中文摘要：

针对混合像元分解过程中，由于数据噪声引起的端元提取不准确问题，引入了群智能算法中的粒子群优化算法，并对粒子群优化算法进行了改进，重新定义了位置和速度的表示方法和更新策略，得到离散粒子群优化（discreteparticleswarlYIoptimization，D-PSO），能够在离散空间中进行搜索，解决组合优化问题。同时，通过定义目标函数和可行解空间，将端元提取问题改写成组合优化问题，最终实现利用D-PSO进行端元提取。在给出算法的详细流程之后，文章通过一组模拟数据实验和一组实际数据实验验证了D-PSO算法对于具有较大噪声的数据的适应性和提取端元的可信程度，并分析了不同参数对于算法性能的影响。

英文摘要：

For the inaccuracy of endmemher extraction caused by abnormal noises of data during the mixed pixel decomposition process, partiele swarm optimization （PSO）, a swarm intelligence algorithm was introduced and improved in the present paper. By re-defining the position and velocity representation and data updating strategies, the algorithm of discrete particle swarm opti- mization （DPSO） was proposed, which made it possible to search resolutions in discrete space and ultimately resolve combinato- rial optimization problems. In addition, by defining objective funetions and feasible solution spaces, endmember extraction was converted to combinatorial optimization problem, which can be resolved by D-PSO. After giving the detailed flow of applying D- PSO to endmember extraction and experiments based on simulative data and real data, it has been verified the algorithm＇s flexi- bility to handle data with abnormal noise and the reliability of endmember extraction were verified. Furthermore, the influence of different parameters on the algorithm＇s performances was analyzed thoroughly.