Method to suppress speckle noise using time multiplexing in phase‐only holographic display

In holographic display, the reconstructed image suffers from speckle noise severely. In this paper, we propose a method to suppress speckle noise using time multiplexing in phase‐only holographic display. Adjacent pixels of the recorded object are separated into object point groups firstly. Particularly, the pixel interval of each object point group is larger compared with the conventional pixel separation method. And then, sub‐computer–generated holograms (sub‐CGHs) are calculated by the modified Gerchberg–Saxton (GS) algorithm with different initial random phases. Finally, the final integrated image is reconstructed with low speckle noise using time multiplexing technique. Both numerical and optical experimental results are presented to demonstrate the effectiveness and feasibility with our proposed method.     

一种基于二维图像的三维仿真方法研究

针对二维的图像数据,综合运用计算机视觉、计算机图像处理和计算机辅助几何设计理论与技术,提出了一种实用的三维仿真方法.采用阴影恢复形状的方法获取三维形貌信息,利用图像分割技术提取物体的二维轮廓信息,通过三维形貌信息与二维轮廓信息的融合技术建立物体的数字化模型,通过B样条的万法实现数字化模型的重构.实例表明,方法可行有效,能够有效地去除图像的背景信息,改善重构模型的分辨力,为基于二维图像的三维仿真技术的广泛应用提供了条件.     

基于直线段提取及其参数化的矩形重构方法研究

文章根据矩形目标边缘二值图的特点,提出一种基于直线段提取及其参数化的矩形目标重构方法,实现矩形目标位姿参数高精度快速求取。该文提出的矩形目标重构方法主要分两步进行:首先从矩形目标边缘图像的二值图中提取出所有直线段,并将直线段参数化;其次由参数化的直线段提取出近似矩形,再由近似矩形重构出精确的目标矩形,并计算其位姿参数。该文提出的算法可应用于机器人装配及目标跟踪中。     

基于多尺度形态滤波的分水岭图像分割方法

采用多尺度形态滤波器对输入噪声图像及滤波后图像的梯度图像进行平滑，实现了消除噪声、简化图像、保持物体重要轮廓信息的作用．最后，给出一种改进的快速区域合并算法优化分割结果．实验证明，采用文中分割方法可以获得很好的分割结果。     

多视点图像的前景对象自动分割方法

为了将前景对象从多视点图像中自动地分割出来,提出一种基于多视点图像特征分析的对象提取方法.首先采用改进的随机Hough变换提取极线平面图中的直线,并对已检测直线的斜率进行统计分析;然后根据对象在场景中所处的深度,将对应斜率的直线转换到原始图像空间中得到初始轮廓;并利用边缘生长方法缩短断开边缘的间距;最后采用边缘连接方法获得闭合的轮廓曲线.实验结果表明,与基于水平集的主动轮廓模型分割方法相比,文中方法能更加快速、精确地将对象从复杂场景中分割出来.     

Slicing Method for Reverse Engineering Based on Image Mosaic

Reverse engineering dealing with images is traditionally based on image processing and contour recognition. A new method is presented based on the combination of sectional slicing with image mosaic. Sectional contours of the target object are generated by colorful liquid or laser scanning, these images from different views are fused into a set of complete cross-sectional images, thereby the whole practical model is reconstructed in 3D space.     

Reconstruction of 3D contour with an active laser‐vision robotic system

This paper presents a 3D contour reconstruction approach employing a wheeled mobile robot equipped with an active laser‐vision system. With observation from an onboard CCD camera, a laser line projector fixed‐mounted below the camera is used for detecting the bottom shape of an object while an actively‐controlled upper laser line projector is utilized for 3D contour reconstruction. The mobile robot is driven to move around the object by a visual servoing and localization technique while the 3D contour of the object is being reconstructed based on the 2D image of the projected laser line. Asymptotical convergence of the closed‐loop system has been established. The proposed algorithm also has been used experimentally with a Dr Robot X80sv mobile robot upgraded with the low‐cost active laser‐vision system, thereby demonstrating effective real‐time performance. This seemingly novel laser‐vision robotic system can be applied further in unknown environments for obstacle avoidance and guidance control tasks. Copyright © 2011 John Wiley and Sons Asia Pte Ltd and Chinese Automatic Control Society     

综合颜色和轮廓曲线特征的图像检索方法研究

传统的基于内容图像检索（CBIR）及跟踪算法主要利用图像的颜色、纹理等特征进行相似性比较,但大量的实验和应用也表明利用颜色和纹理进行图像相似性比较在空间结构和对象形状上难以精确控制,致使图像检索经常出现一些不可预料的结果。为了提高图像在形状、颜色及纹理上的检索精度,提出了一种综合颜色和图像轮廓曲线特征的检索方法。该方法分割图像并提取图像中感兴趣对象的轮廓,对提取的轮廓进行仿射变换及最小值化处理,经处理后的轮廓带有边缘的完整信息,具有几何不变性;利用聚类的颜色信息,提取主聚类的直方图,所提取的直方图不仅包含了主聚类的颜色信息也包含了该聚类的空间位置信息。利用检索对象与被检索对象的颜色距离直方图及轮廓曲线距离偏差的加权平均度量检索及被检索对象的相似性。实验结果表明,针对基于感兴趣对象的图像检索问题,给出了一种具有高度检索精度的算法。     

Locating object contours in complex background using improved snakes

An active contour model, called snake, can adapt to object boundary in an image. A snake is defined as an energy minimizing spline guided by external constraint forces and influenced by image forces that pull it toward features such as lines or edges. The traditional snake model fails to locate object contours that appear in complex background. In this paper, we present an improved snake model associated with new regional similarity energy and a gravitation force field to attract the snake approaching the object contours efficiently. Experiment results show that our snake model works successfully for convex and concave objects in a variety of complex backgrounds.     

Dynamic wires: An alanog VLSI model for object-based processing

The dynamic-wire methodology provides dedicated lines of communication among groups of pixels of an image which share common properties. In simple applications, object regions can be grouped together to compute the area or the center of mass of each object. Alternatively, object boundaries may be used to compute curvature or contour length. These measurements are useful for higher-level tasks such as object recognition or structural saliency. The dynamic-wire methodology is efficiently implemented in fast, low-power analog hardware. Switches create a true electrical connection among selected pixels, dynamically configuring wires or resistive networks on the fly. Dynamic wires provide a model for object-based processing. This approach is different from present early vision chips which are limited to pixel-based or image-based operations. Using this methodology, we have successfully designed and demonstrated a custom analog VLSI chip which computes contour length.     

一种基于序列图像的交互式快速三维重建方法

针对普通数码相机拍摄的序列图像,提出了一种快速的交互式三维重建方法.首先基于SFM技术得到了相机的内外部参数;然后在图像上交互取点以构建逼近物体轮廓的多边形,结合该多边形,利用轮廓跟踪算法提取出精确的外形轮廓;最后通过匹配轮廓点的方式重建出三维模型.实验结果表明该重建方法是快速而有效的.     

一种新的基于局部轮廓特征的目标检测方法

针对复杂场景中背景复杂、目标周围噪声多及目标只占图像中较小部分而难于检测的问题,提出一种新的基于局部轮廓特征的检测目标方法.该方法首先利用改进的全局概率边界算法 (Globalized probability of boundary, gPb) 算法提取图像的轮廓,然后应用最大类间方差法 (Otsu)进行自动阈值处理得到图像的显著性轮廓; 再提取显著性轮廓的k邻近大致直线轮廓段(k connected roughly straight contour segments, kAS),并以kAS作为局部特征,用于复杂场景中的目标检测.该算法结合 gPb 算法和 Otsu 提取轮廓的显著性轮廓,去除了目标附近的大量噪声边界,有效地提高了检测效率.同时,在检测阶段,测试集与 训练集中提取的不相关特征数目也得到较大减少,从而提高了检测的精度.多组实验结果均表明本文方法的有效性.     

A shape prior constraint for implicit active contours

We present a shape prior constraint to guide the evolution of implicit active contours. Our method includes three core techniques. Firstly, a rigid registration is introduced, using a line search method within a level set framework. The method automatically finds the time step for the iterative optimization processes. The order for finding the optimal translation, rotation and scale is derived experimentally. Secondly, a single reconstructed shape is created from a shape distribution of a previously acquired learning set. The reconstructed shape is applied to guide the active contour evolution. Thirdly, our method balances the impact of the shape prior versus the image guidance of the active contour. A mixed stopping condition is defined based on the stationarity of the evolving curve and the shape prior constraint. Our method is completely non-parametric and avoids taking linear combinations of non-linear signed distance functions, which would cause problems because distance functions are not closed under linear operations. Experimental results show that our method is able to extract the desired objects in several circumstances, namely when noise is present in the image, when the objects are in slightly different poses and when parts of the object are invisible in the image.     

基于梯度矢量流主动轮廓模型的等高线提取算法

为了提取彩色地形图上的等高线,首先把RGB颜色空间转换为HSV颜色空间,对彩色地形图进行分色,以获得棕色等高线的二值图像;然后利用数学形态学的方法对二值等高线图像滤波,消除等高线线体内的孔洞.利用梯度矢量流主动轮廓模型在等高线二值图像上直接提取未经细化的等高线,并结合等高线断裂区域的等高线流向场连接断裂的等高线.最后验证了文中算法的有效性.     

基于等高线的三角网建模及真实感地形重建

三维地形是自然环境模拟中不可缺少的重要组成部分,具有广泛的应用价值.文中提出了一种基于等高线的三角网建模算法.该算法利用等高线固有的特性及其比邻拓扑关系,将等高线作为特征线并适当增加特征点,改进三角网生长算法,构建带约束条件的狄洛尼三角网.实验采用我国东北某山区的真实等高线数据运用该算法模拟地形.结果表明,该算法具有较高的构网效率,保留了等高线所包含的丰富的地形特征,较好地实现了三维真实感地形重建.     

单像素宽度目标轮廓提取的实现

在人脸检测、火灾识别等应用中,应用物体的轮廓特征来检测和定位目标物体是一种有效的方法.本文提出一种基于连通区域面积阈值化的实现算法,可以同时实现噪声消除与轮廓提取,并据此定位图像中的物体目标.实验结果显示,只要噪声面积没有超过物体面积,应用该算法即可实现噪声完全消除,并能够得到连续的无交叉的单像素宽度的物体轮廓,且轮廓不变形.     

基于双向轮廓跟踪的面部轮廓线生成算法

为了提高医学图像中面部轮廓线的分割效果,提出一种新的面部轮廓线生成算法(bidirectional contour tracking,BCT).该算法首先利用边缘检测算法对CT图像进行检测,然后利用头部CT图像中各组织的灰度特征和图像的对称性,对检测后的图像进行双向轮廓跟踪,并获得面部的轮廓线.另外,根据面部轮廓线的特点,使用中点法可生成辅助轮廓线.以一组颅脑CT图像为例来验证算法的效果,实验结果表明,新的生成算法提高了轮廓线的生成速度,并有很好的分割效果.     

基于深度生成模型的煤矿运输皮带异物检测

为了能够精准地对煤矿皮带运输机上的异物进行检出,提出了一种基于深度生成模型的皮带异物检测方法.首先,利用常规的变分自编码器(variational autoencoder,VAE)对图像进行重构,根据原始图像与重构图像之间的重构误差对图像中是否存在异物进行检出.然后,为了解决变分自编码器所生成的重构图像通常较为模糊的问...     

基于概率分布图的运动目标轮廓快速提取方法

以对图像分析起重要作用的目标轮廓提取技术为重点,研究并提出一种基于概率分布图的目标轮廓快速提取方法,该方法先从视频中检测到前景目标并建立目标概率模型,再根据建立的模型计算目标概率分布图,用该分布图提取出目标轮廓。对2330幅包含运动目标的视频帧进行测试,结果表明,该方法简单有效,处理速度快,提取的轮廓准确、清晰,对目标形变具有很好的鲁棒性。