玉米叶片重金属铅含量的SVD-ANFIS高光谱预测模型

重金属污染农作物后可通过食物链进入人体从而严重危害身体健康.如何快速准确地监测农作物中重金属含量已成为当今生态与粮食安全等领域的重要研究内容.常规的生化监测方法存在操作繁琐、过程长、具有破坏性等缺点,而高光谱遥感具有光谱分辨率高、信息量大、生化反演能力强、方便快捷、对监测对象无损伤等优势,因此利用高光谱遥感技术监测农作...     

Reference guided image super-resolution via efficient dense warping and adaptive fusion

Due to the limited improvement of single-image based super-resolution (SR) methods in recent years, the reference based image SR (RefSR) methods, which super-resolve the low-resolution (LR) input with the guidance of similar high-resolution (HR) reference images are emerging. There are two main challenges in RefSR, i.e. reference image warping and exploring the guidance information from the warped references. For reference warping, we propose an efficient dense warping method to deal with large displacements, which is much faster than traditional patch (or texture) matching strategy. For the SR process, since different reference images complement each other, and have different similarities with the LR image, we further propose a similarity based feature fusion strategy to take advantage of the most similar reference regions. The SR process is realized by an encoder–decoder network and trained with pixel-level reconstruction loss, degradation loss and feature-level perceptual loss. Extensive experiments on three benchmark datasets demonstrate that the proposed method outperforms state-of-the-art SR methods in both subjective and objective measurements.     

A comparative study between PVO-based framework and multi-predictor mechanism in reversible data hiding

Sorting-based reversible data hiding (RDH) methods like pixel-value-ordering (PVO) can predict pixel values accurately and achieve an extremely low distortion on the embedded image. However, the excellent performance of these methods was not well explained in previous works, and there are unexploited common points among them. In this paper, we propose a general multi-predictor (GMP) framework to summarize PVO-based RDH methods and explain their high prediction accuracy. Moreover, by utilizing the proposed GMP framework, a more efficient sorting-based RDH method is given as an example to show the generality and applicability of our framework. Comparing with other PVO-based methods, the proposed example method can achieve significant improvement in embedding performance. It is hopeful that more efficient sorting-based RDH algorithms can be designed according to our proposed framework by designing better predictors and their combination methods.     

一种适用于混响环境的双传声器自适应指向性算法

在许多语音信号处理系统(如助听器)中,都采用了指向性算法处理在空间上相互分离的信号,但在客厅、会议室等室内环境中混响的存在严重影响了指向性系统的降噪性能,现有的去混响算法不能有效地抑制干扰噪声。该文提出一种适用于混响环境的自适应双传声器指向性算法,采用两个间距很小的全向性传声器,将自适应零限波束形成(ANF)结构和利用概率模型抑制混响的方法相结合,实现了在混响环境中的自适应指向性。与现有指向性和抑制混响算法相比,该算法采用一个简单的结构同步实现了指向性和抑制混响,具有较低的复杂度和较强的实时性。仿真验证了算法在混响环境中的指向性降噪性能。     

Function approximation-based sliding mode adaptive control

For the position tracking in DC motor with unknown bound time-varying dead zone uncertainties, a novel sliding mode adaptive controller is proposed by means of sliding mode and function approximation technique in this paper. First, control law with an uncertain term and another compensative term is obtained using sliding mode technique, and then the function approximation technique is employed to transform the uncertain term into finite combinations of orthonormal basis functions. The concrete expressions of uncertain term and compensative term can thus be derived based on the Lyapunov design. Actual system control experiments of the sliding adaptive control proposed are given.     

基于2D实值离散Gabor变换的SAR原始数据压缩

该文采用时频分析的方法,结合合成孔径雷达(SAR)原始数据的线性调频特性,提出了一种基于2D实值离散Gabor变换的SAR原始数据压缩方法。该方法对I,Q两路原始数据进行分块,先对每一块进行二维实值离散Gabor变换(2D-RDGT),在时频平面内对各频率平面根据方差进行比特分配,然后采用BAQ量化各频率平面。用同一块数据进行压缩解压缩成像实验并与已有的方法进行比较,实验结果表明该文提出的方法在数据域和图像域的性能都优于已有的方法。     

卫星系统新技术--应用机遇及发展策略考虑(上)

结合市场导向下的技术驱动重要性，重点论述现代卫星系统新技术及其在中国的应用机遇和发展策略。     

一种天波雷达多径扩展多普勒杂波抑制方法

该文分析了天波超视距雷达(Over The Horizon Radar, OTHR)多径扩展多普勒杂波(Spread Doppler Clutter, SDC)的产生机理。由于阵列存在幅相误差且期望信号的功率大于SDC功率,自适应数字波束形成(Adaptive Digital Beam Forming, ADBF)将降低SDC抑制能力,同时还会导致信号对消,严重降低信噪比。针对以上问题,该文提出一种自适应抑制SDC的方法。该方法首先采用改进噪声子空间拟合自校正法消除阵列幅相误差,得到期望信号和SDC准确的到达仰角,然后采用正交投影权矢量进行ADBF处理,避免了强期望信号条件下ADBF权矢量估计不准的问题。理论分析和仿真实验表明该方法能够较彻底地抑制多径SDC。     

考虑负载均衡和用户体验的垂直切换算法

在超密集异构无线网络中,针对城区交通高峰期,大规模车载终端短时间聚集性移动引起的网络拥塞问题,该文提出一种考虑负载均衡和用户体验(LBUE)的垂直切换算法。首先,引入网络环境感知模型预测网络未来的拥塞程度,并提出一个融合自组织网络的网络架构,缓解网络拥塞。其次,定义业务适应度和负收益因子,并提出一种基于秩和比(RSR)的自适应切换判决算法,为用户筛选出当前环境下满意度最高的目标网络。实验结果表明,该算法能够有效降低终端接入网络的阻塞率和掉话率,实现网络间负载均衡并提升用户体验。     

Large scale automatic image annotation based on convolutional neural network

Automatic image annotation is one of the most important challenges in computer vision, which is critical to many real-world researches and applications. In this paper, we focus on the issue of large scale image annotation with deep learning. Firstly, considering the existing image data, especially the network images, most of the labels of themselves are inaccurate or imprecise. We propose a Multitask Voting (MV) method, which can improve the accuracy of original annotation to a certain extent, thereby enhancing the training effect of the model. Secondly, the MV method can also achieve the adaptive label, whereas most existing methods pre-specify the number of tags to be selected. Additionally, based on convolutional neural network, a large scale image annotation model MVAIACNN is constructed. Finally, we evaluate the performance with experiments on the MIRFlickr25K and NUS-WIDE datasets, and compare with other methods, demonstrating the effectiveness of the MVAIACNN.