In order to get effectively feature vectors of samples, a method of feature extraction is proposed based on non-negative matrix factorization (NMF) with approximate orthogonal constraint. An objective function is defi...
详细信息
This study aims at characterizing wheat canopies caused by powdery mildew (Blumeria graminis f. sp. tritici) with multi-angular hyperspectral data. The filling stage (23 May, 2012) was chosen to achieve such a goal, c...
详细信息
ISBN:
(纸本)9781479911127
This study aims at characterizing wheat canopies caused by powdery mildew (Blumeria graminis f. sp. tritici) with multi-angular hyperspectral data. The filling stage (23 May, 2012) was chosen to achieve such a goal, considering that the disease can show distinctive symptoms during the months of May and June. A total of 37 sample plots were selected including 32 normal canopies and 5 diseased canopies with varied severity. To minimizing the soil background influences, multi-angular hyperspectral data were acquired at different view angles (0°, 45° and 90°). The results showed that the proportion of wheat vegetation and soil changed greatly and the hyperspectral reflectance values correspondingly changed. Consequently, the reflectance at different viewing angles showed great differences, but the curves had the same change trends. The results showed that, to accurately identify the spectral differences caused by powdery mildew, the optimal angle or a combination of several angles must be firstly found from multi-angular hyperspectral measurements.
The complex problems usually have netted structure, namely netted problems. The generally solving methods are based on sequence-searching or tree-searching of this kind of problems. But the structure of netted problem...
详细信息
In this paper, we constructed the architecture of mobile heterogeneous sensor network by introducing user equipments (UEs) in static wireless sensor network. We analyzed the failure of traditional static clustering al...
详细信息
In our study, support vector value contourlet transform is constructed by using support vector regression model and directional filter banks. The transform is then used to decompose source images at multi-scale, multi...
详细信息
In our study, support vector value contourlet transform is constructed by using support vector regression model and directional filter banks. The transform is then used to decompose source images at multi-scale, multi-direction and multi-resolution. After that, the super-resolved multi-spectral image is reconstructed by utilizing the strong learning ability of support vector regression and the correlation between multi-spectral image and panchromatic image. Finally, the super-resolved multi- spectral image and the panchromatic image are fused based on regions at different levels. Our experi- ments show that, the learning method based on support vector regression can improve the effect of super-resolution of multi-spectral image. The fused image preserves both high space resolution and spectrum information of multi-spectral image.
Aiming at the low-rate and short-distance communication in existing temperature and humidity monitoring system, this paper designs a remote monitoring system based on 3G and Internet technology. This system consists o...
详细信息
In order to make data collection more convenient, quick and accurate in working site in the existing wireless data acquisition system, one kind of multi-function handheld terminal is designed which combines the wirele...
详细信息
To improve the reliability of spectrum sensing, a cooperative spectrum sensing information transmission scheme is discussed in this paper. Pre-coding and cyclic delay diversity (CDD) techniques are fully considered an...
详细信息
Group delay distortion between channels is one of the most important factors which affect the BER (bit error rate) performance of DBF (digital beam forming) System. The basic principles of DBF and the concept of group...
详细信息
Herein, a new identity recognition method of plantar pressure image (PPI) was investigated based on compressed sensing. During the process of identity recognition, the PPIs were collected with platform system in norma...
详细信息
ISBN:
(纸本)9781479925667
Herein, a new identity recognition method of plantar pressure image (PPI) was investigated based on compressed sensing. During the process of identity recognition, the PPIs were collected with platform system in normal walking speed. The sparse representation of PPI was then obtained according to the sparse basis (i.e., wavelet basis). Finally, measurement vectors were calculated by the Topelitz measurement matrix and the PPI was recognized by compressed sensing classifier. The results showed that the accuracy of identity recognition of PPI based on compressed sensing exceeded 97.76%, demonstrating the effectiveness and stability of the Topelitz-compressed sensing algorithm. Meanwhile, the method used in this study reduced the data storage amount and increased the real-time recognition during the PPI process.
暂无评论