Intelligent control based on wavelet decomposition and neural network for predicting of human trajectories with a novel vision-based robotic

In this paper, an intelligent novel vision-based robotic tracking model is developed to predict the performance of human trajectories with a novel vision-based robotic tracking system. The developed model is based on wavelet packet decomposition, entropy and neural network. We represent an implementation of a novel vision-based robotic tracking system based on wavelet decomposition and artificial neural (WD-ANN) which can track desired human trajectory pattern in real environments. The input–output data set of the novel vision-based robotic tracking system were first stored and than these data sets were used to predict the robotic tracking based on WD-ANN. In simulations, performance measures were obtained to compare the predicted and human–robot trajectories like actual values for model validation. In statistical analysis, the RMS value is 0.0729 and the R² value is 99.76% for the WD-ANN model. This study shows that the values predicted with the WD-ANN can be used to predict human trajectory by vision-based robotic tracking system quite accurately. All simulations have shown that the proposed method is more effective and controls the systems quite successful.     

分层优化机制引导的视觉机械臂联合模型优化

针对视觉机械臂系统整体精度不高、不易部署、校准成本高的问题,提出了具有分层优化机制的自适应多精英引导的复合差分进化算法（AMECoDEs-LO）。首先,对机械臂运动学模型和手眼标定外参模型进行系统集成。然后,以AMECoDEs算法为基础对种群中阶段性数据进行主成分分析,按照当前代各维度向量支配度的不同,划分参数优化的优先级,以参数降维优化的思想实现了对种群收敛精度和速度的隐式引导。在仿真和真实环境下与现有的一流演化算法进行了对比验证。最后针对视觉传感器对环境噪声敏感问题,加入不同强度的高斯白噪声验证系统的鲁棒性。实验结果表明,该算法精度高、收敛速度快、鲁棒性好且不需要额外的校准仪器,可用于视觉机械臂的快速部署。     

A multimedia-enhanced collaborative learning environment

Abstract The proliferation of the Internet has brought about the notion of online virtual communities. One enabling technology for online communities is multiuser environments such as Multi-User Dimensions (MUDs) and Object-Oriented MUDS (MOOs). These text-based collaborative learning environments have recently have been integrated with the World Wide Web, thus harnessing the graphics and multimedia-rich environments available therein. Learners can directly experience, manipulate, and create objects in their rich multimedia form. MUDs and MOOs are augmented with synchronous collaboration technology that provided simultaneous control and viewing of shared documents and applications. In this paper, we describe a multimedia-enhanced MOO system called SpaceALIVE! and our experiences from a pilot project involving Singapore students who use SpaceALIVE! as a collaborative learning environment are reported.     

Dynamic calibration of pan-tilt-zoom cameras for traffic monitoring.

Pan-tilt-zoom (PTZ) cameras have been widely used in recent years for monitoring and surveillance applications. These cameras provide flexible view selection as well as a wider observation range. This makes them suitable for vision-based traffic monitoring and enforcement systems. To employ PTZ cameras for image measurement applications, one first needs to calibrate the camera to obtain meaningful results. For instance, the accuracy of estimating vehicle speed depends on the accuracy of camera calibration and that of vehicle tracking results. This paper presents a novel calibration method for a PTZ camera overlooking a traffic scene. The proposed approach requires no manual operation to select the positions of special features. It automatically uses a set of parallel lane markings and the lane width to compute the camera parameters, namely, focal length, tilt angle, and pan angle. Image processing procedures have been developed for automatically finding parallel lane markings. Interesting experimental results are presented to validate the robustness and accuracy of the proposed method.     

Collaborative telemedicine for interactive multiuser segmentation of volumetric medical images

Telemedicine has evolved rapidly in recent years to enable unprecedented access to digital medical data, such as with networked image distribution/sharing and online (distant) collaborative diagnosis, largely due to the advances in telecommunication and multimedia technologies. However, interactive collaboration systems which control editing of an object among multiple users are often limited to a simple “locking” mechanism based on a conventional client/server architecture, where only one user edits the object which is located in a specific server, while all other users become viewers. Such systems fail to provide the needs of a modern day telemedicine applications that demand simultaneous editing of the medical data distributed in diverse local sites. In this study, we introduce a novel system for telemedicine applications, with its application to an interactive segmentation of volumetric medical images. We innovate by proposing a collaborative mechanism with a scalable data sharing architecture which makes users interactively edit on a single shared image scattered in local sites, thus enabling collaborative editing for, e.g., collaborative diagnosis, teaching, and training. We demonstrate our collaborative telemedicine mechanism with a prototype image editing system developed and evaluated with a user case study. Our result suggests that the ability for collaborative editing in a telemedicine context can be of great benefit and hold promising potential for further research.     

Dynamic Calibration of Pan–Tilt–Zoom Cameras for Traffic Monitoring

Pan–tilt–zoom (PTZ) cameras have been widely used in recent years for monitoring and surveillance applications. These cameras provide flexible view selection as well as a wider observation range. This makes them suitable for vision-based traffic monitoring and enforcement systems. To employ PTZ cameras for image measurement applications, one first needs to calibrate the camera to obtain meaningful results. For instance, the accuracy of estimating vehicle speed depends on the accuracy of camera calibration and that of vehicle tracking results. This paper presents a novel calibration method for a PTZ camera overlooking a traffic scene. The proposed approach requires no manual operation to select the positions of special features. It automatically uses a set of parallel lane markings and the lane width to compute the camera parameters, namely, focal length, tilt angle, and pan angle. Image processing procedures have been developed for automatically finding parallel lane markings. Interesting experimental results are presented to validate the robustness and accuracy of the proposed method.     

多用户眼动跟踪数据的可视化共享与协同交互

随着数字图像处理技术的发展,以及计算机支持的协同工作研究的深入,眼动跟踪开始应用于多用户协同交互.但是已有的眼动跟踪技术主要针对单个用户,多用户眼动跟踪计算架构不成熟、标定过程复杂,眼动跟踪数据的记录、传输以及可视化共享机制都有待深入研究.为此,建立了基于梯度优化的协同标定模型,简化多用户的眼动跟踪标定过程;然后提出面向多用户的眼动跟踪计算架构,优化眼动跟踪数据的传输和管理.进一步地,探索眼动跟踪数据的可视化形式在协同交互环境下对用户视觉注意行为的影响,具体设计了圆点、散点、轨迹这3种可视化形式,并验证了圆点形式能够有效地提高多用户协同搜索任务的完成效率.在此基础上,设计与开发了基于眼动跟踪的代码协同审查系统,实现了代码审查过程中多用户眼动跟踪数据的同步记录、分发,以及基于实时注视点、代码行边框和背景灰度、代码行之间连线的可视化共享.用户实验结果表明,代码错误的平均搜索时间比没有眼动跟踪数据可视化分享时减少了20.1%,显著提高了协同工作效率,验证了该方法的有效性.     

网络环境下协同虚拟拆卸训练平台

为实现复杂装备拆卸的多人协同工作,规划协同拆卸虚拟训练的工作流程以及网络环境下多人协同拆卸虚拟训练平台的体系框架;采用基于拆卸混合图的协同拆卸串、并行操作的管理方法,并分析协同拆卸过程中的多维拆卸信息,给出各种拆卸信息的协同可视化方法;协同拆卸虚拟训练原型系统的工作过程及其有效性通过示例进行说明并得到验证。     

Hybrid tracking for outdoor augmented reality applications

We've developed a fully mobile, wearable AR system that combines a vision-based tracker (primarily software algorithms) that uses natural landmarks, with an inertial tracker (custom hardware and firmware) based on silicon micromachined accelerometers and gyroscopes. Unlike other vision-based and hybrid systems, both components recover the full 6 DOF pose. Fusing the two tracking subsystems gives us the benefits of both technologies, while the sensors' complementary nature helps overcome sensor-specific deficiencies. Our system is tailored to affordable, lightweight, energy-efficient mobile AR applications for urban environments, especially the historic centers of European cities.     

Multiuser collaborative work in virtual environment based CASE tool

VRCASE is a virtual environment based Computer Aided Software Engineering (CASE) tool. It provides a 3D multiuser collaborative software modeling environment with automatic object-class abstraction, class diagram generation, and C++ skeleton generation facilities for assisting Object-Oriented software development. It allows multiple concurrent users to model software system collaboratively. To achieve efficient collaborative software development in VRCASE, we have proposed and implemented a Fine-grained locking and notification mechanism together with visual indicators to maintain system consistency among multiple concurrent users. The system evaluation shows that our approach can effectively support multiuser collaborative software design in VRCASE.     

Potential of multimodal and multiuser interaction with virtual holography

Virtual holography is a disruptive technology that can inspire innovations in variety of fields through blending the physical world with sensory-rich virtual world. The technology enables users to naturally and intuitively manipulate objects and navigate in 3D space. The zSpace virtual holography platform is described. The platform provides a 3D display and head-tracking technology that transforms PCs into virtual-holographic computing facility using a stereoscopic user interface with an interactive stylus. The major components of the platform and its potential benefits, along with some of the current applications are briefly described.The use of the zSpace platform to explore and manipulate a number of space system models is outlined. The models considered include Titan Saturn system, a joint NASA/ESA mission; Mars Science Lab concept; James Webb Telescope; and a Lunar Lander concept. In each of the applications considered, the platform is enhanced by using multimodal interactions, and providing support for multiuser collaboration. The multimodal interactions, which enable more engaging, enhanced accessibility, are achieved by fusing information from a set of stylus input, 3D gestures, and neural input. Simultaneous and collaborative multiuser interactions are described, which support both local and distributed teams, using variety of displays.Emerging and future enhancements of the zSpace platform are outlined, along with novel future applications.     

A framework for collaborative computing and multi-sensor data fusion in body sensor networks

Body Sensor Networks (BSNs) have emerged as the most effective technology enabling not only new e-Health methods and systems but also novel applications in human-centered areas such as electronic health care, fitness/welness systems, sport performance monitoring, interactive games, factory workers monitoring, and social physical interaction. Despite their enormous potential, they are currently mostly used only to monitor single individuals. Indeed, BSNs can proactively interact and collaborate to foster novel BSN applications centered on collaborative groups of individuals. In this paper, C-SPINE, a framework for Collaborative BSNs (CBSNs), is proposed. CBSNs are BSNs able to collaborate with each other to fulfill a common goal. They can support the development of novel smart wearable systems for cyberphysical pervasive computing environments. Collaboration therefore relies on interaction and synchronization among the CBSNs and on collaborative distributed computing atop the collaborating CBSNs. Specifically, collaboration is triggered upon CBSN proximity and relies on service-specific protocols allowing for managing services among the collaborating CBSNs. C-SPINE also natively supports multi-sensor data fusion among CBSNs to enable joint data analysis such as filtering, time-dependent data integration and classification. To demonstrate its effectiveness, C-SPINE is used to implement e-Shake, a collaborative CBSN system for the detection of emotions. The system is based on a multi-sensor data fusion schema to perform automatic detection of handshakes between two individuals and capture of possible heart-rate-based emotion reactions due to the individuals’ meeting.     

Interactive multi-user video retrieval systems

In this paper we present two interactive multi-user systems for video search and browsing. The first is composed by web applications which allows multiuser interaction in a distributed environment; such applications are based on the Rich Internet Application paradigm, designed to obtain the levels of responsiveness and interactivity typical of a desktop application. The second system implements a multi-user collaborative application within a single location, exploiting multi-touch devices. Both systems use the same backend, based on a service oriented architecture (SOA) that provides services for automatic and manual annotation, and an ontology-based video search and browsing engine. Ontology-based browsing let users to inspect the content of video collections; user queries are expanded through ontology reasoning. User-centered field trials of the systems, conducted to assess the user experience and satisfaction, have shown that the approach followed to design these interfaces is extremely appreciated by professional archivists and people working on multimedia.     

Locality Preserving Collaborative Representation for Face Recognition

Face recognition has many applications in pattern recognition and computer vision, and many face recognition methods have been proposed. Among them, the recently proposed collaborative representation based face recognition has attracted the attention of researchers. Many variants and extensions of collaborative representation based classification (CRC) have been presented. However, most of CRC methods do not consider data locality, which is crucial for classification task. In this article, a novel collaborative representation based face recognition method, LP-CRC, is proposed, which balances data locality and collaborative representation. The proposed method incorporates a locality adaptor term into the robust collaborative representation based classification framework, leading to a novel unified objective function. The Augmented Lagrange Multiplier is used to optimize the objective function. Tests on standard benchmarks demonstrate that the proposed face recognition method is superior to existing methods and robust to noise and outliers.     

基于Web的协同商标图案设计系统研究

图案的协同设计是计算机支持的协同工作的一个典型应用 ,针对纺织商标图案设计的要求 ,给出了一个基于 Web的协同商标图案设计系统的体系结构 ,重点阐述了在同步设计环境中基于事件驱动机制的多用户同步设计思想 ,并提出了一个基于动态的最高优先级策略来控制系统的并发     

FlexiFrag: A design pattern for flexible file sharing in distributed collaborative applications

The need for flexible file sharing in distributed systems is increasing in applications such as calendar management, collaborative editing of documents, collaborative software developments etc. The file sharing policies required in these applications are often very different from the traditional read/write policies. Hence, a flexible way of specifying and implementing sharing policies on individual files in file systems is required. We propose a distributed object-based system model of constructing file systems. The object-based system model is based on a pattern called FlexiFrag. We show how a distributed object-based system and in particular distributed file system can be constructed using the pattern in a flexible way.     

GameSense: game-like in-image advertising

Considering the continuously increasing availability and accessibility of multimedia contents via social networking sites, our research addresses how to monetize the social multimedia contents with an efficient advertising approach. This paper presents a novel game-like advertising system called GameSense, which is driven by the compelling contents of online images. The contextually relevant ads (i.e., product logos) are embedded at appropriate positions within the online games, which are created on the basis of online images. The ads are selected based on multimodal relevance, i.e. text relevance, user relevance and visual content similarity. The game is able to provide viewers rich experience and thus promotes the embedded ads to provide more effective advertising. GameSense represents one of the first attempts toward effective online mashup applications which connect a photo-sharing site with an advertising agency. The effectiveness of GameSense is evaluated over a large-scale real world image set.     

Camera calibration using one-dimensional information and its applications in both controlled and uncontrolled environments

Camera model and its calibration are required in many applications for coordinate conversions between the two-dimensional image and the real three-dimensional world. Self-calibration method is usually chosen for camera calibration in uncontrolled environments because the scene geometry could be unknown. However when no reliable feature correspondences can be established or when the camera is static in relation to the majority of the scene, self-calibration method fails to work. On the other hand, object-based calibration methods are more reliable than self-calibration methods due to the existence of the object with known geometry. However, most object-based calibration methods are unable to work in uncontrolled environments because they require the geometric knowledge on calibration objects. Though in the past few years the simplest geometry required for a calibration object has been reduced to a 1D object with at least three points, it is still not easy to find such an object in an uncontrolled environment, not to mention the additional metric/motion requirement in the existing methods. Meanwhile, it is very easy to find a 1D object with two end points in most scenes. Thus, it would be very worthwhile to investigate an object-based method based on such a simple object so that it would still be possible to calibrate a camera when both self-calibration and existing object-based calibration fail to work. We propose a new camera calibration method which requires only an object with two end points, the simplest geometry that can be extracted from many real-life objects. Through observations of such a 1D object at different positions/orientations on a plane which is fixed in relation to the camera, both intrinsic (focal length) and extrinsic (rotation angles and translations) camera parameters can be calibrated using the proposed method. The proposed method has been tested on simulated data and real data from both controlled and uncontrolled environments, including situations where no explicit 1D calibration objects are available, e.g. from a human walking sequence. Very accurate camera calibration results have been achieved using the proposed method.     

A vision-based fast base frame calibration method for coordinated mobile manipulators

The mobile manipulators (MMs) have been increasingly adopted for machining large and complex components. In order to ensure the machining efficiency and quality, the MMs usually need to cooperate with each other. However, due to the low motion accuracy of the mobile platform, the relative pose accuracy between the coordinated MMs are difficult to guarantee, so an effective calibration method is needed to on-line obtain the relative pose of the MMs. For this purpose, a vision-based fast base frame calibration method is proposed in this paper, which can quickly and accurately obtain the relative pose between the coordinated MMs. The method only needs to add a camera and a marker, and then a frame network of the calibration system can be generated by installing the marker at three different positions. Based on the Perspective-n-Points principle and the robot forward kinematics, the transformation matrix of the marker frame with respect to the camera frame and the robot base frame can be determined by simply obtaining the images of the marker at different positions and corresponding robot joint angles. Then, the relative pose between the base frames of coordinated MMs can be determined by the calibration equation established based on a frame closed chains. In addition, the calibration method is capable of real-time calculation by dividing the calibration process into off-line and on-line stages. Simulation and experimental results have verified the effectiveness of the proposed method.     

Online robot calibration based on vision measurement

Robot calibration is a useful diagnostic method to improve positioning accuracy in robot production and maintenance. Unlike traditional calibration methods that require expensive equipment and complex steps, a vision-based online robot calibration method that only requires several reference images is presented in this paper. The method requires a camera that is rigidly attached to the robot end effector (EE), and a calibration board must be settled around the robot where the camera can see it. An efficient automatic approach to detect the corners from the images of the calibration board is proposed. The poses of the robot can be estimated from the detected corners. The kinematic parameters can be conducted automatically based on the known poses of the robot. Unlike in the existing self-calibration methods, the great advantage of this online self-calibration method is that the entire process of robot calibration is automatic and without any manual intervention, enabling the robot calibration to be completed online when the robot is working. Therefore, the proposed approach is particularly suitable for unknown environments, such as deep sea or outer space. In these high-temperature and/or high-pressure environments, the shapes of the robot links are easy to change. Thus, the robot kinematic parameters are changed by allowing the robot to grab objects with different qualities to verify the performance of the online robot calibration. Experimental studies on a GOOGOL GRB3016 robot show that the proposed method has high accuracy, convenience, and high efficiency.