多次投影算法在视频监控人脸检测中的应用

根据视频监控图像在时间上的连续性和空间上的继承性,利用连续三帧视频图像对称差分,找到运动区域,再结合人脸肤色的聚类特征确定出人脸候选区域,然后改进了利用投影的人脸定位算法,将单次投影发展为多次投影,并且结合人脸的几何特征,实现视频监控中复杂背景下的多人脸检测。实验表明,该算法复杂度小,准确率较高,对姿态、表情、背景等变化情况下人脸的检测均具有较好的鲁棒性。     

视频监控中人脸识别算法稳定性的改进

如果单纯地采用静态人脸识别算法对视频图像进行检测、识别,忽略了视频中重要的前后帧相关的特性,会造成识别结果的不稳定。为了解决识别结果不稳定的问题,对视频监控中的人脸识别算法进行了改进,根据视频前后帧相关性对人脸运动进行估计并将其应用在视频监控的软件产品中。实验证明,该算法提高了传统单帧人脸识别算法的稳定性,具有较好的应用价值。     

改进的 AdaBoost人脸检测方法

针对传统 AdaBoost算法检测速度快准确率低的问题,本文提出了一种改进的 AdaBoost算法以提高人脸的正确检测率,该算法首先利用快速积分图提取人脸的 Haar特征,然后使用阈值设定的方法对传统的 AdaBoost算法进行改进,并将每次检测的最优弱分类器级联形成最终的强分类器,通过强弱分类器对 Haar特征判别,从而检测图像中的人脸部分。采用本方法对多种实验图像集进行人脸检测实验, FERET彩色图像库的正确检测率为96.07%,视频图像的正确检测率为 96%。实验结果表明,本文所设计的人脸检测算法能够对静态图像以及视频图像中的人脸进行有效检测,为人脸的正确识别打下了基础,该算法也为计算机视觉领域的研究提供一种有效方法。     

基于深度学习检测器的多角度人脸关键点检测

针对人脸关键点检测(人脸对齐)在应用场景下的速度和精度需求,首先在SSD基础之上融合更多分布均匀的特征层,对人脸框坐标进行级联预测,形成对于多尺度人脸信息均具有更加鲁棒响应的深度学习检测器MR-SSD。其次在局部二值特征LBF的级联形状回归方法基础上,提出了基于面部像素差值的多角度初始化算法。采用端正人脸正负90°倾斜范围内的五组特征点形状进行初始化,求取每组回归后形状的眼部特征点像素均方差值并以最大者对应方案作为最终回归形状,从而实现对多角度倾斜人脸优异的拟合效果。本文所提出的最优架构可以实时获得极具鲁棒性的人脸框坐标并且可实现对于多角度倾斜人脸的关键点检测。     

面向人脸特征点定位和姿态估计任务协同的DCNN方法

为了提高复杂背景下面部信息的识别性能,提出了一种面向人脸特征点定位和姿态估计任务协同的深度卷积神经网络(DCNN)方法。首先从视频图像中检测出人脸信息;其次设计一个深度卷积网络模型,将人脸特征点定位和姿态估计两个任务协同优化,同时回归得到人脸特征点坐标和姿态角度值,然后融合生成相应的人机交互信息;最后采用公开数据集和实际场景数据进行测试,并与其他现有方法进行比对分析。实验结果表明:该方法在人脸特征点定位和姿态估计上表现出较好的性能,在光照变化、表情变化、部分遮挡等复杂条件下人机交互应用也取得了良好的准确性和鲁棒性,平均处理速度约16帧/s,具备一定的实用性。     

基于人脸肤色和特征的实时检测跟踪算法

针对实时视频中的运动人体目标,提出一种基于人脸肤色和特征的快速人脸检测和跟踪方法.首先运用帧差法和形状信息检测出视频中的运动人体目标;然后在YCbVCr色彩空间中,根据肤色的色度聚类特性建立Gaussian模型,分割出肤色区域,去除噪声后,结合人脸的几何特征和器官独有的颜色特征滤除非人脸肤色区域,准确定位人脸在图像中的位置;利用控制策略驱动摄像机,根据人脸信息使人的头肩部位始终处于视频图像的中心,从而实现运动跟踪.为了增强系统对光线变化的适应性,提出了适当的Gaussian模型参数更新策略.实验结果表明,该算法能够适应复杂背景下的人脸检测,具有速度快、准确率高、鲁棒性好的特点,实现了运动人脸的可靠跟踪.     

RME:基于滑动窗口的实时人脸检测算法

研究了基于滑动窗口的视频实时人脸检测,提出了刚性运动估计(RME)算法.该算法以小尺度人脸瞬时刚性运动为假设,根据几何变换对窗口图像的运动进行描述,以光流代替运动矢量计算运动参数进而识别窗口图像的刚性、非刚性运动类型,通过排除非刚性窗口以提高人脸检测效率.对比实验与分析表明,该算法在准确率与时间效率方面具有优势.     

一种基于动态时间规划的视频特征检索改进算法

针对基于"视频指纹"特征的视频检索算法在实际应用中存在视频亮度整体漂移、突变干扰以及视频再编辑的问题,提出了一种基于动态时间规划的视频特征检索改进算法.该算法在原"视频指纹"算法的基础上采用了新的视频检索策略:首先,对视频帧进行区域分割,将"视频指纹"由单分量扩展到多分量;然后,采用基于粒度的相似性比较算法,用比对每帧视频指纹的变化,取代比较视频指纹本身;最后,采用改进的动态时间规划算法进行视频特征匹配,定位目标视频.在算法评估中,建立了由74段广告视频和154段再编辑视频组成的测试集.通过试验证明,改进算法可以有效应对视频检索过程中的亮度整体漂移、突变干扰和视频再编辑问题,检索算法具有很好的鲁棒性.     

数字电视中视频芯片的自适应去隔行算法研究

文章提出了一种适用于数字电视视频处理芯片上的隔行——逐行格式转换算法。该算法能正确检测出视频的运动和静止信息,从而自适应的采用帧内边缘相关算法或者帧间交织算法进行隔行到逐行的格式转换;并且能准确的检测出并转换具有3-2下拉特征的电影模式视频序列。经仿真验证,该算法与其他算法相比具有占用系统资源少、运算速度快的优点,因此非常适合应用在视频处理芯片中。     

基于卷积神经网络级联的蒙面人脸检测算法

精确地检测蒙面人脸是鉴别和追踪罪犯或者恐怖分子的重要手段,因此,一个高效的蒙面人脸检测算法这对于打击犯罪,维护社会治安稳定有重要意义。然而,由于面具遮挡导致的人脸信息缺失,传统的人脸检测算法很难取得令人满意的结果。针对这一问题,在本论文中,我们提出了一种适用于蒙面人脸检测的卷积神经网络级联算法。该级联网络共有三级,在训练时,第一级采用整个训练样本集进行训练,之后逐级对前一级训练中分类错误的样本进行训练,以获得更强的辨别能力。这一策略也能避免第一级网络的过度拟合。为了进一步保证算法的检测精度,我们采用迁移学习的方法,利用大型的通用人脸数据集和蒙面人脸数据集来训练和微调分类网络模型。此外,我们还优化了每一级的网络结构,从而提高了计算效率。我们在蒙面人脸的测试数据集上对算法进行测试。实验结果表明,我们在87. 8%的召回率下取得了86. 6%的精确率。并且,相比于传统的卷积神经网络算法,我们的方法具有较高的检测精度和检测效率。     

A virtual teleconferencing system based on face detection and 3D animation in a low‐bandwidth environment

In this article, we proposed a novel teleconferencing system that combines a facial muscle model and the techniques of face detection and facial feature extraction to synthesize a sequence of life‐like face animation. The proposed system can animate realistic 3D face images in a low‐bandwidth environment to support virtual videoconferencing. Based on the technique of feature extraction, a face detection algorithm for the virtual conferencing system is proposed in this article. In the proposed face detection algorithm, the YCbCr skin color model is used to detect the possible face area of the image; the feature points of the face is determined by using the symmetry property of the face and the gray level characteristics of the eyes and the mouth. According to the positions of the feature points on a facial image, we can compute the transformation values of the feature points. These values will then be sent via a network from the sender's side to the receiver's side frame by frame. We can synthesize the realistic facial animations on the receiver's side based on these. Experimental results show that the proposed system can achieve a practical animated face‐to‐face virtual conference with good facial expressions and a low‐bandwidth requirement. © 2010 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 20, 323–332, 2010     

Video Frame Prediction by Joint Optimization of Direct Frame Synthesis and Optical-Flow Estimation

Video prediction is the problem of generating future frames by exploiting the spatiotemporal correlation from the past frame sequence. It is one of the crucial issues in computer vision and has many real-world applications, mainly focused on predicting future scenarios to avoid undesirable outcomes. However, modeling future image content and object is challenging due to the dynamic evolution and complexity of the scene, such as occlusions, camera movements, delay and illumination. Direct frame synthesis or optical-flow estimation are common approaches used by researchers. However, researchers mainly focused on video prediction using one of the approaches. Both methods have limitations, such as direct frame synthesis, usually face blurry prediction due to complex pixel distributions in the scene, and optical-flow estimation, usually produce artifacts due to large object displacements or obstructions in the clip. In this paper, we constructed a deep neural network Frame Prediction Network (FPNet-OF) with multiple-branch inputs (optical flow and original frame) to predict the future video frame by adaptively fusing the future object-motion with the future frame generator. The key idea is to jointly optimize direct RGB frame synthesis and dense optical flow estimation to generate a superior video prediction network. Using various real-world datasets, we experimentally verify that our proposed framework can produce high-level video frame compared to other state-of-the-art framework.     

多级FFD配准视频人脸超分辨率重建

超分辨率重建是解决视频人脸识别中人脸分辨率低的有效方法,但由于人脸畸变、表情变化等非刚性变化导致无法精确配准和重建.针对此问题,提出基于B样条的多级模型自由形式形变(FFD)弹性配准算法.先用低分辨率FFD网格全局配准,再对全局配准后的图像分块并计算对应子图块的相关性系数,对相关性系数小的子图块用高分辨率FFD网格局部细配准.在配准的寻优过程中采用基于混沌因子的自适应步长最速下降法提高寻优效率.配准后,采用POCS算法对多帧图像重建高分辨率图像来识别.在标准视频库和自建视频库上实验仿真,结果表明在人脸畸变和表情变化很大的情况下,也能够精确的配准和很好的重建,得到较高识别率.     

Optical flow-based motion compensation algorithm for very low-bit-rate video coding

In this article, we propose an efficient compression algorithm for very low-bit-rate video applications. The algorithm is based on (a) an optical-flow motion estimation to achieve more accurate motion prediction fields; (b) discrete cosine transformation (DCT) coding of the motion vectors from the optical-flow estimation to reduce the motion overheads; and (c) an adaptive threshold technique to match optical flow motion prediction and minimize the residual errors. Unlike the classic block-matching based DCT video coding schemes in MPEG-1/2 and H.261/3, the proposed algorithm uses optical flow for motion compensation and the DCT is applied to the optical flow field instead of predictive errors. Thresholding techniques are used to treat different regions to complement optical flow technique and to efficiently code residual data. While maintaining a comparable peak signal-to-noise ratio (PSNR) and computational complexity with that of ITU-T H.263/TMN5, the reconstructed video frames of the proposed coder are free of annoying blocking artifacts, and hence visually much more pleasant. The computer simulation are conducted to show the feasibility and effectiveness of the algorithm. Results at 11 kbps are presented which can be used for videophone applications in the existing public switched telephone network (PSTN). © 1998 John Wiley & Sons, Inc. Int J Imaging Syst Technol, 9, 230–237, 1998     

Research on Facial Expression Capture Based on Two-Stage Neural Network

To generate realistic three-dimensional animation of virtual character, capturing real facial expression is the primary task. Due to diverse facial expressions and complex background, facial landmarks recognized by existing strategies have the problem of deviations and low accuracy. Therefore, a method for facial expression capture based on two-stage neural network is proposed in this paper which takes advantage of improved multi-task cascaded convolutional networks (MTCNN) and high-resolution network. Firstly, the convolution operation of traditional MTCNN is improved. The face information in the input image is quickly filtered by feature fusion in the first stage and Octave Convolution instead of the original ones is introduced into in the second stage to enhance the feature extraction ability of the network, which further rejects a large number of false candidates. The model outputs more accurate facial candidate windows for better landmarks recognition and locates the faces. Then the images cropped after face detection are input into high-resolution network. Multi-scale feature fusion is realized by parallel connection of multi-resolution streams, and rich high-resolution heatmaps of facial landmarks are obtained. Finally, the changes of facial landmarks recognized are tracked in real-time. The expression parameters are extracted and transmitted to Unity3D engine to drive the virtual character's face, which can realize facial expression synchronous animation. Extensive experimental results obtained on the WFLW database demonstrate the superiority of the proposed method in terms of accuracy and robustness, especially for diverse expressions and complex background. The method can accurately capture facial expression and generate three-dimensional animation effects, making online entertainment and social interaction more immersive in shared virtual space.     

A variable-depth search algorithm for the recursive bipartitioning of signal flow graphs

We discuss the use of local search techniques for mapping video algorithms onto programmable high-performance video signal processors. The mapping problem is very complex due to many constraints that need to be satisfied in order to obtain a feasible solution. The complexity is reduced by decomposing the mapping problem into three subproblems, namely delay management, partitioning, and scheduling. We present the partitioning problem and the representation of video algorithms by signal flow graphs. Furthermore, we propose a solution strategy that is based on recursive bipartitioning of these graphs. The bipartitions are generated using a variable-depth search algorithm. The results demonstrate that the frequently cited flexibility of local search techniques can be successfully exploited in handling complicated problems.     

Face Age Estimation Based on CSLBP and Lightweight Convolutional Neural Network

As the use of facial attributes continues to expand, research into facial age estimation is also developing. Because face images are easily affected by factors including illumination and occlusion, the age estimation of faces is a challenging process. This paper proposes a face age estimation algorithm based on lightweight convolutional neural network in view of the complexity of the environment and the limitations of device computing ability. Improving face age estimation based on Soft Stagewise Regression Network (SSR-Net) and facial images, this paper employs the Center Symmetric Local Binary Pattern (CSLBP) method to obtain the feature image and then combines the face image and the feature image as network input data. Adding feature images to the convolutional neural network can improve the accuracy as well as increase the network model robustness. The experimental results on IMDB-WIKI and MORPH 2 datasets show that the lightweight convolutional neural network method proposed in this paper reduces model complexity and increases the accuracy of face age estimations.     

基于YOLOv3和DeepSort的车流量检测

针对传统多目标跟踪算法的检测跟踪精度低、鲁棒性差的缺点,基于经典的Tracking-By-Detection模式,提出一种基于YOLOv3和DeepSort的车流量检测方法,实现了车辆视频监控端到端的车流量视频的实时监测与跟踪计数。采用深度学习YOLOv3算法检测视频车辆目标,然后利用深度学习DeepSort算法对检测到的车辆进行实时跟踪计数。实验结果表明该方法应对快速移动的车辆和环境光照的影响时,对车流量的检测效果良好,平均精度达到94.7%,端到端的算法可行且有效,适用于对车辆视频的批处理。     

运动背景中结合特征位移矢量场模糊分割与 OTSU法的运动检测

运动背景中的运动检测难度较大,背景运动补偿后差分以及分割光流场可实现动目标和背景的分离,差分前需进行鲁棒的背景估计,且差分后易出现空洞,而光流估计在噪声以及目标运动速度较大时并不准确,尤其在光照变化时,两种方法均易失效。本文提出一种特征点位移矢量场模糊分割与图像自适应阈值化相结合的运动检测方法,实现在无任何关于运动目标或者运动背景先验信息条件下的动目标检测。通过改进的 SIFT匹配方法生成鲁棒的特征位移矢量场,采用模糊 C均值聚类算法对 SIFT位移矢量场进行无监督分类,实现动目标与背景特征的自适应分离。 OTSU法和形态学操作实现图像的自适应分割,用以修正特征点凸包,最终分割出动目标区域。与鲁棒的背景运动补偿后差分以及光流估计的对比实验表明,在目标运动速度较大、光照变化以及噪声情况下,本文方法均能够检测出运动目标,且在光照变化下的优势明显。