Vivitar is well recognized as the top 3 brand in american camera industry . vivitar offers wide range of photographic products , including distinctive premium manual camera , single - use camera , motorized camera , zoom camera , water - proof camera , digital camera , binoculars , monocular for your choice Vivitar相机及光学产品在全球各地闻名巳久，备有各种型号数码相机zoom相机aps相机全自动相机防水相机手动相机镜头脚架望远镜及监察系统等可供选择。
This thesis , taking the key scientific and technological project of henan province “ the development of the binocular vision surveillance system ” as the research background , devotes main efforts to the research of the vision surveillance system based on dsp in the aspects both hardware and software , mainly including : 1 . hardware system design of monocular visual surveillance system based on dsp and fpga the actual application has set higher and higher real time demands for the visual surveillance system 本文依托河南省自然科学基金攻关项目“双目视觉监控系统研制” ,分硬件和软件两个方面对基于dsp的视觉监控系统进行了探讨研究,主要包括: (一) dsp + fpga的单目视觉监控系统的硬件设计视觉监控系统的实际应用对系统的实时性提出了越来越高的要求。
In the applied part , kernel method is used to improve the method of classification with one class training data . the improved method is combined with ground plane transformation method , so that information from monocular vision and stero vision can be fused effectively . based on this , a demo system of obstacle detecting in outdoor scenes is developed 在实践应用部分，本文利用核函数方法，改造了现有的单类判别方法，并结合双目视觉技术中的重投影方法，实现了单、双目信息的有效融合，研制了一个自然场景下的障碍检测实验演示系统。
In order to acquire 3d spatial position and motion parameters of moving target , the limitation of second focus method to get the depth of target is analyzed according to perspective projection model of target centroid . then , the constraint for obtaining 3d position and motion parameters of moving target centroid from monocular image sequence is presented and proved in this paper . with this constraint , a nonlinear extended kalman filter algorithm for estimating 3d spatial position and motion parameters of moving target centroid from monocular image sequence is proposed 进一步，为获取目标的空间位置和运动参数等三维信息，在目标和成像系统都运动的情况下，根据目标质心的透视投影成像模型，首先分析了二次成像法获取目标深度信息的缺陷；然后给出了由单目序列图像获取目标质心的空间位置和运动参数的条件，并提出利用多帧单目序列图像和应用非线性扩展卡尔曼滤波算法来估计目标质心的空间位置和运动参数；最后对提出的估计方法进行了多组仿真验证，证明该方法可行有效。
First of all , via comparing several familiar measure methods , this paper supplies a measure technique of monocular image analysis , which includes lane detection and obstacle detection . and then the paper sets up the model on distance between two vehicles . in the end , the result and analysis of the system processing is given , and the system is estimated in three aspects , further some improvements are advanced 本文首先通过对比各种常见车距测量方法引出单目图像分析的测量技术，该系统包括车道检测和前车检测两部分；然后建立了车距测量模型；最后给出系统处理结果及分析，并从三个方面对系统进行了评价，提出了改进措施。
The 3d surface reconstruction from monocular multiple imagines is hotspot in the research domain of images in recent years . based on the analysis of lambertain , phong , torrance - sparrow and cook - torrance illumination models , a method for 3d surface reconstruction from multiple shaded images with different illumination is presented in the paper 由单目多幅二维图像重构曲面的三维几何形状近年来一直是图像领域研究的难点和热点，本文在分析多种曲面测量方法的基础上，根据在不同照明情况下获得的多幅图像，以lambertain 、 phone 、 torrance - sparrow 、 cook - torrance多种光照模型为依据，提出一种三维曲面重构方法。
Visual analysis of human motion has been receiving increasing attention from researchers in the fields of image processing and computer vision during the past few years . it has a lot of applications in virtual reality , smart surveillance system , advanced user interface , motion analysis and video compressing , etc . this paper focuses on the technology of human motion tracking based on video , first , we make a summarization of the domestic and overseas status of the research in this field . on the basis of this , we analyse the technical difficulties of human motion tracking . as most of the existing model - based methods of human motion tracking perform not so good in some situation as they need mannual intervention , and also the precision of tracking is not so satisfying during the research of tracking of walking people because of the self - occlusion of legs , this paper proposes an algorithm of automatic detection and tracking of legs of the walking people based on monocular image sequences , in which we analyse the features of walking people , track the five joints of lower limbs , get various parameters , and then re - construct the walking process . the main research achievement is as follows : 1 ) we propose an algorithm of markerless automatic extraction of leg skeleton . first we divide the video into continuous image sequences , after background subtraction , the satisfying human region could be extracted , then we get a single - connected region by converting the rgb image to binary image and median filtering . afterwards , the contour of lower limbs in the frame with a widest boundingbox is detected , using sobel operator , to find the ankle joint of leg behind according to the features and rules of walking , then , the joint of knee of leg behind , hip , ankle of leg in front , knee of leg in front could be got in turn . so , model of leg skeleton is constructed 首先将视频分解成许多连续的静态图像帧,经过背景去除,把感兴趣的人体区域提取出来,通过二值化,中值滤波等预处理方法得到只有人体的一个单连通区域,然后用sobel算子检测出boundingbox最宽帧中人体下半身的轮廓,根据运动规律及特征找到后腿踝关节点,结合从boundingbox最窄帧中所获取的腿长依次得到后腿膝关节,跨部关节,前腿踝关节,前腿膝关节四点,从而构建出腿部骨架模型。 2 )实现了人体步行腿部骨架的跟踪算法。在完成对腿部骨架模型的自动初始化之后,本文对跨关节、膝关节及踝关节分别采用运动建模、圆周相交定点算法、运动预测及预测点周围搜索rgb相似矩形块三种方法确定每一帧中其实际坐标,从而重构出腿部骨架的运动过程。
