数字图像监测作物生长特征的研究进展

为对作物进行田间数量化管理以及长势监测,从数字图像监测作物长势的基本原理、数字图像获取方法、图像分析处理技术以及数字图像在作物长势监测方面的应用4个方面进行概述,简要归纳了数字图像基本原理、获取及分析方法,总结出可以利用数字图像实现作物覆盖度、叶面积指数、生物量、氮素营养诊断进行监测,认为对于数字图像的获取应明确获取标...     

Realization of Intelligent Vehicle System for Target Recognition and Tracking

After analyzing target recognition and tracking technique, a method of developing specifically target tacking system is proposed, which uses digital image manipulation to target recognition. Software and hardware design of intelligent vehicle are presented in detail. The system uses digital image manipulation technology to cognize the certain target through a pickup camera installed on the front of the intelligent vehicle. When the target is moving, singlechip receives the commands from the computer and then control the vehicle to trace target. The system can run by itself, regardless of artificial control. This design provides a platform for the research of Growing Machine Intelligence system.     

Multi-yesolution Encoding of Medical Image in PACS

It is necessary to transmit and review medical images effectively in PACS (Picture Archive & Communication System, PACS) , and multi -resolution encoding can improve image compression efficiency. The progressive property of 2D image wavelet transform is studied, and a multi - resolution medical image encoding method is described. This encoding method means that, the lower frequency subimage in wavelet domain should be encoded prior to those higher frequency subimage. Also, in the medical image process of transmission and reviewing, the same order will be followed. The experiment has improved that the proposed method can speedup the medical image transmission and reviewing in PACS effectively.     

Development of CMOS Digital Image Sensor

The CMOS image sensor has developed from passive pixel sensors and active pixel sensors to digital pixel sensors(DPS),which is the trend of image sensors.The advantage of DPS is that the imaging system can be integrated on a chip as imaging system-on-a-chip,decreasing the cost and power consumption,improving the imaging quality.The A/D conversion is the key component of the CMOS sensor.The authors analyze and compare the theories,performances and features of the chip level,column level and pixel level integrated ADC of the image sensor.They present the present and the future trend of the development about digital image sensor in the home and abroad.     

Improved marching cubes by combining case lookup table and adjacency lookup sub-table

The marching cubes (MC) is an effective surface rendering method in three-dimensional visualization for medical image sequence. However, most existing MC algorithms are slow and inefficient because they have to process all the cubes for isosurface extraction. An efficient MC algorithm is proposed by combing the case lookup table and a novel adjacent lookup sub-table to exclude unrelated empty cubes. By explicitly building the fix-length adjacent lookup sub-table that is independent on image sequences, the volumes elements are constrained to those only intersect with the isosurface. Both execution time and temporary storage space are further reduced by incorporating the heap data structure in algorithmic implementation. Experimental results on human head, chest foot CT data sets by using the visualization toolkit package show that the traversal cubes decreases by 95%, and the reconstruction time decreases by 20% without any loss of reconstruction quality. Therefore, the proposed method can remarkably speed up the rendering time and be easily integrated into 3D visualization for clinical application.     

Research and implementation on handwritten numeralrecognition technique based on fuzzy mode

Based on simulation and numeral recognition of the 24-bit bmp images of postal codes obtained by CCD transducer, a binarization method based on coloring matter is proposed, which is employed to extract the binary image of the frame line of postal code and the binary image of the mail character separately. The procedure of image processing is analyzed, which includes detecting and separating borderlines of postal code frames, image binarization, smoothing noise-removal, slant rectification, extraction of postal code numerals, position normalization processing, subdivision of digital image, feature extraction of character recognition, and so on. The pretreatment process of image recognition is described. Then, character feature extraction is conducted for pretreated images, while the angle correctness for postal code frames and characters is performed. Finally, the recognition result is determined. In this method, the difficulty of separating frame line from postal code character line is eliminated. In order to improve recognition rate, the combination of many methods of handwritten numeral is used, resulting in improved recognition rate of postal codes. The experiment shows that this method can obtain higher recognition rate, providing reference for the separation technique in postal system.     

应用数字图像技术估测冬小麦冠层生物量垂直分布特征的研究

用数字图像技术研究了冬小麦冠层生物量的垂直分布。表明用一行小麦图像比多行小麦图像估测小麦生物量能更好地满足线性回归关系,估测效果更佳,以此为基础进一步研究了分层像素数估测小麦冠层分层现存生物量和有效生物量的方法。利用分层绿色像素数(LGPN)指标定性分析了不同栽培模式下冬小麦群体有效生物量的垂直分布和动态变化,并确定了基于图像特征的可用于定量分析的小麦群体垂直分布指数（I）。     

基于Matlab的玉米根系图像拼接、根系提取分析系统

为了对玉米根系生长进行准确的观察、取样、测定。通过采用沈阳大气环境研究所自主研发的根系监测系统(SYIAE-01)获取玉米根系的图片,基于Matlab数字图像识别方法(IBR)采用SIFI和OTSU法编写了由图像几何畸变校正、图像拼接、根系图像提取及根系面积计算三部分组成的根系图像软件,利用这一软件研究分析所采集的根系数字图像。结果表明,以Matlab为基础编写的根系图像拼接、提取分析系统初步实现了玉米根系特征的原位识别,通过该系统可以为提高玉米根系图像整理的工作效率,为计算根系面积提供帮助。     

Enhancing the Industrial Computerized Tomography by Wavelet Method

In industrial computerized tomography ( I C T ) , with the wavelet analysis method, we enhance the image of ICT. Comparing with the old image of ICT, this method can reduce the noise of the image and can filter the non white noise. This method can be applied in medical computerized tomography, too.     

A compensation method of human visual system based-on NR-IQA

Visual contrast resolution is lower in the low-light level. A compensation method for low-light image based on no-reference image quality assessment(NR-IQA in short) is presented. A mathematical model for extracting vision evaluation parameters is built. The best image quality assessment function is achieved to assess the quality of compensated image. The third step was to get the relationship between the assessment function and the corresponding compensation factors. The method of automatic optimization can be used to quickly acquire the optimal quality from an be taken from scotopic vision, especially image applied to the compensation of video image sequences rapidly.     

Image-Based Soil Deformation Measurement in Geotechnical Model Test

Deformation measurement and analysis play an important role in geotechnical model tests. Using the concept of quadrilateral isoperimetric element, the strain filed was achieved from the calculation method based on displacement modes, and the verification results show that this measurement technique has a reliable precision. The soil deformation in model test of square shallow foundation was measured by using this technique, and the results show that the measurement system based on digital image correlation method can realize the whole process quantitative measurement of soil displacement field and shear strain filed. This deformation measurement technique provides a tool for the qualitative and quantitative analysis of soil micromechanics characteristics.     

Representation of Uncertain Area in Image Based on Cloud-model

Aiming at the problem of representation of regions in the process of image processing, the paper presents a method applied to representation of spatial uncertain area in image based on Cloud-model. In two-dimension universe of discourse of image, the linguistic term of the polygons, which have uncertain edge, can be accomplished by relaxation iteration. The linguistic term of the polygons can be considered Cloud-core of Cloud-model. Based on the characteristics of pixels of transition region of fuzzy edge, Object-clouds of polygons can be constructed by Backward-cloud-generator. So Object-cloud can be representation model of spatial uncertain area and spatial uncertain area in image can be represented by digital characteristics of Object-cloud. Experiments testify the method. It enriches the cloud theory, and proposes a new idea for image comprehending and analyzing, especially remote sensing image.     

应用数字图像分析技术进行冬小麦 拔节期氮营养诊断

传统的作物营养诊断如植株全氮、生物量和植株硝酸盐浓度测试等需要进行大量的田间取样和实验室分析,时效性不足,难以适应作物生长期间追肥诊断的需要。通过田间试验,应用数字图像技术对拔节期作物的氮营养状况进行了研究,发现冠层数字图像色彩参数可以用来表征冬小麦拔节期的氮营养状况。数字图像标准化红光值R/(R+G+B)与冬小麦常规营养诊断指标如叶绿素仪读数、茎基部硝酸盐浓度、植株全氮含量和地上部生物量之间的相关系数达到了0.809~0.946,是较好的表征作物氮营养状况的诊断指标。     

牧草观测自动化技术研究与系统设计

针对内蒙古自治区生态观测需求,特别是草地生态系统观测需求,选取牧草观测为研究内容,提出基于嵌入式技术和并行计算技术的实时远程可控可视的牧草观测自动化技术思路。采用特征像素图像识别方法,实现牧草覆盖度的自动测量、牧草的发育期图像自动识别。利用摄影测量技术结合图像处理技术获得像高转物高变换算法,实现层高与株高的自动测量。结合现代电子技术以及DSP技术、图像处理技术设计了牧草自动观测智能传感器,传感器在观测前端完成图像采集、处理与模式识别后,再将处理后的结果通过网络传向服务器端,可通过智能手机或PC访问服务器远程查看观测数据,实现牧草覆盖度、层（株）高以及牧草生长期的自动观测。测试结果表明,图像处理与实测覆盖度数值显著相关检验R_0.05>0.90,与实测株高数值显著相关检验R_0.05>0.85。相对于在后端PC系统进行图像处理,不但可以提高观测系统的数据运算处理速度,而且鲁棒性好,同时能够大大减轻数据传输压力,适合对体积、功耗、工作环境及稳定性要求极高的场合。     

图像处理技术估测水稻叶面积指数的研究

为了探讨图像处理技术测定水稻叶面积指数（LAI）的可行性,利用数码相机获取水稻冠层影像,通过图像处理获取冠层图像的覆盖度,并建立模型从而估测出水稻LAI。试验结果表明,利用覆盖度与实测叶面积指数之间建立的关系模型可以估测水稻LAI,并对利用该模型测出的叶面积指数与实测叶面积指数进行统计检验,它们之间的相关系数在0.77~0.93*之间,达到显著或极显著水平。说明通过覆盖度估测水稻叶面积指数是可行的,该研究结果为获取水稻LAI提供了有效途径。     

Research on Pattern Recognizing Technique for Immunity of Blood Cells

This paper gives a new technique of automatically recognizing for immunity in pharmacological experiment. The realization of automatization of pharmacological experiment is very important and widely needed in pharmacology research and medical diagnosis. At the first, the paper introduces the system component and procession. The microscope image with complicated background is segmented. To improve the recognition speed and accuracy of the system, a way of dispatching image and multiprocessing for isolated cell is presented. The parameters of blood cells are obtained automaticly. The testing shows that the deviation of obtained pharmacological parameter doesn't exceed.     

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。     

基于数字图像技术的冬小麦不同施氮和灌溉处理颜色特征分析

本文在大田条件下对不同施氮和灌溉处理下冬小麦数字图像的颜色特征进行了研究探讨。初步得出以下结论：充分灌溉条件下不同施肥处理间的色调值差异几乎持续到成熟期;而满足氮肥需求的条件下不同灌溉处理的色调值差异主要表现在灌浆后期至成熟期;数字图像能够反映冬小麦的生育时期。     

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.     

Dynamisches Entscheidungsmodell zur Lenkung von Unkrautkontrollmaßnahmen in Wintergetreide mit Hilfe digitaler Bildverarbeitung

Dynamic decision model for weed control methods in cereals by means of digital image analysis
Field experiments were conducted to study weed-crop competition in winter wheat, -barley and -rye. Weed cover and crop cover was determined over time by digital image analysis of slides taken in the field. The relation of percentage weed coverage and crop coverage was most suitable to quantify the competition of weed population on the crop. In addition the model "UNPROG" was established to predict yield losses caused by weed competition and to estimate the profitability of chemical or mechanical weed control. The model was tested on 22 farms in Nordrhein-Westfalia in autumn 1991 and spring 1992. In 65 out of 72 field plots (92 %) of winter cereals "UNPROG" gave correct prediction with respect to necessity of weed control.