Color invariance

This paper presents the measurement of colored object reflectance, under different, general assumptions regarding the imaging conditions. We exploit the Gaussian scale-space paradigm for color images to define a framework for the robust measurement of object reflectance from color images. Object reflectance is derived from a physical reflectance model based on the Kubelka-Munk theory for colorant layers. Illumination and geometrical invariant properties are derived from the reflectance model. Invariance and discriminative power of the color invariants is experimentally investigated, showing the invariants to be successful in discounting shadow, illumination, highlights, and noise. Extensive experiments show the different invariants to be highly discriminative, while maintaining invariance properties. The presented framework for color measurement is well-founded in the physics of color as well as in measurement science. Hence, the proposed invariants are considered more adequate for the measurement of invariant color features than existing methods     

Colour invariants under a non-linear photometric camera model and their application to face recognition from video

Illumination invariance remains one of the most researched, yet the most challenging aspect of automatic face recognition. In this paper the discriminative power of colour-based invariants is investigated in the presence of large illumination changes between training and query data, when appearance changes due to cast shadows and non-Lambertian effects are significant. Specifically, there are three main contributions: (i) a general photometric model of the camera is described and it is shown how its parameters can be estimated from realistic video input of pseudo-random head motion, (ii) several novel colour-based face invariants are derived for different special instances of the camera model, and (iii) the performance of the largest number of colour-based representations in the literature is evaluated and analysed on a database of 700 video sequences. The reported results suggest that: (i) colour invariants do have a substantial discriminative power which may increase the robustness and accuracy of recognition from low resolution images in extreme illuminations, and (ii) that the non-linearities of the general photometric camera model have a significant effect on recognition performance. This highlights the limitations of previous work and emphasizes the need to assess face recognition performance using training and query data which had been captured by different acquisition equipment.     

二值化的SIFT特征描述子及图像拼接优化

目的 针对SIFT算法计算复杂度高、存储开销大和近几年提出的BRIEF（binary robust independent elementary features）、ORB（oriented BRIEF）、BRISK（binary robust invariant scalable keypoints）和FREAK（fast retina keypoint）等二进制描述子可区分性弱和鲁棒性差的问题,提出基于SIFT的二进制图像局部特征描述子。方法 首先,对传统SIFT的特征空间和特征向量分布在理论和实验上进行分析,在此基础上结合二进制特征描述子的优势对SIFT进行改进。不同于传统的二进制特征描述子,本文算法对传统SIFT特征向量在每一维上的分量进行排序后,以该特征向量的中值作为量化阈值,将高维浮点型SIFT特征向量转化成位向量得到二进制特征描述子。并使用易于计算的汉明距离代替欧氏距离度量特征点间的相似性以提高匹配效率。然后,在匹配阶段将二进制特征描述子分为两部分并分别对其进行匹配,目的是通过初匹配剔除无效匹配特征点来进一步缩短匹配时间。最后,对提出的量化算法的可区分性及鲁棒性进行验证。结果 该量化算法在保持SIFT的较强的鲁棒性和可区分性的同时,达到了低存储、高匹配效率的要求,解决了SIFT算法的计算复杂度高、二进制描述子鲁棒性和可区分性差的问题。此外,在匹配阶段平均剔除了77.5%的无效匹配特征点,减少了RANSAC（random sample consensus）的迭代次数。结论 本文提出的量化算法可用于快速匹配和快速图像拼接中,提高匹配和拼接效率。     

Edge and corner detection by photometric quasi-invariants

Feature detection is used in many computer vision applications such as image segmentation, object recognition, and image retrieval. For these applications, robustness with respect to shadows, shading, and specularities is desired. Features based on derivatives of photometric invariants, which we is called full invariants, provide the desired robustness. However, because computation of photometric invariants involves nonlinear transformations, these features are unstable and, therefore, impractical for many applications. We propose a new class of derivatives which we refer to as quasi-invariants. These quasi-invariants are derivatives which share with full photometric invariants the property that they are insensitive for certain photometric edges, such as shadows or specular edges, but without the inherent instabilities of full photometric invariants. Experiments show that the quasi-invariant derivatives are less sensitive to noise and introduce less edge displacement than full invariant derivatives. Moreover, quasi-invariants significantly outperform the full invariant derivatives in terms of discriminative power.     

Illumination-robust variational optical flow using cross-correlation

We address the problem of variational optical flow for video processing applications that need fast operation and robustness to drastic variations in illumination. Recently, a solution [1] has been proposed based on the photometric invariants of the dichromatic reflection model [2]. However, this solution is only applicable to colour videos with brightness variations. Greyscale videos, or colour videos with colour illumination changes cannot be adequately handled. We propose two illumination-robust variational methods based on cross-correlation that are applicable to colour and grey-level sequences and robust to brightness and colour illumination changes. First, we present a general implicit nonlinear scheme that assumes no particular analytical form of energy functional and can accommodate different image components and data metrics, including cross-correlation. We test the nonlinear scheme on standard synthetic data with artificial brightness and colour effects added and conclude that cross-correlation is robust to both kinds of illumination changes. Then we derive a fast linearised numerical scheme for cross-correlation based variational optical flow. We test the linearised algorithm on challenging data and compare it to a number of state-of-the-art variational flow methods.     

结构上下文:一种新的物体类别描述符

局部描述符(如SIFT)方法能够将图像中关键点的局部表观信息作为图像的特征,具有旋转不变性、尺度变换不变性、仿射不变性等性质,被广泛应用于物体分类、物体识别、图像匹配等领域。但是,它存在一个重要缺陷:只能描述物体的局部特征,忽略了整个物体的构造,而这在表示物体时是非常重要的。设计了一个新的"结构上下文"局部描述符,通过当前关键点和其他关键点间的空间拓扑结构关系描述各个关键点的特征。实验证明这种描述符在描述相同物体种类时特别有效。     

尺度与颜色不变性图像特征描述

尺度不变特征变换是目前公认的鲁棒性最强的图像特征描述方法之一,在尺度不变性和几何不变性方面具有较好的特性,但该方法主要适用于灰度图像,对图像颜色的区分能力不强,因此,一些对象可能会因为颜色的不同而被错误的区分.另外,尺度不变特征变换对关键点局部范围内描述子主方向的依赖性非常强,直接决定了匹配的正确率,但是研究表明,主方向分配产生的误差仅有三分之二左右能控制在[-20。,+20。]范围内,因此部分特征会有三分之一的概率因为主方向分配的误差较大而不能正确匹配.针对以上两个问题,本文提出了一种具有颜色和尺度不变性的局部特征描述方法,颜色不变性通过将RGB图像转换到高斯颜色模型下实现,特征描述过程中不再分配主方向,而用局部相对方向,尺度不变性通过构建高斯金子塔实现.实验选取阿姆斯特丹数据集图像进行了测试,结果表明本文方法比传统尺度不变特征变换方法,在特征点的数目、分布均匀性以及匹配精度方面均有所提高.     

局部图像描述符最新研究进展

目的 局部图像描述符广泛应用于许多图像理解和计算机视觉应用领域,如图像分类、目标识别、图像检索、机器人导航、纹理分类等。SIFT算法的提出标志着现代局部图像描述符研究的开始。主要对最近发展的现代局部图像描述符进行了综述。方法 首先,介绍了4大类局部图像描述符:局部特征空间分布描述符、局部特征空间关联描述符、基于机器学习的局部描述符、扩展局部描述符(局部颜色描述符、局部RGB-D描述符、局部空时描述符)。对局部图像描述符进行了分析和分类,并总结了局部图像描述符的不变性、计算复杂度、应用领域、评价方法和评价数据集。最后,展望了局部图像描述符的未来研究方向。结果 近年来局部图像描述符研究取得了很大进展,提出了很多优秀的描述符,在辨别性、鲁棒性和实时性方面有了很大提高,应用领域不断拓展。结论 局部图像描述符应用广泛,是计算机视觉领域的重要基础研究。而目前,局部图像描述符还存在许多问题,还需进一步的深入研究。     

Invariants for Parameterised Boolean Equation Systems

The concept of invariance for Parameterised Boolean Equation Systems (PBESs) is studied in greater detail. We identify an issue with the associated theory and fix this problem by proposing a stronger notion of invariance called global invariance. A precise correspondence is proven between the solution of a PBES and the solution of its invariant-strengthened version; this enables one to exploit global invariants when solving PBESs. Furthermore, we show that global invariants are robust w.r.t. all common PBES transformations and that the existing encodings of verification problems into PBESs preserve the invariants of the processes involved. These traits provide additional support for our notion of global invariants, and, moreover, provide an easy manner for transferring (e.g. automatically discovered) process invariants to PBESs. We provide several examples that illustrate the use of global invariants for a variety of verification problems.     

基于归一化rgb彩色模型的运动阴影检测

提出了一种基于归一化rgb空间的运动阴影检测方法。首先推导了rgb彩色模型的光度测定不变性和它的相关重要性质;结合阴影区域在亮度和颜色上的特征,在rgb空间分割出候选阴影区域,利用区域的空间关系检测出真实的阴影。对大量不同光照条件和不同阴影投射表面的运动人视频的测试表明,该方法具有良好的适应性和鲁棒性。