Using vanishing points for camera calibration and coarse 3D reconstruction from a single image

In this paper, we show how to calibrate a camera and to recover the geometry and the photometry (textures) of objects from a single image. The aim of this work is to make it possible walkthrough and augment reality in a 3D model reconstructed from a single image. The calibration step does not need any calibration target and makes only four assumptions: (1) the single image contains at least two vanishing points, (2) the length (in 3D space) of one line segment (for determining the translation vector) in the image is known, (3) the principle point is the center of the image, and (4) the aspect ratio is fixed by the user. Each vanishing point is determined from a set of parallel lines. These vanishing points help determine a 3D world coordinate system R _o. After having computed the focal length, the rotation matrix and the translation vector are evaluated in turn for describing the rigid motion between R _o and the camera coordinate system R _c. Next, the reconstruction step consists in placing, rotating, scaling, and translating a rectangular 3D box that must fit at best with the potential objects within the scene as seen through the single image. With each face of a rectangular box, a texture that may contain holes due to invisible parts of certain objects is assigned. We show how the textures are extracted and how these holes are located and filled. Our method has been applied to various real images (pictures scanned from books, photographs) and synthetic images.     

Real-time CAM-based Hough transform algorithm and its performance evaluation

Abstract. This paper proposes a highly parallel Hough transform algorithm for real-time straight-line extraction and its hardware implementation on a content-addressable memory (CAM). To achieve high-speed processing, incrementation for voting, which composes the Hough transform, and calculations for coordinate updating are carried out for the every scan line, not every edge pixel, and extracting maxima in Hough space is executed by parallel comparing. Moreover, variously weighted voting achieves more accurate line extraction in spite of the quantization error and noise in the image space. In the implementation, the CAM acts as a PE (processing-element) array that effectively performs highly parallel processing for the Hough transform and also as a memory for two-dimensional Hough space, and both voting and peak extraction are directly executed by the CAM. Evaluations of CAM hardware size, processing time and the accuracy of line extraction show that a real-time and high-resolution Hough transform for a 256256 picture can be achieved using a single CAM chip with current VLSI technology. This CAM-based Hough transform algorithm promises to be an important step towards the realization of a real-time and compact image-understanding system. Received: 15 August 1998 / Accepted: 15 March 2000     

利用小变换和特征加权进行纹理分割

为了提高纹理图象分割的边缘准确性和区域一致性以及降低分割错误率,提出了一种基于小波变换的利用特征加权来进行纹理分割的方法。该方法包括特征提取、预分割和后分割3个阶段,其中,特征提取在金字塔结构小小以变换的基础上进行;预分割利用均人矣类算法来对原始图象进行初步的分割;后分割则根据预分割的结果对特征进行加权,然后利用最小距离分类器来实现图象的最后分割。与传统的方法相比,该方法在分割错误率、边缘准确性以及区域一致性等方面均有明显的改善。     

一种复杂背景下的运动目标提取算法

本文首先概述了目标提取的诸多算法,然后针对复杂背景下的运动目标提取,重点研究了帧间图像差分算法,设计了一种目标提取算法模型,最后提出了一种基于对象的目标提取方法并进行了仿真实验。     

人脸检测与识别技术综述

人脸的自动识别是模式识别、图像处理等学科的研究热点,并在商业和法律方面有广阔的应用前景(如身份证、信用卡、护照等身份认证以及智能小区管理、电视监控系统等等),近年来关于人脸自动识别的研究取得了很大的进展。但是,这些研究成果离这一问题的彻底解决还有很大的距离,这一课题仍然是当前研究的热点问题之一。本文重点对现有的人脸检测与识别的方法及研究进行总结,并比较了各种方法的优缺点。并在最后指出了进一步工作的方向。     

基于8邻域编码逐像素跟踪法的指纹细节特征提取算法

研究并实现基于8邻域编码逐像素跟踪法的细节特征提取算法。该算法能有效提取细化后指纹图像中的端点和分叉点,通过回朔跟踪法,能有效去除图像中的伪特征点。实验结果表明该算法较大幅度提高了特征提取的速度,并能够较准确的滤除伪特征点,缩短了图像后处理时间,可以满足实际应用的需要。     

基于网站结构分析页面信息提取的方法研究

在分析网站结构的基础上,把同类信息划归为一个页面组,建立相应的XML模板库,进行web信息挖掘,为实现页面信息快速查询和信息分类提供了很好的方法。     

基于表格语义的Web信息抽取方法的研究

在Web页面常用到表格这种元素。本文提出一种根据表格语义来进行信息抽取方法。首先提出了一种短语语义相似度的度量方法,然后利用短语语义的相似度确定表格标题行(列),并对表格行(列)与抽取字段的对应关系进行计算,最后计算表格的整体语义,度量该表格与所要抽取的内容有多大相关度。     

Blind Source Extraction for Noisy Mixtures by Combining Gaussian Moments and Generalized Autocorrelations

In the blind source extraction problem, the concept of generalized autocorrelations has been successfully used when the desired signal has special temporal structures. However, their applications are only limited to noise-free mixtures, which is not realistic. Therefore, this paper addresses the extraction of the noisy model based on these temporal characteristics of sources. An objective function, which combines Gaussian moments and generalized autocorrelations, is proposed. Maximizing this objective function, we present a blind source extraction algorithm for noisy mixtures. Simulations on synthesized signals, images, artificial electrocardiogram (ECG) data and the real-world ECG data show the better performance of the proposed algorithm. Moreover, comparisons with the existing algorithms further indicate its validity and also show its robustness to the estimated error of time delay.     

Feature Extraction using Unit-linking Pulse Coupled Neural Network and its Applications

In this paper, we use Unit-linking PCNN (Pulse Coupled Neural Network), the simplified model of PCNN consisting of spiking neurons, to code a 2-dimensional image into a 1-dimensional time sequence called global Unit-linking PCNN image icon or time signature, including features of the original image and having the translation, rotation, and scale invariance. Dividing an image into multiple parts can obtain local Unit-linking PCNN image icons corresponding to the image’s local regions, which can reflect the local changes of the image. In the meantime, the global and the local Unit-linking PCNN image icons are used in navigation, object detection, and image authentication. In navigation, global Unit-linking PCNN image icon shows qualified performance especially in non-stationary-video navigation. Object detection using global Unit-linking PCNN image icon, is independent of variances of translation, rotation, and scale, and object segmentation is avoided. In image authentication, using local Unit-linking PCNN image icon can authenticate correctly some juggled images failed to authenticate by using local histogram or local mean intensity, and can locate the juggled positions in the juggled images with some accuracy.