面向手术器械语义分割的半监督时空Transformer网络

基于内窥镜的微创手术机器人在临床上的应用日益广泛,为医生提供内窥镜视频中精准的手术器械分割信息,对提高医生操作的准确度、改善患者预后有重要意义.现阶段,深度学习框架训练手术器械分割模型需要大量精准标注的术中视频数据,然而视频数据标注成本较高,在一定程度上限制了深度学习在该任务上的应用.目前的半监督方法通过预测与插帧,可...     

基于双阈值滑动窗口子镜头分割和完全连通图的关键帧提取方法

随着多媒体技术的发展,当今工作和生活中的多媒体信息日渐丰富。如何通过分析海量视频快速有效地检索出有用信息成为一个日益严重的问题。为了解决上述问题,提出了一种基于双阈值滑动窗口 子镜头分割和完全连通图的关键帧提取方法。该方法采用基于双阈值的镜头分割算法,通过设置双阈值滑动窗口来判断镜头的突变边界和渐变边界,从而划分镜头;并采用基于滑动窗口的子镜头分割算法,通过给视频帧序列加一个滑动窗口,在窗口的范围内利用帧差来对镜头进行再划分,得到子镜头;此外,利用基于子镜头分割的关键帧提取算法,通过处理顶点为帧、边为帧差的完全连通图的方法来提取关键帧。实验结果表明,与其他方法相比,提出的方法平均精确率较高,并且平均关键帧数目较低,可以很好地提取视频的关键帧。     

A bag-of-regions representation for video classification

A bag-of-regions (BoR) representation of a video sequence is a spatio-temporal tessellation for use in high-level applications such as video classifications and action recognitions. We obtain a BoR representation of a video sequence by extracting regions that exist in the majority of its frames and largely correspond to a single object. First, the significant regions are obtained using unsupervised frame segmentation based on the JSEG method. A tracking algorithm for splitting and merging the regions is then used to generate a relational graph of all regions in the segmented sequence. Finally, we perform a connectivity analysis on this graph to select the most significant regions, which are then used to create a high-level representation of the video sequence. We evaluated our representation using a SVM classifier for the video classification and achieved about 85 % average precision using the UCF50 dataset.     

深度学习在视频对象分割中的应用与展望

视频对象分割是指在给定的一段视频序列的各帧图像中,找出属于特定前景对象的所有像素点位置区域.随着硬件平台计算能力的提升,深度学习受到了越来越多的关注,在视频对象分割领域也取得了一定的进展.本文首先介绍了视频对象分割的主要任务,并总结了该任务所面临的挑战.其次,对开放的视频对象分割常用数据集进行了简要概述,并介绍了通用的性能评估标准.接着,综述了视频对象分割的研究现状,详细地分析了当前的各种方法,并将它们划分为三大类:半监督的方法,即给出视频第一帧图像中感兴趣对象的详细人工真值标注,分割出视频剩余图像中的感兴趣对象;无监督的方法,即不给任何人工标注信息,自动识别并分割出视频中的前景对象;交互式的方法,即在分割过程中,通过人工交互式的参与,结合粗略的人工标注先验信息,进行视频对象分割.第三类方法的条件相当于前两者的折中:相对于第一类方法,它虽然需要人工的参与,但只需要少量的标注工作量;相对于第二类方法,它给视频序列中某些帧的图像适当地添加了一些人工标注信息,从而更具针对性.最后,对深度学习在视频对象分割任务中的应用,进行了总结和展望.     

利用时空相关性的HEVC帧内编码块快速划分

目的 为了提升高效视频编码（HEVC）的编码效率,使之满足高分辨率、高帧率视频实时编码传输的需求。由分析可知帧内编码单元（CU）的划分对HEVC的编码效率有决定性的影响,通过提高HEVC的CU划分效率,可以大大提升HEVC编码的实时性。方法 通过对视频数据分析发现,视频数据具有较强的时间、空间相关性,帧内CU的划分结果也同样具有较强的时间和空间相关性,可以利用前一帧以及当前帧CU的划分结果进行预判以提升帧内CU划分的效率。据此,本文给出一种帧内CU快速划分算法,先根据视频相邻帧数据的时间相关性和帧内数据空间相关性初步确定当前编码块的编码树单元（CTU）形状,再利用前一帧同位CTU平均深度、当前帧已编码CTU深度以及对应的率失真代价值决定当前编码块CTU的最终形状。算法每间隔指定帧数设置一刷新帧,该帧采用HM16.7模型标准CU划分以避免快速CU划分算法带来的误差累积影响。结果 利用本文算法对不同分辨率、不同帧率的视频进行测试,与HEVC的参考模型HM16.7相比,本文算法在视频编码质量基本不变,视频码率稍有增加的情况下平均可以节省约40%的编码时间,且高分辨率高帧率的视频码率增加幅度普遍小于低分辨率低帧率的视频码率。结论 本文算法在HEVC的框架内,利用视频数据的时间和空间相关性,通过优化帧内CU划分方法,对提升HEVC编码,特别是提高高分辨率高帧率视频HEVC编码的实时性具有重要作用。     

基于变化检测的视频对象分割算法研究

随着基于对象视频应用的发展,视频对象的分割成为人们研究的热点。提出了一种基于变化检测的视频对象分割算法。该算法首先求出连续两帧图像之间的差分,利用帧间变化信息可以得到视频对象的运动区域,根据差分图像的中值（MED）和中值绝对差（MAD）及原始图像均值确定阈值并滤除噪声,用数学形态学方法进行后处理,最终得到精确的视频运动对象。实验结果表明,该方法能够从背景不变的视频序列中较好地提取出视频运动对象,而且算法简单、高效、准确。     

Extracting semantic video objects

We present an accurate and user-interactive semantic video object (SVO) extraction system. Although we also obtain an SVO with an accurate boundary by integrating temporal and spatial information, our way is quite different from others' work. Instead of fusing spatial and temporal segmentations on the first or all the frames of a video sequence, our system adaptively performs spatial and temporal segmentation and fusion when necessary. To achieve this, our system detects the variations between successive frames. We only need to fuse the spatial and temporal segmentation when a large variation occurs. Otherwise, the system tracks the previous SVO's boundary. We find this simple method efficient in both speed and accuracy. Since the temporal segmentation, spatial segmentation, spatio-temporal fusion, and boundary tracking all employ simple algorithms, our system has a low computational complexity     

Context-based segmentation of image sequences

We describe an algorithm for context-based segmentation of visual data. New frames in an image sequence (video) are segmented based on the prior segmentation of earlier frames in the sequence. The segmentation is performed by adapting a probabilistic model learned on previous frames, according to the content of the new frame. We utilize the maximum a posteriori version of the EM algorithm to segment the new image. The Gaussian mixture distribution that is used to model the current frame is transformed into a conjugate-prior distribution for the parametric model describing the segmentation of the new frame. This semisupervised method improves the segmentation quality and consistency and enables a propagation of segments along the segmented images. The performance of the proposed approach is illustrated on both simulated and real image data.     

基于深度学习的视频语义分割综述

目前对视频语义分割的研究主要分为两方面,一是如何利用视频帧之间的时序信息提高图像分割的精度;二是如何利用视频帧之间的相似性确定关键帧,减少计算量,提升模型的运行速度.在提升分割精度方面一般设计新的模块,将新模块与现有的CNNs结合;在减少计算量方面,利用帧序列的低层特征相关性选择关键帧,同时减少操作时间.本文首先介绍视频语义分割的发展背景与操作数据集Cityscapes、CamVid;其次,介绍现有的视频语义分割方法;最后总结当前视频语义分割的发展情况,并对未来的发展给出一些展望和建议.     

光流估计下的移动端实时人脸检测

为了提高移动设备人脸检测准确率,提出一种应用于移动设备的实时人脸检测算法。通过改进Viola-Jones方法进行人脸区域快速分割,在不损失速度的情况下提高分割精度;同时应用了光流估计方法将卷积神经网络子网络在离散关键帧上的特征提取结果传播至非关键帧,提高神经网络实际检测运行效率。实验使用YouTube视频人脸数据库、自建20人各1 min正位人脸视频数据库和实际检测项目在不同分辨率下进行,实验结果表明运行速度在2.35帧/秒~22.25帧/秒,达到了一般人脸检测水平;人脸检测在10%误检率下召回率由Viola-Jones的65.93%提高到82.5%~90.8%,接近卷积神经网络检测精度,满足了移动设备实时人脸检测的速度和精度要求。     

Multi-body Factorization with Uncertainty: Revisiting Motion Consistency

Dynamic analysis of video sequences often relies on the segmentation of the sequence into regions of consistent motions. Approaching this problem requires a definition of which motions are regarded as consistent. Common approaches to motion segmentation usually group together points or image regions that have the same motion between successive frames (where the same motion can be 2D, 3D, or non-rigid). In this paper we define a new type of motion consistency, which is based on temporal consistency of behaviors across multiple frames in the video sequence. Our definition of consistent “temporal behavior” is expressed in terms of multi-frame linear subspace constraints. This definition applies to 2D, 3D, and some non-rigid motions without requiring prior model selection. We further show that our definition of motion consistency extends to data with directional uncertainty, thus leading to a dense segmentation of the entire image. Such segmentation is obtained by applying the new motion consistency constraints directly to covariance-weighted image brightness measurements. This is done without requiring prior correspondence estimation nor feature tracking.     

基于视音频特征和文本信息的新闻视频自动场景分割

提出了一种基于视音频特征和文本信息的新的场景自动分割技术.其基本思想是先探测新闻视频的镜头边界,再用文本检测方法识别主题字幕帧以得到分割信息.用短时能量和短时平均零交叉率参数探测静音分片.将视音频特征和文本信息相结合以实现自动场景分割.实验使用135 400帧的测试数据达到了85.8%的准确率和97 5%的重现率.实验结果表明此方法是有效的、稳健的.     

视频目标分割中帧间相似性传播的研究

目前视频目标分割算法多是基于匹配和传播策略分割目标,常常以掩模或者光流的方式利用前一帧的信息,探索了新的帧间特征传播方式,利用短时匹配模块提取前一帧信息并传播给当前帧,提出一种面向视频序列数据的目标分割模型。通过长时匹配模块和短时匹配模块分别与第一帧和前一帧做相关操作进行像素级匹配,得到的全局相似性图和局部相似性图,以及前一帧的掩模和当前帧的特征图,经过两个优化网络后通过分割网络得到分割结果。在视频目标分割公开数据集上的实验表明,所提出方法在单目标和多目标上分别取得了86.5%和77.4%的区域相似度和轮廓精度均值,每秒可计算21帧。提出的短时匹配模块比仅使用掩模更有利于提取前一帧的信息,通过长时匹配模块和短时匹配模块的结合,不使用在线微调即可实现高效的视频目标分割,适合应用于移动机器人视觉感知。     

Motion segmentation and depth ordering using an occlusion detector

We present a novel method for motion segmentation and depth ordering from a video sequence in general motion. We first compute motion segmentation based on differential properties of the spatio-temporal domain, and scale-space integration. Given a motion boundary, we describe two algorithms to determine depth ordering from two- and three- frame sequences. An remarkable characteristic of our method is its ability compute depth ordering from only two frames. The segmentation and depth ordering algorithms are shown to give good results on 6 real sequences taken in general motion. We use synthetic data to show robustness to high levels of noise and illumination changes; we also include cases where no intensity edge exists at the location of the motion boundary, or when no parametric motion model can describe the data. Finally, we describe human experiments showing that people, like our algorithm, can compute depth ordering from only two frames, even when the boundary between the layers is not visible in a single frame.     

基于光流的快速人体姿态估计

针对目前深度学习领域人体姿态估计算法计算复杂度高的问题,提出了一种基于光流的快速人体姿态估计算法.在原算法的基础上,首先利用视频帧之间的时间相关性,将原始视频序列分为关键帧和非关键帧分别处理（相邻两关键帧之间的图像和前向关键帧组成一个视频帧组,同一视频帧组内的视频帧相似）,仅在关键帧上运用人体姿态估计算法,并通过轻量级光流场将关键帧识别结果传播到其他非关键帧.其次针对视频中运动场的动态特性,提出一种基于局部光流场的自适应关键帧检测算法,以根据视频的局部时域特性确定视频关键帧的位置.在OutdoorPose和HumanEvaI数据集上的实验结果表明,对于存在背景复杂、部件遮挡等问题的视频序列中,所提算法较原算法检测性能略有提升,检测速度平均可提升89.6%.     

一种鲁棒的视频分割算法

无论是在图象识别，还是在基于MPEG－4的图象压缩编码等应用领域，视频对象分割取是其中一个很重要的技术环节，为了在静止背景的情况下，能很好地解决多目标分割的问题，同时能进行单目标的分割，提出了一种鲁棒性较好的视频分割算法，该算法通过对图象序列中每连续3 帧图象进行对称差分，首先检测出目标的运动范围，然后通过对差分结构进行聚类分析来确定该帧图象中视频对象的个数，接着再利用在二值差分图象上收缩的活动轮廓，把视频对象的轮廓精确地包围起来，即得到该帧分割结果；最后利用光流法来对视频对象进行投注跟踪，修正，另外还利用多个图象序列对该方法进行了试验，实验结果表明，在静止背景下，该算法无论是对运动的单目标，还是对运动的多目标，均能较好地从静止背景中分离出来，即能得到理想的分割结果，故具有一定的鲁棒性和实用性。     

Video segmentation using a histogram-based fuzzy c-means clustering algorithm

The purpose of video segmentation is to segment video sequence into shots where each shot represents a sequence of frames having the same contents, and then select key frames from each shot for indexing. Existing video segmentation methods can be classified into two groups: the shot change detection (SCD) approach for which thresholds have to be pre-assigned, and the clustering approach for which a prior knowledge of the number of clusters is required. In this paper, we propose a video segmentation method using a histogram-based fuzzy c-means (HBFCM) clustering algorithm. This algorithm is a hybrid of the two approaches aforementioned, and is designed to overcome the drawbacks of both approaches. The HBFCM clustering algorithm is composed of three phases: the feature extraction phase, the clustering phase, and the key-frame selection phase. In the first phase, differences between color histogram are extracted as features. In the second phase, the fuzzy c-means (FCM) is used to group features into three clusters: the shot change (SC) cluster, the suspected shot change (SSC) cluster, and the no shot change (NSC) cluster. In the last phase, shot change frames are identified from the SC and the SSC, and then used to segment video sequences into shots. Finally, key frames are selected from each shot. Simulation results indicate that the HBFCM clustering algorithm is robust and applicable to various types of video sequences.     

Modified intelligent scissors and adaptive frame skipping for video object segmentation

MPEG-4 introduces the concept of video object to support content-based functionalities. Video object segmentation is a crucial step for object-based coding and manipulation. In this paper, a robust semi- automatic video object segmentation scheme is proposed. To efficiently and accurately define the initial object contour, modified intelligent scissors is proposed on the basis of original intelligent scissors. It can improve about 6–8 times the processing speed with only slight sacrifice of accuracy, which just meets the requirements of initial object extraction for semi-automatic approach. To avoid errors accumulating and propagating during object tracking, an adaptive frame skipping scheme is proposed to decompose video sequence into video clips. For rigid and non-rigid video objects, two different image segmentation algorithms are utilized, and then region-based backward projection technique is adopted to interpolate the video object plane (VOPs) of other frames within every video clip. The proposed approach can cope with occlusion/disocclusion problem to most extent. Experimental results demonstrate the effectiveness and robustness of the method.     

用于立体视频会议系统的立体对象分割与跟踪算法

基于对象的立体视频编码压缩技术能在立体视频会议系统中得到很好的应用，从立体视频信号中正确分割出立体视频对象是基于对象的立体视频编码压缩的一个前提条件，基于立体视频会议图像序列的时空特性和左右通道间的视差特性，提出了一种立体视频对象分割与跟踪算法，首先利用空域分割和运动检测相结合的方法，提取左通道中的运动物体；然后，提出一种左右通道间基于边缘轮廓的二级视差匹配算法，并根据已分割的左通道运动对象提取右通道的视频运动对象；最后利用对象边界轮廓的跟踪方法对后续图像中的运动对象进行快速跟踪，实验结果说明文中算法能够应用于立体视频会议图像序列的立体对象分割与跟踪。     

自适应权重更新的轻量级视频目标分割算法

目的 针对现有视频目标分割（video object segmentation,VOS）算法不能自适应进行样本权重更新,以及使用过多的冗余特征信息导致不必要的空间与时间消耗等问题,提出一种自适应权重更新的轻量级视频目标分割算法。方法 首先,为建立一个具有较强目标判别性的算法模型,所提算法根据提取特征的表征质量,自适应地赋予特征相应的权重;其次,为了去除冗余信息,提高算法的运行速度,通过优化信息存储策略,构建了一个轻量级的记忆模块。结果 实验结果表明,在公开数据集DAVIS2016 （densely annotated video segmentation）和DAVIS2017上,本文算法的区域相似度与轮廓准确度的均值J&F分别达到了85.8%和78.3%,与对比的视频目标分割算法相比具有明显的优势。结论 通过合理且无冗余的历史帧信息利用方式,提升了算法对于目标建模的泛化能力,使目标掩码质量更高。