| 1. | Study on optimal bands selection of multi - spectral remote sensing data 多光谱遥感数据最佳波段选择的研究 |
| 2. | Band setting tuning condenser 波段选择用调谐电容器 |
| 3. | There are two kinds of dimensionality reduction methods , band selection and feature extraction 降维方法主要有波段选择和特征提取两大类方法。 |
| 4. | Wavelength band selection algorithm based on background radiance subtraction and its application to target detection 减背景的波段选择算法及其在目标探测中的应用 |
| 5. | The research of response wave band for conventional projectiles detecting and tracking by using infrared focal plane sensor 应用于弹丸跟踪测量的红外器件工作波段选择 |
| 6. | Principal component analysis ( pca ) , segmented pincipal components transform ( spct ) , band selection based on genetic algorithm ( ga ) and high order component are introduced here , which are all effective in for dimensionality reduction 本文介绍了主分量分析、分段主成分变换、基于遗传算法和高阶矩的波段选择四种降维方法。 |
| 7. | At a more advanced stage , polarimetric basis , implement system , scheme designs , production method and wavelength selection are considered , being useful to the study of polarimetric technology detecting atmosphere 进一步讨论了开展偏振探测技术研究所应考虑的有关偏振类型、实现体制、方案设计、产品算法和波段选择中的问题,对偏振探测技术研究具有参考价值。 |
| 8. | The main tasks and innovative points of this study as follow : 1 . based on the spectrum anlysis , statistical characteristic and snr ( signal to noise ratio ) of hyperspectral remote sensing image , some optimal bands for desertification monitoring was selected 本研究的主要工作和创新点包括以下几个方面: 1从光谱特性、图象的统计特征和信噪比三个方面讨论了高光谱遥感数据波段选择的方法。 |
| 9. | For the bands selection of hyper spectral image , an algorithm called selected projection pursuit is established and a quick calculating method is developed , the calculating speed is increased 80 ( the bands number of hyperspectral image ) limes . the nonlinear principal curves is researched , it is the nonlinear expansion of pca 针对高光谱图像光谱波段的最优波段选择问题,构造了选元投影寻踪算法,并为此建立了一种快速选元投影寻踪算法,使算法的速度提高将近80倍(波段总数的倍数) 。 |
| 10. | In the light of field features in desertification areas , the data quality and band combination of different bands are assessed , the indicators , principles and methods for data assessment and band option are put forward to , and optional band combination for desertification monitoring is determined primarily . the data pre - treatment model for desertification monitoring is developed after studying the pre - treatment algorithm of restoration and rebuilding of hyperspectral resolution data . the spectral features and variation rules of different objects in experimental areas are understood and analyzed 针对荒漠化地区的地物特征,对高光谱数据不同波段的数据质量、波段组合进行定性和定量的评价,提出用于数据评价、波段选择的指标、原则和方法;初步确定一个适用于荒漠化监测的优化波段组合,建立适合于荒漠化监测的数据预处理模式;初步分析、掌握研究区内各类地物的光谱特性及变异规律;针对荒漠化地区特点对多种分类方法进行探讨分析;建立荒漠化监测主要评价因子的定量反演模型。 |