基于阿里云的无土栽培营养液信息采集系统

为实现对无土栽培营养液中影响作物生长的各重要因子的精准测量与控制,笔者研制了一种基于阿里云的温室无土栽培营养液信息监测系统。该系统主要包括采集模块、控制模块、云平台和应用终端4个部分。首先利用传感器实时测量营养液的电导率、酸碱度、液温、液位和含氧量等影响因子信息,然后进行数据整合处理,并通过无线通信模块传送至控制模块及阿里云平台进行数据保存,最后通过Web端实时监控营养液各信息变化。研究结果表明,该系统能够实时准确监测营养液的信息,合理反馈供给作物所需营养液信息,达到功能设计要求,而且系统成本低,具有一定的实用价值。     

基于机器视觉的棉花群体叶绿素监测

研究了利用机器视觉技术快速获取棉花群体叶绿素信息的方法，以期获得预测性高的颜色特征参数。结果表明，RGB颜色系统的G－R、(G－R)/(G+R)、r与g的组合值和棉花功能叶叶绿素含量、群体绿色指数呈极显著相关，而且拟合度较高；HIS颜色系统的Hue值和棉花功能叶叶绿素含量、群体绿色指数之间也极显著相关。对筛选出的两组模型进行检验，预测精度在84.07%~93.04%之间，推荐预测精度最高的G－R参数作为获取棉花群体叶绿素信息的最佳颜色指标。G－R预测叶绿素含量和群体绿色指数的模型分别为y=－1.3008+0.2125(G－R)－0.0038(G－R)2（R²=0.8669**）和y=－0.9726+0.1227 (G－R)－0.0016(G－R)²（R²=0.7487**）。     

农产品远程价格信息采集和发布系统的研究

利用TC35与低功耗单片机结合设计便携式手持数据采集终端,采用手持信息采集终端收集信息,通过GSM方式传送到数据中心,数据中心负责处理和发布信息,实现了农产品远程价格信息的采集和发布,用户可通过上网或手机短信进行价格查询。系统实时性好,可靠性高,克服了以往信息采集发布的缺点,能够有效的进行农产品价格信息方面的信息传递工作及数据统计。详细阐述了手机模块TC35中SMS功能的工作原理、便携式手持终端的硬件设计与软件实现。经示范应用,系统达到了设计目标。     

基于无线传感器网络的鱼塘监控系统

本文设计了基于无线传感器网络的鱼塘实时在线智能监控系统,有效解决了传统的鱼塘观测手段存在的问题,例如：费时费力、步骤复杂、成本高等。该系统在鱼塘的监测区域中利用无线传感器节点,测得该区域中的温度和溶氧量,并通过Zigbee网络将数据传输到终端控制系统,控制系统作出判断并发出报警信号和控制增氧机的状态。系统中以MSP430和XBEE模块为核心芯片,能够实时在线监测鱼塘中的一些参数,例如温度、溶氧量等。同时该系统还可以进一步扩展使用GPRS或3G网络实现远程监控。     

A Real-time Expert System Based on Adaptive Predication of Process State

The combination of the measured real time state acquisition from the process with predictive process for the fature state is used to predicate the variable tendency for process state. This method is useful to avoid delay and enhance real time ability of the control information of the expert system. Also a described knowledge and structure of real time process state are proposed. This system can be applied to other kind of practice systems with slow time variable, uncertainty and delay.     

Principle and Scheme of a Feeder Automation Based System Protection

A new principle and scheme of a Feeder Automation based system protection using the channel of communication is proposed. The conjoint protection devices exchanging fault signal with direction information and the fault can be cleared instantly. These information can hel Pto isolate the fault zone and restructure the network rapidly. The recover is used for instantaneous faults. The optical MODEM disjoins the SCADA communication and Boolean signals functions using coding technology. So the fault flags can be exchanged rapidly peer-to-peer and special optical cables are not needed. Frames between optical MODEM are sent automatically. This scheme presented is successful through physical simulation experiment and has operated for about two years in a real distribution network.     

利用神经网络提取棉花叶片数字图像氮素含量的初步研究

选取6种输入向量组合，利用线性网络、BP网络以及径向基网络等3种神经网络模型进行比较研究，筛选最适宜网络模型和最佳输入组合，建立叶片数字图像彩色信息和叶片氮含量的关系模型，探索利用神经网络技术获取叶片数字图像信息的方法。结果表明，径向基网络在利用数字图像(B，H，G-R，G/R)指标作为网络输入向量时，能够实现获取棉花叶片数字图像氮含量的目标。径向基网络训练的180组样本的训练精度均达到极显著水平（r = 0.9022**），30组测试样本的预测值与实测值也达到极显著相关（r = 0.8674**），径向基网络和(B，H，G-R，G/R)向量是一种适合本研究的数学模型。对利用神经网络提取棉花叶片数字图像氮含量技术的初步探索，拓展了神经网络和数字图像技术在农业生产中的应用。     

Online Controlling and Measuring System of Pulse Xenon Lumps

The controlling and measurement system of pulse xenon lumps adopts high precision L C constant current charger, which can charge the storage energy capacitors with high repetition precision and communicate with computer real time. The system adopts quantification transforming model to measure the signals, which can reduce the interference and distortion. The multi tenors working model, which is used in computer controlling system, realizes the controlling and detection real time.     

光强倒数色度空间的彩色人脸光照预处理

为了解决彩色人脸识别中色彩信息易受光照影响的问题,提出一种基于光强倒数色度空间(IICS)的彩色人脸图像预处理方法。本方法首先将图像均匀地分割成子块;将每个图像块变换为IICS空间中的一个二维数据集,并根据数据集的线性分布特性估计图像块的光照颜色;然后对全部图像块的光照估计进行颜色直方图统计,根据直方图对分块估计的结果进行合并;最后,利用估计得到的光照和对角模型将图像光照校正到标准白光下,用于人脸识别。在AR和FERET人脸库上的实验表明,通过引入本光照预处理,有效增强了彩色人脸识别方法对光照变化的鲁棒性,提高了识别精度。     

A Lane-Finding Algorithm Based on Edge Detection and Feature Tracking

This paper do some research on the problem of computer vision on autonomous vehicle navigation system on highways. This algorithm first extracts the lane edges by means of wavelet transformation. Then the feature model of the lane markings is built,Which are tracked them in real time. Finally in terms of the parameterized model for the appearance of the lane in the image it fits the lane and get the road direction. This information assures that the whole system can realize lateral control and longitude control.     

Automatic head recognition by integrating mean shift with multiple features

To improve the head detection accuracy in video sequences captured with fixed vertical monocular camera, a novel method of head recognition based on mean shift and multiple features is proposed. Firstly, mean shift based image segmentation algorithm with color information and spatial information is suggested to derive the candidate head components in images. Furthermore, by referring to two features that the contour of human head regions are approximate round and the hair color distribution is clustered, the evaluation models based on the contour information and inside color information of candidate head components are presented for head recognition. The experimental results show that the proposed algorithm can effectively reduce the light interfere and eliminate fake target whose color information is similar to hair color distribution. The detection rate for static images can reach about 89.4%.     

Design of nondestructive test system for plasma clots

One of the most important measures that are used to guarantee blood transfusion safety is to detect clots in the plasma before transfusion. To overcome the disadvantages of manual detection method, this research designs a nondestructive testing (NDT) system for plasma clots inspection based on machine vision technique and artificial neural networks. The key technology for system design are studied and presented. Image acquisition is performed by custom-designed software based on MATLAB platform, and the methods of image cut, reverse color, median filter as well as gray cutting are adopted to preprocess image. The use of fisher discrimination method, combined with iterative threshold segmentation method and the selection of connected domain, can successfully eliminate the interference of air bubble and correctly extract the image of plasma clots. Plasma clots are discriminated by a recognition model based on artificial neural network BP algorithms. The results of clinical contrast experiment shows that the system can effectively detect whether plasma contains plasma clots and the new system shows a much higher degree of repeatability and stability. From the image acquisition and processing to the recognition of plasma clots, the detecting time of a sample is no more than 1 min.     

Color and textural quality of packaged wild rocket measured by multispectral imaging

Green color and texture are important attributes for the perception of freshness of wild rocket. Packaging of green leafy vegetables can postpone senescence and yellowing, but a drawback is the risk of anaerobic respiration leading to loss of tissue integrity and development of an olive-brown color. The hypothesis underlying this paper is that color and textural quality of packaged wild rocket leaves can be predicted by multispectral imaging for faster evaluation of visual quality of leafy green vegetables in scientific experiments. Multispectral imaging was correlated to sensory evaluation of packaged wild rocket quality. CIELAB values derived from the multispectral images and from a spectrophotometer changed during storage, but the data were insufficient to describe variation in sensory perceived color and texture. CIELAB values from the multispectral images allowed for a more detailed determination of color compared to measurement with a spectrophotometer with an 8 mm aperture. Furthermore, the multispectral images enabled subtraction of background information of the sample and gave more accurate results on visual color of wild rocket leaves. The combination of wavelengths in the NIR range describing textural changes, and wavelengths in the VIS range describing color changes was optimal for quantification of sensory perceived color and textural quality of packaged wild rocket.     

基于最小阈值法的棉花幼苗识别研究

 面对纯机械式分苗机构经常出现的漏分和多分的问题,本文提出使用基于最小阈值法的图像识别技术对棉花幼苗进行识别和分离。使用了HSV颜色空间内与光照条件无关的H值将RGB真彩色图像转化为灰度图像,以提高图像处理的实时性。基于最小值阈值法,提出一种能够有效地将处于复杂背景下的棉花幼苗茎部图像提取的方法,使用棉花幼苗茎部图像的面积和长宽比等几何信息能有效识别棉花幼苗,并得到棉花幼苗茎部的重心坐标。本文的研究证明了用图像处理中的最小阈值法识别棉花幼苗是可行的。     

Multiresolution Wavelet Transform for Detection of EEG Abnormal Rhythms

The signal of brain activity is a non-stationary random signal including lots of physiology and disease information, which is of important action for doctors to judge pathological changes in brain. So the analysis and process of the EEG signals are always attended. In this paper, the authors take account of the time-frequency localization of wavelet transform and use multiresolution wavelet transform to detect EEG abnormal rhythms. The signals of different scales after EEG signals are transformed by multiresolution wavelet transform not only reflect the frequency information of the signals, namely the more great scale is the lower of the frequency of the signals,but also reflect the time information of the signals, namely EEG state at that time. The test results indicate that the abnormal rhythms of the EEG signals can be detected effectively if right wavelet basis is selected.     

Design of nondestructive examination system for bridge cables surface defect

Aiming at the drawbacks of the current detecting methods, a nondestructive examination system design for bridge cables based on high speed digital signal processors chip DM642 is presented, and the hardware platform of the system is built. This examination system mainly consists of four parts: the image defaults acquisition part, DM642 hardware platform, creeping part and defaults locating equipment. The designed system is tested on the hardware platform based on digital image processing algorithm. The experimental results show that the detecting system has the advantages of high stability and reliability, real time, mass storage, and nondestructive examination, etc. This system uses high technology and has significant meaning on detecting the current bridge cables health, furthermore, this method can be used in other examination fields.     

基于数字图像的玉米叶面积测量方法研究

【研究目的】以数字图像处理技术为基础,采用数码相机获取数字图像,建立使用Visual C++6.0开发的图像处理软件进行玉米叶面积测量的方法。【方法】首先,用数码相机拍摄挂在墙上粘贴着玉米叶片的参照白板来获得数字图像。然后提取图像的蓝色分量,利用中值滤波、膨胀、腐蚀等方法去除图像噪声,最大类间方差法自动阈值分割目标。接着进行区域标记与区域像素数统计,区域像素数结合图像分辨率就可以获得玉米叶片的实际面积。【结果】与直尺法所测结果具有很好的相关性,且比直尺法更精确,【结论】此种拍摄方法避免了几何畸变的产生。蓝色分量图像中目标和背景的灰度差异最大,便于分割。     

基于移动溯源与图像分析的茶叶品级鉴定方法研究

为解决茶叶在质量追溯时防伪和品质鉴定问题, 以六安瓜片为研究对象, 提出一种结合移动计算和图像分析的茶叶质量追溯方法。该方法的实现以 Android操作系统为平台, 通过扫描茶叶质量追溯二维码查询溯源信息。在此基础上, 利用智能终端拍照获取完整的单片茶叶正面照片并上传至后台服务器。后台编写的 MATLAB图像处理程序对采集的图像进行预处理和特征参数提取, 将提取的颜色和形状共 7项特征参数作为参数集合, 运用 SVM分类器对茶叶进行分类, 最终将结果反馈到溯源客户端。测试结果证明, 该方法能快速帮助消费者对茶叶品级进行初步鉴定。     

A New Fault Location Method Based on Two Terminal Information of Self synchronous Rectification

In accordance with the high and extra high voltage long distance transmission line,this paper presents a fault location method based on two terminal information of self synchronous rectification.We adopt the long transmission line model,consider the effect of distribution capacity and can correct the sample phase angle difference in the real time btween two terminals.So that this method can avoid the fault location error owing to asynchronous message on the two terminals.Tested by a lot of simulations,the results are very satisfied.     

Real-time Infrared Image Acquisitionand Processing System Based on PCI Bus

In the system of infrared imaging acquisition, it is necessary to improve data transfer to satisfy the characteristics of high speed and real time. So,this paper introduces PCI bus and PCI inerface to imaging acquisition. The protocol of data transfer of PCI local bus and the structure of PCI9050 are studied in detail, and the IRFPA data acquisition system are described based on the protocol of data transfer of PCI local bus. The system adopts frame buffer to make slow transmission between peripheral circuit and PCI bus.CPLD is also used as a master of logic time control?