基于图像熵的高动态范围场景的自动曝光算法

自动曝光控制是通过控制曝光量使图像亮度最优化的过程,由于图像亮度与曝光值有着直接的关系,因而图像亮度在自动曝光算法中被广泛应用.虽然熵已用于各种图像处理应用,但是很少应用在自动曝光中.基于图像熵提出一种新的自动曝光算法,不同于传统的主要依赖于图像亮度的算法.首先根据图像熵值大小来判断光照条件,通过图像熵大小的比较,把图像的各区域划分为感兴趣区域与不感兴趣区域.然后由图像熵值大小采用分配权重方法对不同区域分配权重,最后进行准确地自动曝光.由于该算法主要基于图像熵值的大小,所以曝光效果不受图像中对象位置影响,使得该算法更灵活.实验结果表明,该算法对高动态范围场景可以准确地检测出各种光照条件,提高相机系统输出图像的动态范围,同时还增加了自动曝光的准确性.     

视觉注意机制在图像增强中的应用研究

将视觉注意机制引入到直方图构造中,并在此基础上提出了一种新的基于灰度级信息量直方图的图像增强算法.该算法利用Itti视觉注意计算模型对图像的显著性进行分析,获得全局显著图;然后,将全局显著图划分为若干等大的子区域,求取各子区域的平均显著值,并做归一化处理,得到子区域的加权统计系数;再将各子区域的灰度级加权统计值相加,得到灰度级信息量直方图;最后,依据直方图均衡化的映射函数,调整灰度级的动态范围.实验结果表明,该算法明显优于经典的GHE算法和AHE算法,具有满意的视觉效果.     

复杂背景下钢索图像的纹理分割与边界识别

 针对复杂背景下钢索图像难以准确分割的问题,提出一种基于纹理分析的钢索图像分割与边界识别方法.采用基于模糊Hough变换的纹理方向检测方法确定钢索走向,利用边缘方向密度直方图作为纹理特征,对与钢索纹理方向相应的边缘方向赋予不同权重,抑制纹理分割中背景的干扰,对钢丝绳图像进行聚类分割,采用检测平行直线的方法确定其边界,并根据算法参量对边界进行修正.在实验中,对比了边缘方向密度直方图特征与灰度共生矩阵、局部二值模式在钢索图像纹理分割中的结果与计算时间,结果表明边缘方向密度直方图特征计算速度快、受背景干扰小,分割准确率高.本文方法无须预先训练,受背景干扰小,可以准确地识别出钢索并确定其边界,能满足钢丝绳视觉检测的要求.     

复杂背景下钢索图像的纹理分割与边界识别

针对复杂背景下钢索图像难以准确分割的问题,提出一种基于纹理分析的钢索图像分割与边界识别方法.采用基于模糊Hough变换的纹理方向检测方法确定钢索走向,利用边缘方向密度直方图作为纹理特征,对与钢索纹理方向相应的边缘方向赋予不同权重,抑制纹理分割中背景的干扰,对钢丝绳图像进行聚类分割,采用检测平行直线的方法确定其边界,并根据算法参量对边界进行修正.在实验中,对比了边缘方向密度直方图特征与灰度共生矩阵、局部二值模式在钢索图像纹理分割中的结果与计算时间,结果表明边缘方向密度直方图特征计算速度快、受背景干扰小,分割准确率高.本文方法无须预先训练,受背景干扰小,可以准确地识别出钢索并确定其边界,能满足钢丝绳视觉检测的要求.     

基于HDR图像处理的数码相机成像式亮度测量方法

提出了一种基于高动态范围图像处理的成像式亮度测量方法。该方法首先利用一组由低动态范围时间曝光序列图像合成的HDR图像,经色彩空间变换得到色刺激值,然后利用数码相机特性曲线标定系数计算亮度值。通过对室外场景的实测实验,证明了算法的优越性。     

一种基于自动多次曝光面结构光的形貌测量方法

为解决视觉测量中重建强反射表面时遇到的过度曝光或曝光不足的问题,提出了一种基于自动多次曝光的面结构光测量方法。该方法的核心是根据基准点像素值随曝光时间的变化计算相机响应曲线。利用相机响应曲线和不同曝光时间下的图像计算出当前场景测量所需的曝光次数和曝光时间。将具有不同曝光时间的图像序列融合成新的条纹图像序列进行重建。实验结果表明:所提方法能够准确计算每次曝光的时间,克服了强反射表面引起的条纹图像饱和或过暗的问题,能够实现高动态范围表面反射率物体的三维形貌光学非接触测量。     

范围限制的自适应亮度保持多阈值直方图均衡算法研究

针对目前直方图均衡算法难以实现,且易造成亮度饱和等问题,本文提出了一种范围限制的自适应亮度保持多阈值直方图均衡算法。首先,对输入图像进行适当平滑,从而获得它的直方图峰值点个数（N+1）。然后,对Otsu算法进行N阈值扩展,并通过这种方法获得图像的N个分割阈值,从而按照此阈值对图像进行分割。为了能够最大程度地保持输入图像的亮度,利用输入图像和输出图像的均值亮度最小误差（AMBE）准则,重新计算了图像的均衡范围。最后,利用新的均衡范围分别对每一个子图像进行均衡。实验表明,使用本算法处理Lena图的绝对均值亮度误差为0.416 4,明显优于使用RLBHE算法的0.629 5。本算法能够获得更清晰的图像细节,同时图像的整体亮度保持的也较好。     

范围限制的自适应亮度保持多阈值直方图均衡算法研究（英文）

针对目前直方图均衡算法难以实现,且易造成亮度饱和等问题,本文提出了一种范围限制的自适应亮度保持多阈值直方图均衡算法。首先,对输入图像进行适当平滑,从而获得它的直方图峰值点个数(N+1)。然后,对Otsu算法进行N阈值扩展,并通过这种方法获得图像的N个分割阈值,从而按照此阈值对图像进行分割。为了能够最大程度地保持输入图像的亮度,利用输入图像和输出图像的均值亮度最小误差(AMBE)准则,重新计算了图像的均衡范围。最后,利用新的均衡范围分别对每一个子图像进行均衡。实验表明,使用本算法处理Lena图的绝对均值亮度误差为0.416 4,明显优于使用RLBHE算法的0.629 5。本算法能够获得更清晰的图像细节,同时图像的整体亮度保持的也较好。     

邻域差值法确定灰度变换的分段点

光电跟踪测量设备电视系统受到自然条件的影响,往往捕获不到清晰的画面,很容易出现对比度极低的图像。针对此种情况,提出了一种用邻域差值来确定分段点的灰度变换法。通过计算像素55邻域的灰度差值,取最小的12个值之和ND。在大量实验的基础上确定合适的阈值T,与ND相比较,确定出图像边缘像素的灰度值范围,据此确定分段灰度变换公式的分段点。实验结果表明,在原图像对比度为1.19%的基础上,通过该算法处理后图像的对比度是原图像的18.79倍,是直方图均衡化后图像的6.97倍,是直方图规定化后图像的41.41倍,图像对比度达到了22.36%,图像的直方图也由单峰突出变为比较均衡的状态。该算法无论在数据上还是在视觉上都取得了很好的效果,满足了电视系统的跟踪要求,已经应用在光电跟踪测量设备上,有较好的实用价值。     

基于多尺度区域对比的显著目标识别

为了对图像中的显著目标进行更精确的识别,提出一种新的基于多尺度区域对比的视觉显著性计算模型。首先基于多尺度思想将图像分别分割为不同数目的超像素,对超像素内的像素颜色值取平均以生成抽象化图像;然后根据显著特征的稀少性及显著特征的聚集性,计算单一尺度下超像素颜色特征的显著性值;最后通过取各尺度超像素显著度的平均值来融合多尺度显著图,得到最终的视觉显著图。实验表明,以MSRA图库中的1 000张随机自然图片为例,该模型较现有较好的区域对比模型,显著目标识别的精确率提高了14.8%,F-Measure值提高了9.2%。与现有的算法相比,该模型提高了算法对显著目标大小的适应性,减少了背景对显著目标识别的干扰,具有更好的一致性,能更好地识别显著目标。     

Adaptive threshold selection for background removal in fringe projection profilometry

In fringe projection profilometry, background and shadow are inevitable in the image of an object, and must be identified and removed. In existing methods, it is nontrivial to determine a proper threshold to segment the background and shadow regions, especially when the gray-level histogram of the image is close to unimodal, and an improper threshold generally results in misclassification of the object and the background/shadow. In this paper, an adaptive threshold method is proposed to tackle the problem. Different from the existing automatic methods, the modulation-level histogram, instead of the gray-level histogram, of the image is employed to determine the threshold. Furthermore, a new weighting factor is proposed to improve Otsu's method to segment the image with a histogram close to unimodal, and the modulation difference of the object pixels and the background/shadow pixels is intensified significantly by the weighting factor. Moreover, the weighting factor is adaptive to the image. The proposed method outperforms existing methods either in accuracy, efficiency or automation. Experimental results are given to demonstrate the feasibility and effectiveness of the proposed method.     

光谱谐波分析的新型HAC非监督分类器

高光谱影像分类是识别影像信息的重要途径之一,研究其算法对地物识别、动态变化监测和专题信息提取等方面具有重要意义。非监督分类由于其具有无须先验知识的特点,被广泛应用于高光谱影像分类。结合谐波分析理论提出一种新的高光谱影像非监督分类算法,即谐波分析分类器(harmonic analysis classifier,HAC)。首先,该算法统计第一谐波分量并绘制其直方图,根据波峰数目及位置确定初始地物类别和聚类中心像元。然后将待分类像元光谱的波形信息映射到谐波分解次数、振幅和相位的特征空间中,利用同类地物在特征空间中表现聚集性这一特征,根据最小距离原则对待分类像元进行归类。最后,计算聚类中心像元间的欧式距离,通过设置距离阈值完成类间合并,从而达到高光谱影像分类的目的。提取两种地物类别的光谱曲线,经谐波分析后得到谐波分解次数、振幅和相位量,并分析其在特征空间中的分布情况验证了HAC算法的正确性。同时将HAC算法应用到EO-1卫星的Hyperion高光谱影像得到其分类结果,通过对比K-MEANS,ISODATA和HAC算法的高光谱影像分类结果,证实HAC算法作为一种非监督分类方法在高光谱影像分类方面具有较好的应用性。     

Two-dimensional Otsu's thresholding segmentation method based on grid box filter

Otsu algorithm, an automatic thresholding method, is widely used in classic image segmentation applications. In this paper, a novel two-dimensional (2D) Otsu thresholding algorithm based on local grid box filter is proposed. In our method, firstly by utilizing the coarse-to-fine idea, the 2D histogram is divided into regions by grid technique, and each region is used as a point to form a new 2D histogram, to which 2D Otsu thresholding algorithm and an improved particle swarm optimization (PSO) algorithm are applied to get the region number of the new 2D histogram threshold. Then on the result region, the mean of the 2D histogram is computed base on box filter, and the two algorithms are applied again to obtain the final threshold for the original image. Experimental results on real data show that the proposed algorithm gets better segmentation results than the traditional recursion Otsu algorithm. It significantly reduces the time of segmentation process and simultaneously has the higher segmentation accuracy.     

Automatic ridgelet image enhancement algorithm for road crack image based on fuzzy entropy and fuzzy divergence

True estimation of the boundary of a road crack and its size is a major task for its automatic detection. The improvement of visual effects of a road image is necessary for such a task. Therefore, we propose an automatic ridgelet image enhancement algorithm. A nonlinear function plays an important role in the enhancement algorithm in the ridgelet domain of an image. However, it is difficult to adjust the parameters of the nonlinear function adaptively with the variation of the road crack image input. Based on the fuzzy entropy criterion, we introduce two fuzzy divergences and two supplementary linear combinations between the fuzzy entropy and two fuzzy divergences as new measurements to solve the threshold segmentation problem in the ridgelet domain. According to the distribution histogram of magnitudes of the ridgelet high-frequency coefficients, we obtain the optimal segmentation thresholds that act as the parameters of the nonlinear function by using the maximum or minimum measurements of fuzzy entropy and fuzzy divergence, respectively. The self-adaptive nonlinear function makes it possible to realize the automatic enhancement of a road crack image. Experimental results show that our image enhancement algorithm can effectively enhance the global and local contrastive effects on road crack images.     

自适应红外目标特征增强算法

利用直方图均衡化和灰度变换增强算法,不能有效增强红外图像目标。鉴于此,在研究红外图像特点的基础上,提出了一种自适应红外目标特征增强算法。该算法先对红外图像进行中值滤波,滤除掉图像中的随机噪声,然后利用直方图分割将红外图像分为目标和背景2部分,通过线性加权叠加抑制背景和增强目标。实验表明,该算法不仅能够根据红外图像中目标的灰度特性自适应地选取直方图分割阈值,而且在去除噪声和增加对比度的同时还抑制了背景,达到了预期的效果。该算法尤其适用于目标和背景像素比例相近时直方图具有局域双峰特征的红外图像中目标的增强。     

Color correction for tiled projection with irregularly shaped,overlapping region

In this Letter, a new, constrained color-matching algorithm that removes the color variations is presented, in which all the color gamut of the projectors is mapped into a common gamut that can be produced by all the devices in the system. The smoothness constraints on the difference between two adjacent pixels are taken into account to calculate the luminance attenuation map of each pixel in the overlapping region to achieve luminance seamlessness. The experimental results demonstrate the validity and superiority of this correction algorithm.     

基于灰度冗余图像融合增强研究

为了改善原图像直方图像素灰度分布集中于低灰度级,与经过常规直方图均衡化处理的图像直方图像素灰度分布集中于高灰度级且均具有灰度冗余的图像增强效果,提出了一种新的图像增强算法.对原始图像进行常规直方图均衡处理,并对原始图像与进行了常规直方图均衡处理的图像分别在尽可能大的范围内进行映射,使两者变换后都尽可能去除灰度冗余而有较大的动态范围.取变换后的两图像各自的优点,融合成一幅效果最好的图像.实验结果验证了理论分析的正确性.     

Mean-shift跟踪算法及其在光电跟踪系统中的应用

针对光电跟踪系统中实时提取运动目标脱靶量的应用需求,设计了一种基于灰度直方图的Mean-shift 图像跟踪算法,对算法中目标模型与候选模型的建立进行了改进,抑制了背景像素对目标跟踪产生的影响。算法在系统上位机Visual C+ + 6.0平台上实现,当光电跟踪系统捕获到运动目标后,利用Mean-shift图像跟踪算法跟踪运动目标,并实时将运动目标脱靶量作为伺服控制系统的输入信号,驱动跟踪器跟踪目标。实验结果表明：设计的算法可以实时、准确、有效地跟踪运动目标,使稳定后的脱靶量换算得到的角偏差量控制在30"之内。     

Image enhancement via Median-Mean Based Sub-Image-Clipped Histogram Equalization

This paper presents a robust contrast enhancement algorithm based on histogram equalization methods named Median-Mean Based Sub-Image-Clipped Histogram Equalization (MMSICHE). The proposed algorithm undergoes three steps: (i) The Median and Mean brightness values of the image are calculated. (ii) The histogram is clipped using a plateau limit set as the median of the occupied intensity. (iii) The clipped histogram is first bisected based on median intensity then further divided into four sub images based on individual mean intensity, subsequently performing histogram equalization for each sub image. This method achieves multi objective of preserving brightness as well as image information content (entropy) along with control over enhancement rate, which in turn suits for consumer electronics applications. This method avoids excessive enhancement and produces images with natural enhancement. The simulation results show that MMSICHE method outperforms other HE methods in terms of various image quality measures, i.e. average luminance, average information content (entropy), absolute mean brightness error (AMBE) and background gray level.