Shot boundary detection based on mutual information and canny edge detector

Shot boundary detection servers as the preliminary step to video retrieval. Most of error detections in the present algorithms are caused by object and camera. Many researchers make use of mutual information to detect shot boundary, and the effect is good, however, object motion reduce performance of algorithm in the methods. In this paper, the author present a novel method of shot boundary detection based on the knowledge of mutual information and canny edge detector. We extract video frame edge using canny edge detector, then distinguish object motion and shot transform effectively by analyzing frame edge differences, reducing error detections caused by object motion, improving recall and precision. Experiments prove this method is robust to object motion, performance is better.     

Contour detection improved by frequency domain filtering of gradient image

We propose an intermediate computational step,frequency domain filtering of gradient image,to improve contour detection performance of gradient-based edge detectors.This step is inspired by analyzing the spectrum distribution of object contours and texture edges in the frequency domain of gradient image.We illustrate the principle and efect of this step by adding it to the Canny edge detector.The resulting operator can selectively retain object contours and region boundaries,and meanwhile can dramatically reduce non-meaningful elements caused by textured background.We use several types of images to compare the proposed method and other related methods qualitatively and quantitatively.Experimental results show that the proposed method can efectively enhance the contour detection of Canny edge detector and achieves similar detection performance to two other related methods but runs faster.     

On detection performance of MIMO radar for Rician target

By using spatial diversity, multiple-input-multiple-output (MIMO) radar can improve detection performance for fluctuating targets. In this paper, we propose a spatial fluctuation target model for MIMO radar, where targets are classified as non-fluctuating target, Rayleigh target and Rician target. Based on Stein’s lemma, we use relative entropy to study detection performance of optimum detector for Rician target. It is found that in low signal noise ratio (SNR) region, the performance improvement of MIMO ra...     

基于模糊决策方法的管道泄漏诊断与定位

A leak detection plays a key role in the overall integrity monitoring for a oil pipeline system. A fuzzy decision-making approach to pipeline leak localization is proposed in this paper. The two main methods, pressure gradient localization and negative pressure wave localization, are combined with fuzzy logical decision-making method to form a novel fault diagnosis scheme. The combination scheme can improve the precision of localization. An application example, 14km long oil pipeline leak detection and localization, is illustrated. This method is compared with others through practical experiments and its validity is confirmed by the results.     

High-speed maneuvering target detection approach based on joint RFT and keystone transform

Increasing the integration time is an effective method to improve small maneuvering target detection performance in radar applications.However,range migration and Doppler spread caused by maneuvering target motion during the integration time make it difficult to improve the coherent accumulation of target’s energy and detection performance.In this study,a new method based on Radon Fourier transform(RFT) and keystone transform(KT) for high-speed maneuvering target detection is proposed.The proposed algorithm utilizes second-order KT to correct the range curvature,and the improved dechirping method to compensate for the Doppler spread.RFT is then used to correct the range walk for target coherent detection.The method is capable of correcting the range migration and the time-varied Doppler frequency of the target without knowing its velocity and acceleration.The advantage of the proposed method is that it can increase the coherent integration time and improve detection performance under the condition of Doppler frequency ambiguity.Compared with the second-order RFT algorithm,the computational burden of the proposed method is greatly reduced under the premise that the two methods have similar estimation accuracy of range,velocity and acceleration.Numerical experiments demonstrate the validity of the proposed algorithm.     

Diagnosis and Localization of Pipeline Leak Based on Fuzzy Decision-making Method

A leak detection plays a key role in the overall integrity monitoring for a oil pipeline system.A fuzzy decision-making approach to pipeline leak localization is proposed in this paper. The two main methods,pressure gradient localization and negative pressure wave localization,are combined with fuzzy logical decision-making method to form a novel fault diagnosis scheme.The combination scheme can improve the precision of localization.An application example,14km long oil pipeline leak detection and localization,is illustrated.This method is compared with others through practical experiments and its validity is confirmed by the results.     

基于颜色和特征匹配的视频图像人脸检测实现技术

A face detection method using statistical skin-color model and facial feature matching is presented in this paper.According to skin-color distribution in YUV color space,we develope a statistical skin-color model through interactive sample training and learning.Using this method we convert the color image to binary image and then segment face-candidate regions in the video images.In order to improve the quality of binary image and remove unwanted noises,filtering and mathematical morphology are empolied.After these two processing,we use facial feature matching for further detection.The presence or absence of a face in each region is verified by means of mouth detector based on a template matching method.The experimental results show the proposed method has the features of high speed and high efficiency,but also robust to face variation to some extent.So it is suitable to be applied to real-time face detection and tracking in video sequences.     

Level Set method for license plate localization technology

Localization of license plate is an important factor in license plate recognition system. Currently although there are some methods for the localization, some limits such as low accuracy exist. So a better method should be found to solve this problem. Level Set, which has been proved efficient currently, gives new prospect to license plate localization. In this paper, based on the original thought of Level Set method, the Mumford-Shah model with Level Set method is obtained, further the finite difference and a third order TVD （Total Variation Diminishing） Runge-Kutta time discretization scheme is analyzed, and applied in license plate image localization. Computation results show that better edge detection results from level set method are obtained compared to other edge detection methods such as Roberts, Sobel and Canny. Level Set method drops much edge of non-target area which has a lot of value to target edge detection and target position tracking.     

Dust collector localization in trouble of moving freight car detection system

For a long time,trouble detection and maintenance of freight cars have been completed manually by inspectors.To realize the transition from manual to computer-based detection and maintenance,we focus on dust collector localization under complex conditions in the trouble of moving freight car detection system.Using mid-level features which are also named flexible edge arrangement(FEA) features,we first build the edge-based 2D model of the dust collectors,and then match target objects by a weighted Hausdorff distance method.The difference is that the constructed weighting function is generated by the FEA features other than specified subjectively,which can truly reflect the most basic property regions of the 3D object.Experimental results indicate that the proposed algorithm has better robustness to variable lighting,different viewing angle,and complex texture,and it shows a stronger adaptive performance.The localization correct rate of the target object is over 90%,which completely meets the need of practical applications.     

Geometric primitive extraction by the combination of tabu search and subpixel accuracy

In this paper,a novel method for extracting the geometric primitives from geometric.Specifically,tabu search is combined with subpixel accuracy to improve detection accuracy and convergent speed.On the one hand,this new shape detection method not only has TS‘s ability to find the global optimum,but also keeps all advantages of tabu search.On the other hand,it has subpixel accuracy ability to match the local optimum.     

图像边缘轮廓自适应阈值的角点检测算法

目的 基于边缘轮廓的角点检测算法的检测性能虽然相对比较稳定,但是它对边缘轮廓的局部变化敏感,并且只是给予一个经验门限去提取角点,为此提出一种对局部变化和噪声稳健的基于图像边缘轮廓自适应阈值的角点检测算法。方法 该算法利用各向异性高斯方向导数滤波器对不同边缘和角点模型进行表征,提取表征边缘和角点的灰度及几何变化的不变属性,并通过正则化计算得到区别边缘和角点的自适应阈值。该算法首先利用Canny边缘检测器检测输入图像的边缘映射并从边缘映射中提取出边缘轮廓;然后利用各向异性高斯方向导数滤波器对所提取出的边缘曲线进行滤波平滑,计算出每一像素点的响应并与自适应阈值作比较,把响应大于阈值的点作为候选角点;最后,对候选角点进行非极大值抑制得到最终角点集。结果 提出的算法分别与Harris算法,He & Yung算法,以及ANDDs算法在仿射变换和高斯噪声的实验环境下进行比较,其性能指标为平均重复率与定位误差;并且对每个角点检测算法在无噪声和有噪声的情况下进行了角点匹配比较。4种算法的两个指标的平均排名为Harris 3.375,He &Yung 2.625,ANDDs 2.625,本文算法 1.375。本文算法在仿射变换以及高斯噪声的情况下有着良好的平均重复率和定位误差,优于其他3种算法。匹配实验中的错误点以及丢失点也少于其他3种算法。结论 图像的特征检测在计算机视觉领域是一个重要的课题,在许多视觉系统中,检测特征往往作为复杂计算的第1步。因此,这一步的可靠性会极大地影响着视觉系统整体的结果。而角点作为图像的重要特征,对其研究具有重大意义。本文算法不同于传统的基于边缘的角点检测器仅利用边缘轮廓的信息,还利用到图像边缘像素的灰度信息。而且,本文算法还采用一个自适应全局阈值,避免了角点的误判。正则化的灰度变化有效减少了噪声或者光照对检测性能的影响。通过角点匹配实验、仿射变换实验以及高斯噪声实验,可以看出,本文的角点检测器拥有良好的检测性能,并且对噪声具有稳健性。     

一种广泛适用的激光雷达数据特征提取方法

提出了一种新颖的、无需先验知识的、广泛适用于各种环境的激光雷达数据特征提取方法来解决同步 定位与地图创建（SLAM）中的特征提取问题．这种方法采用经典的图像特征提取方法——Harris 角点探测器,具 体来说,是多尺度Kanade-Tomasi 角点探测器,来提取特征．这种方法可以从各种尺度的测量数据中提取稳定、精 确的特征点,并同时可以得到特征点描述器和不确定性信息．文章将这种方法应用在了软件仿真环境及经典数据集 上,包括：2 维的维多利亚公园数据集、英特尔研究中心数据集（Intel Research Center dataset）以及3 维的麻省理工 学院美国国防部高级研究计划局城市竞赛数据集（MIT DARPA Urban Challenge dataset）．实验结果表明这种方法可 以从各种环境中提取高精度、高重复性的稳定特征．     

使用多弦长曲率多项式的角点检测算法

在弦到点的距离累加(CPDA)技术和曲率积的基础上,提出了多弦长曲率多项式的角点检测算法。首先利用Canny边缘检测器抽取边缘,然后对于不同弦长下边缘轮廓曲率局部极大值点,计算曲率的和;对于非极值点,计算曲率的积。该方法不仅可以显著增强曲率极值点的峰值,而且避免了曲率积对一些角点平滑。最后,为了降低人为设定门限带来的错检或漏检,利用局部自适应阈值去判别角点。实验结果表明,与其他的角点检测算法相比,该方法具有很强的鲁棒性,它的平均检测准确率提高了14.5%,而且在角点数重复率准则上平均性能提高了12.6%。     

基于多尺度曲率乘积的鲁棒图像角点检测

为了更好地进行图像角点检测,在曲率尺度空间(CSS)框架下,提出了一种基于多尺度乘积的角点检测技术,其中曲率尺度积函数被定义为各个尺度下轮廓曲率的乘积,而角点则被定义为曲率乘积的局部极值点。这种尺度积不仅能显著地增强角点曲率极值点的峰值,同时能抑制噪声影响,而且不改变角点的位置,为了说明该技术的优点,根据角点数一致性(CCN)准则证明了该技术优于其他的角点检测算法。实验结果表明,该方法不仅具备优越的检测效果,并对噪声有较强的鲁棒性。     

一种基于角点的Mean Shift目标跟踪算法*

为了提高经典的Mean Shift算法在复杂场景中的跟踪性能,提出了一种基于角点的目标表示方法。首先,利用Harris角点检测算法提取表示目标主要特征的角点;其次,基于提取的角点,建立目标模型,将其嵌入Mean Shift算法进行跟踪。该方法仅用少量的关键点表示目标,能够自动去除目标和背景中的次要特征,有效地抑制背景成分对目标定位的影响,从而改进Mean Shift目标跟踪算法的性能。通过测试两个复杂环境下的视频,实验结果表明,相对于传统的目标跟踪算法,提出的方法取得了更好的性能。     

迭代分割逼近:新的基于局部响应显著度的角点检测

为了提高角点检测算法的精确度,同时保持较低的时间复杂度,提出了一种基于自定义的局部角点响应显著度和迭代分割逼近的角点检测方法。首先,定义了一个新的测度量——局部角点响应显著度(LCRS),用来衡量一个候选角点在其局部区域内的响应显著程度,并证明了基于LCRS的角点检测准则等价于局部自适应阈值法。其次,将LCRS视作区域的响应显著度性质,把寻找角点的任务转化为寻找高显著性区域。据此,提出迭代分割的策略用来逐步收缩显著区域,最终逼近真实角点的位置。迭代分割逼近(ISA)算法可以使用不同的角点响应函数(CRF)定义,而且其平均情况时间复杂度与Harris算法相同。实验结果表明,当采用Noble算子的CRF时,ISA算法平均误检率、漏检率分别比Noble算子低4.62%和5.59%;而当采用Harris算子的CRF时,这两个比率也分别比Harris算子低2.87%和3.37%。而且这两种情况下ISA算法的平均运行时间均小于Harris算子和Noble算子。     

基于亚像素边缘定位的排针参数精密测量

为了提高排针参数的检测效率和精度,提出了一种利用亚像素边缘定位对排针进行非接触测量的方法.首先采用LOG算子对图像进行整像素级的边缘粗定位,在抑制噪声的同时,保持图像边缘的完整性.然后采用改进的Zemike矩进行亚像素边缘定位.最后通过最小二乘法拟合离散的边缘点得出排针的精确边缘.实验结果表明,该方法边缘定位精度高,稳...     

基于气门油封的亚像素边缘检测

针对气门油封的尺寸检测问题, 本文提出了一种基于Zernike矩改进算法的亚像素边缘检测方法. 首先, 对比分析了高斯滤波和双边滤波的预处理效果, 结果表明双边滤波在滤波和保留边缘信息方面具有更好的表现. 然后, 采用Canny算子进行边缘粗定位, 并利用自适应的Zernike矩过度模型进行亚像素级定位. 最后, 采用最小二乘拟合圆法获取圆心坐标和半径. 经试验证明, 优化后算法的边缘定位平均误差更小, 精度更加准确.     

改进的Harris亚像素角点快速定位

针对Harris算法检测角点存在偏差、运算慢、像素级精度难于满足实际应用需要等问题,改进了Harris角点检测方法。该方法在Harris提取角点过程中,通过两次角点筛选,剔除非角点和伪角点,利用角点响应函数执行非极大值抑制,以局部角点响应函数最大值的像素点作为初始角点,并以该初始角点为中心,以一定半径搜索角点簇,采用最小二乘法加权角点簇与待求角点的欧几里得距离,精化初始角点坐标,从而实现Harris亚像素角点准确快速定位。实验结果表明了该方法的有效性和实用性。     

利用圆结构元的形态学角点检测

提出一种基于圆盘结构元的形态学角点检测算法,使用形态学方法,在圆盘结构元高帽运算后剩余部分中确定一个三角形区域,通过检测三角形的顶点获得图像中的角点.在检测角点的同时,利用三角形区域的几何特征完成检测角的角度和朝向估计,并引入结构元尺寸自学习机制自动确定结构元尺寸,完成角检测.与其他6种角检测方法的对比实验证明了文中方法的优越性,并对其他角检测方法中很少涉及的角度和朝向估计给出了实验结果.