提出了一种提取运动对象的新的视频序列分割算法。
This paper presents a new automatic video sequence segmentation algorithm that extracts moving objects.
本文提出了一种自动的视频序列分割方法,适用于分割室外和室内视频序列中的运动物体。
An automatic method of the video-sequence segmentation is proposed in this paper, which can be used to segment moving objects in video sequences outdoors and indoors.
视频序列分割是实现视频对象提取、处理和识别的基础,也是基于内容的视频压缩和检索的前提。
The segmentation of video is the basis of the video object extraction, processing and recognition. It is also the premise of the content-based video compression and retrieving.
该方法先将视频序列分割出前景对象与背景对象,然后分别针对分割出来的前景对象与背景对象进行压缩,而此时背景就可以只压缩一帧或者关键几帧。
In this algorithm, the foreground objects and background are divided and then compressed separately. We only need to compress one or several background of key frames.
由于输入视频序列的每一帧被分割成任意形状的视频对象平面(VOP),这样每个VOP描述了一个语义意义的对象或所感兴趣的视频内容。
Each frame of the input sequence is segmented into arbitrarily shaped image regions (VOP's) such that each VOP describes one semantically meaningful object or video content of interest.
针对视频序列,仅利用其时域信息,提出了一种简单有效的运动前景分割算法。
This paper represents a simple moving foreground segmentation method in video sequences only using their temporal information.
该文提出了一个基于内容的音频分析系统,对视频序列实现基于音频分析的场景检测和分割。
In this paper, a content-based audio data analysis system is proposed, which accepts video sequence and implements scene detection and segmentation from audio part.
基于视频序列的数字图像拼接技术主要包括全局快速配准算法、运动目标分割算法和无缝融合算法。
The techniques of digital image mosaics from video sequence consist of image global fast registration algorithm, motion object segment algorithm, and seamless blending algorithm.
提出了一种视频序列中运动目标的分割算法。
This paper presents an algorithm of moving objects segmentation in video sequence.
视频序列的镜头分割亦称镜头变化检测是视频检索中的关键技术之一。
Partitioning a video sequence into shots or detecting shot change is one of key techniques in video indexing.
视频对象分割,旨在分割出视频序列中的运动对象并沿时间轴跟踪运动对象的演进。
Video object segmentation aims to partition an image sequence into moving objects and to track the evolution of the moving objects along the time axis.
从视频序列中分割出视频对象是实现基于内容压缩编码方法的关键。
Video objects segmentation from video sequence is the key of implementing content-based compression coding method.
对200帧可见光视频序列和100帧红外图像序列中运动汽车进行检测分割实验,检出率分别达到96%和94%。
Two image sequences including 200 frames of optical images and 100 frames of infrared image are detected and the detection ratio achieves 96% and 94% respectively.
为了生成视频对象面,需要对视频序列中的运动对象进行有效的分割;
Segmentation and tracking of video moving object is used for guiding the extraction of video object plane from the video sequence.
经过对新算法的实验测试,结果显示,对于象视频会议一类的目标简单、背景静止的视频序列,可以得到良好的分割结果。
Experimental results show that for such videos as in conference environment with still background and simple objects, the proposed algorithm can achieve good results.
视频序列首先被分成一个个的镜头,在每个镜头内对视频对象进行分割和跟踪。
Video sequences are divided into shots first, in which video objects segmentation and tracking are implemented.
针对背景相对静止的视频序列,提出了基于CNN差分图象合并的视频分割算法,并构建了与该算法相关的五个CNN模板。
Aim at video sequences with static background, the difference merged image algorithm based on CNN is presented. In order to realize the algorithm, five CNN templates are constructed.
实验结果表明:该算法能够较好地从视频序列中分割运动前景和背景,比较适合于在基于内容的视频编码标准MPEG - 4中使用。
Experiment results show that the algorithm can preferably segment moving foreground and background in video sequence and it fits for MPEG-4coding standard, which is content-based.
在视频序列的人体运动分析中,实时分割出运动的人体,是研究的起始关键步骤。
In the field of the analysis of human motion in the video sequence, segmenting the motion human body in real-time is the first key step.
按照MPEG - 4的校验模型,视频序列必须先分割成具有语义意义的视频对象,然后对其运动、形状和纹理分别进行编码。
According to the MPEG-4 verification model, video sequence must be segmented into semantic video objects. Their motion, shape and texture information are coded respectively.
视频运动对象分割的目标是从视频帧序列中间分割出满足一定特征的语义区域。
Segmentation of video moving object is extraction of semantic area meet certain characteristics from video sequence.
因此,基于视频序列的检测和分割技术己成为世界性的研究课题和相关产品开发的热点之一。
So, the Detection and segmentation based on video has become one of the hotspots about the worldwide research and product development.
因此,有必要研究细胞神经网络在视频序列图像中目标分割和追踪的应用及其相关算法。
So, it is necessary to study the segment and the tracking of moving object in video image.
视频序列的镜头分割亦称镜头变化检测是视频检索中的关键技术之一。
Partitioning a video sequence into shots or detecting shot change is one of the key techniques in video indexing.
典型视频测试序列的实验结果表明,本方法可取得接近于像素级的分割精度。
Experimental results on typical test sequences demonstrate that the proposed approach can achieve pixel-level accuracy for com-pressed-domain video object extraction.
随着新的视频压缩标准MPEG - 4的出现,如何从视频序列中分割出在语义上有意义的单独运动对象显得极其重要。
The new video coding standard MPEG-4 is enabling content-based function. It needs for the segmentation of semantically meaningful moving object in video sequences.
对视频序列进行分割,传统的方法是通过比较连续的视频帧之间像素间的灰度直方图差异来实现的。
The conventional segmentation methods are based on histogram difference and pixel difference between the successive frame pairs.
针对背景相对运动是视频序列,提出了基于光流场阈值的CNN视频分割算法。
Aim at video sequences with dynamic background, the CNN video motion segmentation algorithm based on optical flow field threshold is presented.
针对背景相对运动是视频序列,提出了基于光流场阈值的CNN视频分割算法。
Aim at video sequences with dynamic background, the CNN video motion segmentation algorithm based on optical flow field threshold is presented.
应用推荐