基于GPU的视频序列中运动目标轮廓提取

传统的高斯混合建模算法对阴影的抑制效果差,且存在噪声干扰和对光照突变比较敏感的问题。采用了一种改进的高斯混合建模方法进行运动目标轮廓提取。该方法利用Canny边缘图像对噪声和光照适应性强的特点,将传统高斯混合模型与Canny边缘检测相结合来提取目标轮廓。但是,该方法复杂度高且计算量大,不满足视频分析实时性的需求,因此,运用GPU强大计算能力和并行处理的优势,基于CUDA平台设计并实现了该运动目标轮廓提取算法。实验结果表明,该算法增强了对噪声和光照的适应性,且有效抑制了图像中的阴影,在保证效果的前提下能够更快速地提取视频序列中的运动目标轮廓。     

复杂场景下的快速目标检测算法

针对场景发生改变的目标检测,提出了一种快速的目标检测算法。该算法将像素点划分为背景点和前景点两类,使用聚类的方法并采取像素级收敛条件分别建立背景和前景模型。背景模型的更新适用于全局发生缓慢的变化,稳定的前景模型向背景模型的转化对光照等其他场景突变具有很好的鲁棒性,使背景模型实时逼近真实背景,同时改进连通域扫描分割算法,提高目标分割速度。实验结果表明,该方法具有很好的鲁棒性,能够快速准确地检测出运动目标,为在DSP等嵌入式系统上实现实时目标检测提供了有利条件。     

基于着陆器平台的一种运动目标检测算法

针对基于传统混合高斯模型算法对光照突变敏感,以及运动物体速度缓慢时产生的“重影”现象,根据深海自主观测的应用需求提出了一种三帧差法结合动态自适应学习率的改进混合高斯模型算法。利用三帧差法快速定位出视频帧的背景、前景及干扰区,对不同区域给予不同的学习率和更新策略,减小了运算量和提高了算法的收敛速率。实验结果表明,该算法能有效地处理深海环境中海流扰动、浮游物干扰以及光线突变带来的影响,具有良好的实时性和鲁棒性,在深渊着陆器的实际工程应用中能够准确地检测出运动目标。     

基于数学形态学的运动目标检测算法

帧差法和背景差法都是重要的运动目标检测方法,帧差法不能完全提取出目标的所有相关点,而背景差法又受环境光照的影响。针对传统运动目标检测算法的不足,提出一种基于数学形态学的帧差法与背景差法相结合的运动目标检测算法。先将帧差法得到的图像经过数学形态学处理,再将其与背景差法得到的图像相结合。实验表明,该算法能适应复杂变化的环境,准确地提取运动目标,对复杂干扰场景下的实时运动目标检测得到了较为满意的效果。     

基于改进均值建模的自适应三帧差分算法研究

针对实际视频图像中复杂的背景环境（光照变化、有微动物体等）,运动目标检测算法不易提取出完整的运动目标,提出了基于改进均值背景模型的自适应三帧差分算法。该算法利用前k帧建立的均值背景模型作为三帧差分法的中间帧,再采用三帧差分法,并对差分结果选取自适应阈值来二值化,将两个检测出的目标进行“与”运算,最后通过形态学处理、滤波等,获得运动目标的真实位置。最后试验结果表明,提出的算法能够适应比较复杂的背景环境,不易受光照变化或其他微小变化的影响,又能有效克服空洞和边缘丢失的现象,并且检测准确率更高,适用于无人监控环境。     

基于双目视觉的运动目标检测算法研究

运动目标检测是实现目标识别与跟踪的基础,它是计算机视觉研究领域的重要组成部分。鉴于传统的运动目标检测算法容易受到噪声、光照及外部环境影响,导致难以准确检测到运动目标的缺点,提出了基于视差的目标检测方法和基于灰度的目标检测方法相结合的算法进行运动目标检测。该方法是将两种算法检测出的前景目标相交部分作为运动目标,克服了双目视觉在目标检测中难以准确的获得目标轮廓,单目视觉容易受环境变化影响的缺点,可以在环境光线发生变化时、物体被照射产生阴影时、目标发生遮挡时准确检测出运动目标,从而提高目标检测的稳定性。     

基于像素值聚类的运动目标检测方法

提出了一种基于像素值聚类的运动目标检测方法。在RGB空间进行背景提取,将一幅图像中的每个像素点在时间轴上进行聚类,提取背景模板;之后采用当前图像与背景模板进行比较,从而检测出运动目标,并同时进行背景模板的更新。在此过程中采用了模板替换机制以节约存储空间;在背景建模部分加入结束判定部分,以自适应的建立背景模板。相比于经典的混合高斯（GMM）和codebook方法,该算法的运行时间至少缩短了1／4,提高了检测速度。实验结果表明,该算法能够在不同条件下快速准确的检测运动目标。     

基于循环相关滤波算法的复杂背景目标跟踪方法研究

为了实现在复杂情况中对特定目标的路线跟踪,主要研究了基于循环相关滤波器的目标跟踪算法,并针对复杂环境情况下影响跟踪性能的条件进行分析比较。该算法是一种基于线性分类器的监督学习算法,通过添加空间正则化分量减少边界效应,提取准确目标。在OTB-50和OTB-100数据集上进行算法验证,实验表明,该算法的跟踪结果优于其他算法,在快速移动、背景杂乱、光照变化、遮挡、移出视线和运动模糊6种复杂情况下跟踪准确度比传统算法均高出0.1以上。     

视频监视中运动物体检测的一种新算法

本文提出一种结合阈值分割以及区域生长的算法检测视频中运动物体的算法.首先对相邻的图像帧进行差分并根据3σ准则二值化差分图像,然后对二值图像进行扫描去除虚假目标区域和孤立亮点、并记录各区域的边界值,最后用区域生长的办法得到运动物体的完整信息.实验表明,在背景复杂、光照不均匀的视频中,该算法比帧间差分法、数学形态学的方法等能够更精确地检测出多个运动物体,在提取目标的同时,不留下任何背景像素,使下一步的目标跟踪更精确.     

一种用于电力监控的行人运动检测与跟踪算法

在传统的行人检测跟踪算法中,主要采用HOG+SVM对视频中的行人直接进行检测,针对传统算法在复杂背景及多行人条件下,行人检测效果较差,且实时性低等缺点,提出一种融合目标运动检测与目标跟踪的行人检测算法。首先采用Vibe算法提取视频中的运动目标,并通过对Vibe算法的改进消除初始帧存在的阴影问题。针对视频中的运动目标采用Adaboost算法对运动目标区域进行行人检测,减小视频中背景的干扰,加快检测速度。最后采用卡尔曼滤波算法和匈牙利最优匹配算法对视频监控中的行人进行跟踪。仿真实验结果显示,该算法能够对电力监控视频中存在的行人进行检测跟踪。     

Pseudoreal-time activity detection for railroad grade-crossing safety

It is important to understand the factors underlying grade-crossing crashes and to examine potential solutions. We have installed a camera in front of a locomotive to examine grade-crossing accidents (or near accidents). We present a computer vision system that automatically extracts possible near-accident scenes by detecting the activity of vehicles crossing in front of the train after signals are ignited. We present a fast algorithm to detect moving objects recorded by a moving camera with minimal computation. The moving object is detected by: 1) estimating the ego motion of the camera and 2) detecting and tracking feature points whose motion is inconsistent with the camera motion. We introduce a pseudoreal-time ego-motion (camera-motion) estimation method with a robust optimization algorithm. We present experiments on ego-motion estimation and moving-object detection. Our algorithm works in pseudoreal-time and we expect that our algorithm can be applied to real-time applications such as collision warning in the near future, with the development of hardware technology.     

基于光伏阵列输出特性的GMPPT算法研究

针对局部阴影条件下光伏阵列的P-V曲线呈现多峰值的情况,在研究光伏阵列输出特性的基础上提出了一种全局最大功率点追踪GMPPT(global maximum power point tracking)算法。该算法由均匀光照和局部阴影条件下的两个最大功率点追踪算法构成。通过所提出的局部阴影检测手段判别光伏阵列所处的光照条件,从而决定使用哪个子算法。最后将该算法在Matlab中进行仿真验证。仿真结果表明在局部阴影条件下该算法能快速地追踪到全局最大功率点,且避免了对整条P-V曲线的扫描。在均匀光照条件下要比传统的最大功率点追踪算法(扰动观察法)更快地定位到最大功率点。     

旋转摄像机下的快速目标检测算法

对于动态场景下的目标检测,传统的方法已经不能适用.提出一种基于SIFT特征点预测的匹配算法,提高了运动目标检测的速度和准确率.在此过程中,用仿射参数模型结合最小二乘法求解出全局运动参数,再对运动进行补偿.采用ORSA的方法去除外点的影响;采用基于残差图像块的更新策略,实时更新特征点集.最后使用背景差法来实现运动目标的检...     

Analogic CNN algorithm for estimating position and size of moving objects

An analogic CNN algorithm is proposed for detection of multiple moving objects in high resolution, grey‐scale images taken from a fixed camera. The algorithm, based on simple 3 × 3 templates, can be implemented using CNN hardware, providing the real‐time operation required in surveillance and traffic control applications. Efficient separation of moving objects from the background is obtained through automatic threshold selection. The performance of the proposed method is shown using real‐life indoor and outdoor video sequences. Copyright © 2004 John Wiley & Sons, Ltd.     

Smoke detection in open areas with texture analysis and support vector machines

Early and certain fire detection is one of the important issues to keep infrastructures safe. Especially, it becomes an urgent problem for open places such as port facilities, large factories, and power plants, due to its large harmful effect to the surrounding areas. In these places, direct detection of fire or flame has some difficulties because they are open and hence have problem to set sensor devices. Therefore, smoke is an important and useful sign to detect fire or flames robustly even in such cases. In this paper, we present a novel smoke detection method based on image information. First, we extract moving objects in an image sequence as smoke candidate regions in a preprocessing step. Since smoke has a characteristic pattern as image information, we focus on the texture pattern of smoke. Here, we use texture analysis to extract feature vectors of the images. To classify extracted areas of moving objects to smoke or nonsmoke, we use support vector machines (SVMs) with texture features as an input feature vector. Extraction of moving objects is sometimes easily and greatly affected by environmental conditions such as wind, background objects, and so forth. It obviously causes bad classification results. To solve this problem, we additionally accumulate the results of classification with SVM about time to obtain accurate extraction result of smoke regions under these conditions. Experimental results using real‐scene data show that our method works effectively under several different environmental conditions. © 2012 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.     

Lane Detection With Moving Vehicles in the Traffic Scenes

A lane-detection method aimed at handling moving vehicles in the traffic scenes is proposed in this brief. First, lane marks are extracted based on color information. The extraction of lane-mark colors is designed in a way that is not affected by illumination changes and the proportion of space that vehicles on the road occupy. Next, for vehicles that have the same colors as the lane marks, we utilize size, shape, and motion information to distinguish them from the real lane marks. The mechanism effectively eliminates the influence of passing vehicles when performing lane detection. Finally, pixels in the extracted lane-mark mask are accumulated to find the boundary lines of the lane. The proposed algorithm is able to robustly find the left and right boundary lines of the lane and is not affected by the passing traffic. Experimental results show that the proposed method works well on marked roads in various lighting conditions     

一种基于改进块匹配算法的运动车辆检测

在传统的基于块匹配算法的运动车辆检测中,因为直接对灰度图像进行匹配而带来计算量大、光照变化较敏感和实时性差的缺陷。针对这些问题,提出了基于概率松弛标记算法的块匹配算法,先通过概率松弛标记算法求取灰度图像的边缘,然后通过块匹配算法根据匹配的相似度得到位移矢量场,并对其进行矢量中值滤波,最后通过顺序区域增长把运动车辆分割出来。实验结果表明,这种算法鲁棒性强、实时性好,与传统算法比较在效率大幅度提高的情况下准确率也得到了一定的提升。