结合直方图反投影的多特征运动阴影检测算法

针对视频监控中运动阴影影响目标检测跟踪准确性的问题,提出一种结合直方图反投影的多特征运动阴影检测算法。首先利用背景减除法,得到前景区域并进行初步筛选;然后在背景区域建立亮度、颜色、梯度特征的联合直方图,以反投影的方式投影到前景区域得到运动阴影概率图;最后结合空间一致性和滞后阈值,对概率图进行分割得到运动阴影区域。与典型算法进行对比的实验结果表明,本文算法能够有效区分阴影与目标,适用于实时的运动目标检测与跟踪。     

一种改进的基于纹理和颜色的运动阴影检测

精确地消除活动阴影对运动目标的影响是智能视频监控的核心任务之一,针对当前运动阴影检测中采用的纹理信息过于粗糙、阈值选取需要人工干涉等问题,通过对NCC(归一化互相关)纹理算法进行改进,并结合亮度和归一化颜色特性,提出一种自适应的运动阴影检测方法。以混合高斯模型得到的前景像素为基础,通过阴影在亮度和归一化颜色的特性筛选出候选的阴影区域,结合改进的纹理算法进一步缩小阴影区域范围,最后利用空间后处理得到真实阴影。实验结果表明,该算法在有效降低噪声干扰的情况下能够较好区分局部纹理不明显的运动目标和阴影。     

基于YC_bC_r颜色空间的背景建模及运动目标检测

高斯混合模型广泛应用于基于背景建模的运动目标检测中。首先在YCbCr颜色空间采用自适应高斯混合模型对背景的每个像素建模;然后,对输入的当前帧图像的每一像素值与该像素点对应的高斯混合背景模型的各个高斯模型进行比较,将前景运动区域（包括运动目标、投射阴影）从场景中提取出来;最后,采用局部二元图（Lo-cal Binary Pattern,LBP）来提取纹理特征,利用背景在阴影覆盖前后的纹理相似性去除投射阴影,同时结合阴影的空间几何特性优化运动目标检测结果。实验结果表明,该算法能有效地检测出投射阴影和运动目标,具有较高的实际应用价值。     

基于自适应阈值的前景提取算法

针对固定场景视频监控中运动目标提取的问题,提出了一种基于自适应阈值的前景提取方法。该算法通过混合高斯模型(GMM)对背景建模及更新,利用自适应阈值的方法,实现了模型门限的自适应调整和前景目标的分割。然后通过阴影抑制,滤波以及形态学处理的方法对前景目标进行后处理,改善了前景目标分割的质量。通过对不同场景的测试仿真表明,该算法能够有效地并且比较完整地提取出运动目标。     

基于阴影向量扩展的阴影检测方法

图像处理中阴影检测是一个重要的主题。本文提出了一种基于阴影向量扩展的阴影检测新方法。该方法依据阴影区域的光学特性,先找出前景中能够表达阴影区域主要特征的阴影向量,再根据阴影向量扩展出整个阴影区域。测试图库的实验结果表明该方法能有效的检测出前景中的阴影,并且改善了传统方法在强阴影识别方面的缺陷,以及常常把目标局部误识别为阴影的问题。     

Efficient method of moving shadow detection and vehicle classification

Moving shadow detection and removal from the extracted foreground regions of video frames, aim to limit the risk of misconsideration of moving shadows as a part of moving objects. This operation thus enhances the rate of accuracy in detection and classification of moving objects. With a similar reasoning, the present paper proposes an efficient method for the discrimination of moving object and moving shadow regions in a video sequence, with no human intervention. Also, it requires less computational burden and works effectively under dynamic traffic road conditions on highways (with and without marking lines), street ways (with and without marking lines). Further, we have used scale-invariant feature transform-based features for the classification of moving vehicles (with and without shadow regions), which enhances the effectiveness of the proposed method. The potentiality of the method is tested with various data sets collected from different road traffic scenarios, and its superiority is compared with the existing methods.     

基于颜色对立空间的运动目标的阴影检测

利用背景差分法检测运动目标,目标阴影和目标本身均会被当作前景检测出来。针对上述问题,提出了基于颜色对立空间的运动目标阴影的检测方法。该方法首先将提取的前景图像由常见的RGB格式转换成CIELAB颜色对立空间格式,再分别对其L＊、a＊和b＊三个通道进行边缘检测。由于CIELAB颜色对立空间所具有的接近人类视觉的特性,用上述检测出的边缘进行相关的数学形态学的处理,便可检测出阴影。实验结果表明该方法便捷快速,能够有效检测出运动目标的阴影。     

基于灰度特征和自适应阈值的虚拟背景提取研究

针对虚拟背景提取(Visual Background extractor,ViBe)算法在目标检测时容易出现鬼影和运动目标阴影的缺点,该文提出了一种基于灰度特征和自适应阈值的ViBe背景建模改进方法。该算法首先利用ViBe算法进行背景建模,得到前景目标,然后对前景目标进行灰度特征判断和自适应阈值比较,得到没有鬼影和运动目标阴影的运动目标。实验结果表明,改进后的算法可以很好地弥补ViBe算法的不足,提高ViBe算法的识别准确率。     

一种有效的图像阴影自动去除算法

目标跟踪与检测研究中,在检测运动前景时也会检测到运动目标投射的阴影。阴影使得运动目标发生几何变形,可能造成运动目标粘连,甚至造成检测不到目标。阴影去除后才能较真实的得到运动目标重心。本文研究一种利用图像YCbCr颜色信息去除阴影的方法。首先利用背景减的方法得到带影子的目标区域,其次进行YCbCr空间的背景减,由于影子和目标物体在YCbCr空间背景减信息有较大差别,因此可以通过阈值判断得到去影之后的精确目标区域,目标物体识别的精确性和鲁棒性将会得到提高。实验结果表明,该方法在去除阴影的同时又较好地保留了前景目标的信息,是一种有效的阴影去除方法。      

室内夜间微弱光源下运动目标检测和阴影去除

提出一种新的室内夜间微弱光源照明情况下的运动目标检测方法。首先进行背景建模, 获取稳固的背景图像, 之后对背景和当前帧图像进行图像增强处理, 提高其清晰度; 采用相对背景减法检测前景运动目标, 并对差分图像进行去噪和修补; 利用前景目标区域、阴影区域和背景区域像素亮度值存在差异的特点, 检测和去除背景差分图像中可能存在的阴影, 获得准确的运动目标。在室内夜间环境下采集视频进行试验, 结果验证了所提方法的有效性。     

基于颜色和梯度差估计器的运动阴影检测

针对当前运动阴影检测中采用的纹理信息过于粗糙问题,提出一种基于梯度差估计器并融合亮度和归一化颜色特征的阴影检测方法。以混合高斯模型得到的前景像素为基础,通过阴影在亮度和归一化颜色上的特性筛选出候选的阴影区域,然后利用梯度差估计器确定最终的阴影区域。实验结果表明,本文算法能很好地区分局部纹理不明显的运动目标和阴影。     

基于HSV空间阴影去除方法研究与应用

在智能视频监控系统中,运动阴影如果被误判为运动目标,将会影响到场景中运动目标的准确提取、跟踪和预测。针对这一问题,设计了一种基于HSV颜色空间的阴影去除方法。方法首先将背景差法和三帧差分法相结合,用于提取运动目标,再将提取的含有阴影的运动目标区域映射到其HSV色彩空间,通过与背景和相邻帧的亮度、饱和度比较,实现对阴影区域的检测和去除,处理过程中无需提前确定特征判别参数。将所设计的方法在标准高速公路视频数据库中进行测试并应用于实时的视频监控系统,验证结果表明该方法能更加有效的消除阴影,从而准确的检测出运动目标,同时方法对光线变化具有一定的鲁棒性。     

Object Tracking via Partial Least Squares Analysis

We propose an object tracking algorithm that learns a set of appearance models for adaptive discriminative object representation. In this paper, object tracking is posed as a binary classification problem in which the correlation of object appearance and class labels from foreground and background is modeled by partial least squares (PLS) analysis, for generating a low-dimensional discriminative feature subspace. As object appearance is temporally correlated and likely to repeat over time, we learn and adapt multiple appearance models with PLS analysis for robust tracking. The proposed algorithm exploits both the ground truth appearance information of the target labeled in the first frame and the image observations obtained online, thereby alleviating the tracking drift problem caused by model update. Experiments on numerous challenging sequences and comparisons to state-of-the-art methods demonstrate favorable performance of the proposed tracking algorithm.     

Velocity measurement based on orthogonal CCD shadow photograph system in Ballistic range

A method of measuring the velocity of fast moving object by charge coupled device(CCD) shadow photograph system is developed.This system consists of high resolution orthogonal CCD cameras,time detecting device and the pulsed laser which can generate two short laser pulses with adjustable interval more than 100 μs.Experiments are conducted to measure the velocity of the flying steel ball.The results show that the proposed velocity measurement is effective in modern ballistic measurement.     

改进的自适应灰度视频序列阴影检测方法

提出了一种自适应的阴影检测方法,去除了传统固定阈值阴影检测方法残留的阴影边缘,有效地改善了阴影检测效果。首先采用kmeans聚类、求前景灰度直方图峰值间平均值等方法得到自适应的阈值,在此基础上,计算满足阈值约束的前景像素点,将该点及其8邻域点都作为可去除的阴影点进行标记。最后,去除标记的阴影点及极小面积的前景区域。本文对已有的阴影检测算法进行了改进,加入了自适应的阈值计算方法并去除了原有算法检测后残留的阴影边缘,在对室内及室外视频序列进行的检测中都取得了较好的效果。      

基于HSV颜色空间检测与Gabor筛选器的阴影检测

针对视频分析中难以完全将前景(FG)和运动阴影正确分离,提出一种基于阴影HSV颜色空间特性与Gabor筛选器的阴影分割方法。首先,采用一种基于复杂背景(BG)的运动目标检测方法提取出运动目标;其次,采用基于HSV颜色空间阴影特性初步判定阴影区域;最后,设计基于感兴趣区域(ROI,region of interest)的Gabor筛选器对初步判定后的阴影区域进行筛选,从而检测出阴影。对不同光照和环境条件下的视频序列进行测试结果表明,方法效果好,阴影检测率高,可应用于智能视频监控的目标检测。     

基于颜色空间转换的运动目标检测与阴影去除

针对室内视频监控中运动目标检测常出现的阴影误检,提出了一种基于颜色空间转换的自适应背景建模和阴影消除算法.在RGB空间采用自适应背景差对视频图像进行前景背景分离,并将检测出的前景目标锁定在活动轮廓矩形框内进行目标跟踪,对于误检的虚假目标(即阴影),利用其亮度等信息,在HSV空间去除.经实验验证,该算法对阴影的去除有良好的效果,能准确检测出真实目标.     

An efficient method of cast shadow removal using multiple features

Features of images are often used for cast shadow removal. A technique based on using only a single feature cannot universally distinguish an object pixel from a shadow pixel of a video frame. On the other hand, the use of multiple features increases the computational cost of a shadow removal technique considerably. In this paper, an efficient yet simple method for cast shadow removal from video sequences with static background using multiple features is developed. The basic idea of the proposed technique is that a simultaneous use of a small number of multiple features, if chosen judiciously, can reduce the similarity between object and shadow pixels without an excessive increase in the computational cost. Using the features of gray levels, color composition, and gradients of foreground and background pixels, a method is devised to create a complete object mask. First, based on each of the three features, three individual shadow masks are constructed, from which three corresponding object masks are obtained through a simple subtraction operation. The object masks are then merged together to generate a single object mask. Each of the three shadow masks is created so as to cover as many shadow pixels as possible, even if it results in falsely including in them some of the object pixels. As a result, the subsequent object masks may lose some of these pixels. However, the object pixels missed by one of the object masks should be able to be recovered by at least one of the other two, since they are generated based on features complementary to the one used to construct the first one. The final object mask obtained through a logical OR operation of the three individual masks can, therefore, be expected to include most of the object pixels. The proposed method is applied to a number of video sequences. The simulation results demonstrate that the proposed method provides a mechanism for shadow removal that is superior to some of the recently proposed techniques without imparting an excessive computational cost.     

Video object segmentation in rainy situations based on difference scheme with object structure and color analysis

A scheme based on a difference scheme using object structures and color analysis is proposed for video object segmentation in rainy situations. Since shadows and color reflections on the wet ground pose problems for conventional video object segmentation, the proposed method combines the background construction-based video object segmentation and the foreground extraction-based video object segmentation where pixels in both the foreground and background from a video sequence are separated using histogram-based change detection from which the background can be constructed and detection of the initial moving object masks based on a frame difference mask and a background subtraction mask can be further used to obtain coarse object regions. Shadow regions and color-reflection regions on the wet ground are removed from the initial moving object masks via a diamond window mask and color analysis of the moving object. Finally, the boundary of the moving object is refined using connected component labeling and morphological operations. Experimental results show that the proposed method performs well for video object segmentation in rainy situations.