Bayesian modeling of dynamic scenes for object detection

Accurate detection of moving objects is an important precursor to stable tracking or recognition. In this paper, we present an object detection scheme that has three innovations over existing approaches. First, the model of the intensities of image pixels as independent random variables is challenged and it is asserted that useful correlation exists in intensities of spatially proximal pixels. This correlation is exploited to sustain high levels of detection accuracy in the presence of dynamic backgrounds. By using a nonparametric density estimation method over a joint domain-range representation of image pixels, multimodal spatial uncertainties and complex dependencies between the domain (location) and range (color) are directly modeled. We propose a model of the background as a single probability density. Second, temporal persistence is proposed as a detection criterion. Unlike previous approaches to object detection which detect objects by building adaptive models of the background, the foregrounds modeled to augment the detection of objects (without explicit tracking) since objects detected in the preceding frame contain substantial evidence for detection in the current frame. Finally, the background and foreground models are used competitively in a MAP-MRF decision framework, stressing spatial context as a condition of detecting interesting objects and the posterior function is maximized efficiently by finding the minimum cut of a capacitated graph. Experimental validation of the proposed method is performed and presented on a diverse set of dynamic scenes.     

A temporal-spatial background modeling of dynamic scenes

Moving object detection in dynamic scenes is a basic task in a surveillance system for sensor data collection. In this paper, we present a powerful background subtraction algorithm called Gaussian-kernel density estimator (G-KDE) that improves the accuracy and reduces the computational load. The main innovation is that we divide the changes of background into continuous and stable changes to deal with dynamic scenes and moving objects that first merge into the background, and separately model background using both KDE model and Gaussian models. To get a temporal-spatial background model, the sample selection is based on the concept of region average at the update stage. In the detection stage, neighborhood information content (NIC) is implemented which suppresses the false detection due to small and un-modeled movements in the scene. The experimental results which are generated on three separate sequences indicate that this method is well suited for precise detection of moving objects in complex scenes and it can be efficiently used in various detection systems.     

动态背景下空时特性均显著的运动目标检测

从序列图像中提取变化区域是运动检测的主要作用,动态背景的干扰严重影响检测结果,使得有效性运动检测成为一项困难工作。受静态图像显著性检测启发,提出了一种新的运动目标检测方法,采用自底向上与自顶向下的视觉计算模型相结合的方式获取图像的空时显著性：先检测出视频序列中的空间显著性,在其基础上加入时间维度,利用改进的三帧差分算法获取具有运动目标的时间显著性,将显著性目标的检测视角由静态图像转换为空时性均显著的运动目标。实验和分析结果表明：新方法在摄像机晃动等动态背景中能较准确检测出空时均显著的运动目标,具有较高的鲁棒性。     

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...     

Neural network approach to background modeling for video object segmentation.

This paper presents a novel background modeling and subtraction approach for video object segmentation. A neural network (NN) architecture is proposed to form an unsupervised Bayesian classifier for this application domain. The constructed classifier efficiently handles the segmentation in natural-scene sequences with complex background motion and changes in illumination. The weights of the proposed NN serve as a model of the background and are temporally updated to reflect the observed statistics of background. The segmentation performance of the proposed NN is qualitatively and quantitatively examined and compared to two extant probabilistic object segmentation algorithms, based on a previously published test pool containing diverse surveillance-related sequences. The proposed algorithm is parallelized on a subpixel level and designed to enable efficient hardware implementation.     

Improved background modeling for real-time spatio-temporal non-parametric moving object detection strategies

Answering to the growing demand of machine vision applications for the latest generation of electronic devices endowed with camera platforms, several moving object detection strategies have been proposed in recent years. Among them, spatio-temporal based non-parametric methods have recently drawn the attention of many researchers. These methods, by combining a background model and a foreground model, achieve high-quality detections in sequences recorded with non-completely static cameras and in scenarios containing complex backgrounds. However, since they have very high memory and computational associated costs, they apply some simplifications in the background modeling process, therefore decreasing the quality of the modeling.     

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.     

基于聚类的背景建模与运动目标检测方法

为克服目前动态背景建模方法中计算量和存储量大的问题,提出了一种基于聚类的动态背景建模与运动目标分割方法。由于动态背景下每个像素的取值在时间轴上呈多峰分布形式,因此将每个峰看成一个子类,用聚类技术快速实现了动态背景的建模与更新,然后利用建立的背景模型快速、准确地实现运动目标的分割。实验结果表明：提出的背景建模方法能有效捕获并适应背景的动态变化,可显著降低目前动态背景建模方法的计算量和内存需求量,易于在基于DSP 或 FPGA等硬件系统上实时实现。     

Fuzzy-neural self-adapting background modeling with automatic motion analysis for dynamic object detection

In this paper we propose a system that involves a Background Subtraction, BS, model implemented in a neural Self Organized Map with a Fuzzy Automatic Threshold Update that is robust to illumination changes and slight shadow problems. The system incorporates a scene analysis scheme to automatically update the Learning Rates values of the BS model considering three possible scene situations. In order to improve the identification of dynamic objects, an Optical Flow algorithm analyzes the dynamic regions detected by the BS model, whose identification was not complete because of camouflage issues, and it defines the complete object based on similar velocities and direction probabilities. These regions are then used as the input needed by a Matte algorithm that will improve the definition of the dynamic object by minimizing a cost function. Among the original contributions of this work are; an adapting fuzzy-neural segmentation model whose thresholds and learning rates are adapted automatically according to the changes in the video sequence and the automatic improvement on the segmentation results based on the Matte algorithm and Optical flow analysis. Findings demonstrate that the proposed system produces a competitive performance compared with state-of-the-art reported models by using BMC and Li databases.     

Three-dimensional model-based object recognition and segmentation in cluttered scenes

Viewpoint independent recognition of free-form objects and their segmentation in the presence of clutter and occlusions is a challenging task. We present a novel 3D model-based algorithm which performs this task automatically and efficiently. A 3D model of an object is automatically constructed offline from its multiple unordered range images (views). These views are converted into multidimensional table representations (which we refer to as tensors). Correspondences are automatically established between these views by simultaneously matching the tensors of a view with those of the remaining views using a hash table-based voting scheme. This results in a graph of relative transformations used to register the views before they are integrated into a seamless 3D model. These models and their tensor representations constitute the model library. During online recognition, a tensor from the scene is simultaneously matched with those in the library by casting votes. Similarity measures are calculated for the model tensors which receive the most votes. The model with the highest similarity is transformed to the scene and, if it aligns accurately with an object in the scene, that object is declared as recognized and is segmented. This process is repeated until the scene is completely segmented. Experiments were performed on real and synthetic data comprised of 55 models and 610 scenes and an overall recognition rate of 95 percent was achieved. Comparison with the spin images revealed that our algorithm is superior in terms of recognition rate and efficiency.     

Hierarchical contour-based segmentation of dynamic scenes

A motion segmentation algorithm is introduced. The algorithm is based on the assumption of one coherent moving area (without holes) on a static background. It does coarse-to-fine pyramid-based boundary refinement that attempts to classify the blocks into three classes: inside, border, and outside     

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.     

复杂背景下圆形物体分割算法

对如何从复杂的工业图像中准确提取圆形目标进行了研究。阐述了传统分割方法应用于复杂图像中提取圆形目标的局限性,提出了基于双阈值结合数学形态学运算的分割算法。首先分别根据两个阈值进行分割得到两幅二值图像,然后根据目标是圆形以及其大致位置等先验知识分别对两幅图进行腐蚀,开启,闭合等数学形态学运算,将高阈值分割得到的图像中的边界信息叠加到低阈值分割得到的图像中,实现对复杂背景图像中圆形物体的准确分割与提取,解决了复杂背景图像中物体识别率低的问题。实验结果表明本方法对复杂背景的图像预处理是有效的。     

Generalized Stauffer�CGrimson background subtraction for dynamic scenes

We propose an adaptive model for backgrounds containing significant stochastic motion (e.g. water). The new model is based on a generalization of the Stauffer–Grimson background model, where each mixture component is modeled as a dynamic texture. We derive an online K-means algorithm for updating the parameters using a set of sufficient statistics of the model. Finally, we report on experimental results, which show that the proposed background model both quantitatively and qualitatively outperforms state-of-the-art methods in scenes containing significant background motions.     

Fast moving object detection with non-stationary background

The detection of moving objects under a free-moving camera is a difficult problem because the camera and object motions are mixed together and the objects are often detected into the separated components. To tackle this problem, we propose a fast moving object detection method using optical flow clustering and Delaunay triangulation as follows. First, we extract the corner feature points using Harris corner detector and compute optical flow vectors at the extracted corner feature points. Second, we cluster the optical flow vectors using K-means clustering method and reject the outlier feature points using Random Sample Consensus algorithm. Third, we classify each cluster into the camera and object motion using its scatteredness of optical flow vectors. Fourth, we compensate the camera motion using the multi-resolution block-based motion propagation method and detect the objects using the background subtraction between the previous frame and the motion compensated current frame. Finally, we merge the separately detected objects using Delaunay triangulation. The experimental results using Carnegie Mellon University database show that the proposed moving object detection method outperforms the existing other methods in terms of detection accuracy and processing time.     

具有强鲁棒性的三维对象多视变分分割方法

针对校准摄像机采集系列图像的三维分割重构问题,提出了一种新的面向概率描述的变分方法。首先,计算系列图像的极大似然曲面,可重构与分割保持一致的三维曲面;接着,融合联合概率,可重构目标对象及图像背景的平均强度及标准差;最后,采用水平集框架,可实现对曲面能量方程的数值模拟。该方法适用于复杂拓扑结构重构及噪声数据处理。实验结果表明,该方法实用性好,鲁棒性强,对任意三维对象的分割重构效果较形状雕刻方法及体视分割方法理想。     

多特征稳健主成分分析的视频运动目标分割

提出一种多特征稳健主成分分析(MFRPCA)算法,该算法融合多种视觉特征进行视频运动目标分割,分割的目的即将运动目标从静止信息中提取出来,分割的主要过程是将多特征视频矩阵分解为低秩矩阵和稀疏矩阵.矩阵分解过程是求解一个带受限条件的核范数与L2,1范数组合的最小化问题,此最小化问题可以通过增广拉格朗日乘子法(ALM)有效求解.与其他算法相比,本文算法融合了图像的颜色、边缘和纹理特征等多个特征,通过对变化检测基准数据集进行检测,本文算法获得的查全率为0.486 0和F度量为0.559 7,实验结果表明,本文算法的稳健性和可靠性均优于其他算法.