多特征分层融合的相关滤波鲁棒跟踪

目的 为提高目标跟踪的鲁棒性,针对相关滤波跟踪中的多特征融合问题,提出了一种多特征分层融合的相关滤波鲁棒跟踪算法。方法 采用多通道相关滤波跟踪算法进行目标跟踪时,从目标和周围背景区域分别提取HOG（histogram of oriented gradient）、CN（color names）和颜色直方图3种特征。提出的分层融合算法首先采用自适应加权融合策略进行HOG和CN特征的特征响应图融合,通过计算特征响应图的平滑约束性和峰值旁瓣比两个指标得到融合权重。将该层融合结果与基于颜色直方图特征获得的特征响应图进行第2层融合时,采用固定系数融合策略进行特征响应图的融合。最后基于融合后的响应图估计目标的位置,并采用尺度估计算法估计得到目标更准确的包围盒。结果 采用OTB-2013（object tracking benchmark 2013）和VOT-2014（visual object tracking 2014）公开测试集验证所提跟踪算法的性能,在对多特征分层融合参数进行分析的基础上,与5种主流基于相关滤波的目标跟踪算法进行了对比分析。实验结果表明,本文算法的目标跟踪精度有所提高,其跟踪精度典型值比Staple算法提高了5.9%（0.840 vs 0.781）,同时由于有效地融合了3种特征,在多种场景下目标跟踪的鲁棒性优于其他算法。结论 提出的多特征分层融合跟踪算法在保证跟踪准确率的前提下,跟踪鲁棒性优于其他算法。当相关滤波跟踪算法采用了多个不同类型特征时,本文提出的分层融合策略具有一定的借鉴性。     

融合颜色属性和空间信息的显著性物体检测

摘 要：目的：提出了一种基于颜色属性和空间信息的显著性物体检测算法,并将其用于交通标志的检测。方法：首先,训练颜色属性得到颜色-像素值分布,据此将图像划分为不同的颜色聚簇,每个聚簇的显著性取决于其空间紧致性。其次,将每个聚簇分割为多个区域,用颜色属性描述子表示每个区域,计算区域的全局对比度。最后,同时考虑区域对比度和相应聚簇的空间紧致性,得到最终的显著图。在此基础上,将交通标志的先验知识转换为自上而下的显著性图,形成任务驱动的显著性模型,对交通标志进行检测。结果：在公开数据集上的测试结果表明,该算法取得最高92%的查准率,优于其它流行的显著性算法。在交通标志数据集上的检测取得了90.7%的正确率。结论：本文提出了一种新的显著性检测算法,同时考虑了区域的颜色和空间信息,在公开数据集上取得了较高的查准率和查全率。在对交通标志的检测中也取得了较好的结果。     

Outdoor Localization Using Stereo Vision Under Various Illumination Conditions

We present a mobile robot localization method using only a stereo camera. Vision-based localization in outdoor environments is a challenging issue because of extreme changes in illumination. To cope with varying illumination conditions, we use two-dimensional occupancy grid maps generated from three-dimensional point clouds obtained by a stereo camera. Furthermore, we incorporate salient line segments extracted from the ground into the grid maps. The grid maps are not significantly affected by illumination conditions because occupancy information and salient line segments can be robustly obtained. On the grid maps, a robot's poses are estimated using a particle filter that combines visual odometry and map matching. We use edge-point-based stereo simultaneous localization and mapping to obtain simultaneously occupancy information and robot ego-motion estimation. We tested our method under various illumination and weather conditions, including sunny and rainy days. The experimental results showed the effectiveness and robustness of the proposed method. Our method enables localization under extremely poor illumination conditions, which are challenging for even existing state-of-the-art methods.     

一种基于MDARNet的低照度图像增强方法

由于低照度环境下所采集的图像存在亮度低、对比度差、出现噪声和色彩失衡等低质问题,严重影响其在图像处理应用中的性能.为了提升低照度图像质量,以获得具有完整结构和细节且自然清晰的图像,结合Retinex理论与卷积神经网络,提出了一种基于MDARNet的低照度图像增强方法,并引入Attention机制模块和密集卷积模块以提升性能.首先,MDARNet利用同时包含二维和一维的3个不同尺度卷积核对图像进行初步特征提取,并用像素注意模块对多尺度特征图进行针对性学习;其次,设计跳跃连接结构对图像进行特征提取,使图像特征被最大限度地利用;最后,用通道注意模块和像素注意模块同时对提取到的特征图进行权重学习和照度估计.实验结果表明：MDARNet能够有效提升低照度图像的亮度、对比度、色彩等;且相较于一些经典算法,该方法在视觉效果及客观评价指标（PSNR,SSIM,MS-SSIM,MSE）能够得到更好的效果.     

对比度、颜色一致性和灰度像素保持的消色算法

目的 为了解决目前消色算法中不能同时保持原始图像的对比度,颜色一致性和灰度像素特征的问题,提出一种新的优化算法,最大限度地同时保留这些视觉特性。方法 为了保持原始图像的结构和局部对比度信息,用双高斯模型构建像素对之间的误差能量项;为了保持颜色一致性,采用局部线性嵌入模型构建能量项,确保原始图像中颜色一致的像素在结果图像中也拥有一样的灰度级;为了保持灰度像素特征,先标记出原始图像中的灰度像素,并强制规定这些像素的灰度值是已知的且在消色变换的过程中始终不变,然后用双高斯模型构建出灰度像素与其他像素之间的误差能量项。线性结合这3个能量项,得到目标能量函数,再通过迭代法求解出使总能量值达到最小的灰度值,从而得到了最终的消色结果。结果 实验结果表明,本文算法能够同时较好地保持原始图像中的对比度、颜色一致性和灰度像素特征。结论 本文算法基本符合人类对图像对比度变化的感知程度,而且能够很好地保持细节信息和全局结构,可应用于数字打印、模式识别等方面,具有很大的应用价值。     

基于模糊理论的低照度彩色图像增强算法

低照度彩色图像存在整体亮度低、对比度差、颜色偏暗和信噪比低等特点,传统图像增强算法对其增强效果非常有限。提出了一种基于模糊理论的低照度彩色图像增强算法,将三原色(red,green,blue,RGB)图像转换成色相饱和度(HSV)图像,以保证增强处理不引起图像的色彩失真。对亮度图像进行非线性变化,实现动态范围展宽;采用修正后的隶属度函数将图像映射到模糊平面,实现对比度增强。实验结果表明:该算法显著地提高了图像整体亮度和对比度,改善了低照度彩色图像的视觉效果。     

Distributed multi-camera visual mapping using topological maps of planar regions

This paper presents a multi-agent solution for cooperative visual mapping using planar regions. Each agent is assumed to be equipped with a conventional camera and has limited communication capabilities. Our approach starts building topological maps from independent image sequences where natural landmarks extracted from conventional images are grouped to create a graph of planes. With this approach the features observed in several images belonging to the same planar region are stored only once, reducing the size of the individual maps. In a distributed scenario this is very important because smaller maps can be transmitted faster, which makes our approach better suited for cooperative mapping. The later fusion of the individual maps is obtained via distributed consensus without any initial information about the relations between the different maps. Experiments with real images in complex scenarios show the good performance of our proposal.     

一种自适应彩色数字图像盲隐藏方法

提出了一种将24位真彩色图像隐藏于另一幅24位真彩色图像的新方法。该方法采用硬c均值聚类及多分辨率彩色量化技术，实现了彩色图像的自适应盲隐藏。它具有隐藏信息量大、恢复图像的误差小及使用方便的特点，对常见的图像处理与攻击具有一定的抵抗能力。另外，通过超混沌的置乱技术，使隐藏到载体图像中的数据有非常好的伪随机特征，具有很高的安全性。该方法在PC机上实验，得到较好的实验结果。     

一种新的基于MSRCR光照补偿算法

对质量较差的人脸图像进行光照补偿,多尺度Retinex算法是传统的算法中比较有效的一种,但是Retinex算法处理的人脸图像会产生"泛白、颜色失真、对比度低"现象,为了提高人脸识别率,为此提出了一种新的带色彩恢复的多尺度Retinex算法(MSRCR)对彩色图像进行光照补偿.在对MSRCR理论进行研究的基础上,对原有算法进行改进,使用了快速傅里叶变换,运行速度快于已有传统方法.经过实验证明,改进算法使图像的对比度,亮度,隐藏的细节等方面都有很大的增强.论述了该算法的原理和实现方法,同时通过实验将其与直方图均衡,Gamma变换等方法进行比较.实验结果表明:该算法对彩色图像光照补偿有很好的效果.     

结合暗原色图像参考的单幅图像去雾*

针对在暗原色先验理论下对天空区域的透射率估计总是过于偏小的问题,提出了一种基于暗原色图像的透射率纠正方法。以暗原色图像为参考,提取其天空等明亮区域的灰度归一化值替换生成新的透射率图。该方式提高了天空区域的透射率值,使其更接近于真实值。实验结果表明,对于各类雾化图像,在无需调整各参数值的情况下,该算法均能很好地避免天空区域出现色差失真问题;同时对于不含天空区域的图像,去雾仍然有效。此外,算法执行时无需进行复杂的天空区域识别及提取等操作。算法在实际去雾应用中实现了无参化,自动化程度高;对于分辨率为640?480彩色图像,速度可达1.5帧/s。     

融合颜色特征的尺度自适应相关跟踪

对于彩色视频的目标跟踪,传统基于相关滤波的跟踪方法没有利用视频帧的颜色信息,针对该问题本文在相关跟踪框架下提出了一种融合颜色特征的尺度自适应目标跟踪方法。该方法首先将HSV三个通道归一化后作为目标的颜色特征,并与灰度特征以及HOG特征进行融合,然后利用核相关滤波定位目标的中心位置,最后再利用尺度金字塔模型对目标尺度进行估计。在公开的彩色视频数据集上对所提方法进行测试,并和多种跟踪方法进行对比。实验结果表明,该方法的平均跟踪性能优于其它方法,验证了方法的有效性。     

采用双尺度图像分解的水下彩色图像增强

目的 为解决水下图像的色偏和低对比度等问题,提出一种基于双尺度图像分解的水下彩色图像增强算法。方法 通过基于均值和方差的对比度拉伸方法改善图像的色偏问题,并利用中值滤波降低红通道对比度拉伸后引入的噪声;采用双尺度图像分解绿通道图像补偿红通道图像细节;在处理后的红通道图像中引入原始图像红通道的真实细节与颜色。结果 选取不同水下图像作为实验数据集,将本文方法与暗通道先验的方法、基于融合的方法、自动红通道恢复方法以及一种基于卷积神经网络深度学习的方法相比较,首先从主观视觉效果进行定性分析,然后通过不同评测指标进行定量分析。主观定性分析结果表明,提出的方法相比较其他方法能够更好地解决图像色偏和红色阴影问题;定量分析中,自然图像质量评价（natural image quality evaluation,NIQE）指标和信息熵（information entropy,IE）值较基于融合的方法和深度学习的方法分别提高了1.8%和13.6%,且水下图像质量评价指标（underwater image quality measurement method,UIQM）较其他方法更优。结论 提出的双尺度图像分解方法利用水下图像成像特点解决图像色偏以及低对比度问题,具有良好的适应能力,同时算法复杂度低且鲁棒性较高,普遍适用于复杂的水下彩色图像增强。     

二乘向量机在图像插值技术中的应用研究

图像插值过程实际上是利用已有的像素点来估计与这些像素点相邻的未知像素的颜色。可将一幅图像视为由像素坐标映射而成的二维颜色曲面。这样插值问题就可以视为由已知的像素构成的颜色曲面函数的回归问题。而基于统计学习理论(SLT)的支持向量机(SVM)方法为解决这种高维非线性问题提供了一种新的途经。该文讨论了最小二乘向量机实现数字图像插值的应用方法,并进行了图像放大的试验验证。试验表明:基于RBF核的最小二乘向量机回归技术对数字图像的插值具有很强的适应性,其性能与已有的双立方插值技术相当。     

Adaptive enhancement of underwater images using multi-objective PSO

Underwater images have poor clarity and bad contrast due to low illumination in deep water. Moreover, underwater images are bluish-green in appearance due to inherent wavelength absorption property of water. Therefore, the study of underwater images is a difficult task. Being computationally simple, histogram-based enhancement techniques are obvious choice for improvement of contrast and color of underwater images. However, due to lack of any guidance mechanism, these techniques can overstretch the histogram leading to artifacts in the image. Hence, an adaptive method named ‘Contrast and Information Enhancement of Underwater Images’ (CIEUI) is proposed, which enhances underwater images by improving their contrast and information content using Multi-Objective Particle Swarm Optimization (MOPSO). Objective functions of MOPSO are chosen to act as guiding mechanism to ensure color & contrast correction and information enhancement respectively without introducing artifacts. Computed results not only have good contrast and color performance but also have better information content. The proposed CIEUI technique performs quantitatively and qualitatively better as compared to state-of-the-art algorithms.

     

最佳结构元素尺寸的自适应确定算法

基于空间数据的表示不仅要依赖于尺度特征的研究，而且只有在特定的尺度下提取的要素特征才具有现实意义。由于不同尺寸的结构元素适合不同空间尺度的图像特征。结构元素尺寸过大或者过小都会达不到最佳的特征边缘提取效果。因此结构元素尺寸的设计在提取图像特征信息中起着重要的作用。通过数学形态学梯度性质与结构元素尺寸关系的分析，首先得出了结构元素尺寸占与特征要素边缘尺寸γ和特征要素空间尺度λ之间的定量关系，然后通过计算比较相邻尺度间梯度图像的差值信息设计出了一种最佳结构元素尺寸的自适应确定算法。试验结果表明，该算法能够根据特征要素边缘的尺寸来求出最佳地结构元素尺寸。通过典型梯度算子提取的边缘与利用该算法设计的结构元素尺寸提取的边缘的比较结果证明，该算法在稳健性、定位精度和对比度等方面都优于典型梯度算子。     

一种改善Tent混沌序列随机性的方法

Tent混沌映射具有良好的遍历性和均匀性,但其随机性不理想。为此,提出一种改善Tent混沌序列随机性的方法。通过将Tent混沌映射变换为分段混沌映射,增大Lyapunov指数,改善相关系数和功率谱特性。对序列进行NIST随机性测试,结果表明,该分段Tent映射的序列具有较好的随机性,适用于通信与信息安全领域。     

Depth computations from polyhedral images

A method is developed for the computation of depth maps, modulo scale, from one single image of a polyhedral scene. Only affine shape properties of the scene and image are used, no metric information. Results from simple experiments show good performance, both concerning exactness and robustness. It is also shown how the underlying theory may be used to single out and characterize certain singular situations that may occur in machine interpretation of line drawings.     

基于颜色矩的图像检索算法研究

为克服基于文字的图像检索技术对大型图像数据库实施困难、描述不完整等弊端,对RGB颜色矩和Munsell颜色矩进行研究,RGB颜色矩只适用于简单图像,Munsell颜色矩无法判断图片具体信息。为此,采用信息融合技术进行检索判断层的融合,选择多颜色空间融合颜色矩,在分析传统融合算法基础上,提出一种改进融合算法NewcombMNZ。实验结果表明,该算法能提高检索精准度和排序值,对噪声具有良好的鲁棒性,且能减少检索性能较差的特征对融合结果的影响,适用于特征数量较少的情况。     

Harvesting maps on the web

Maps are one of the most valuable documents for gathering geospatial information about a region. Yet, finding a collection of diverse, high-quality maps is a significant challenge because there is a dearth of content-specific metadata available to identify them from among other images on the Web. For this reason, it is desirous to analyze the content of each image. The problem is further complicated by the variations between different types of maps, such as street maps and contour maps, and also by the fact that many high-quality maps are embedded within other documents such as PDF reports. In this paper, we present an automatic method to find high-quality maps for a given geographic region. Not only does our method find documents that are maps, but also those that are embedded within other documents. We have developed a Content-Based Image Retrieval (CBIR) approach that uses a new set of features for classification in order to capture the defining characteristics of a map. This approach is able to identify all types of maps irrespective of their subject, scale, and color in a highly scalable and accurate way. Our classifier achieves an F1-measure of 74%, which is an 18% improvement over the previous work in the area.     

Visual tests for measuring the picture quality of teleconsultations for medical purposes

Telemedicine provides a new way of delivering medical services. The good quality of the picture is, however, essential for a proper and reliable teleconsultation, especially in the cases when visual information about the patient's physical condition is of great importance as in ophthalmology and dermatology. Therefore real-time telemedical applications need standards for these procedures, e.g. minimum requirements for resolution, as well as contrast and color discrimination. The present study was carried out to test these parameters in a real environment. A panel of different resolution, contrast sensitivity and color discrimination tests was carried out for five test persons via PictureTel videoconference system by ISDN 128 kbit/s line speed and in a normal way. The good color discrimination of the teleconsultation system makes it possible to use the system in the evaluation of different skin lesions and exemas. However, the poor resolution and especially poor contrast sensitivity makes the use of the equipment valueless in the evaluation of diseases where the diagnoses are based on the discrimination of small details, like the biomicroscopical analysis of inflammatory cells in the aqua's humor in cases of intraocular inflammation. The authors are suggesting a simple panel of tests to optimize and standardize these parameters.