基于码书和纹理特征的运动目标检测

复杂环境下如何进行鲁棒的运动目标检测是计算机视觉领域热门研究课题。本文提出了一种新的码书和高斯局部二值模式(GLBP)的纹理描述的运动物体检测方法,在线学习构建码书纹理背景模型。首先用码书以类似聚类的方式构建每个像素的码书模型,根据码字的颜色和亮度相似性,将背景像素分布用聚类码字的形式表示出来,同时在模型初始化和运动检测阶段不断更新码字以反映背景变化。然后用单高斯模型来学习背景像素变化的概率,生成GLBP纹理算子,同时在线更新GLBP反映图像空间纹理信息变化。最后融合三个特征将当前帧分割为前景背景两部分。通过实验视频表明本方法在实际视频中取得了较好的鲁棒的效果。      

应用粒子滤波及先验概率模型进行图像分割的新算法

基于粒子滤波在非线性非高斯情况下具有较好的预测结果,本文提出了一种自适应背景图像分割新算法,该算法利用粒子滤波对下一帧的前景区域进行预测,进而计算出下一帧各像素点属于背景的概率以指导下一帧图像分割;在前景像素值与背景像素值相近的情况下利用先验知识进行图像分割是一种较好的方法,本文以粒子滤波预测结果与先验概率模型计算结果的均值作为当前像素点属于背景的概率来进行图像分割,实验结果表明,该方法在背景变化范围较大的情况下,可以减少前景点误分割为背景点的概率.     

基于ViBe的改进运动目标检测方法

提出一种基于ViBe算法的改进运动目标检测方法。改进的方法利用二十帧图像进行背景模型的初始化,通过比较SILTP特征值来对前后景像素进行分类,模型更新机制采用替代异常值的方式。在不同场景下的实验结果表明,改进后的算法对光照变化、鬼影产生和噪声具有强鲁棒性。     

基于广义B样条滤波器的图像边缘检测

为了更准确有效地提取图像边缘,提出一种基于广义B样条数字滤波器的边缘检测算法.首先由线性微分方程推导出广义B样条的一般形式.其后,利用广义B样条函数组建了边缘检测微分算子模板,该模板继承了广义B样条尺度因子α,通过调节α,可以改变边缘算子滤波器的幅值特性和带通特性,进而获得边缘表征的最佳效果.而后,结合变分公式和广义B样条函数构造广义B样条光滑滤波器,该滤波器实现了在光滑滤波意义下的直接样条变换,与边缘检测模板算子配合使用可提高边缘检测的抗噪能力.实验证明：该边缘检测算法能有效地检测出图像边缘,无论是边缘提取效果还是抗干扰能力都优于传统的差分算子.     

Semi-automatic 2D-to-3D video conversion based on background sprite generation

This paper presents a technique for semi-automatic 2D-to-3D stereo video conversion, which is known to provide user intervention in assigning foreground/background depths for key frames and then get depth maps for non-key frames via automatic depth propagation. Our algorithm treats foreground and background separately. For foregrounds, kernel pixels are identified and then used as the seeds for graph-cut segmentation for each non-key frame independently, resulting in results not limited by objects’ motion activity. For backgrounds, all video frames, after foregrounds being removed, are integrated into a common background sprite model (BSM) based on a relay-frame-based image registration algorithm. Users can then draw background depths for BSM in an integrated manner, thus reducing human efforts significantly. Experimental results show that our method is capable of retaining more faithful foreground depth boundaries (by 1.6–2.7 dB) and smoother background depths than prior works. This advantage is helpful for 3D display and 3D perception.     

A Hybrid Contextual Approach to Wildland Fire Detection Using Multispectral Imagery

We propose a hybrid contextual fire detection algorithm for airborne and satellite thermal images. The proposed algorithm essentially treats fire pixels as anomalies in images and can be considered a special case of the more general clutter or background suppression problem. It utilizes the local background around a potential fire pixel and discriminates fire pixels based on the squared Mahalanobis distance in multispectral feature space. It also employs the normalized thermal index to identify background fire pixels that should be excluded from the calculation of the statistical properties of the local background. The use of the squared Mahalanobis distance naturally incorporates the covariance of the multispectral image into the decision and requires the setting of a single detection threshold. By contrast, previous contextual algorithms only incorporate the statistical properties of individual bands and require the manual setting of multiple thresholds. Compared with the latest Moderate Resolution Imaging Spectroradiometer fire product (version 4), our algorithm improves user accuracy and producer accuracy by 1.5% and 2.6% on average, respectively, and up to 28% for some images. In addition, the novel use of the squared Mahalanobis distance allows us to create fire probability images that are useful for fire propagation modeling. As an example, we demonstrate this use for the airborne data.     

基于概率神经网络改进的GrabCut算法

针对GrabCut算法在分割图像时效率低,且容易出现欠分割与过分割的问题,提出了一种基于概率神经网络(PNN)改进的GrabCut(PNN_GrabCut)算法.该算法用PNN模型替换GrabCut算法中的高斯混合模型(GMM)进行t-links权值计算,以提升算法的计算效率;通过构建前景和背景直方图,选取像素值出现频...     

Striping Noise Detection and Correction of Remote Sensing Images

This paper presents an image destriping system for correcting striping noise of remote-sensing images. The developed system identifies stripe positions based on edge-detection and line-tracing algorithms. Pixels not affected by striping are used as control points to construct cubic spline functions describing spatial gray level distributions of an image. Detected stripes are corrected by replacing the pixels with more reasonable gray values computed from constructed spline functions. Gray values of clean pixels not affected by stripes are not altered to preserve data genuineness. Several experimental results demonstrate that the developed system can correctly detect stripes in remote-sensing images and effectively repair them. Evaluations of the results based on an quantitative image quality index indicate that the image quality has been improved significantly after destriping. The destriped images are not only visually more plausible but also can provide better interpretability and are more suitable for computerized analysis.      

基于改进的混合高斯模型的运动目标检测方法

为了改善混合高斯模型在光照突变时容易产生大量误检的缺陷,采用了一种高斯模型与均值法相结合并为前景像素建立计数器的方法。在建立背景模型时,运用多帧图像求平均值的方法初始化混合高斯模型的背景;为每帧图像的前景像素数建立计数器,并以此消除被误判为前景的区域;对检测出的前景区运用数学形态学处理,得到图像真正的前景区域。结果表明,该算法不仅克服了初始背景中的干扰,而且消除了光照突变时的误检,提高了运动目标的检测率。     

基于脉冲耦合神经网络和施密特正交基的一种新型图像压缩编码算法

自从脉冲耦合神经网络(PCNN)被提出以来,在图像处理、模式识别、人工智能等领域得到了广泛应用.由于其生物学背景的特性,使得其能够对灰度图像进行完美的分割:PCNN局部连接域的作用及阈值指数衰减特性,使得具有近似灰度特性的邻近像素能够同时处于激活状态,这就构成了PCNN分割特性的基础,使得图像分割结果既能较好地包含原始图像细节信息,又能避免一些无意义的小分割块的产生.借鉴施密特正交化思想,利用自然初始基对每一分割区域进行变换,得到一组正交基的变换系数,相对于分割前图像的数据量大为减少,存储空间需求小,从而实现了压缩.相对于JPEG算法,该方法使重建图像的质量得到显著提高,同时也使得逐步重建图像成为可能.     

Automatic color image contrast enhancement using Gaussian mixture modeling,piecewise linear transformation,and monotone piecewise cubic interpolant

Conventional contrast enhancement algorithms use complicated nonlinear mapping functions with parameters specified manually. In this paper, a parameter-free piecewise linear transformation and monotone piecewise cubic interpolation are used for color image contrast enhancement. The Gaussian mixture model is used to divide luminance histogram of input color image into multiple sub-histograms. Each sub-histogram is mapped linearly or nonlinearly to a portion of available output dynamic range proportional to its extent and the number of its pixels. The proposed algorithm has more controlled contrast enhancement than conventional algorithms to preserve natural outlook and local details in the input color image. This is done by considering brightness histogram preservation of input image by proposed algorithm, due to considering extent of each sub-histogram for allocating a portion of output dynamic range to it. Experimental results show that the proposed algorithm produces better or comparable contrast-enhanced images with natural outlook than several conventional algorithms on various types of images.     

复杂背景下基于贝叶斯-全概率联合估计的前景检测

针对复杂背景下前景提取较为困难或者提取准确率较低等问题,该文提出了基于贝叶斯-全概率联合估计的目标检测模型并引入了背景误差控制变量的概念。通过选择适当的特征向量,在贝叶斯-全概率估计模型下,背景像素将会分为静止与运动两种不同的类型,进而准确提取前景像素点。实验结果表明,该模型是一个较为通用的目标检测模型,在目标提取时,该文算法对各种类型的视频背景环境(包括复杂背景)都具有较好的适用效果。     

基于同类邻点预测的高光谱图像无损压缩

提出了一种基于聚类、对类波段重排、搜索同类相邻点预测的高光谱数据无损压缩方法。根据谱向特征,进行高光谱图像按像素聚类,对各个分类,根据波段间相关系数,利用最大生成树进行波段重排。对每种分类像素,搜索同类邻点,训练预测系数,并进行三维预测。残差采用Golomb-Rice编码。实验证实了算法的有效性。     

基于最小二阶导数的低复杂度视频背景建模算法

为了训练出适应于视频压缩域的高质量背景模型,该文根据像素点在时域上的分布特征,提 出一种基于最小二阶导数的低复杂度视频背景建模算法。首先,根据函数 的二阶导数性质来判断其波动特性;然后,通过二次差分拟合像素点在时域上的二阶导数, 得到各个像素点的稳定 性;最后,根据设定阈值分离出各个位置的像素点在训练周期内最平稳的值,将其作为相应 位置的背景模型值。实 验结果显示,与AVS2相比,BD-rate节省了9.83%,BD- PSNR提升了 0.37 dB。与AVS2-S的背景建模算法相比, 本算法有效改善了前景污染问题,降低了算法复杂度。     

A variational model and graph cuts optimization for interactive foreground extraction

In this paper, an interactive segmentation method is proposed, which is based on an improved Chan–Vese model, i.e. multiple piecewise constant model with geodesic active contour. The k-means method is used to learn the models of the foreground and background, which are the optimal piecewise constant approximation of the original image according to the input seeds clue by the user. Based on the piecewise constant models of the foreground and background, the multiple piecewise constant with a geodesic active contour energy function can be minimized by effective graph cuts algorithm, and the minimum cuts can be used to partition the image into the foreground and background. Numerical experiments demonstrate the superior performance of the proposed interactive foreground extraction method based on the improved Chan–Vese model compared to the original Chan–Vese model by simple user interaction.     

Nonlinear prediction for Gaussian mixture image models

Prediction is an essential operation in many image processing applications, such as object detection and image and video compression. When the images are modeled as Gaussian, the optimal predictor is linear and easy to obtain. However, image texture and clutter are often non-Gaussian, and, in such cases, optimal predictors are difficult to obtain. In this paper, we derive an optimal predictor for an important class of non-Gaussian image models, the block-based multivariate Gaussian mixture model. This predictor has a special nonlinear structure: it is a linear combination of the neighboring pixels, but the combination coefficients are also functions of the neighboring pixels, not constants. The efficacy of this predictor is demonstrated in object detection experiments where the prediction error image is used to identify "hidden" objects. Experimental results indicate that when the background texture is nonlinear, i.e., with fast-switching gray-level patches, it performs significantly better than the optimal linear predictor.     

Visibility improvement of underwater turbid image using hybrid restoration network with weighted filter

Due to the attenuation of light passes through water, the captured underwater images suffer from low-contrast, halo artifacts, etc. To address this issue, the hybrid network with a weighted filter is proposed to improve the visibility of the obscured (turbid) images. In the captured image, the brighter pixels (near-to-source) are called foreground regions and the darker pixels (far-from-source) are called background regions. In order to ensure the adaptability of the proposed algorithm, the considered datasets are collected on different atmospheric light such as pond, lake, and fisheries tank. The foreground area of an image can be enhanced using the thresholding and masking technique. The background hazy region can be recovered by a hybrid Dehazenet called Generative Adversarial Network and Convolutional Neural Network. With this, the transmission map with high accuracy and color deviation can be addressed. Then both the regions are blended and the Amended Unsharp Mask filter is used to toughen the distorted edges. Finally, the blended restored image is weighted with a contrast factor to obtain the visibility improved image. The subjective and objective evaluation is done on considering the standard non-reference metric called Underwater Image Quality Measure comprises measures of color, sharpness, and contrast for a variety of water types with different atmospheric light. It is observed that the proposed technique showed a metric improvement of 57% compared to other existing techniques in an average manner. Overall, it is inferred that the proposed technique produces better results in both subjective and objective evaluation, thus it outperforms other state-of-the-art techniques.

     

Binarization of color document images via luminance and saturationcolor features

This paper presents a novel binarization algorithm for color document images. Conventional thresholding methods do not produce satisfactory binarization results for documents with close or mixed foreground colors and background colors. Initially, statistical image features are extracted from the luminance distribution. Then, a decision-tree based binarization method is proposed, which selects various color features to binarize color document images. First, if the document image colors are concentrated within a limited range, saturation is employed. Second, if the image foreground colors are significant, luminance is adopted. Third, if the image background colors are concentrated within a limited range, luminance is also applied. Fourth, if the total number of pixels with low luminance (less than 60) is limited, saturation is applied; else both luminance and saturation are employed. Our experiments include 519 color images, most of which are uniform invoice and name-card document images. The proposed binarization method generates better results than other available methods in shape and connected-component measurements. Also, the binarization method obtains higher recognition accuracy in a commercial OCR system than other comparable methods.     

建立灰度图像的背景模型方法研究

建立背景模型是在灰度图像序列中进行目标跟踪常用的方法。建立背景模型的目的是对背景象素点的分布及其变化情况作一个描述，以便将前景目标从背景中分离出来。本文对几种建立背景模型的方法做了比较，并通过实验分析了各自的优缺点。     

融合ViBe改进算法和图像均值的运动目标检测

针对视频前景提取(ViBe)算法在模型初始化时因前景像素干扰导致的“鬼影”问题,面对复杂背景环境的更新策略问题,提出利用图像像素均值作为参考对ViBe算法模型进行初始化优化;同时,提出随背景模型复杂度变化的自适应更新策略。利用邻域像素和连续帧背景像素的相似性进行背景模型初始化;然后通过计算样本间各像素的方差判定背景模型是否稳定,建立自适应的更新策略;最后提取运动目标。通过CDnet2014数据集验证表明：该算法有效改善了“鬼影”现象,提高了背景模型在复杂环境下的鲁棒性,各项客观评价指标也有所提升。