xu, Yanfei Zhong, Liangpei Zhang
JournalGeoscience and Remote Sensing, IEEE Transactions on
Date PublishedFeb
Keywordsadaptive subpixel mapping framework, adaptive subpixel mapping technique, Algorithm design and analysis, artificial images, back-propagation neural network, boundary-mixed pixel, class abundance, class labels, coarser spectrally unmixed fraction images, decision agents, feature detection agent kinds, feature extraction, fine-resolution map, geophysical image processing, hard classification method, identical mixed pixel type, image classification, linear subpixel, mixed pixel problem, mixed pixel structure reconstruction, multi-agent systems, multiagent subpixel mapping framework, multiagent system, neural nets, remote sensing, remote-sensing image classification, remote-sensing imagery, soft classification, spatial attraction model, spectral unmixing techniques, subpixel mapping accuracy, subpixel mapping agents, subpixel mapping algorithm performance, subpixel mapping problem, subpixel spatial attribution, synthetic remote-sensing images, traditional subpixel mapping algorithms

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. Experiments with artificial images and synthetic remote-sensing images were performed to evaluate the performance of the proposed 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.

Citation Key6479297