保持视觉稳定性的增强现实注册算法

提出了一种保持视觉稳定性的增强现实注册算法,特征点在视频中的初匹配基于随机树检索统计得到,初步匹配的特征点采用半几何限制结合单应矩阵迭代的方法进行错误匹配排除,随后采用光流法跟踪特征点,最后根据共面POSIT算法计算出物体世界坐标系到摄像机坐标系的变换矩阵。由于采用了特征点跟踪方法,在一定程度上有效的防止了虚拟物体在视觉上的抖动。     

The effects of augmented reality on students' academic achievement and motivation in a biology course

This study aimed to investigate the effects of augmented reality (AR) activities on students' academic achievement and motivation in a biology course. For this purpose, a mixed study was conducted, and a pretest and posttest control group model was used. In addition, the opinions of the experimental group students and the teacher about the AR activities were taken, and classroom observations were made during the study. The study group consisted of 40 (22 female and 18 male) ninth‐grade biology course students. The control group followed the biology course programme, whereas the experimental group students conducted AR activities in addition to the course programme using tablets. Consequently, it was found that the motivation of the students in the experimental group increased more than that of the students in the control group. However, no significant difference was found between the academic achievement scores of the groups. The teacher and the students stated that AR activities might be effective in increasing course success and motivation.     

增强现实在儿童教育领域中的应用研究

增强现实是将真实环境和虚拟物体实时地叠加到同一个画面或空间,增强现实技术应用到儿童教育领域可以增加教育的趣味性,丰富教育内容,具有对儿童的吸引力,可以达到寓教于乐的目的。文章围绕增强现实的概念,研究了增强现实在儿童教育领域中的应用形式,并通过市场上的具体产品对每种应用形式进行了说明。从实例出发对增强现实在儿童教育领域的具体实现方式进行了探讨,最后以教育游戏为例说明了增强现实儿童教育类产品的设计过程。     

基于增强现实的制造数据记录系统设计与实现

针对传统制造业数字化水平不高的问题,提出了基于增强现实的生产数据记录系统;分析了车间数字化转型的软件架构需求,应用了 RESTful风格的前后端分离软件架构,将系统数据库和前端应用解耦,实现了基于HTTP协议的网络通讯;通过包含BLSTM的深度学习算法,对设备仪表图像进行检测识别,实现了制造过程关键生产数据智能化获取;通过对生产流程的分析和多维信息之间的联系,建立了基于增强现实的引导式生产数据记录应用;生产实践证明,系统能够实现生产任务的引导和过程数据的记录,工人工作效率提高,系统响应迅速,有利于车间生产过程的数字化转型.     

增强现实诱导维修进程识别策略

针对传统的增强现实维修系统不能有效对维修状态进行感知和判断的问题进行了研究,提出了一种基于概率神经网络（probabilistic neural network, PNN）的维修进程识别的策略。该策略将关注的焦点由维修对象本身转移到附近的已拆卸零件放置区域,利用曲波变换生成已拆卸零件边缘图像,然后生成Hu不变矩特征值,再将特征值作为PNN神经网络的输入进行进程零件的分类识别,从而得到当前的维修进程。实验表明,该策略下识别的准确度明显高于图像匹配方法与曲波不变矩方法,为场景感知提供了新的思路和解决方案。     

A mixed methods assessment of students' flow experiences during a mobile augmented reality science game

Current studies have reported that secondary students are highly engaged while playing mobile augmented reality (AR) learning games. Some researchers have posited that players' engagement may indicate a flow experience, but no research results have confirmed this hypothesis with vision‐based AR learning games. This study investigated factors related to students' engagement – as characterized by flow theory – during a collaborative AR, forensic science mystery game using mobile devices. School Scene Investigators: The Case of the Stolen Score Sheets is a vision‐based AR game played inside the school environment with Quick Response codes. A mixed methods approach was employed with 68 urban middle school students. Data sources included pre‐ and post‐surveys, field observations and group interviews. Results showed that neither gender nor interest in science was an important predictor of variability in flow experience. Gaming attitude uniquely predicted 23% of the variance in flow experience. Student flow experience features included a flash of intensity, a sense of discovery and the desire for higher performance. The findings demonstrated a potential for mobile AR science games to increase science interest and help students learn collaboration skills. Implications for future research concerning mobile AR science games are discussed.     

A method to measure the uniformity of the virtual image distance in an augmented reality or virtual reality device

The virtual image distance in an augmented reality (AR) or virtual reality (VR) device is an important factor in determining its performance. In this paper, a method for measuring the virtual image distance and its uniformity is proposed. The setup for measurement consists of a two-dimensional spatial sensor array on the translational stage and a pinhole array plate placed in front of the AR or VR device. As the distance between the pinhole plate and the two-dimensional spatial sensor array were changed, the positions of the rays through each pinhole were measured by a two-dimensional spatial sensor array. The ray trajectories through each pinhole were obtained by fitting these positions to straight lines. The relative distances between these ray trajectories were calculated with respect to the distance from the pinhole plate. This method is effective for measuring the uniformity, such as the azimuthal dependence of the virtual image distance or the dependence of the virtual image distance on the distance from the optical axis of the VR lens.     

Efficient lookup table based camera pose estimation for augmented reality

Until now, exising camera pose estimation methods for the widely used square marker‐based augmented reality (AR) are either highly sensitive to noise or much time consuming, and developers have to work hard to find the proper trade‐off between computational speed and quality in mobile AR applications where computational resources are limited. The major difficulty is that only the four corner points of the square AR marker are available, and no redundant point correspondences can be used for a stable estimation. To solve this problem, an efficient lookup table (LUT)‐based non‐iterative solution is presented in this paper that achieves high stability in the presence of noise better than the most robust and accurate iterative solutions in the field, with the same level of accuracy and a much lower computational complexity. Our central idea consists of extracting a key parameter β from the camera pose and creating a LUT for β by taking the symmetrical structure of the square marker into account, thereby exploiting additional information. Copyright © 2011 John Wiley & Sons, Ltd.     

Real‐time recognition and tracking for augmented reality books

An augmented reality book (AR book) is an application in which such multimedia elements as virtual 3D objects, movie clips, or sound clips are augmented to a conventional book using augmented reality technology. It can provide better understanding about the contents and visual impressions for users. For AR books, this paper presents a markerless tracking method, which recognizes and tracks a large number of pages in real‐time, even on PCs with low computation power. For fast recognition with respect to a large number of pages, we propose a generic randomized forest that is an extension of a randomized forest. In addition, we define the spatial locality of the subregions in an image to resolve the problem of a dropping recognition rate under a complex background. For tracking with minimal jittering, we also propose the adaptive keyframe‐based tracking method, which automatically updates the current frame as a keyframe when it describes the page better than the existing one. Copyright © 2011 John Wiley & Sons, Ltd.     

增强现实中基于自然特征的实时跟踪方法

在增强现实系统的复杂场景中,对目标的实时跟踪受到场景中诸多因素的制约,导致实时跟踪方法效率低且不准确,为此提出一种基于自然特征的实时跟踪方法。设计了一种螺旋分割模型,对捕获的图像进行螺旋分割,利用SURF算法在分割子块中提取特征点,并进行匹配。在对目标进行跟踪定位时,利用前一帧来预测当前帧目标出现的位置,以减少SURF算法的扫描区域,加速系统运算效率。实验中分别对场景光线强弱、视点和仿射变化以及目标被部分遮挡等不同情况进行测试,该方法均表现出较高的跟踪效率。     

A survey of mobile and wireless technologies for augmented reality systems

Recent advances in hardware and software for mobile computing have enabled a new breed of mobile augmented reality (AR) systems and applications. A new breed of computing called ‘augmented ubiquitous computing’ has resulted from the convergence of wearable computing, wireless networking, and mobile AR interfaces. In this paper, we provide a survey of different mobile and wireless technologies and how they have impact AR. Our goal is to place them into different categories so that it becomes easier to understand the state of art and to help identify new directions of research. Copyright © 2008 John Wiley & Sons, Ltd.     

The integration of optical and magnetic tracking for multi-user augmented reality

Multi-user augmented reality systems are especially dependent on precise registration. In this paper, we present a hybrid tracking system that combines optical and magnetic tracking. The magnetic tracking is used to give a robust estimate of position and orientation which then can be refined in realtime by optical tracking. The system is more precise than a magnetic tracker and both faster and more reliable than an optical tracker.     

面向移动增强现实的实时深度学习目标检测方法综述

移动增强现实(AR)借助智能移动终端将虚拟信息和真实世界进行实时融合,能否实时准确地对 环境中需要增强的物体进行目标检测直接决定了系统的性能。随着深度学习的快速发展,近年来出现了大量的 基于深度学习的目标检测方法。由于存在移动增强设备计算能力有限、能耗大、模型尺寸大以及卸载任务到边 缘云端的网络延迟严重等问题,将深度学习方法应用于移动 AR 的目标检测是一项具有挑战性的问题。首先从 Two stage 和 One stage 的 2 方面对目前深度学习目标检测算法进行综述;然后对面向移动 AR 的目标检测系统 架构进行归纳分类,分析了基于本地端、云端或边缘端和协作式的移动 AR 目标检测系统并总结了各自的优势 和局限性;最后对移动 AR 中目标检测亟待解决的问题和未来发展方向进行了展望和预测。     

Nonoverlapped view management for augmented reality by tabletop projection

Augmented reality (AR) by a projector allows for the easy association of information by labeling the objects. When a projector is installed above a workspace and pointed downward, supportive information can be presented; however, the label will be deformed if the object is nonplanar. Also, a label might be projected in a region where it is hidden by the object, i.e., a blind area. In this paper, we propose a view management technique to allow interpretation by improving the legibility of the information. We propose the nonoverlapped gradient descent (NGD) method, which determines the position of a newly added label by avoiding overlap with the surrounding labels and linkage lines. The issues of presenting in a shadow or blind area are also addressed by estimating these areas based on the approximation of objects as a simple solid. The results of an experiment show that the visibility of the labels was improved by using this method.     

ARCosmetics: a real-time augmented reality cosmetics try-on system

A virtual cosmetics try-on system provides a realistic try-on experience for consumers and helps them efficiently choose suitable cosmetics. In this article, we propose a real-time augmented reality virtual cosmetics try-on system for smartphones (ARCosmetics), taking speed, accuracy, and stability into consideration at each step to ensure a better user experience. A novel and very fast face tracking method utilizes the face detection box and the average position of facial landmarks to estimate the faces in continuous frames. A dynamic weight Wing loss is introduced to assign a dynamic weight to every landmark by the estimated error during training. It balances the attention between small, medium, and large range error and thus increases the accuracy and robustness. We also designed a weighted average method to utilize the information of the adjacent frame for landmark refinement, guaranteeing the stability of the generated landmarks. Extensive experiments conducted on a large 106-point facial landmark dataset and the 300-VW dataset demonstrate the superior performance of the proposed method compared to other state-of-the-art methods. We also conducted user satisfaction studies further to verify the efficiency and effectiveness of our ARCosmetics system.     

Enhancing augmented reality with cognitive and knowledge perspectives: a case study in museum exhibitions

ABSTRACT

In this paper, we present our results related to the definition of a methodology that combines augmented reality (AR) with semantic techniques for the creation of digital stories associated with museum exhibitions. In contrast to traditional AR approaches, we augment real-world elements by supplementing contents of a museum exhibition with additional inputs that provide new and different meanings. In this way we augment a cultural resource with respect to both its presentation and meaning. The methodology is framed in the cultural re-mediation theory and is grounded on a set of ontologies aimed at modelling a cultural resource and correlating it with external multimedia objects and resources. To provide an easy tool for the creation of museum narratives, the methodology makes use of a set of recognised practices widely adopted by museum curators that have been formalised through inference rules. The defined methodology has been experimented in a scenario related to Flemish paintings to validate the augmentation of cultural objects with two different approaches, the first basing on similarities and the second on dissimilarities.     

Multi-sensor based real-time 6-DoF pose tracking for wearable augmented reality

Wearable augmented reality (WAR) combines a live view of a real scene with computer-generated graphic on resource-limited platforms. One of the crucial technologies for WAR is a real-time 6-DoF pose tracking, facilitating registration of virtual components within in a real scene. Generally, artificial markers are typically applied to provide pose tracking for WAR applications. However, these marker-based methods suffer from marker occlusions or large viewpoint changes. Thus, a multi-sensor based tracking approach is applied in this paper, and it can perform real-time 6-DoF pose tracking with real-time scale estimation for WAR on a consumer smartphone. By combining a wide-angle monocular camera and an inertial sensor, a more robust 6-DoF motion tracking is demonstrated with the mutual compensations of the heterogeneous sensors. Moreover, with the help of the depth sensor, the scale initialization of the monocular tracking is addressed, where the initial scale is propagated within the subsequent sensor-fusion process, alleviating the scale drift in traditional monocular tracking approaches. In addition, a sliding-window based Kalman filter framework is used to provide a low jitter pose tracking for WAR. Finally, experiments are carried out to demonstrate the feasibility and robustness of the proposed tracking method for WAR applications.     

面向增强现实的多传感器组合位姿注册算法

持续稳定的准确注册是构建增强现实系统的关键,为提高跟踪注册的稳定性和精度,提出了一种基于互补滤波(CF)和无迹卡尔曼滤波(UKF)的多传感器融合注册方案.该算法采用互补滤波器融合陀螺仪、加速度计和地磁感应计数据估计摄像头姿态;在处理视觉图像时,结合惯性姿态数据进行图像特征匹配;利用UKF融合视觉和惯性数据进行摄像头位置估计.实验表明:该算法在跟踪稳定性、精度、效率和抗干扰能力均优于传统的基于扩展卡尔曼滤波(EKF)的融合算法.