面向惯性约束聚变实验靶图像的快速椭圆检测

目的：针对惯性约束核聚变实验中靶图像轮廓模糊、亮度不均匀等问题,并从提高图像处理实时性角度出发,提出了一种高可靠性和高精度的快速椭圆检测方法。方法：首先利用椭圆边缘点在它与圆心相连方向上具有较大灰度变化率这一特点,以预估中心点为极点建立极坐标系,通过从极点出发的射线上灰度变化率极值点搜索实现椭圆边缘点检测,极值点搜索在图像局部范围进行保证边缘点检测的有效性和实时性;其次利用基于RANSAC的自适应椭圆参数提取算法得到最终椭圆参数,该方法利用椭圆参数空间聚类分析选取最优椭圆参数,从而实现了一致样本集的自适应选择,保证了椭圆参数拟合精度的同时提高了算法的适应性和鲁棒性。结果：采用本文算法检测一幅图像的平均时间约为110ms,与常用椭圆检测方法相比检测速度有显著提高。结论：对比实验表明,本文提出的椭圆检测方法与其他方法相比具有更高的精度、更快的实时性和更强的鲁棒性。     

基于最大内切圆的椭圆孔组检测

针对当前一些椭圆孔组工件检测成本高、时效低等问题,提出了一种基于最大内切圆的椭圆孔组检测方法。首先对椭圆孔组图像进行去噪、二值化和边缘检测等预处理;再根据椭圆的几何性质,结合椭圆中心估计方法和最值距离选取方法,求出椭圆最大内切圆,从而确定椭圆的中心坐标、长短轴长和倾斜角。实验数据表明,该方法能对椭圆孔组进行快速精确检测,在估计出椭圆中心的基础上能快速截取有效椭圆弧,大幅减少无效采样;与基于中心估计Hough椭圆检测算法和基于最小二乘改进椭圆检测算法相比,具有耗时短、精度高等优点,可有效应用于椭圆孔组工件的自动化检测。     

使用广义正交概念的K-RANSAC椭圆提取

开发了一个使用广义正交概念的K-RANSAC椭圆提取算法.该算法通过使用广义正 交概念,成功地把圆的所有性质推广到椭圆;通过仿射变换把水平-垂直种子点对一般化为任意 种子点对情况;通过对边缘点集的归一化运算,有效地正则化了提取椭圆的边缘点集的病态性; 并通过直接估计椭圆参数的广义本征分析技术,进一步提高椭圆的可检测性和拟合精度.理论 分析和实验结果表明,所开发的椭圆提取算法具有鲁棒性强、适用范围广、精度高、速度快等 优点.     

A fast and effective ellipse detector for embedded vision applications

Several papers addressed ellipse detection as a first step for several computer vision applications, but most of the proposed solutions are too slow to be applied in real time on large images or with limited hardware resources. This paper presents a novel algorithm for fast and effective ellipse detection and demonstrates its superior speed performance on large and challenging datasets. The proposed algorithm relies on an innovative selection strategy of arcs which are candidate to form ellipses and on the use of Hough transform to estimate parameters in a decomposed space. The final aim of this solution is to represent a building block for new generation of smart-phone applications which need fast and accurate ellipse detection also with limited computational resources.     

基于中点提取的椭圆检测算法

针对Hough变换检测椭圆时存在运算速度慢、需要大量储存空间的问题,提出一种快速的随机椭圆检测算法。该算法随机采样2点并搜索第3点,再利用椭圆极径性质求出椭圆中心坐标,接着通过坐标变换得到简化的椭圆方程,解方程组求出椭圆剩下的参数。在证据收集确认候选椭圆时,只选取椭圆外切矩形内的边缘点,同时利用特殊的累积记录函数对候选椭圆参数进行进一步判别。实验结果表明,该算法具有检测速度快、精度高、抗椭圆部分缺失的能力强等优点。     

基于中心估计的椭圆检测

椭圆检测在图像理解中有重要的作用。为克服标准Hough变换对时空需求高的缺点,设计了一种改进算法。通过椭圆对称特性估计图像中可能存在的椭圆中心,利用长轴确定椭圆中心及夹角参数只需一维累积数组对椭圆短轴的投票,采用聚类分析技术将检测到的虚椭圆归类到对应的真实椭圆。对合成图像和实际图像的实验表明算法的正确和高效。     

一种识别SAR图像中椭圆目标的方法

提出了一种对SAR图像中的椭圆形目标进行自动识别的综合方法。它利用SAR图像所具有的统计特性、CFAR检测对SAR图像进行预处理。根据中心椭圆算法构造椭圆并计算以此灰度占空比系数,采用马氏距离从背景中识别出目标。实际SAR图像实验结果表明了该方法的有效性。     

一种改进的虹膜快速定位算法

针对现有虹膜定位算法的局限性,提出一种检测变形瞳孔的算法,实现了精确快速的虹膜定位,并通过最大类间方差法确定图像阈值。变形瞳孔近似椭圆,因此利用最长弦定位内边界。由于瞳孔虹膜近似同心,利用圆灰度梯度算子小范围搜索外边缘。此算法精确定位了变形瞳孔,避免了外边缘搜索的盲目性,提高了虹膜定位的精度与速度。     

基于计算机视觉的公交系统人流量检测算法

提出了一种基于计算机视觉的公交系统人流量检测方法。通过分析现场行人视频数据，运用图像处理的方法提取图像中通行的行人以及通过视场内的人流量，阐述了复杂背景、低分辨率和特殊拍摄角度条件下的人头特征曲线提取算法和基于部分椭圆弧的椭圆模板参数估算法，试验结果表明了该算法的正确性和有效性。     

Application of the Fisher-Rao Metric to Ellipse Detection

The parameter space for the ellipses in a two dimensional image is a five dimensional manifold, where each point of the manifold corresponds to an ellipse in the image. The parameter space becomes a Riemannian manifold under a Fisher-Rao metric, which is derived from a Gaussian model for the blurring of ellipses in the image. Two points in the parameter space are close together under the Fisher-Rao metric if the corresponding ellipses are close together in the image. The Fisher-Rao metric is accurately approximated by a simpler metric under the assumption that the blurring is small compared with the sizes of the ellipses under consideration. It is shown that the parameter space for the ellipses in the image has a finite volume under the approximation to the Fisher-Rao metric. As a consequence the parameter space can be replaced, for the purpose of ellipse detection, by a finite set of points sampled from it. An efficient algorithm for sampling the parameter space is described. The algorithm uses the fact that the approximating metric is flat, and therefore locally Euclidean, on each three dimensional family of ellipses with a fixed orientation and a fixed eccentricity. Once the sample points have been obtained, ellipses are detected in a given image by checking each sample point in turn to see if the corresponding ellipse is supported by the nearby image pixel values. The resulting algorithm for ellipse detection is implemented. A multiresolution version of the algorithm is also implemented. The experimental results suggest that ellipses can be reliably detected in a given low resolution image and that the number of false detections can be reduced using the multiresolution algorithm.     

Adaptive fuzzy c-shells clustering and detection ofellipses

Several generalizations of the fuzzy c-shells (FCS) algorithm are presented for characterizing and detecting clusters that are hyperellipsoidal shells. An earlier generalization, the adaptive fuzzy c-shells (AFCS) algorithm, is examined in detail and is found to have global convergence problems when the shapes to be detected are partial. New formulations are considered wherein the norm inducing matrix in the distance metric is unconstrained in contrast to the AFCS algorithm. The resulting algorithm, called the AFCS-U algorithm, performs better for partial shapes. Another formulation based on the second-order quadrics equation is considered. These algorithms can detect ellipses and circles in 2D data. They are compared with the Hough transform (HT)-based methods for ellipse detection. Existing HT-based methods for ellipse detection are evaluated, and a multistage method incorporating the good features of all the methods is used for comparison. Numerical examples of real image data show that the AFCS algorithm requires less memory than the HT-based methods, and it is at least an order of magnitude faster than the HT approach.     

基于凸包裁剪的行人视频检测算法

为了解决行人群体视频检测的难题,提出一种基于凸包裁剪的行人视频检测算法。该算法采用局部凸包技术搜索行人外部轮廓,利用凹点挖掘技术裁剪轮廓曲线,建立相应规则排除非头部线段,通过最小二乘拟合法对头部曲线进行快速椭圆检测。实验结果表明,该算法能准确地检测出重叠或连通的头部,排除非头部物体,且处理速度快,实际应用价值高。     

Ellipse proposal and convolutional neural network discriminant for autonomous landing marker detection

Autonomous landing in complex environments is a critical problem for unmanned aerial vehicle autonomous control, and efficiently detecting landing identification mark in real‐world scenario is still challenging. Due to the limited computational power of airborne computing equipment, current target detection algorithms cannot meet the demand efficiently. In this paper, we proposed a new landing marker detection algorithm for autonomous landing systems in a real environment. We used an ellipse detection algorithm to detect the ellipse landmark or other elliptical objects. Furthermore, convolution neural networks were utilized to obtain the correct landmarks, which is robust, fast and can achieve a speed of 25 fps with 720p resolution video on an Intel NUC onboard computer. Unlike the other methods, the accuracy and speed of our algorithm is verified in a real‐time application with more harsh conditions. During system testing, the flight system can detect the object above 20 m, track it, and automatically land on it with this vision algorithm. The algorithm has helped us achieve the first position at Mohamed Bin Zayed International Robotics Challenge in Abu Dhabi this year.     

基于角点特征融合的Mean-shift跟踪算法

传统Harris检测算法不能很好地适应跟踪环境。为此,提出一种基于角点特征融合的Mean-shift跟踪算法。考虑人体姿态变化或遮挡对多区域跟踪的影响,采用角点更新策略,将特征融合主色调模型的跟踪结果与多区域跟踪结果进行权衡。实验结果表明,该算法能克服人体姿态变化或遮挡对跟踪的影响,实时性满足一般跟踪系统的要求,且在非遮挡状况下,其跟踪准确率比传统算法高。     

基于轮廓信息的人脸检测

针对彩色图像提出了一种基于肤色模型、脸部轮廓信息以及眼睛特征的人脸检测算法。采用基于YCbCr色彩空间的肤色分割模型,初步筛选人脸的候选区域;在此基础上进行边缘检测,获得人脸轮廓信息,并利用遗传算法拟合脸部的椭圆;在椭圆的水平方向根据眼睛的几何特征来检测“眼睛对”,再根据“三停五眼”来定位人脸,并利用左右对称性验证人脸。实验表明,该算法对于彩色图像的正面人脸检测具有良好的效果。     

基于SIFT的椭圆区域鲁棒数字水印方案

如何有效抵抗去同步攻击是数字图像水印研究领域的热点问题之一。利用图像仿射协变特征,提出一种可有效抵抗去同步攻击的鲁棒水印算法。对目前流行的利用多尺度Harris和SIFT描述算子来匹配图像的方法,后者有较好的匹配效果,对恢复同步水印更加稳定,并且能较好抵抗去同步攻击。该算法利用性能稳定的SIFT算子提取图像特征点,并通过基于最小生成树聚类算法的选择策略获得一组稳定且彼此独立的椭圆仿射协变特征区域,基于特征区域,利用椭圆归一化得到具有缩放和旋转不变性的圆形区域。将圆形区域进行非下采样轮廓变换（NSCT）,其中非下采样轮廓变换不仅克服了小波（Wavelet）变换的非奇异性最优基缺点,而且提供了优于轮廓（Contourlet）变换的平移不变性。将水印嵌入变换后的低频子带中。该算法实现盲提取,仿真实验结果表明,提出的算法是有效的且对常规图像处理、几何攻击以及组合攻击均具有较好的鲁棒性。     

基于边界曲线弧分割的多椭圆检测

不同于传统的Hough变换算法,提出一种基于边界弧分割的椭圆检测方法。首先将边界从交点处分割成弧段,将得到弧段划分为长弧和短弧两组并按长度降序排序,然后从两组中找出属于某个椭圆的若干弧段,利用最小二乘法拟合得到候选椭圆并验证是否为真正椭圆。实验表明该算法能快速检测出图中椭圆,运行时间远小于采用随机Hough变换算法,在具有噪声、椭圆残缺的情况下仍能有较好的检测结果。     

Ellipse Motion Estimation Using Parametric Snakes

In this paper we propose a multiscale parametric snake model for ellipse motion estimation across a sequence of images. We use a robust ellipse parameterization based on the geometry of the intersection of a cylinder and a plane. The ellipse parameters are optimized in each frame by searching for local minima of the snake model energy including temporal coherence in the ellipse motion. One advantage of this method is that it just considers the convolution of the image with a Gaussian kernel and its gradient, and no edge detection is required. A detailed study about the numerical evaluation of the snake energy on ellipses is presented. We propose a Newton–Raphson-type algorithm to estimate a local minimum of the energy. We present some experimental results on synthetic data, real video sequences and 3D medical images.     

基于EM算法的多椭圆形目标检测

提出了一种椭圆形多目标检测算法。根据椭圆形目标在形状上与高斯分布相对应的特点,计算目标的特征均值和协方差矩阵,采用主元素法来描述椭圆形目标的大小、位置及主轴。对于包含多个目标的重叠区域,设计了一种加权的EM迭代算法,从而精确计算该区域的目标数、各椭圆的统计特性及位置、形状和大小。把该算法应用于水果及运动目标检测,获得稳定、精确的分割结果。     

持续有界扰动系统的嵌套不变椭圆集鲁棒控制

为了抑制外部持续有界扰动和模型不确定性对系统稳定性控制的影响,通过不变集理论,采用嵌套不变椭圆集鲁棒控制算法实现系统的快速稳定控制。控制算法分为离线算法和在线算法两部分。离线时根据公式得到一维状态变量序列,通过线性矩阵不等式方法优化得到嵌套不变椭圆集。在线时,根据系统状态变量在嵌套不变椭圆集的位置,构建新的不变椭圆集并计算得到系统的控制律。给出新的不变椭圆集满足系统控制要求的理论证明。通过与不变单椭圆集控制算法进行仿真比较,结果验证了上述算法的有效性,为持续有界扰动下模型不确定性系统的稳定控制,提供一种有效的控制方法。