基于分层六角网格对简单三维物体的快速识别

提出了一种利用目前的CRS系统摄取六角网格数字图像的方法,并对获取的图像提出了基于金字塔处理的、从边缘检测等低层处理到模式识别等高层处理的算法.借助串行计算机模拟,利用六角几何和并行处理构架来识别六角网格数字图像中的物体.实验结果表明,该算法能够快速地识别一些简单的三维物体.最后提出了一个2层的六角网格视网膜的设计方案.文中论证了用于图像分析的六角像素网格的鲁棒性.     

A Fisher-Rao Metric for Paracatadioptric Images of Lines

In a central paracatadioptric imaging system a perspective camera takes an image of a scene reflected in a paraboloidal mirror. A 360° field of view is obtained, but the image is severely distorted. In particular, straight lines in the scene project to circles in the image. These distortions make it difficult to detect projected lines using standard image processing algorithms. The distortions are removed using a Fisher-Rao metric which is defined on the space of projected lines in the paracatadioptric image. The space of projected lines is divided into subsets such that on each subset the Fisher-Rao metric is closely approximated by the Euclidean metric. Each subset is sampled at the vertices of a square grid and values are assigned to the sampled points using an adaptation of the trace transform. The result is a set of digital images to which standard image processing algorithms can be applied. The effectiveness of this approach to line detection is illustrated using two algorithms, both of which are based on the Sobel edge operator. The task of line detection is reduced to the task of finding isolated peaks in a Sobel image. An experimental comparison is made between these two algorithms and third algorithm taken from the literature and based on the Hough transform.     

Differentiation-Based Edge Detection Using the Logarithmic Image Processing Model

The logarithmic image processing (LIP) model is a mathematical framework which provides a specific set of algebraic and functional operations for the processing and analysis of intensity images valued in a bounded range. The LIP model has been proved to be physically justified by that it is consistent with the multiplicative transmittance and reflectance image formation models, and with some important laws and characteristics of human brightness perception. This article addresses the edge detection problem using the LIP-model based differentiation. First, the LIP model is introduced, in particular, for the gray tones and gray tone functions, which represent intensity values and intensity images, respectively. Then, an extension of these LIP model notions, respectively called gray tone vectors and gray tone vector functions, is studied. Third, the LIP-model based differential operators are presented, focusing on their distinctive properties for image processing. Emphasis is also placed on highlighting the main characteristics of the LIP-model based differentiation. Next, the LIP-Sobel based edge detection technique is studied and applied to edge detection, showing its robustness in locally small changes in scene illumination conditions and its performance in the presence of noise. Its theoretical and practical advantages over several well-known edge detection techniques, such as the techniques of Sobel, Canny, Johnson and Wallis, are shown through a general discussion and illustrated by simulation results on different real images. Finally, a discussion on the role of the LIP-model based differentiation in the current context of edge detection is presented.     

有关正六边形点阵结构数字图像的研究

传统连续图像信号的采样过程采用的是矩形点阵结构。当连续图像信号的频带处于一个圆形区域之内时，正六边形点阵结构的采样密度比矩形点阵结构的采样密度要降低13．4％。但目前图像输入输出设备只支持矩形点阵结构的数字图像，所以首先讨论了满足Nyquist采样定理的正六边形点阵结构的采样矩阵(空间采样间隔)，及矩形点阵结构数字图像和正六边形点阵结构数字图像之间的转换。另一方面由于正六边形点阵结构的数字图像是不可分离信号，这给图像处理造成许多的不便。为此提出了一种基于可分离滤波器阵列的图像分解方法，降低了计算复杂度，得到类似矩形图像小波变换所得的多尺度分解结构，并给出重构图像的实验结果。     

硅通孔键合硅片预对准边缘信息采集与处理

研究硅通孔即TSV(through-silicon vias)键合硅片的预对准边缘信息采集与处理方法。TSV硅片与标准硅片相比,有减薄、键合不同心、边缘毛刺多、存在崩边;缺口被填充、内有鼓胶、镀铜等工艺特点,使得传统基于线阵CCD一维图像采集与处理预对准方法失败。针对TSV硅片的特点,把线阵CCD配合扫描运动采集的一维原始图像集拼接获得二维图像,应用二维图像处理技术提取边缘信息,硅片整周边缘数据用最小二乘圆拟合算法识别出圆心位置,缺口边缘数据用Hough直线变换识别出缺口两条斜边,其交点定位为缺口位置,从而实现TSV硅片的自动预对准。实际测量表明,该方法预对准重复性定位精度<20um、预对准时间<40s,满足指标需求,为光刻机能够曝光TSV硅片提供有力支持。     

六角网格上的图象处理算法的研究

经研究表明,屏幕上的点最佳分布是按六角网格形式分布的,文中首先讨论了六角网格的特点,屏幕用正六边形覆盖,即每个象素对应着一个正六边形,而将正六边形的中心点做为网格点;并从图形图象处理的角度分析了它的优点,如显示的直线（或曲线）没有“断开”的感觉,每个象素与所有相邻象素之间只有一种相邻关系,这就为许多图象处理提供了简便的实现途径,然后提出了在六角网格上进行图象处理的数字化过程以及在图象恢复时几何失真校正的算法,可以看出,在达到同样精度时计算量比方型网格上有明显减少。     

六角网格中三维物体模式识别算法

提出一些算法,这些算法预期成为在六角网格中实现对三维物体快速、并行的模式识别的整体方案的一部分。这些算法包括在7-像素六角邻域之内基于灰度差值的边缘检测、局部边缘减薄和基于7-点六角掩模的特征提取。通过串行计算机模拟,这些算法对诸如方体等一些简单物体的真实六角网格数字图像的实验性验证已经显示了在快速识别三维物体轮廓的关键性特征方面的成功。     

An optimal frequency domain filter for edge detection in digital pictures

Edge detection and enhancement are widely used in image processing applications. In this paper we consider the problem of optimizing spatial frequency domain filters for detecting edges in digital pictures. The filter is optimum in that it produces maximum energy within a resolution interval of specified width in the vicinity of the edge. We show that, in the continuous case, the filter transfer function is specified in terms of the prolate spheroidal wave function. In the discrete case, the filter transfer function is specified in terms of the sampled values of the first-order prolate spheroidal wave function or in terms of the sampled values of an asymptotic approximation of the wave function. Both versions can be implemented via the fast Fourier transform (FFT). We show that the optimum filter is very effective for detecting blufred and noisy edges. Finally, we compare the performance of the optimum edge detection filter with other edge detection filters using a variety of input images.     

Edge Detection in Pipe Images Using Classification of Haar Wavelet Transforms

Automatic image interpretation for pipe inspection is a relatively recent area of research, which has great potential benefit. An important component of such systems is crack detection, or, more generally, edge or discontinuity detection. This paper describes a new approach to edge detection and applies it to pipe images. The method labels each pixel in an image as an edge pixel or a nonedge pixel by processing the Haar wavelet transform of the image in a window about the pixel using a support vector machine. As a pixel classifier, to within a moderate morphological tolerance, the detector has an accuracy of 99% on the images on which it has been tested and compares favorably with the commonly used Canny edge detector.     

Contrast Enhancement Based Image Detection Using Edge Preserved Key Pixel Point Filtering

In existing methods for segmented images, either edge point extraction or preservation of edges, compromising contrast images is so sensitive to noise. The Degeneration Threshold Image Detection (DTID) framework has been proposed to improve the contrast of edge filtered images. Initially, DTID uses a Rapid Bilateral Filtering process for filtering edges of contrast images. This filter decomposes input images into base layers in the DTID framework. With minimal filtering time, Rapid Bilateral Filtering handles high dynamic contrast images for smoothening edge preservation. In the DTID framework, Rapid Bilateral Filtering with Shift-Invariant Base Pass Domain Filter is insensitive to noise. This Shift-Invariant Filtering estimates value across edges for removing outliers (i.e., noise preserving base layers of the contrast image). The intensity values are calculated in the base layer of the contrast image for accurately detecting nearby spatial locations using Shift-Invariant base Pass Domain Filter (SIDF). At last, Affine Planar Transformation is applied to detect edge filtered contrast images in the DTID framework for attaining a high quality of the image. It normalizes the translation and rotation of images. With this, Degeneration Threshold Image Detection maximizes average contrast enhancement quality and performs an experimental evaluation of factors such as detection accuracy, rate, and filtering time on contrast images. Experimental analysis shows that the DTID framework reduces the filtering time taken on contrast images by 54% and improves average contrast enhancement quality by 27% compared to GUMA, HMRF, SWT, and EHS. It provides better performance on the enhancement of average contrast enhancement quality by 28%, detection accuracy rate by 26%, and reduction in filtering time taken on contrast images by 30% compared to state-of-art methods.     

分层六角网格中物体边缘检测的算法

本文提出了在分层六角网格中基于像素灰度实现边缘检测的边缘点确定算法和边缘构造算法。文中首先介绍了六角网格结构的优势和1：3面积比、1：4面积比两类六角网格金字塔,而后给出了相应的实验论证。实验结果显示应用六角网格金字塔的算法对图像数据中的缝隙与噪声具有鲁棒性,1：4面积比六角金字塔在边缘检测中优于1：3面积比金字塔。     

Statistical edge detection: learning and evaluating edge cues

We formulate edge detection as statistical inference. This statistical edge detection is data driven, unlike standard methods for edge detection which are model based. For any set of edge detection filters (implementing local edge cues), we use presegmented images to learn the probability distributions of filter responses conditioned on whether they are evaluated on or off an edge. Edge detection is formulated as a discrimination task specified by a likelihood ratio test on the filter responses. This approach emphasizes the necessity of modeling the image background (the off-edges). We represent the conditional probability distributions nonparametrically and illustrate them on two different data sets of 100 (Sowerby) and 50 (South Florida) images. Multiple edges cues, including chrominance and multiple-scale, are combined by using their joint distributions. Hence, this cue combination is optimal in the statistical sense. We evaluate the effectiveness of different visual cues using the Chernoff information and Receiver Operator Characteristic (ROC) curves. This shows that our approach gives quantitatively better results than the Canny edge detector when the image background contains significant clutter. In addition, it enables us to determine the effectiveness of different edge cues and gives quantitative measures for the advantages of multilevel processing, for the use of chrominance, and for the relative effectiveness of different detectors. Furthermore, we show that we can learn these conditional distributions on one data set and adapt them to the other with only slight degradation of performance without knowing the ground truth on the second data set. This shows that our results are not purely domain specific. We apply the same approach to the spatial grouping of edge cues and obtain analogies to nonmaximal suppression and hysteresis.     

λτ-space representation of images and generalized edgedetector

An image and surface representation based on regularization theory is introduced in this paper. This representation is based on a hybrid model derived from the physical membrane and plate models. The representation, called the λτ-representation, has two dimensions; one dimension represents smoothness or scale while the other represents the continuity of the image or surface. It contains images/surfaces sampled both in scale space and the weighted Sobolev space of continuous functions. Thus, this new representation can be viewed as an extension of the well-known scale space representation. We have experimentally shown that the proposed hybrid model results in improved results compared to the two extreme constituent models, i.e., the membrane and the plate models. Based on this hybrid model, a generalized edge detector (GED) which encompasses most of the well-known edge detectors under a common framework is developed. The existing edge detectors can be obtained from the generalized edge detector by simply specifying the values of two parameters, one of which controls the shape of the filter (τ) and the other controls the scale of the filter (λ). By sweeping the values of these two parameters continuously, one can generate an edge representation in the λτ space, which is very useful for developing a goal-directed edge detection scheme for a specific task. The proposed representation and the edge detector have been evaluated qualitatively and quantitatively on several different types of image data such as intensity, range, and stereo images     

Digital Twin-driven online anomaly detection for an automation system based on edge intelligence

Accurate anomaly detection is critical to the early detection of potential failures of industrial systems and proactive maintenance schedule management. There are some existing challenges to achieve efficient and reliable anomaly detection of an automation system: (1) transmitting large amounts of data collected from the system to data processing components; (2) applying both historical data and real-time data for anomaly detection. This paper proposes a novel Digital Twin-driven anomaly detection framework that enables real-time health monitoring of industrial systems and anomaly prediction. Our framework, adopting the visionary edge AI or edge intelligence (EI) philosophy, provides a feasible approach to ensuring high-performance anomaly detection via implementing Digital Twin technologies in a dynamic industrial edge/cloud network. Edge-based Digital Twin allows efficient data processing by providing computing and storage capabilities on edge devices. A proof-of-concept prototype is developed on a LiBr absorption chiller to demonstrate the framework and technologies' feasibility. The case study shows that the proposed method can detect anomalies at an early stage.     

基于双层级联GAN的草图到真实感图像的异质转换

不同于pix2pix框架将边缘线条图转换为真实感图像的工作,文中探讨更便于人机交互的手绘草图到真实感图像的转换问题.首先设计双层级联生成对抗网络(GAN)结构实现转换任务.第一层GAN根据草图的形态结构、语义内容等信息生成粗粒度真实感图像,第二层GAN将第一层的结果转换为更生动形象的高分辨真实感图像.然后,针对上述网络训练中现有可用的“草图-图像”数据集十分稀缺的问题,提出依据给定的图像自动生成模拟草图数据的方法.通过改进HED边缘检测算法获得草图轮廓,并采用移动最小二乘策略对轮廓进行变形,模拟草图形态意向可辨、线条简洁、具有随意性的特点.实验表明,将手绘草图作为输入,文中方法转换结果图的合理性和视觉真实感优于基于边缘线条图训练的方法.此外,文中方法可以推广到涉及草图处理的其它应用领域.     

基于多尺度自适应加权的改进Canny算子

在Canny算法框架下,对彩色遥感图像进行多尺度滤波分析。定义多个不同尺度的高斯滤波器,在每个尺度下,分别对遥感图像RGB三个通道进行滤波和梯度计算,取三个通道的梯度最大值为该尺度下的遥感图像梯度值。根据各个尺度的滤波器对噪声的抑制能力及边缘定位能力的不同,自适应地确定相应的权值大小,然后再将这些不同尺度下检测到的梯度图像用自适应确定的权值进行加权合成最终的梯度图像。在此基础上,由非极大值抑制和双阈值处理得到图像边缘。实验结果表明,该算法比传统的Canny算子在噪声抑制和边缘定位方面具有更优的性能,适合彩色遥感图像的边缘检测。     

New Riemannian techniques for directional and tensorial image data

This paper develops new geometrical filtering and edge detection algorithms for processing non-Euclidean image data. We view image data as residing on a Riemannian manifold, and we work with a representation based on the exponential map for this manifold together with the Riemannian weighted mean of image data. We show how the weighted mean can be efficiently computed using Newton's method, which converges faster than the gradient descent method described elsewhere in the literature. Based on geodesic distances and the exponential map, we extend the classical median filter and the Perona-Malik anisotropic diffusion technique to smooth non-Euclidean image data. We then propose an anisotropic Gaussian kernel for image filtering, and we also show how both the median filter and the anisotropic Gaussian filter can be combined to develop a new edge preserving filter, which is effective at removing both Gaussian noise and impulse noise. By using the intrinsic metric of the feature manifold, we also generalise Di Zenzo's structure tensor to non-Euclidean images for edge detection. We demonstrate the applications of our Riemannian filtering and edge detection algorithms both on directional and tensor-valued images.     

常用边缘检测技术的对比

边缘检测是图像处理和计算机视觉中的基本问题,边缘检测的目的是标识数字图像中亮度变化明显的点.经典的边缘检测算法如canny算子等是通过计算图像中局部小区域的差分来实现边缘检测的.这类算子对噪声非常敏感,并且常常会在检测边缘的同时加强噪声.多尺度形态学边缘检测利用不同的结构元素去作用图像,通过形态腐性和形态膨胀操作,获得了效果很好的图像边缘检测算法.单尺度形态学梯度算子也能很好提检测图像边缘,但结构元素的选取对输出结果影响较大.通过使用多尺度形态学梯度算子,可以弥补结构元素的大小问题.仿真结果表明,该算法能得到较为理想的图像边缘信息,其抗噪声性能明显优于经典的算子检测算法.     

An edge detection framework conjoining with IMU data for assisting indoor navigation of visually impaired persons

Smartphone applications based on object detection techniques have recently been proposed to assist visually impaired persons with navigating indoor environments. In the smartphone, digital cameras are installed to detect objects which are important for navigation. Prior to detect the interested objects from images, edges on the objects have to be identified. Object edges are difficult to be detected accurately as the image is contaminated by strong image blur which is caused by camera movement. Although deblurring algorithms can be used to filter blur noise, they are computationally expensive and not suitable for real-time implementation. Also edge detection algorithms are mostly developed for stationary images without serious blur. In this paper, a modified sigmoid function (MSF) framework based on inertial measurement unit (IMU) is proposed to mitigate these problems. The IMU estimates blur levels to adapt the MSF which is computationally simple. When the camera is moving, the topological structure of the MSF is estimated continuously in order to improve effectiveness of edge detections. The performance of the MSF framework is evaluated by detecting object edges on video sequences associated with IMU data. The MSF framework is benchmarked against existing edge detection techniques and results show that it can obtain comparably lower errors. It is further shown that the computation time is significantly decreased compared to using techniques that deploy deblurring algorithms, thus making our proposed technique a strong candidate for reliable real-time navigation.