Advances in Engineering Advances in Engineering features breaking research judged by Advances in Engineering advisory team to be of key importance in the Engineering field. Papers are selected from over 10,000 published each week from most peer reviewed journals.
Pattern Recognition, Volume 46, Issue 11, November 2013, Pages 2902-2926.
Yanfei Zhong, Liangpei Zhang.
State Key Laboratory of Information Engineering in Surveying, Mapping, and Remote Sensing, Wuhan University, 129 Luoyu Road, Wuhan, Hubei province, PR China.
Abstract
A new sub-pixel mapping strategy inspired by the clonal selection theory in artificial immune systems (AIS), namely, the clonal selection sub-pixel mapping (CSSM) framework, is proposed for the sub-pixel mapping of remote sensing imagery, to provide detailed information on the spatial distribution of land cover within a mixed pixel. In CSSM, the sub-pixel mapping problem becomes one of assigning land-cover classes to the sub-pixels while maximizing the spatial dependence by the clonal selection algorithm. Each antibody in CSSM represents a possible sub-pixel configuration of the pixel. CSSM evolves the antibody population by inheriting the biological properties of human immune systems, i.e., cloning, mutation, and memory, to build a memory cell population with a diverse set of locally optimal solutions. Based on the memory cell population, CSSM outputs the value of the memory cell and finds the optimal sub-pixel mapping result. Based on the framework of CSSM, three sub-pixel mapping algorithms with different mutation operators, namely, the clonal selection sub-pixel mapping algorithm based on Gaussian mutation (G-CSSM), Cauchy mutation (C-CSSM), and non-uniform mutation (N-CSSM), have been developed. They each have a similar sub-pixel mapping process, except for the mutation processes, which use different mutation operators. The proposed algorithms are compared with the following sub-pixel mapping algorithms: direct neighboring sub-pixel mapping (DNSM), the sub-pixel mapping algorithm based on spatial attraction models (SASM), the BP neural network sub-pixel mapping algorithm (BPSM), and the sub-pixel mapping algorithm based on a genetic algorithm (GASM), using both synthetic images (artificial and degraded synthetic images) and real remote sensing imagery. The experimental results demonstrate that the proposed approaches outperform the previous sub-pixel mapping algorithms, and hence provide an effective option for the sub-pixel mapping of remote sensing imagery.
