Contour-Based Multi-Source Information Fusion for Motion Segmentation

A motion segmentation framework that effectively exploited the multiple sources of image information and fused these sources of the information synergisti-cally was proposed to serve the purpose of motion segmen- tation. A Markov process was formulated for motion seg- mentation in which two feature spaces were established to estimate the state transition Probability density function （PDF） and the initial state, respectively. An information fusion space was developed such that each motion struc-ture was described as a single distribution in this space. The proposed framework can naturally embed the evolution equations of the active contour methods into the seg-mentation to achieve contour-based segmentation results. Extensive empirical evaluations demonstrate the robust-ness and the promise of this framework.     

Real-time Facial Features Tracker Based on Topologic Information and Similarity Analysis

Real-time facial features tracking of video can be widely used in face recognition, video surveillance, face animation and Human-Computer Interaction. We present a fast tracking approach, and our method only requires simple device---a digital camera and a PC, and our approach needs limited user interactions. We first use eigenface and topologic information to detect the position and the size of face from the first frame, and facial features of the first frame are acquired automatically. The successor of the first frame can be tracked by using similarity analysis and motion estimation, the automatic tracker of first frame is also used to resolve the features occlusion problem when the tracked features disappear which is a difficult issue for tracking. Experimental results show that our approach is easily implemented, and the analysis also shows the high robustness of our method.     

运动捕捉技术在影视动画制作中的应用研究

运动捕捉技术是影视动画制作中的新技术。在对运动捕捉技术分析的基础上，讨论了基于光学运动捕捉技术制作动画的原理和方法，并详细描述了标记点跟踪和三雏重建等技术在影视动画制作过程中的应用。     

QoS Routing in Wireless Mesh Networks

An H-hop interference model is proposed, where the transmission is successfully received if no other nodes that are within H hops from the receiver are transmitting on the same channel simultaneously. Based on this model. the interference-free property in the Time division multiple access Wireless mesh networks is analyzed. A heuristic algorithm with max-rain time slots reservation strategy is developed to get the maximum bandwidth of a given path. And it is used in the bandwidth guaranteed routing protocol to find a path for a connection with bidirectional bandwidth requirement. Extensive simulations show that our routing protocol decreases the blocking ratios significantly compared with the shortest path routing.     

An Algorithm of Wavelet Image Fusion Based on Visual Saliency

Considering the characteristics of wavelet transform and human visual system saliency, a novel image fusion algorithm was proposed. Based on multi-scale wavelet decomposition, visual saliency model had been introduced into calculating the intensity, direction and texture global integrated saliency of each pixel at each level frequency component. And it adaptively acquired the weighted fusing coefficients. Experiments show that this algorithm can achieve more clear minutia. Comparing with regional feature-based wavelet fusion algorithm, it improves fusion performance of human vision and objective evaluation. It is also benefit to detection and recognition.     

Perceptual Quality Assessment of SAR Image Compression Based on Image Content Partition and Neural Network

Image quality assessment （IQA） is of fundamental importance for image compression applications. Traditional IQA measures used for Synthetic aperture radar （SAR） image compression do not consider the properties of Human visual system （HVS）. Since human beings are the final users in most SAR image applications, the objective evaluation coordinate to human＇s perception is the most acceptable and practical IQA method. In this paper, we propose a novel objective approach based on image content partition and Neural network （NN） by introducing the HVS and SAR image characteristics. Experimental results demonstrate that the proposed metric correlates well with subjective quality of SAR image compression and outperforms those state-of-art objective models using Structural similarity index （SSIM）, Singular value decomposition （SVD） and Visual information fidelity （VIF）.     

Identifying Periodical Activities Independent of Video Content

In this research, a completely new and accurate method has been presented for detecting periodic activities with the help of machine vision. The proposed method is independent of motion tracking complex algorithms unlike the previous strategies and it is fully independent of contents and types of activities by performing low level calculation. Not using of heavy computations while improving the ability of periodicity detection is regarded as the unique feature of this method. The use of general and flexible framework in this method causes to facilitate the machine vision periodic activities identification process.     

Bidirectional Background Modeling for Video Surveillance

Traditional background model methods often require complicated computations, and are sensitive to illumination and shadow. In this paper, we propose a block-based background modeling method, and use our proposed method to combine color and texture characteristics. Suppression and relaxation are the two key strategies to resist illumination changes and shadow disturbance. The proposed method is quite efficient and is capable of resisting illumination changes. Experimental results show that our method is suitable for real-word scenes and real-time applications.     

Recognition of dynamic video contents with global probabilistic models of visual motion.

The exploitation of video data requires methods able to extract high-level information from the images. Video summarization, video retrieval, or video surveillance are examples of applications. In this paper, we tackle the challenging problem of recognizing dynamic video contents from low-level motion features. We adopt a statistical approach involving modeling, (supervised) learning, and classification issues. Because of the diversity of video content (even for a given class of events), we have to design appropriate models of visual motion and learn them from videos. We have defined original parsimonious global probabilistic motion models, both for the dominant image motion (assumed to be due to the camera motion) and the residual image motion (related to scene motion). Motion measurements include affine motion models to capture the camera motion and low-level local motion features to account for scene motion. Motion learning and recognition are solved using maximum likelihood criteria. To validate the interest of the proposed motion modeling and recognition framework, we report dynamic content recognition results on sports videos.     

Real-Time Hand Motion Parameter Estimation with Feature Point Detection Using Kinect

This paper presents a real-time Kinect- based hand pose estimation method. Different from model-based and appearance-based approaches, our approach retrieves continuous hand motion parameters in real time. First, the hand region is segmented from the depth image. Then, some specific feature points on the hand are located by the random forest classifier, and the relative displacements of these feature points are transformed to a rotation invariant feature vector. Finally, the system retrieves the hand joint parameters by applying the regression functions on the feature vectors. Experimental results are compared with the ground truth dataset obtained by a data glove to show the effectiveness of our approach. The effects of different distances and different rotation angles for the estimation accuracy are also evaluated.     

3D Reconstruction of Periodic Human Walking Trajectories Based on Single View

Periodicity of a moving body is one of important characteristics in activity monitoring. We present a method to estimate the trajectory of human gait in 3D space from a single camera by exploring the periodicity of the human movement. Geometric constraints are established to characterize the periodic motion, which are invariant under viewing geometry variations. According to our analysis, these geometric constraints reduce the overall computational complexity of evaluating periodicity. Meanwhile, with the help of these geometric constraints, we develop a novel method to reconstruct the 3D motion trajectory from a single camera. Experimental results demonstrate the accuracy and robustness of the algorithm.     

Wavelet-Based Synthesis of the Multifractional Brownian Motion

The multifractional Brownian motion （mBm） is introduced as a natural extension of traditional fractional Brownian motion （fBm）. The selling point of mBm is that its Hǒlder regularity is allowed to vary from point to point, such that makes it a promising model for those stochastic processes whose regularity evolves in time. A wavelet-based algorithm to synthesize a realization of mBm is proposed in this work. The desired local regularity of the multifractional process is obtained by controlling the weights of the wavelet expansion of the Gaussian white noise. This approach is not only time saving, also appro-priate for generating the multifractional process that is non-Gaussian and autocovariance function unknown in ad- vance. The validity is verified by numerical experiments and real-world data.     

Closed-form connectivity-preserving solutions for motioncompensation using 2-D meshes

Motion compensation using two-dimensional (2-D) mesh models requires computation of the parameters of a spatial transformation for each mesh element (patch). It is well known that the parameters of an affine (bilinear or perspective) mapping can be uniquely estimated from three (four) point correspondences (at the vertices of a triangular or quadrilateral mesh element). On the other hand, overdetermined solutions using more than the required minimum number of point correspondences provide increased robustness against correspondence-estimation errors, however, this necessitates special consideration to preserve mesh-connectivity. This paper presents closed-form, overdetermined solutions for least squares estimation of affine motion parameters for a triangular mesh, which preserve mesh-connectivity using patch-based or node-based connectivity constraints. In particular, four new algorithms are presented: patch-constrained methods using point correspondences or spatio-temporal intensity gradients, and node-constrained methods using point correspondences or spatio-temporal intensity gradients. The methods using point correspondences can be viewed as postprocessing of a dense motion field for best representation in terms of a set of irregularly spaced samples. The methods that are based on spatio-temporal intensity gradients offer closed-form solutions for direct estimation of the best node-point motion vectors (equivalently the best transformation parameters). We show that the performance of the proposed closed-form solutions are comparable to those of the alternative search-based solutions at a fraction of the computational cost.     

A CMOS Word Alignment Configurable Transceiver for Multi-Standard Fiber Communication Systems

This paper describes a configurable transceiver which can realize multiple operation modes to meet various fiber communication standards. With this configurable architecture, the transceiver can operate in 2：1, 3：1, 4：1, 5：1, 6：1, 8：1, 10：1 multiplexing modes and 1：2, 1：3, 1：4, 1：5, 1：6, 1：8, 1：10 demultiplexing modes with internal synchronized clock signals. Comma detection and word alignment circuits are also included in the receiver to meet the standards using 8B/10B code. This configurable multi-mode transceiver has been implemented in a 0.25μm CMOS technology.     

Yb3+: GdGaGe2O7制备、结构及光谱性能

采用固相法制备了10at.% Yb3+: GdGaGe2O7多晶粉体，通过X射线粉末衍射用Rietveld全谱拟合给出了其空间群为P21/c,晶格常数a、b、c和β、Gd/Yb和Ga的原子坐标为。Ge1、Ge2、O1～O7的原子坐标。通过吸收谱、激发谱、光致发光谱和Raman光谱确定Yb3+的晶场能级分裂；1003nm发光在低温8K和室温(300K)时上能级荧光寿命为0.493ms和0.774ms。在室温下测量荧光寿命变长主要由再吸收所引起。Yb3+:GdGaGe2O7的吸收和发射光谱均很宽，荧光寿命长，是潜在的全固态激光工作物质。     

使用简易深度成像设备的高尔夫挥杆动态贝叶斯网络三维重建

基于简易深度成像设备的动作捕捉系统因其与传统设备相比更加廉价且易于使用而倍受关注。然而,此类设备图像分辨率很低,肢体间互相遮挡,缺乏3维动作重建的基本数据条件。该文融合人体关节点父子关系与关节点在运动中的多阶马尔可夫性,提出一个描述人体关节点空间关系与动态特性的动态贝叶斯网络(DBN)模型,基于该DBN模型并利用高尔夫挥杆运动的相似性,构建了一种高尔夫挥杆3维重建系统DBN-Motion(DBN-based Motion reconstruction system),使用简易深度成像设备Kinect,有效地解决了肢体遮挡的问题,实现了高尔夫挥杆动作的捕获和3维重建。实验结果表明,该系统能够在重建精度上媲美商用光学动作捕捉系统。     

Survivable Routing Protocol for Green Wireless Mesh Networks Based on Energy Efficiency

This paper proposes a new Energyefficient Survivable Routing Protocol（ESRP）based on solar energy and wind mixed for power supply in green wireless mesh networks（WMNs）.The ESRP combines hop penalty strategy and flooding delaying strategy to improve the performances of traditional routing protocol.This paper uses QualNet to simulate and verify the performances of proposed ESRP.Compared with the traditional routing protocol,the simulation results show that the energy utilization of ESRP is more efficient by 13%.At the same time,ESRP is more load-balanced to postpone the appearance of the first energy depletion node and reduce the number of energy depletion nodes,and thus it effectively improves network survivability.     

A Reliable Method of Image Registration Based on Optical Flow Field and Feature Extraction

A novel method for solving the automated registration problems based on the global optical flow field and feature extracted from images is proposed. The method can be preformed with three steps. Firstly, the global optical flow field is computed, which provides a platform of background registration. Secondly, the optical flow field and the edge feature of moving target are integrated to segment the whole target. Finally, the registration of moving targets is finished through the transformation computation of perspective projection model. The simulation experiments for infrared images show that the method proposed is not accurate, but robust to motion of scene, which is ideally suited for the application of automated image registration.     

基于GA的压缩域中全局运动估计及在字幕遮挡区域恢复中的应用

文章提出了一种直接使用压缩域中的运动矢量进行全局运动估计的方法,并用遗传算法优化输入运动矢量与全局运动参数所产生运动矢量的平均匹配误差.最终的实验结果表明本文的方法能够很好的估计出全局运动的参数.并且提出了一种运用全局/局部运动信息进行视频中字幕遮挡区域的恢复的方法.实验结果表明该方法取得了较好的视觉效果.     

射频收发机电路的电磁干扰问题

现代无线通信收发机中，广泛应用了高集成度的芯片，元器件的布局也高度密集。在得到了低功耗、小尺寸的同时，有可能导致通信系统不能正常工作。