一种简单易行的运动对象分割方法

在兼顾运动图像分割效果和实时性的原则上,提出了一种简单有效的分割方法。首先利用二次帧差的方法求出图像帧的运动区域,去除结果中不准确的小区域,最后利用二次扫描的方法填充该区域。实验证明：利用该方法得到了较好的分割效果并节省了处理时间。     

基于时空信息融合的视频对象分割系统

提出了一种有效的时空融合视频分割系统.首先利用基于梯度的分水岭算法对图像进行分割,并利用基于时空联合的区域合并方法克服过分割现象,然后结合改进的帧差掩模对目标进行提取.试验结果表明,由于该系统充分利用了图像的颜色信息,能较完整地分割出对象,并且对象边缘更加准确.     

视频序列中运动对象提取方法的研究

为了寻求提取结果与时间的折中，仅利用视频序列中的时域信息，提出了一种自动的运动对象提取方法。首先阈值化运动区域求出图像帧差掩模，然后利用二次扫描的方法得到运动对象掩模，填充就可以提取出准确的运动对象。实验证明该算法简单可行，在实时性的应用中具有一定的优势。     

一种基于灰度连续区域分割的视频对象分割方法

针对目前许多分割方法中分割边界不精确、计算复杂和缓存帧多等问题，提出了一种结合空间区域分割和运动象素检测的自动分割方法：先将当前视频帧分割为不同的灰度连续区域，再利用二次帧差确定视频图像中的运动象素，然后按一定的规则确定哪些灰度连续区域属于运动区域，从而有效地从静止的复杂背景中分割出运动对象区域。实验结果表明这种分割方法计算简单、分割边界比较精确。     

基于边缘特征的自动运动对象分割

为了准确分割出视频场景中的运动对象,该文提出了一种基于边缘特征的运动对象分割及跟踪算法。首先对相邻帧进行自适应变化检测,得到相邻帧二值差分图像。结合当前帧Canny算子检测的边缘图像,获得运动对象的初始边缘模板。其次对运动对象的运动分为快变和慢变两部分进行跟踪并更新运动对象的边缘模板。最后对运动对象的边缘模板进行数学形态学处理得到运动对象的外轮廓,使用梯度向量流场作为外力的改进活动轮廓算法收缩获得运动对象准确的闭合轮廓曲线。该算法对运动对象的整体运动和局部形变都有很强的鲁棒性, 能够得到运动对象准确的轮廓,并且对复杂背景有很好的适应性。     

基于计算机视觉的运动物体的检测与识别

本文创造性地提出了"帧差法+GrabCut图像分割算法+CNN卷积神经网络"模型,并以球场上的篮球轨迹识别问题为例进行实际应用。     

视频运动对象分割技术的研究

新的视频压缩标准MPEG－4采纳了基于对象／模型的编码方法，但是对象的分割问题至今仍未得到满意的解决。本文介绍了视频运动对象分割技术的发展概况，重点讨论了其中的关键技术－－运动对象的分割与跟踪，并指出一些需要深入研究的问题。     

基于计算机视觉的运动目标跟踪算法

截至目前,运动目标跟踪已经历经了几十年的发展研究,其作为当前社会一项至关重要的先进技术,对于人们的日常工作生活以及社会经济、军事政治等其他各领域均有着积极的帮助作用。特别是在计算机视觉技术逐渐发展成熟的今天,运动目标跟踪与计算机视觉技术的融合程度也越来越高。基于此,本文将选择当前比较常见的一种目标跟踪算法即Kalman filter算法,并以运动的人脸作为跟踪目标,着重围绕基于计算机视觉的运动目标跟踪算法进行简要分析研究。     

一种基于全景视觉的运动目标检测方法

针对基于全景视觉系统采集的图像序列中运动目标检测的方法进行了研究,采用三帧差法和混合高斯模型相融合的算法对运动目标进行检测。不但解决了三帧差法无法检测出全部目标信息的缺点,而且还避免了背景减除法容易出现两个目标的假现象,在背景颜色和目标颜色相近时检测效果较好。实验表明,该算法能准确检测出运动目标,具有较好的实时性。     

一种基于帧内图像分区的视频对象自动分割算法

视频运动对象的自动分割是实现新一代对象基视频编码标准MPEG-4的重要技术,本文提出了一种基于帧内图像分区的运动对象自动分割算法.首先以时域运动信息为依据利用高斯检验方法得到二值运动掩模图像,并建立MRF随机场模型进一步检验,然后提出了一种结合非线性变换的改进分水岭算法进行帧内图像分区,以划定对象区域与背景区域的界线,最后对时域分割和帧内分区结果进行比重运算,得到最终运动对象.针对MPEG-4标准测试序列和自采集手指视频序列的实验结果说明了算法的有效性.     

Hybrid Morphology Processing Unit Architecture for Moving Object Segmentation Systems

Video segmentation is a key operation in MPEG-4 content-based coding systems. For real-time applications, hardware implementation of video segmentation is inevitable. In this paper, we propose a hybrid morphology processing unit architecture for real-time moving object segmentation systems, where a prior effective moving object segmentation algorithm is implemented. The algorithm is first mapped to pixel-based operations and morphological operations, which makes the hardware implementation feasible. Then the high computation load, which is more than 4.2 GOPS, can be overcome with a dedicated morphology engine and a programmable morphology PE array. In addition, the hardware cost, memory size, and memory bandwidth can be reduced with the partial-result-reuse concept. This chip is designed with TSMC 0.35 μm 1P4M technology, and can achieve the processing speed of 30 QCIF frames or 7,680 morphological operations per second at 26 MHz. Simulation shows that the proposed hardware architecture is efficient in both hardware complexity and memory organization. It can be integrated into any content-based video processing and encoding systems. Shao-Yi Chien was born in Taipei, Taiwan, R.O.C., in 1977. He received the B.S. and Ph.D. degrees from the Department of Electrical Engineering, National Taiwan University (NTU), Taipei, in 1999 and 2003, respectively. During 2003 to 2004, he was a research staff in Quanta Research Institute, Tao Yuan Shien, Taiwan. In 2004, he joined the Graduate Institute of Electronics Engineering and Department of Electrical Engineering, National Taiwan University, as an Assistant Professor. His research interests include video segmentation algorithm, intelligent video coding technology, image processing, computer graphics, and associated VLSI architectures. Bing-Yu Hsieh was born in Taichung, Taiwan, in 1979. He received the B.S.E.E and M.S.E.E degrees from National Taiwan University (NTU), Taipei, in 2001 and 2003, respectively. He joined MediaTek, Inc., Hsinchu, Taiwan, in 2003, where he develops integrated circuits related to multimedia systems and optical storage devices. His research interests include object tracking, video coding, baseband signal processing, and VLSI design. Yu-Wen Huang was born in Kaohsiung, Taiwan, in 1978. He received the B.S. degree in electrical engineering and Ph. D. degree in the Graduate Institute of Electronics Engineering from National Taiwan University (NTU), Taipei, in 2000 and 2004, respectively. He joined MediaTek, Inc., Hsinchu, Taiwan, in 2004, where he develops integrated circuits related to video coding systems. His research interests include video segmentation, moving object detection and tracking, intelligent video coding technology, motion estimation, face detection and recognition, H.264/AVC video coding, and associated VLSI architectures. Shyh-Yih Ma received the B.S.E.E, M.S.E.E, and Ph.D. degrees from National Taiwan University in 1992, 1994, and 2001, respectively. He joined Vivotek, Inc., Taipei County, in 2000, where he developed multimedia communication systems on DSPs. His research interests include video processing algorithm design, algorithm optimization for DSP architecture, and embedded system design. Liang-Gee Chen was born in Yun-Lin, Taiwan, in 1956. He received the BS, MS, and Ph.D degrees in Electrical Engineering from National Cheng Kung University, in 1979, 1981, and 1986, respectively. He was an Instructor (1981–1986), and an Associate Professor (1986–1988) in the the Department of Electrical Engineering, National Cheng Kung University. In the military service during 1987 and 1988, he was an Associate Professor in the Institute of Resource Management, Defense Management College. From 1988, he joined the Department of Electrical Engineering, National Taiwan University. During 1993 to 1994 he was Visiting Consultant of DSP Research Department, AT&T Bell Lab, Murray Hill. At 1997, he was the visiting scholar of the Department of Electrical Engineering, University, of Washington, Seattle. Currently, he is Professor of National Taiwan University. From 2004, he is also the Executive Vice President and the General Director of Electronics Research and Service Organization (ERSO) in the Industrial Technology Research Institute (ITRI). His current research interests are DSP architecture design, video processor design, and video coding system. Dr. Chen is a Fellow of IEEE. He is also a member of the honor society Phi Tan Phi. He was the general chairman of the 7th VLSI Design CAD Symposium. He is also the general chairman of the 1999 IEEE Workshop on Signal Processing Systems: Design and Implementation. He serves as Associate Editor of IEEE Trans. on Circuits and Systems for Video Technology from June 1996 until now and the Associate Editor of IEEE Trans. on VLSI Systems from January 1999 until now. He was the Associate Editor of the Journal of Circuits, Systems, and Signal Processing from 1999 until now. He served as the Guest Editor of The Journal of VLSI Signal Processing Systems for Signal, Image, and Video Technology, November 2001. He is also the Associate Editor of the IEEE Trans. on Circuits and Systems II: Analog and Digital Signal Processing. From 2002, he is also the Associate Editor of Proceedings of the IEEE. Dr. Chen received the Best Paper Award from ROC Computer Society in 1990 and 1994. From 1991 to 1999, he received Long-Term (Acer) Paper Awards annually. In 1992, he received the Best Paper Award of the 1992 Asia-Pacific Conference on Circuits and Systems in VLSI design track. In 1993, he received the Annual Paper Award of Chinese Engineer Society. In 1996, he received the Out-standing Research Award from NSC, and the Dragon Excellence Award for Acer. He is elected as the IEEE Circuits and Systems Distinguished Lecturer from 2001–2002.     

基于时空联合的红外运动目标分割算法

针对野外复杂背景下红外运动车辆分割这一难题,提出了一种时空联合的运动目标分割算法.该算法首先通过自适应变化检测提取出初始目标,然后在初始目标外接矩形区域中做分水岭变换,最后通过基于初始目标模板投影和运动投影的区域合并,得到精确的目标.实验结果表明,该算法能快速精确地从复杂背景中分割出目标.     

局部运动场景中运动对象的压缩域分割算法

压缩域视频运动对象的分割技术近年来逐渐被人们所重视,并且成为较实用的技术之一.该文针对目前压缩域中运动对象分割质量不高的问题,提出一种压缩域分割的改进算法.该算法首先从MPEG压缩码流中提取运动矢量,并对矢量进行运动累加和中值滤波处理,最后利用贝叶斯风险决策对非零运动矢量区域进行校正,最终得到较好的分割结果.该文还定义了压缩域分割质量的评价参数分割率和错分率,为评价压缩域的分割结果提供了客观评价标准.     

基于全方位视觉的移动机器人运动目标检测*

针对移动机器人动态背景下运动目标的检测,提出一种基于全方位视觉的检测算法。首先,改进了SIFT算法中的特征点提取方法,在将图像划分为若干网格后,再根据特征点所在位置的局部区域熵对每个网格中的候选特征点进行筛选;其次,在SIFT点匹配后采用RANSAC算法去除误匹配点,以提高背景补偿的精度;最后用帧差法检测出运动目标。实验表明,该算法减少了SIFT点的获取时间,并具有良好的鲁棒性,能准确地在机器人运动过程中检测出运动目标。     

基于主动轮廓模型提取运动目标的图像分割技术

复杂背景下的运动目标分割技术是近年来多媒体通信技术的研究热点之一。文中提出一种基于SNAKE模型的运动目标分割技术。首先，利用运动检测的方法，从视频图像中粗略提取出运动目标；然后再利用SNAKE模型收敛到更为精确的物体边缘。模拟实验的结果表明，该方法对运动目标的提取有较好的分割效果。     

基于模糊聚类的运动对象分割算法研究

为了从视频序列中分割出完整的、一致的运动视频对象,该文使用基于模糊聚类的分割算法获得组成对象边界的像素,从而提取对象。该算法首先使用了当前帧以及之前一些帧的图像信息计算其在小波域中不同子带的运动特征,并根据这些运动特征构造了低分辨率图像的运动特征矢量集;然后,使用模糊C-均值聚类算法分离出图像中发生显著变化的像素,以此代替帧间差图像,并利用传统的变化检测方法获得对象变化检测模型,从而提取对象;同时,使用相继两帧之间的平均绝对差值大小确定计算当前帧运动特征所需帧的数量,保证提取视频对象的精确性。实验结果证明该方法对于分割各种图像序列中的视频对象是有效的。     

一种新的基于时空马尔可夫随机场的运动目标分割技术

在图像处理领域,视频图像序列中的运动目标分割技术是一个被广泛研究的热点课题。该文提出一种新的基于时空马尔可夫随机场的运动目标分割技术。首先,对视频序列的前后3帧图像进行处理,获得两帧初始标记场;随后,对两帧初始标记场进行“与”操作,获得共同标记场;最后,以原始图像的色彩聚类图像作为先验知识,重新定义Gibbs能量函数,并利用迭代条件模型（ICM）实现最大后验概率（MAP）的估算问题,获得优化标记场。实验结果表明：该模型克服了传统时穿马尔可夫随机场模型因运动产生的晶露遮挡现象,同时减弱了运动一致性造成的空洞现象并削弱了噪声的影响。     

基于视觉运动目标跟踪技术分析

计算机视觉研究的主要问题之一是运动物体的检测与跟踪,它将图像处理、模式识别、自动控制、人工智能和计算机等很多领域的先进技术结合在了一起,主要应用在军事视觉制导、视频监控、医疗诊断和智能交通等各个方面,因此该技术已经成为一个重要的研究方向。阐述了视觉跟踪算法的研究现状和视觉跟踪算法的种类,研究了基于区域的跟踪算法、基于模型的跟踪算法、基于特征的跟踪算法和基于主动轮廓的跟踪算法,探讨了视觉跟踪算法的未来研究方向。