A consensus-based method for tracking: Modelling background scenario and foreground appearance

Modelling of the background (“uninteresting parts of the scene”), and of the foreground, play important roles in the tasks of visual detection and tracking of objects. This paper presents an effective and adaptive background modelling method for detecting foreground objects in both static and dynamic scenes. The proposed method computes SAmple CONsensus (SACON) of the background samples and estimates a statistical model of the background, per pixel. SACON exploits both color and motion information to detect foreground objects. SACON can deal with complex background scenarios including nonstationary scenes (such as moving trees, rain, and fountains), moved/inserted background objects, slowly moving foreground objects, illumination changes etc.However, it is one thing to detect objects that are not likely to be part of the background; it is another task to track those objects. Sample consensus is again utilized to model the appearance of foreground objects to facilitate tracking. This appearance model is employed to segment and track people through occlusions. Experimental results from several video sequences validate the effectiveness of the proposed method.     

Robust background maintenance by estimating global intensity level changes for dynamic scenes

The maintenance of relevant backgrounds under various scene changes is very crucial to detect foregrounds robustly. We propose a background maintenance method for dynamic scenes including global intensity level changes caused by changes of illumination conditions and camera settings. If the global level of the intensity changes abruptly, the conventional background models cannot discriminate true foreground pixels from the background. The proposed method adaptively modifies the background model by estimating the level changes. Because there are changes caused by moving objects as well as global intensity level changes, we estimate the dominant level change over the whole image regions by mean shift. Then, the problem caused by saturated pixels are handled by an additional scheme. In the experiments for dynamic scenes, our proposed method outperforms previous methods by adaptive background maintenance and handling of saturated pixels.     

Change detection for moving object segmentation with robust background construction under Wronskian framework

Although background subtraction techniques have been used for several years in vision systems for moving object detection, many of them fail to provide good results in presence of noise, illumination variation, non-static background, etc. A basic requirement of background subtraction scheme is the construction of a stable background model and then comparing each incoming image frame with it so as to detect moving objects. The novelty of the proposed scheme is to construct a stable background model from a given video sequence dynamically. The constructed background model is compared with different image frames of the same sequence to detect moving objects. In the proposed scheme the background model is constructed by analyzing a sequence of linearly dependent past image frames in Wronskian framework. The Wronskian based change detection model is further used to detect the changes between the constructed background scene and the considered target frame. The proposed scheme is an integration of Gaussian averaging and Wronskian change detection model. Gaussian averaging uses different modes which arise over time to capture the underlying richness of background, and it is an approach for background building by considering temporal modes. Similarly, Wronskian change detection model uses a spatial region of support in this regard. The proposed scheme relies on spatio-temporal modes arising over time to build the appropriate background model by considering both spatial and temporal modes. The results obtained by the proposed model is found to provide accurate shape of moving objects. The effectiveness of the proposed scheme is verified by comparing the results with those of some of the existing state of the art background subtraction techniques on public benchmark databases. We found that the average F-measure is significantly improved by the proposed scheme from that of the state-of-the-art techniques.     

基于边缘帧差和高斯混合模型的行人目标检测*

针对高斯混合模型存在背景更新收敛性差,易受环境噪声和光照突变影响,易产生虚假目标等问题,提出一种基于高斯混合模型的改进算法,用于视频中行人目标检测。通过将帧差法引入高斯混合模型,快速区分背景区域和运动目标区域,从而提取前景中完整的行人目标。结合视频帧边缘和边缘帧差信息,采用多种模型更新率,提高高斯混合模型对复杂背景的自适应性和快速收敛性,从而消除环境噪声和光照突变的影响,避免检测出虚假目标。实验结果表明,相比较传统高斯混合模型,该方法可以有效去除噪声和光照的干扰,收敛性更佳,行人检测效果更鲁棒。     

统计建模与对象更新机制相结合的背景减法

基于混合高斯模型（Gaussian Mixture Models,GMM）或码书模型（Codebook,CB）的传统背景建模算法和改进后的G-KDE算法被广泛地运用于运动目标检测中,但是在光照突变、非静止背景和运动目标短暂停留再运动的场景中不能正确地检测出运动目标。针对以上问题,提出了一种从静止摄像机的视频序列中检测运动目标的背景减算法。通过统计像素的经历作为时间序列,利用核密度估计判断背景像素是否受到运动目标干扰,使用K-均值聚类算法的两个连续阶段来确定可靠的背景区域,通过像素更新适应渐进的光照变化,提出一种基于对象的背景更新机制适应突然的光照变化以及非静止背景、鬼影等干扰。对实际摄取的视频进行了仿真实验,结果表明该算法比其他三种方法检测运动目标鲁棒性更好,准确性更高。     

背景差方法在复杂场景条件下的应用

针对运动目标检测中背景模型的维护问题,提出了基于动态三元组(DTDG)的背景建模方法.该方法给出了动态三元组的概念,对每个像素维护一个动态三元组,根据像素的动态变化信息决定更新策略.实现了背景的自动更新,可以适应光照的突变、缓变和场景本身的变化.实验表明了该方法在复杂场景条件下的有效性.     

混合高斯模型结合五帧差分的运动目标检测

在复杂背景下,光照变化、目标短暂遮挡以及背景运动等因素会导致运动目标检测精度较低.提出一种结合改进混合高斯模型和改进五帧差分的运动目标检测算法,首先在混合高斯模型中加入自适应学习率以及背景学习速率更新策略有效解决传统背景更新速率恒定而出现的残影现象;然后利用改进的五帧差分法克服运动目标短暂遮挡问题,并加入光照阈值判别因素,有效减弱光照变化带来的影响;最后对两者结果进行或运算进而得到最终检测结果.实验结果表明,该融合算法在复杂环境下具有一定的抗干扰能力,运动目标检测精度较高.     

A traffic surveillance system using dynamic saliency map and SVM boosting

This paper proposes a traffic surveillance system that can efficiently detect an interesting object and identify vehicles and pedestrians in real traffic situations. The proposed system consists of a moving object detection model and an object identification model. A dynamic saliency map is used for analyzing dynamics of the successive static saliency maps, and can localize an attention area in dynamic scenes to focus on a specific moving object for traffic surveillance purposes. The candidate local areas of a moving object are followed by a blob detection processing including binarization, morphological closing and labeling methods. For identifying a moving object class, the proposed system uses a hybrid of global and local information in each local area. Although the global feature analysis is a compact way to identify an object and provide a good accuracy for non-occluded objects, it is sensitive to image translation and occlusion. Therefore, a local feature analysis is also considered and combined with the global feature analysis. In order to construct an efficient classifier using the global and local features, this study proposes a novel classifier based on boosting of support vector machines. The proposed object identification model can identify a class of moving object and discard unexpected candidate area which does not include an interesting object. As a result, the proposed road surveillance system is able to detect a moving object and identify the class of the moving object. Experimental results show that the proposed traffic surveillance system can successfully detect specific moving objects.     

基于局部更新的分层码本目标检测算法

为了解决复杂环境下如树木摇摆、水波晃动等波动式干扰及光照变化对运动目标检测产生影响的问题,给出了一种基于码本模型的运动目标检测算法。考虑到实际场景中背景的变化主要体现在亮度方面,首先对视频序列图像进行颜色空间转化,由RGB空间转化到YUV空间,然后利用Box模型优化了码本模型参数和训练策略。目标检测时,采用局部背景更新方法,即利用帧差法确定变化区域,结合分层码本思想,实时更新背景模型,以达到精确提取运动目标的目的。对比实验表明在背景中存在扰动或者光照发生变化等情况下,该算法都能够对运动目标进行有效检测,具有一定实用性和鲁棒性。     

Detection of moving objects with a moving camera using non-panoramic background model

This paper presents a fast and reliable method for moving object detection with moving cameras (including pan–tilt–zoom and hand-held cameras). Instead of building large panoramic background model as conventional approaches, we construct a small-size background model, whose size is the same as input frame, to decrease computation time and memory storage without loss of detection performance. The small-size background model is built by the proposed single spatio-temporal distributed Gaussian model and this can solve false detection results arising from registration error and background adaptation problem in moving background. More than the proposed background model based on spatial and temporal information, several pre- and post-processing methods are adopted and organized systematically to enhance the detection performances. We evaluate the proposed method with several video sequences under difficult conditions, such as illumination change, large zoom variation, and fast camera movement, and present outperforming detection results of our algorithm with fast computation time.     

一种基于鲁棒局部纹理特征的背景差分方法

针对复杂场景下运动目标的精确检测这一问题,提出一种对噪声鲁棒并具备灰度尺度不变性的局部纹理特征描述子LBP_Center,将其与像素的颜色信息结合应用于背景建模中,采用随机抽样的机制更新模型,同时引入背景复杂度以去除多模态动态背景产生的噪点。在标准测试数据集上的实验结果表明,该算法对柔性阴影及光照缓慢变化具备良好的鲁棒性,综合性能更优。     

一种自然环境下运动物体监测算法

提出了一种自然环境下运动物体的监测算法,该算法基于时空信息融合与特征识别,主要包括背景分析、前景提取、去除阴影、背景更新。其思想是将图像序列均转换为HSV颜色模型,并分析比较各像素点参数在某一时间段内的变化规律,通过判定公式的判定,便可区分出各像素点在某一帧中是属于背景点、运动物体点还是阴影点。该算法针对风、阳光、闪电等自然条件可能带来的影响进行了改进,并能够在光照突变、运动物体静止后融入背景、背景物体转为运动等情况下智能更新背景,适用于自然环境下运动物体的监测。     

基于动态阈值对称差分和背景差法的运动对象检测算法*

提出一种基于动态阈值对称差分和背景差法的运动对象检测算法.首先通过建立一个基于统计的可靠背景更新模型,由背景差法得到基本准确的前景图像;然后与用对称差分法得到的差分图像综合;最后得到完整可靠的运动目标图像.中间采用了一种动态的最优阈值获取方法,然后用形态学滤波和连通区域面积检测进行后处理,以消除噪声和背景扰动带来的影响,并用区域填充算法来填补目标区域的小孔,从而将视频序列中的运动目标比较可靠地检测出来.实验结果表明,该方法快速、准确,有一定的实际应用价值.     

Dynamic obstacle identification based on global and local features for a driver assistance system

This paper proposes a novel dynamic obstacle recognition system combining global feature with local feature to identify vehicles, pedestrians and unknown backgrounds for a driver assistance system. The proposed system consists of two main procedures: a dynamic obstacle detection model to localize an area containing a moving obstacle, and an obstacle identification model, which is a hybrid of global and local information, for recognizing an obstacle with and without occlusion. A dynamic saliency map is used for localizing an area containing a moving obstacle. For the global feature analysis, we propose a modified GIST using orientation features with MAX pooling, which is robust to translation and size variations of an object. Although the global features are a compact way to represent an object and provide a good accuracy for non-occluded objects, they are sensitive to image translation and occlusion. Thus, a local feature-based identification model is also proposed and combined with the global feature. As such, for the obstacle identification problem, the proposed system mainly follows the global feature-based object identification. If the global feature-based model identifies a candidate area as background, the system verifies the area again using the local feature-based model. As a result, the proposed system is able to provide information on both the appearance of obstacles and the class of an obstacle. Experimental results show that the proposed model can successfully detect obstacle candidates and robustly identify obstacles with and without occlusion.     

A robust framework for joint background/foreground segmentation of complex video scenes filmed with freely moving camera

This paper explores a robust region-based general framework for discriminating between background and foreground objects within a complex video sequence. The proposed framework works under difficult conditions such as dynamic background and nominally moving camera. The originality of this work lies essentially in our use of the semantic information provided by the regions while simultaneously identifying novel objects (foreground) and non-novel ones (background). The information of background regions is exploited to make moving objects detection more efficient, and vice-versa. In fact, an initial panoramic background is modeled using region-based mosaicing in order to be sufficiently robust to noise from lighting effects and shadowing by foreground objects. After the elimination of the camera movement using motion compensation, the resulting panoramic image should essentially contain the background and the ghost-like traces of the moving objects. Then, while comparing the panoramic image of the background with the individual frames, a simple median-based background subtraction permits a rough identification of foreground objects. Joint background-foreground validation, based on region segmentation, is then used for a further examination of individual foreground pixels intended to eliminate false positives and to localize shadow effects. Thus, we first obtain a foreground mask from a slow-adapting algorithm, and then validate foreground pixels (moving visual objects + shadows) by a simple moving object model built by using both background and foreground regions. The tests realized on various well-known challenging real videos (across a variety of domains) show clearly the robustness of the suggested solution. This solution, which is relatively computationally inexpensive, can be used under difficult conditions such as dynamic background, nominally moving camera and shadows. In addition to the visual evaluation, spatial-based evaluation statistics, given hand-labeled ground truth, has been used as a performance measure of moving visual objects detection.     

一种自适应运动目标检测算法及其应用

针对ViBe算法在动态背景下存在鬼影消除时间长、算法适应性差、前景检测噪声多的问题,本文提出一种基于ViBe算法框架的改进算法.该算法采用鬼影检测法标记第1帧中的鬼影区域,并向位于鬼影区域的背景模型中强制引入背景样本,从而快速抑制鬼影;在像素分类过程中,引入自适应分类阈值,解决全局阈值易受动态噪声干扰的问题;在背景模型更新中,根据像素分类的匹配值来动态决定更新因子,提高算法适应场景变化的能力.定性与定量的对比实验结果表明,本文算法相较于ViBe算法能够有效地检测动态背景下的运动目标,应用于河流漂浮物检测场景中也有较好的效果.     

Moving cast shadow detection by exploiting multiple cues

Background subtraction or temporal differencing is commonly applied on an image sequence for foreground/background segmentation. However, cast shadows of moving foreground objects in a scene often result in detection errors for many vision-based applications. To address this problem, the authors propose an algorithm exploiting the information of colour, shading, texture, neighbourhood and temporal consistency to detect shadows efficiently and adaptively. The experimental results show that the proposed method can detect the penumbra as well as the umbra in different kinds of scenarios under various illumination conditions.     

多信息动态融合的运动目标检测方法

针对基于视觉显著性的运动目标检测算法存在时空信息简单融合及忽略运动信息的问题,提出一种动态融合视觉显著性信息和运动信息的运动目标检测方法。该方法首先计算每个像素的局部显著度和全局显著度,并通过贝叶斯准则生成空间显著图;然后,利用结构随机森林算法预测运动边界,生成运动边界图;其次,根据空间显著图和运动边界图属性的变化,动态确定最佳融合权值;最后,根据动态融合权值计算并标记运动目标。该方法既发挥了显著性算法和运动边界算法的优势,又克服了各自的不足,与传统背景差分法和三帧差分法相比,检出率和误检率的最大优化幅度超过40%。实验结果表明,该方法能够准确、完整地检测出运动目标,提升了对场景的适应性。     

基于统计背景模型的运动目标检测方法

运动目标检测是计算机视觉、视频处理等应用领域的重要研究内容。其中减背景技术是一种常用方法。在减背景方法中，背景模型的提取、更新、背景扰动、外界光照条件变化、阴影检测等是必须要考虑的问题。提出了一种有效的运动目标检测方法，较好地解决了以上问题，首先利用统计的方法得到背景模型，并实时地对背景模型更新．以适应光线变化和场景本身的变化，用形态学方法和检测连通域面积进行后处理，消除噪声和背景扰动带来的影响，在HSV色度空间下检测阴影，得到准确的运动目标。实验结果表明，该方法是快速有效的。     

基于区域相关性的全局运动视频中非刚性对象跟踪

提出一种适合全局运动视频中自动探测与跟踪非刚性对象的OT-GAV模型.该模型首先利用基于区域相关性的RDM算法计算相邻帧区域匹配,并结合Q学习与K-S统计法优化匹配结果,获得较为精确的区域运动向量.然后,利用前景和背景存在的运动形态差异,区域动态纹理一致性及对象运动过程中保持区域完整性的特点,逐步实现前景对象区域的探测与合并.实验证明,本模型及其相关算法可在室内和室外环境下,自动探测前景关注对象,获得其较为精确的边缘信息,并实施有效的跟踪.同时,该模型还能够解决对象跟踪过程中的"空洞"问题.