Robust background subtraction in traffic video sequence

For intelligent transportation surveillance, a novel background model based on Mart wavelet kernel and a background subtraction technique based on binary discrete wavelet transforms were introduced. The background model kept a sample of intensity values for each pixel in the image and used this sample to estimate the probability density function of the pixel intensity. The density function was estimated using a new Marr wavelet kernel density estimation technique. Since this approach was quite general, the model could approximate any distribution for the pixel intensity without any assumptions about the underlying distribution shape. The background and current frame were transformed in the binary discrete wavelet domain, and background subtraction was performed in each sub-band. After obtaining the foreground, shadow was eliminated by an edge detection method. Experimental results show that the proposed method produces good results with much lower computational complexity and effectively extracts the moving objects with accuracy ratio higher than 90%, indicating that the proposed method is an effective algorithm for intelligent transportation system.

Background Subtraction and Frame Difference Based Moving Object Detection for Real-Time Surveillance

A new real-time algorithm is proposed in this paperfor detecting moving object in color image sequencestaken from stationary cameras.This algorithm combines a temporal difference with an adaptive background subtraction where the combination is novel.Ⅷ1en changes OCCUr.the background is automatically adapted to suit the new conditions.Forthe background model,a new model is proposed with each frame decomposed into regions and the model is based not only upon single pixel but also on the characteristic of a region.The hybrid presentationincludes a model for single pixel information and a model for the pixel’s neighboring area information.This new model of background can both improve the accuracy of segmentation due to that spatialinformation is taken into account and salientl5r speed up the processing procedure because porlion of neighboring pixel call be selected into modeling.The algorithm was successfully used in a video surveillance systern and the experiment result showsit call obtain a clearer foreground than the singleframe difference or background subtraction method.

Motion Tracking with Fast Adaptive Background Subtraction

To extract and tr ack moving objects is usually one of the most important tasks of intelligent video surveillance systems. This paper presents a fast and adaptive background subtraction algorithm and the motion tracking process using this algorithm. The algorithm uses only luminance components of sampled image sequence pixels and models every pixel in a statistical model. The algorithm is characterized by its ability of real time detecting sudden lighting changes, and extracting and tracking motion objects faster. It is shown that our algorithm can be realized with lower time and space complexity and adjustable object detection error rate with comparison to other background subtraction algorithms. Making use of the algorithm, an indoor monitoring system is also worked out and the motion tracking process is presented in this paper. Experimental results testify the algorithm's good performances when used in an indoor monitoring system.

Robust Background Subtraction Method via Low-Rank and Structured Sparse Decomposition

Background subtraction is a challenging problem in surveillance scenes. Although the low-rank and sparse decomposition(LRSD) methods offer an appropriate framework for background modeling, they fail to account for image's local structure, which is favorable for this problem. Based on this, we propose a background subtraction method via low-rank and SILTP-based structured sparse decomposition, named LRSSD. In this method, a novel SILTP-inducing sparsity norm is introduced to enhance the structured presentation of the foreground region. As an assistance, saliency detection is employed to render a rough shape and location of foreground. The final refined foreground is decided jointly by sparse component and attention map. Experimental results on different datasets show its superiority over the competing methods, especially under noise and changing illumination scenarios.

A method of estimating and subtracting the hydrogen background in the natural carbon target used in the ^(12)C + ^(12)C experiment

The experimental data of 100 A MeV12C +12C elastic scattering are checked by using two-body kinematic calculation and12 C + p elastic scattering. It is shown that the measured data are true and reliable. In the paper,the transformation between the excited energy spectra of the12 C +12C system and the ground state energy spectra of the12 C + p system is introduced. The method of subtraction of the hydrogen background in the natural carbon target used in the experiment is elaborately described and the results are discussed. It is indicated that this method of subtraction of hydrogen background is reasonable and can be used in the data analysis. Based on the elastic scattering cross section of the previous experiment of12C+p at 95.3A MeV, the hydrogen content entered into the reaction is analyzed. The final hydrogen content in the natural carbon target is(2.73 ± 0.12)%.

一种反衍拟合的复小波改进方法在XRF图谱本底扣除中的应用

X射线荧光光谱(XRF)分析是煤中金属元素定量分析的重要方法,本底扣除准确度直接影响矿物金属分选的精细度。针对传统本底扣除方法本底契合度低、衍射峰面积误差大的问题,本文提出了一种基于复小波变换的反衍拟合XRF本底扣除优化方法。利用逆置寻谷的方法获得模拟本底谱线,通过拉格朗日插值法剥离谱线中的重叠峰谷,使模拟谱线进一步逼近实际本底,利用复小波变换方法对模拟本底谱线进行分解与重构,最终获得XRF图谱本底。利用反衍拟合的复小波改进方法对仿真图谱和真实图谱进行本底扣除实验,并与实数小波和双树复小波进行对比分析。实验结果表明,本文提出的方法衍射峰净峰面积误差低于1%,本底面积误差低于0.1%,本底准确性明显优于传统方法。

基于二次移动平均法估计背景光照的二值化方法

针对不均匀光照图像的阈值分割问题,提出一种基于二次移动平均法估计背景光照的改进二值化方法。首先,利用二次移动平均预测法对一维图像空间的灰度序列进行趋势预测,根据预测趋势寻找前景与背景的分界点以此进行背景估计,然后利用背景差法分离出目标图像,最后采用最大类间方差法进行全局分割获得分割结果。为验证算法的有效性,实验采用50幅非均匀光照条件下的图像作为测试样本,并与几种局部阈值分割算法进行了对比。实验结果表明,与传统阈值分割算法相比,该算法能够在减少光照影响获取较为完整的图像信息的同时,在处理速度上也具有明显的提升。

REAL-TIME TRACKING FOR FAST MOVING OBJECT ON COMPLEX BACKGROUND

A real-time tracking system for the fast moving object on the complex background is proposed.The Markov random filed（MRF）model based background subtraction algorithm is used to detect the changing pixels and track the moving object.The prior probability of the segmentation mask is modeled by using MRF,and the object tracking task is translated into the maximum a-posterior（MAP）problem.Experimental results show that the method is efficient at both offline and online moving objects on simple and complex background.

基于图半监督学习的移动相机背景减除

在对移动相机拍摄的视频进行背景减除时,已有的无监督和监督学习模型的泛化能力都比较差。为此提出一种基于图表示和半监督学习的移动相机背景减除模型。首先提出了一种基于凸非凸图全变差正则的半监督学习模型。模型利用L1范数与其广义Moreau包络的差来构造非凸图全变差正则,可避免图全变差中L1正则项带来的有偏估计,并且在理论上可以保证模型中目标函数的整体凸性,进而可以利用交替方向乘子法对模型进行求解。数值实验中,将新模型应用到背景减除中,并在CDnet2014数据集的PTZ挑战上进行了比较实验。实验结果表明,对移动相机视频序列进行背景减除时,新模型在视觉效果和数值指标上都要优于已有的无监督和监督学习模型。

一种提升鬼影抑制性能的改进视觉背景提取算法

运动目标检测为视频帧生成指示运动目标像素的二值图,因此,正确判别待检测场景中的运动目标像素和背景像素是运动目标检测算法的主要任务。本文针对传统场景提取算法背景模型初始化导致的“鬼影”问题,提出了时域区间参考模块,该模块通过时域区间内像素的统计值生成背景参考值,在像素判别阶段利用候选前景像素与该参考值的差异进一步确定前景像素。实验结果表明,本文提出的方法对传统视觉背景提取算法性能进行了提升,对“鬼影”有较强的抑制作用,提高了检测准确度,具有较好的检测性能。

基于视频图像的安全监测算法研究

针对智能视频监控中运动目标检测与提取相关算法易受噪声干扰和易出现空洞现象的问题,利用Matlab环境,将使用背景差分法与二帧差分法获得的二值图像与使用三帧差分法获得的二值图像进行“或”运算得出改进算法,并进行对比评估。实验结果表明,改进后的算法能够避免侦差法检测运动目标过程中出现的空洞现象,能够克服易出现噪声干扰的缺点,得到的目标轮廓也比之前单一算法提取的运动目标更加明确。

Diversity Sampling Based Kernel Density Estimation for Background Modeling

A novel diversity-sampling based nonparametric multi-modal background model is proposed. Using the samples having more popular and various intensity values in the training sequence, a nonparametric model is built for background subtraction. According to the related intensifies, different weights are given to the distinct samples in kernel density estimation. This avoids repeated computation using all samples, and makes computation more efficient in the evaluation phase. Experimental results show the validity of the diversity- sampling scheme and robustness of the proposed model in moving objects segmentation. The proposed algorithm can be used in outdoor surveillance systems.

Adaptive Motion Segmentation for Changing Background

Segmentation of moving objects efficiently from video sequence is very important for many applications. Background subtraction is a common method typically used to segment moving objects in image sequences taken from a statistic camera. Some existing algorithms cannot adapt to changing circumstances and require manual calibration in terms of specification of parameters or some hypotheses for changing background. An adaptive motion segmentation method is developed according to motion variation and chromatic characteristics, which prevents undesired corruption of the background model and does not consider the adaptation coefficient. RGB color space is selected instead of introducing complex color models to segment moving objects and suppress shadows. A color ratio for 4-connected neighbors of a pixel and multi-scale wavelet transformation are combined to suppress shadows. The mentioned approach is scene-independent and high correct segmentation. It has been shown that the approach is robust and efficient to detect moving objects by experiments.

武术难点动作图像多目标自动提取方法研究

提取武术难点动作时常常因无法消除动作图像中的阴影部分,导致存在角点检测重复率高、提取效果差和整体识别率低的问题。为此,提出武术难点动作图像多目标自动提取方法,建立武术动作图像的背景模型,并更新背景模型,通过背景差分与分割处理获取武术动作图像的目标区域。检测目标区域中是否存在阴影,并且消除阴影,检测武术动作角度,根据角度数据完成武术难点动作提取。实验结果表明,所提方法的角点检测重复率低、提取效果好、整体识别率较高。

基于OpenCV-Python的高速公路车辆识别与计数功能研究

为实现传统图像处理方法在智能交通系统中的广泛应用,针对高速公路监控视频中车辆的识别与计数方法进行研究,采用Python编程语言,基于OpenCV库,通过灰度化、去噪、背景减除和形态学运算等一系列传统图像处理方法完成了车辆的识别与计数功能设计,并将该方案与基于YOLOv3模型和简单在线和实时跟踪(SORT)算法相结合的方案进行对比。结果表明,传统图像处理方法可以完成运动目标检测任务,但相对于基于深度学习的方案存在准确度不高和通用性不强的问题,为此提出了将传统图像处理与深度学习相结合的研究建议。

基于改进GMM背景差分方法的蒸汽泄漏检测研究

为检测反应堆回路试验装置蒸汽泄漏,提出了一种改进的基于背景差分法的蒸汽泄漏红外视频检测方法。该方法利用红外相机采集图像,使用Wasserstein距离匹配像素点,采用K-means方法去更新改进的混合高斯背景模型(GMM);在后处理中,采用自适应均值滤波及形态学方法抑制环境噪声,通过对泄漏图像灰度形状面积的分层融合特征判断实现对蒸汽泄漏的分级检测。为实现对算法效果的量化,利用泄漏报警率、F1分数等指标评价检测方法的优劣,提出以Dice系数作为算法分割效果的评价函数;在steamTS200inf数据集上的试验结果表明,泄漏报警率可达98.52%,最后一帧分割Dice值可达78.31%,本文方法可有效检测蒸汽泄漏。

一种触摸屏电极薄膜定位与缺陷检测方法

电极薄膜表面的污渍缺陷检测是工业生产触摸屏过程中一个必要环节,利用图像采集系统结合数字图像处理进行检测,可以将薄膜按结构特征和缺陷分布情况分为两部分;按不同区域特点分别采用背景差分算法和局部增强算法进行缺陷检测,从而解决了传统的人工检测耗时、耗力、不精确等问题,提高了生产效率。

基于加权核范数与3D全变分的背景减除

针对鲁棒主成分分析模型(Robust Principal Component Analysis,RPCA)一般将前景看作背景中存在的异常像素点,从而使得在复杂背景中前景检测精度下降的问题,提出一种基于加权核范数与3D全变分(3D-TV)的背景减除模型。该模型以RPCA为基础,利用加权核范数来约束背景的低秩性,考虑了不同奇异值对秩函数的影响,使其更接近实际背景的秩;然后利用3D-TV来约束前景的稀疏性,考虑了目标在时空上的连续性,有效抑制了复杂背景对前景提取造成的干扰。实验结果表明,与其他4种算法对比,所提模型的F值基本上是最优的,且能准确地分离图像中的背景和前景。

Moving Multi-Object Detection and Tracking Using MRNN and PS-KM Models

On grounds of the advent of real-time applications,like autonomous driving,visual surveillance,and sports analysis,there is an augmenting focus of attention towards Multiple-Object Tracking(MOT).The tracking-by-detection paradigm,a commonly utilized approach,connects the existing recognition hypotheses to the formerly assessed object trajectories by comparing the simila-rities of the appearance or the motion between them.For an efficient detection and tracking of the numerous objects in a complex environment,a Pearson Simi-larity-centred Kuhn-Munkres(PS-KM)algorithm was proposed in the present study.In this light,the input videos were,initially,gathered from the MOT dataset and converted into frames.The background subtraction occurred whichfiltered the inappropriate data concerning the frames after the frame conversion stage.Then,the extraction of features from the frames was executed.Afterwards,the higher dimensional features were transformed into lower-dimensional features,and feature reduction process was performed with the aid of Information Gain-centred Singular Value Decomposition(IG-SVD).Next,using the Modified Recurrent Neural Network(MRNN)method,classification was executed which identified the categories of the objects additionally.The PS-KM algorithm identi-fied that the recognized objects were tracked.Finally,the experimental outcomes exhibited that numerous targets were precisely tracked by the proposed system with 97%accuracy with a low false positive rate(FPR)of 2.3%.It was also proved that the present techniques viz.RNN,CNN,and KNN,were effective with regard to the existing models.

基于自适应背景差分与深度学习的矿山巷道不安全行为的自动识别

煤炭开采行业是公认的高危行业,其中人的行为因素是造成绝大多数事故的直接原因。及时提醒、纠正矿工的不安全行为是避免煤矿事故最重要且最有效的方法。本文基于自适应背景差分模型,提出了一个三阶段优化算法,通过异常值发现、异常值区域像素点平面平滑以及连通域分析算法,实现了矿工子图数据集的有效提取。特别是在异常值发现中,本文采用中位数估计方法,通过分布式中位数计算,求得标准差更稳健的中位数估计量,替代传统矩估计量构造阈值,获得更加稳健的异常值区域,进而提取高质量的矿工子图数据集。实验结果表明,与传统估计方法相比,基于中位数估计得到的标准差所构造的阈值,提取的矿工子图准确率更高,提取的结果更稳健。同时,本文直接对矿工子图标注类别,避免进行边界框的标注,操作简单,快捷高效。最后,本文使用MobileNet模型进行迁移学习,结果进一步表明,中位数估计方法得到的矿工子图数据集的质量优于传统估计方法,子图分类准确度更理想,能够有效地识别矿工的不安全行为。