Adjacent LBP and LTP based background modeling with mixed-mode learning for foreground detection

Pattern Analysis and Applications - Detection of video objects under bad weather and poor illumination condition is a challenging task. We address this issue using the notion of background...     

一种基于改进视觉背景提取算法的前景检测

针对视觉背景提取ViBe算法在前景检测中存在的鬼影现象且长时间难以消除的缺点,提出一种改进的视觉背景提取算法。首先,在视频前n帧序列的帧差法中,引入大津（OTSU）算法求自适应阈值,以分割出更为准确的前景区域;其次,利用去除前景区域的前n帧图像合成一张尽量少的包含前景区域的样本图像;最后利用扩展的邻域范围在合成的样本图像中对模型初始化,并把扩大的范围用在ViBe背景模型更新阶段。该算法与各种经典算法在大量视频库中进行了对比实验,仿真结果表明,改进的ViBe算法能快速消除鬼影对前景检测的影响,前景检测更为准确。     

结合背景和前景先验的显著性检测

目的 显著性检测已成为图像处理过程中的一个重要步骤,已被应用到许多计算机视觉任务中。虽然显著性检测已被研究多年并取得了较大的进展,但仍存在一些不足,例如在复杂场景中的检测不准确或检测结果夹带着背景噪声等。因此,针对已有图像显著性检测方法存在的不能有效抑制背景区域,或不能清晰突显出完整的目标区域的缺点,提出一种结合背景先验和前景先验信息的图像显著性检测算法。方法 首先选取图像的边界超像素作为背景区域,从而根据每个区域与背景区域的差异度来建立背景先验显著图;然后通过计算特征点来构建一个能够粗略包围目标区域的凸包,并结合背景先验显著图来选取前景目标区域,从而根据每个区域与前景目标区域的相似度来生成前景先验显著图;最后融合这两个显著图并对其结果进一步优化得到更加平滑和准确的显著图。结果 利用本文算法对MSRA10K数据库内图像进行显著性检测,并与主流的算法进行对比。本文算法的检测效果更接近人工标注,而且精确率和效率都优于所对比的算法,其中平均精确率为87.9%,平均召回率为79.17%,F值为0.852 6,平均绝对误差（MAE）值为0.113,以及平均运行时间为0.723 s。结论 本文提出了一种结合两类先验信息的显著性检测算法,检测结果既能够有效地抑制背景区域,又能清晰地突显目标区域,从而提高了检测的准确性。     

改进的基于统计模型的前景检测方法

针对基于统计模型的前景检测方法进行改进:一方面,背景模型中记录特征向量属于背景的历史最大概率,在当前帧像素点特征向量与背景模型中已有特征向量匹配时,利用历史最大概率提高其更新速度,使其尽快融入背景;另一方面,对利用贝叶斯决策规则检测的前景目标,剔除其轮廓信息后与背景的空间特征进行匹配,减少阴影对前景检测的影响。实验结果表明,与MoG方法和Li的统计模型方法的前景检测相比,该方法在阴影剔除以及大目标物体遮挡背景恢复等方面都有明显改进。     

Saliency detection via background prior and foreground seeds

Multimedia Tools and Applications - As an image pre-processing technology, saliency detection (DS) can be used in a wide variety of visual tasks. A bottom-up method of DS via background prior and...     

Joint fuzzy background and adaptive foreground model for moving target detection

Moving target detection is one of the most basic tasks in computer vision. In conventional wisdom, the problem is solved by iterative optimization under either Matrix Decomposition (MD) or Matrix Factorization (MF) framework. MD utilizes foreground information to facilitate background recovery. MF uses noise-based weights to fine-tune the background. So both noise and foreground information contribute to the recovery of the background. To jointly exploit their advantages, inspired by two framework complementary characteristics, we propose to simultaneously exploit the advantages of these two optimizing approaches in a unified framework called Joint Matrix Decomposition and Factorization (JMDF). To improve background extraction, a fuzzy factorization is designed. The fuzzy membership of the background/foreground association is calculated during the factorization process to distinguish their contributions of both to background estimation. To describe the spatio-temporal continuity of foreground more accurately, we propose to incorporate the first order temporal difference into the group sparsity constraint adaptively. The temporal constraint is adjusted adaptively. Both foreground and the background are jointly estimated through an effective alternate optimization process, and the noise can be modeled with the specific probability distribution. The experimental results of vast real videos illustrate the effectiveness of our method. Compared with the current state-of-the-art technology, our method can usually form the clearer background and extract the more accurate foreground. Anti-noise experiments show the noise robustness of our method.     

融合似物性前景对象与背景先验的图像显著性检测

为了在复杂背景图像中准确地提取出图像的显著区域,提出一种结合似物性前景对象与背景先验知识的图像显著性检测方法（OFOBP）。该方法首先对图像进行超像素分割,计算超像素颜色空间分布,得到初始显著图;利用似物性检测方法获取多个目标窗口,由窗口建立搜索区域,结合二值化的初始显著图优化目标窗口;再利用多窗口特征对超像素做前景对象预测,获取前景显著图;其次建立背景模板,计算稀疏重构误差获取背景先验图;最后融合两种显著图,得到最终显著检测结果。在公开数据集上与11种算法进行比较,本文算法能够较为准确地检测出显著区域,尤其是在复杂背景下对多个显著目标的检测,存在明显的优势。     

基于前景增强与背景抑制的显著性物体检测

显著性物体检测的关键在于准确地突出前景区域,多数传统方法在处理复杂背景图像时效果不理想。针对上述问题,提出了一种基于前景增强与背景抑制的显著性物体检测方法。首先,利用简单线性迭代聚类(SLIC)将图像进行分割得到多个超像素区域,通过区域间的对比和边界信息分别获得图像的显著区域与背景种子,并通过计算得到基于区域间对比和基于背景的两幅显著图。然后,在两幅图像中运用Seam Carving和Graph based的图像分割法区分显著与非显著区域,进而得到前景增强与背景抑制模板。最终,融合两幅显著图与模板得到最终的显著图。在公开数据集MSRA 1000上对算法进行验证,结果表明,所提算法与7种主流算法相比具有更好的查准率和查全率。     

Feature combination and interaction detection via foreground/background models

One approach to building complex software product families is to partition the possible functions of the system into conceptual chunks called features. Ideally, system instances are rapidly assembled by combining features desired by the particular customer. Unfortunately, features often interact, meaning their combination causes unintended undesirable behavior even though in isolation the features work fine. This paper describes an approach to feature combination and interaction detection via foreground/background models, which allows expressing features as augmentations to the behavior of a base model. It also classifies interactions into three categories, based on how they can be detected, and describes implemented tools which can detect interactions from the three categories. I show why this approach avoids falsely detecting the spurious Type I interactions to which many existing approaches are prone. The tools and methodology, as well as the prevalence of spurious interactions in existing approaches, are illustrated through application to telephony features from the feature interaction contest associated with FIW'98. This data provides evidence that the foreground/background approach catches more nonspurious interactions, with less human effort, than competing approaches.     

基于Manifold Ranking和结合前景背景特征的显著性检测

针对基于图和流形排序（Manifold Ranking）的显著性检测算法（MR算法）过度依赖边界节点的背景特征的问题,提出一种改进的结合前景背景特征的显著性检测算法。首先,对图像进行超像素分割,建立闭环图模型;然后利用流形排序算法根据图像前景特征和背景特征分别得出前景种子和背景种子;再通过亮度和颜色特征对两类种子进行结合,筛选出更为准确的查询节点;最后再利用流形排序算法进行显著值计算,得到最终的显著图。实验表明,改进方法与MR算法相比在精确率、召回率、F值等多个评价指标上均有明显提升,得到的显著图更接近真值。     

A novel target detection algorithm combining foreground and background manifold-based models

This paper focuses on the detection of small objects—more precisely on vehicles in aerial images—on complex backgrounds such as natural backgrounds. A key contribution of the paper is to show that, in such situations, learning a target model and a background model separately is better than training a unique discriminative model. This contrasts with standard object detection approaches for which objects vs. background classifiers use the same model as well as the same types of visual features for both. The second contribution lies in the manifold learning approach introduced to build these models. The proposed detection algorithm is validated on the publicly available OIRDS dataset, on which we obtain state-of-the-art results.     

A fuzzy spatial coherence-based approach to background/foreground separation for moving object detection

The detection of moving objects from stationary cameras is usually approached by background subtraction, i.e. by constructing and maintaining an up-to-date model of the background and detecting moving objects as those that deviate from such a model. We adopt a previously proposed approach to background subtraction based on self-organization through artificial neural networks, that has been shown to well cope with several of the well known issues for background maintenance. Here, we propose a spatial coherence variant to such approach to enhance robustness against false detections and formulate a fuzzy model to deal with decision problems typically arising when crisp settings are involved. We show through experimental results and comparisons that higher accuracy values can be reached for color video sequences that represent typical situations critical for moving object detection.     

Advanced background modeling with RGB-D sensors through classifiers combination and inter-frame foreground prediction

An innovative background modeling technique that is able to accurately segment foreground regions in RGB-D imagery (RGB plus depth) has been presented in this paper. The technique is based on a Bayesian framework that efficiently fuses different sources of information to segment the foreground. In particular, the final segmentation is obtained by considering a prediction of the foreground regions, carried out by a novel Bayesian Network with a depth-based dynamic model, and, by considering two independent depth and color-based mixture of Gaussians background models. The efficient Bayesian combination of all these data reduces the noise and uncertainties introduced by the color and depth features and the corresponding models. As a result, more compact segmentations, and refined foreground object silhouettes are obtained. Experimental results with different databases suggest that the proposed technique outperforms existing state-of-the-art algorithms.     

Non-parametric adaptive region of support useful for corner detection: a novel approach

A novel model for the determination of precise region of support of a point useful for corner detection is proposed in this paper. The proposed model, unlike other existing models is non-parametric and determines adaptive region of support dynamically. The experimental results reveal that the proposed method outperforms the existing corner detection methods and is invariant to image transformations too.     

Dynamic texture as foreground and background

Depending on application, temporal texture can be viewed as either foreground or background. We address two related problems: finding regions of dynamic texture in a video and detecting moving targets in a dynamic texture. We propose efficient and fast methods for both cases. The methods can be potentially used in real-time applications of machine vision. First, we show how the optical flow residual can be used to find dynamic texture in video. The algorithm is a practical, real-time simplification of the sophisticated and powerful but time-consuming method (Fazekas et?al. in Int J Comput Vis 82:48?C63, 2009). We give numerous examples of detecting and segmenting fire, smoke, water and other dynamic textures in real-world videos acquired by static and moving cameras. Then we apply the singular value decomposition (SVD) to a temporal data window in a video to detect targets in dynamic texture via the residual of the largest singular value. For a dynamic background of low-temporal periodicity, such as water, no temporal periodicity analysis is needed. For a highly periodic background such as an escalator, we show that periodicity analysis can improve detection results. Applying the method proposed in Chetverikov and Fazekas (Proceedings of British machine vision conference, vol 1, pp 167?C176, 2006), we find the temporal period and use the resonant SVD to detect moving targets against a time-periodic background.     

Local-to-global background modeling for moving object detection from non-static cameras

Multimedia Tools and Applications - This paper investigates efficient and robust moving object detection from non-static cameras. To tackle the motion of background caused by moving cameras and to...     

A hierarchical approach for background modeling and moving objects detection

In this paper, we propose a hierarchical approach for background modeling and moving objects detections in the intelligent visual surveillance system. The proposed approach models the background in block level and pixel level hierarchically, and the background is represented by texture information in block level and by color information in pixel level respectively. Meanwhile the variable parameters learning rate is proposed to speed up the convergence of the model parameters in the pixel model. The proposed approach provides us with many advantages compared to the state-of-the-art. Experimental results demonstrate the effectiveness and efficiency of the proposed approach.