课堂环境下用于头部行为识别的李群特征表示

头部行为是个体行为的重要组成部分,在课堂环境下对于学生的行为来说更是如此。使用传统的RGB视频图像进行头部行为识别有着许多限制,例如背景的干扰和光线的变化等,而深度图像可以通过包含的深度信息很好地处理这些问题。针对课堂环境下的头部行为识别问题,受到李群理论的启发,提出了一种从深度图像中提取李群特征表示的模型,并且使用该李群特征完成了头部行为识别任务。从深度图像中获取脸部的关键点及关键段信息,通过计算相邻帧之间关键段的旋转及位移获得能够同时表示时间空间信息的李群特征表示,使用支持向量机来完成头部行为的分类识别。在公开数据集上验证了方法的有效性,然后通过Kinect获取制作了课堂环境下的真实行为数据,实验结果表明李群特征表示方法能够有效帮助课堂环境下头部行为的识别,对课堂环境下的学生行为识别提供了帮助。     

Inter-Image Statistics for 3D Environment Modeling

In this article we present a method for automatically recovering complete and dense depth maps of an indoor environment by fusing incomplete data for the 3D environment modeling problem. The geometry of indoor environments is usually extracted by acquiring a huge amount of range data and registering it. By acquiring a small set of intensity images and a very limited amount of range data, the acquisition process is considerably simplified, saving time and energy consumption. In our method, the intensity and partial range data are registered first by using an image-based registration algorithm. Then, the missing geometric structures are inferred using a statistical learning method that integrates and analyzes the statistical relationships between the visual data and the available depth on terms of small patches. Experiments on real-world data on a variety of sampling strategies demonstrate the feasibility of our method. Electronic Supplementary Material  The online version of this article () contains supplementary material, which is available to authorized users.     

Reconstructing Open Surfaces from Image Data

In this paper a method for fitting open surfaces to data obtained from images is presented using a level set representation of the surface. This is done by tracking a curve, representing the boundary, on the implicitly defined surface. This curve is given as the intersection of the level set describing the surface and an auxiliary level set. These two level sets are propagated using the same motion vector field. Special care has to be taken in order for the surfaces not to intersect at other places than at the desired boundary. Methods for accomplishing this are presented and a fast scheme for finding initial values is proposed. This method gives a piecewise linear approximation of the initial surface boundary using a partition of the convex hull of the recovered 3D data. With the approach described in this paper, open surfaces can be fitted to e.g. point clouds obtained using structure from motion techniques. This paper solves an important practical problem since in many cases the surfaces in the scene are open or can only be viewed from certain directions. Experiments on several data sets support the method.     

脑MR图像互信息最大的凸优化分割模型

脑MR图像中普遍存在灰度不均匀性,传统的分割方法无法得到理想的脑组织分割结果.为此提出一种基于互信息最大化准则的变分水平集凸优化分割模型.首先建立最大化图像灰度与标记之间互信息能量的分割模型,并融入偏移场信息;对模型进行水平集表示和凸优化后,再引入边缘指示函数加权的总变差范数;最后采用SplitBregman方法快速求解.实验结果表明,该模型可以得到较准确的脑组织分割和偏移场矫正结果,对噪声和灰度不均匀性有很好的鲁棒性.     

A Super-Resolution Framework for High-Accuracy Multiview Reconstruction

We present a variational framework to estimate super-resolved texture maps on a 3D geometry model of a surface from multiple images. Given the calibrated images and the reconstructed geometry, the proposed functional is convex in the super-resolution texture. Using a conformal atlas of the surface, we transform the model from the curved geometry to the flat charts and solve it using state-of-the-art and provably convergent primal–dual algorithms. In order to improve image alignment and quality of the texture, we extend the functional to also optimize for a normal displacement map on the surface as well as the camera calibration parameters. Since the sub-problems for displacement and camera parameters are non-convex, we revert to relaxation schemes in order to robustly estimate a minimizer via sequential convex programming. Experimental results confirm that the proposed super-resolution framework allows to recover textured models with significantly higher level-of-detail than the individual input images.     

图像点模式匹配的一种凸包序列的图谱方法

利用点集的凸包具有仿射不变性和局部可控性,针对图谱方法难以精确匹配旋转角度较大图像的问题,提出了图像点模式匹配的一种凸包序列的图谱方法,使得匹配在图像旋转角度较大的情形下仍具有稳定性。构建图像特征点集新的图模型（凸包）,利用改进的图谱方法对凸包进行匹配,并减小原始特征点集,迭代上述过程,通过构造凸包序列,自特征点集的外围到内部逐步匹配,得到较精确的匹配对。实现基于凸包序列的图谱方法的图像点模式匹配。实验结果表明,该方法不但能精确匹配旋转角度较小的图像,而且对于旋转角度大的图像以及多光谱图像匹配精度也较高。     

基于一维混沌映射的高效图像加密算法

随着多媒体技术的发展,基于数字图像的应用日益普及,图像本身的安全问题及图像所有者的隐私问题愈发严重。不同于文本数据,数字图像作为一种二维数据,其数据量大,冗余度高,像素间相关性强,将传统的一维数据加密方法直接应用于图像加密中难以达到加密的效果。当前,基于混沌理论的加密方法是图像加密领域的主流方法之一,其往往采用置乱-扩散的经典结构,利用所生成混沌序列的高随机性保证加密结果的安全性,同时具备较高的加密效率。然而,为了进一步增强加密算法的安全性,此类方法提出了大量复杂的混沌映射,如超混沌、多级混沌等,但它们的计算复杂度较一维混沌映射有了大幅增加。对此,文中设计了一种高效的一维复合混沌映射SPM,其将Sine映射和PWLCM映射结合,扩大了混沌映射的范围并保证了结果的遍历性,在不降低安全性的前提下极大地提升了混沌序列的生成效率;基于此,提出了一种新型结构下的高效图像加密算法,该算法仅需一轮置乱-扩散-置乱过程即可完成图像的加密,相较于传统方法减少了加密的轮数,进一步提升了加密的效率。实验表明,所提方法能够有效抵御选择明文/密文攻击,相较于已有算法,加密效率平均提升了约58%,具备较强的实用性。     

Vision-based sparse topological mapping

Most of the existing appearance-based topological mapping algorithms produce dense topological maps in which each image stands as a node in the topological graph. Sparser maps can be built by representing groups of visually similar images of a sequence as nodes of a topological graph. In this paper, we present a sparse/hierarchical topological mapping framework which uses Image Sequence Partitioning (ISP) to group visually similar images of a sequence as nodes which are then connected on the occurrence of loop closures to form a topological graph. An indexing data structure called Hierarchical Inverted File (HIF) is proposed to store the sparse maps so as to perform loop closure at the two different resolutions of the map namely the node level and image level. TFIDF weighting is combined with spatial and frequency constraints on the detected features for improved loop closure robustness. Our approach is compared with two other existing sparse mapping approaches which use ISP. Sparsity, efficiency and accuracy of the resulting maps are evaluated and compared to that of the other two techniques on publicly available outdoor omni-directional image sequences.     

Computing global visibility maps for regions on the boundaries of polyhedra using Minkowski sums

A global visibility map is a spherical image built to describe the complete set of global visible view directions for a surface. In this paper, we consider the computation of global visibility maps for regions on the boundary of a polyhedron. Both the self-occlusions introduced by a region and the global occlusions introduced by the rest of the surfaces on the boundary of the polyhedron are considered for computing a global visibility map. We show that the occluded view directions introduced between a pair of polyhedral surfaces can be computed from the spherical projection of the Minkowski sum of one surface and the reflection of the other. A suitable subset of the Minkowski sum, which shares the identical spherical projection with the complete Minkowski sum, is constructed to obtain the spherical images representing global occlusions. Our method has been successfully tested on many CAD models. It extends the previous methods for computing global visibility maps using convex decomposition, and it exhibits a better performance.     

基于低成本超声传感器的无线传感网生存环境地图构建研究

移动传感器网络节点在监测环境过程中,采集到大量有误差的环境地图数据,导致构建的传感器网络生存环境地图质量低、实时性差.针对以上问题,提出了一种适用于低成本、轻数据量、多网络节点的基于超声传感器组的环境地图构建算法.首先对超声波测量数据进行高斯滤波处理,其次利用处理后的数据进行单一网络节点所属区域地图的构建,再次提取单一节点地图的点特征,并进行匹配,进而得到融合后的全局地图,最终实现传感器网络节点生存环境地图的构建.进一步通过优化子图拼接顺序,降低了构图数据与实际环境数据的误差,提高了传感器网络节点生存环境的地图质量.     

Horizon Map Capture

We present a method for computing horizon maps from captured images of a bumpy surface. 1Horizon maps encode surface self-shadowing effects, and can be used with bump or normals maps to realistically render surfaces with small height perturbations. The method does not rely on complete surface reconstruction, and requires only eight captured images as input. In this paper we discuss how shadow information is extrapolated from the eight captured images to compute the horizon map. Our implementation accounts for the noise and uncertainties in physically acquired data.     

The effect of depth map up-sampling on the overall quality of stereopairs

The quality of depth maps affects the quality of generated 3D content. Practically, the depth maps often have lower resolution than that of color images, thus, Depth map Up-sampling (DU) is needed in various 3D applications. DU can yield specific artifacts which can degrade the quality of depth maps as well as constructed stereoscopic (color plus depth map) images. This paper investigates the effect of DU on 3D perception. The depth maps were up-sampled using seven approaches and the quality of stereoscopic images obtained from up-sampled depth maps was estimated through subjective and objective tests. The objective quality prediction was performed using a depth map quality assessment framework. The method is able to predict the quality of stereoscopic images through evaluation of their corresponding up-sampled depth maps using 2D Image Quality Metrics (IQMs). In order to improve the quality estimation, the framework selects the 2D IQMs with highest correlation to subjective test. Furthermore, motivated by previous researches on multiple metrics combination, a new metric fusion method is proposed. Experimental results show that the combined metric delivers higher performance than single metrics in 3D quality prediction.     

SeisPrho: An interactive computer program for processing and interpretation of high-resolution seismic reflection profiles

SeisPrho is an interactive computer program for processing and interpreting high-resolution seismic reflection profiles developed using the Delphi/Kylix multiplatform programming environment. For this reason, it is available under Windows? and Linux? operating systems. The program allows the users to handle SEG-Y data files (and other non-standard formats) carrying out a processing sequence over the data to obtain, as a final result, bitmap images of seismic sections. Some basic algorithms are implemented, including filtering and deconvolution. However, the main feature of SeisPrho is its interactive graphic interface, which provides the user with several tools for interpreting the data, such as reflector picking and map digitizing. Moreover, the program allows importing and geo-referencing maps and seismic profiles in the form of digital images. Trace-by-trace analysis of seismic signal and sea-bottom reflectivity is also implemented, as well as other special functions such as compilation of time-slice maps from close-spaced grids of seismic lines. SeisPrho is distributed as public domain software for non-commercial purposes by the Marine Geology division of the Istituto di Scienze Marine (ISMAR-CNR). This paper is an introduction to the program and a preliminary guide to the users.     

基于激光雷达与双目视觉的移动机器人SLAM研究

为解决移动机器人在环境未知条件下,利用单一传感器自主导航时不能及时定位、构建地图不精确的问题,提出采用一种改进RBPF算法,在计算提议分布时将移动机器人的观测数据(视觉信息与激光雷达信息)和里程计信息融合;针对一般视觉图像特征点提取算法较慢的问题,采用基于ORB算法对视觉图像进行处理以加快视觉图像处理速度的方法;最后通过在安装有开源机器人操作系统(ROS)的履带式移动机器人进行实验,验证了采用该方法可构建可靠性更高、更精确的2D栅格图,提高了移动机器人SLAM的鲁棒性.     

Active Appearance-Based Robot Localization Using Stereo Vision

A vision-based robot localization system must be robust: able to keep track of the position of the robot at any time even if illumination conditions change and, in the extreme case of a failure, able to efficiently recover the correct position of the robot. With this objective in mind, we enhance the existing appearance-based robot localization framework in two directions by exploiting the use of a stereo camera mounted on a pan-and-tilt device. First, we move from the classical passive appearance-based localization framework to an active one where the robot sometimes executes actions with the only purpose of gaining information about its location in the environment. Along this line, we introduce an entropy-based criterion for action selection that can be efficiently evaluated in our probabilistic localization system. The execution of the actions selected using this criterion allows the robot to quickly find out its position in case it gets lost. Secondly, we introduce the use of depth maps obtained with the stereo cameras. The information provided by depth maps is less sensitive to changes of illumination than that provided by plain images. The main drawback of depth maps is that they include missing values: points for which it is not possible to reliably determine depth information. The presence of missing values makes Principal Component Analysis (the standard method used to compress images in the appearance-based framework) unfeasible. We describe a novel Expectation-Maximization algorithm to determine the principal components of a data set including missing values and we apply it to depth maps. The experiments we present show that the combination of the active localization with the use of depth maps gives an efficient and robust appearance-based robot localization system.     

基于相关性的病理切片图像配准

尽管病理切片图像对配准的要求比较高,而现存的配准方法却难免会产生失配现象。为解决这一问题,提出了一种基于相关性的病理切片图像配准新算法。该算法是采用基于图片中两平行列(行)间的数据来抽取特征的方法。为了避免“干扰”的累积,该算法选择了差值曲线中最强的特征——最大包来作为模板的基元,并根据图片内容的相关性,利用最大包的分布作为模板来进行图像配准,从而降低了“干扰”的影响,使算法配准的稳定度比以前一些算法有较大的提高。实验证明,该算法不仅比较规整,稳定性高,而且计算速度也较快,是一种比较实用的图像配准算法。     

Construction of synthetic spectral reflectance of remotely sensed imagery for planning purposes

Urban and environment development plans commonly lack spectrally based value-added information layers such as expected albedo, emissivity and temperature of the planned landscapes. These can be integrated into plans in order to assist in using specific materials or in the way new landscapes and urban spaces are designed. In contrast to existing space-borne remotely sensed imagery from which information layers as such can be extracted using atmospheric correction tools, development plans are set on paper, in a geographic information system (GIS) or as perspective “artistic images” at best. This paper describes a new software tool within the environment for visualization of images (ENVI 4.1) software, for automatic simulation of such multispectral reflectance images, given thematic maps of planned landscapes and associated spectral signatures.We discuss issues related to the image generation process, the method of spectral signature integration, and to quality assessment measures. An example is provided. We assess the simulated output quantitatively using a pixel-based “goodness-of-fit” measure and by calculating Pearson's correlation coefficients. Results show that simulation of images based on local neighborhood spectral mixtures, have all, mean total-goodness-of-fit measures amounting 99%, and have a general positive linear correlation of around 0.86 with real data. A class-wise correlation of a simulated image with a real reference image shows that large image segments of homogenous land-cover classes, such as vegetation classes, inland waters and some soils, match about 80–90% of corresponding real data. On the other hand, simulated data will match only 20–40% of real values for highly textured land-cover classes with relatively small spatial extent over the image, such as for built-up areas. We conclude with two prospective applications related to the validation of classification algorithms, and to planning exercises.     

Obstacle-Free Pathway Detection by Means of Depth Maps

The detection of surrounding obstacle-free space is an essential task for many intelligent automotive and robotic applications. In this paper we present a method to detect obstacle-free pathways in real-time using depth maps from a pair of stereo images. Depth maps are obtained by processing the disparity between left and right images from a stereo-vision system. The proposed technique assumes that depth of pixels in obstacle-free pathways should increase slightly and linearly from the bottom of the image to the top. The proposed real-time detection checks whether the depth of groups of image columns matches a linear model. Only pixels fulfilling the matching requirements are identified as obstacle-free pathways. Experimental results with real outdoor stereo images show that the method performance is promising.     

一种多幅欠采样图像的凸集投影超分辨率重建方法

介绍了一种由多幅欠采样低分辨率图像重建一幅高分辨率图像的凸集投影超分辨率重建技术。首先介绍了超分辨率空间域迭代重建方法中一个至关重要的因素--成像过程模型;其次通过介绍凸集投影的理论依据,给出了插值-模拟采样迭代超分辨率重建方法的模型和重建步骤;最后通过实验数据对算法进行了验证。     

Aligning archive maps and extracting footprints for analysis of historic urban environments

Archive cartography and archaeologist's sketches are invaluable resources when analysing a historic town or city. A virtual reconstruction of a city provides the user with the ability to navigate and explore an environment which no longer exists to obtain better insight into its design and purpose. However, the process of reconstructing the city from maps depicting features such as building footprints and roads can be labour intensive. In this paper we present techniques to aid in the semi-automatic extraction of building footprints from digital images of archive maps and sketches. Archive maps often exhibit problems in the form of inaccuracies and inconsistencies in scale which can lead to incorrect reconstructions. By aligning archive maps to accurate modern vector data one may reduce these problems. Furthermore, the efficiency of the footprint extraction methods may be improved by aligning either modern vector data or previously extracted footprints, since common elements can be identified between maps of differing time periods and only the difference between the two needs to be extracted. An evaluation of two alignment approaches is presented: using a linear affine transformation and a set of piecewise linear affine transformations.