平面单应性矩阵求解的CUDA并行实现

针对平面单应性矩阵实时求解的需求,提出了RANSAC单应性算法在GPU上并行实现的方法。首先计算出理论上最优的迭代次数;然后根据迭代间数据的独立性将每次迭代看成一个独立的任务映射到CUDA线程上。实验表明,对于较高分辨率的图像,GT240M平台上平均加速比达到了8。     

单应性矩阵自适应估计方法

如何从初始匹配点集中估计出精确的单应性矩阵,有效地剔除误匹配,一直以来都是视觉领域研究的重点和难点,也是实际相关技术应用中最为关键的一步。通过将特征点对相似度概念应用于LMedS的样本选取过程,提出了一种新的单应性矩阵自适应的估计方法。区别于传统LMeds方法从无序匹配点集中随机选取样本的过程,该方法首先以点对间的相似度对整个初始匹配点进行降序排列,然后从前往后依次选取样本。实验结果表明,与LMedS相比,该方法估计出的单应性矩阵更精确、鲁棒,效率更高（得到最佳模型所需的迭代次数仅约为LMedS的1/5）,同时弥补了RANSAC及其改进方法需预先设置距离偏差阈值的不足。     

Personness estimation for real-time human detection on mobile devices

One aim of detection proposal methods is to reduce the computational overhead of object detection. However, most of the existing methods have significant computational overhead for real-time detection on mobile devices. A fast and accurate proposal method of human detection called personness estimation is proposed, which facilitates real-time human detection on mobile devices and can be effectively integrated into part-based detection, achieving high detection performance at a low computational cost. Our work is based on two observations: (i) normed gradients, which are designed for generic objectness estimation, effectively generate high-quality detection proposals for the person category; (ii) fusing the normed gradients with color attributes improves the performance of proposal generation for human detection. Thus, the candidate windows generated by the personness estimation will very likely contain human subjects. The human detection is then guided by the candidate windows, offering high detection performance even when the detection task terminates prior to completion. This interruptible detection scheme, called anytime detection, enables real-time human detection on mobile devices. Furthermore, we introduce a new evaluation methodology called time-recall curves to practically evaluate our approach. The applicability of our proposed method is demonstrated in extensive experiments on a publicly available dataset and a real mobile device, facilitating acquisition and enhancement of portrait photographs (e.g. selfie) on widespread mobile platforms.     

海面图像单应的估算及数据归一化方法

根据海面图像的单应进行距离估算对于海洋工程具有重要意义。结合导管架入水参数观测问题,提出一种海面图像单应的估算方法。该方法以导管架上表面为参考平面,依据其单应矩阵及它与海平面之间的夹角计算出海面图像的单应。重点介绍了根据特征直线计算平面单应矩阵时的数据归一化方法。通过实验分析了这种归一化方法对平面远处距离估算的影响,并根据现场图片中的距离估算误差说明了在实际应用中的效果。该方法可以应用到多种海洋观测当中。     

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。     

基于改进RANSAC算法的单应矩阵鲁棒估计方法

单应矩阵的鲁棒性和精度直接决定了其应用效果,如何利用RANSAC算法估计出鲁棒、精确的单应矩阵,仍是一个有待研究的热点问题。针对传统RANSAC算法迭代次数多、运行时间长、单应矩阵估计精度较低的问题,在SIFT特征匹配算法的基础上,从剔除样本集中不符合图像几何特性的部分外点、快速舍弃不合理单应矩阵和迭代精炼单应矩阵等方面对RANSAC算法进行改进,提出一种基于改进RANSAC算法的单应矩阵估计方法,提高了单应矩阵估计的精度和效率。实验结果表明,该方法有效解决了传统RANSAC算法存在的问题,能够快速、精确估计单应矩阵。另外,对于不同视角和大小的图像,该方法均具有较好的鲁棒性。     

HEASK: Robust homography estimation based on appearance similarity and keypoint correspondences

Accurate homography estimation is a classical problem with high industrial value and has been investigated extensively. Most previous homography estimation methods used either appearance similarity or keypoint correspondences to find their best estimation. In this paper, a novel algorithm is proposed which integrates the advantages of the pixel-based and the feature-based homography estimation approaches. We elegantly combined the probability models of appearance similarity and keypoint correspondences in a Maximum Likelihood framework, which is named as Homography Estimation based on Appearance Similarity and Keypoint correspondences (HEASK). In the model of keypoint correspondences, the distribution of inlier location error is represented by a Laplacian distribution, which outperforms the previous Gaussian distribution in characterizing heavy-tailed distributions. And in the model of appearance similarity, the enhanced correlation coefficient (ECC) is adopted for describing image similarity, and the distribution of ECC is studied and parametrically formulated using a truncated exponential distribution. The proposed model is solved based on an improved framework of random sample consensus (RANSAC). Several simulations summarize the performance of the proposed approach in objective quality measurement, subjective visual quality, and computation time. The experimental results demonstrate that the proposed approach can achieve more accurate homography estimation under different image transformation degrees and with different ratios of inlier keypoint correspondences as compared to the state-of-the-art works.     

Modelling on mobile devices

Software and Systems Modeling - Modelling is central to many disciplines in engineering and the natural and social sciences. A wide variety of modelling languages and tools have been proposed along...     

An economics-based negotiation scheme among mobile devices in mobile grid

In this paper, we propose an economics-based distributed negotiation scheme among mobile devices in mobile grid. In our model, there are energy negotiation and transactions between buyer devices and seller devices. Dynamic allocation of energy resources in mobile grid is performed through online transactions within markets. Mobile devices can be sellers and buyers that use optimization algorithms to maximize predefined utility functions during their transactions. Seller device agents sell the underlying energy resources of the mobile device. Buyer device agent makes buying decisions within the budget constraints to acquire energy resources. An economics-based negotiation algorithm among mobile devices is proposed. The proposed algorithm decomposes mobile grid system optimization problem into a sequence of two sub-problems. In the simulation, the performance evaluation of economics-based negotiation algorithm is evaluated.     

Managing context information in mobile devices

We present a uniform mobile terminal software framework that provides systematic methods for acquiring and processing useful context information from a user's surroundings and giving it to applications. The framework simplifies the development of context-aware mobile applications by managing raw context information gained from multiple sources and enabling higher-level context abstractions.     

Speech recognition for mobile devices

This article presents an overview of different approaches for providing automatic speech recognition (ASR) technology to mobile users. Three principal system architectures with respect to the employment of a wireless communication link are analyzed: Embedded Speech Recognition Systems, Network Speech Recognition (NSR) and Distributed Speech Recognition (DSR). An overview of the solutions having been standardized so far as well as a critical analysis of the latest developments in the field of speech recognition in mobile environments is given. Open issues, pros and cons of the different methodologies and techniques are highlighted. Special emphasis is placed on the constraints and limitations ASR applications are confronted with under different architectures.     

Visualizing information on mobile devices

Visualization can make a wide range of mobile applications more intuitive and productive. The mobility context and technical limitations such as small screen size make it impossible to simply port visualization applications from desktop computers to mobile devices, but researchers are starting to address these challenges. From a purely technical point of view, building more sophisticated mobile visualizations become easier due to new, possibly standard, software APIs such as OpenGLES and increasingly powerful devices. Although ongoing improvements would not eliminate most device limitations or alter the mobility context, they make it easier to create and experiment with alternative approaches.     

支持移动设备接入Gnutella网络的代理架构研究

针对当前移动设备无法加入Gnutella网络实现文件共享网络的现状,提出一种移动代理Gnutella网络架构的设计方案。利用移动代理作为移动设备的代理加入Gnutella网络,帮助移动设备实现文件的共享功能。架构能有效地减少移动设备的信息流量,并支持移动设备在Gnutella网络中实现可移动性。     

Real-time facial animation on mobile devices

We present a performance-based facial animation system capable of running on mobile devices at real-time frame rates. A key component of our system is a novel regression algorithm that accurately infers the facial motion parameters from 2D video frames of an ordinary web camera. Compared with the state-of-the-art facial shape regression algorithm [1], which takes a two-step procedure to track facial animations (i.e., first regressing the 3D positions of facial landmarks, and then computing the head poses and expression coefficients), we directly regress the head poses and expression coefficients. This one-step approach greatly reduces the dimension of the regression target and significantly improves the tracking performance while preserving the tracking accuracy. We further propose to collect the training images of the user under different lighting environments, and make use of the data to learn a user-specific regressor, which can robustly handle lighting changes that frequently occur when using mobile devices.     

Energy-aware resource sharing with mobile devices

Ad hoc sharing of resources by offering remote services through an appropriate infrastructure enables new applications for mobile devices. However, the willingness of device owners to contribute resources to such applications remains low as long as they cannot control the amount of energy spent in sharing. In this paper, we present a framework for energy-aware resource sharing among mobile devices of various kinds that comprises (1) energy-aware strategies for selecting remote service providers and (2) a generic energy estimator for forecasting and accounting the energy consumption of a remote service call. To illustrate the benefit of (1), we show by simulation that the battery lifetime of devices running the framework can be extended up to 40% by service selection strategies that take into account the energy cost of a requested service compared to energy-unaware (random) service selection. For providing the energy-related input for service selection, we present (2) a generic estimator that can be customized easily for different hardware-platforms by solving a linear equation system with coefficients derived from benchmark measurements. We present a prototype-based case study for three different platforms, the Nokia N810, the HTC Touch Cruise and the Samsung Galaxy S showing that for all of them the estimation error is below 10% for 90% of the service calls. Furthermore, measurements conducted with a prototype implementation of the resource sharing framework show that battery lifetime can in fact be extended by energy-aware service selection strategies.     

Automatic form filling on mobile devices

Filling out forms for web based services on mobile devices is a very time consuming and frustrating task for users because of the limited text input capabilities. This is a critical bottleneck to obtaining a wide acceptance of such services, especially mobile commerce that often requires filling user data. We developed an architecture based on a local proxy on a mobile device and a lightweight algorithm for a comprehensive analysis of forms, which leads to the most probable user data to be filled in, driven by an initial rule set [Chie Noda, John Hamard, Enrico Rukzio, Alexander De Luca, Method and Apparatus for Automatic Form Filling on Mobile Devices, Patent. Publication number EP1777629, Publication date 2007-04-25]. We further discuss our implementation and the evaluation results for the algorithm as well as the usability of the prototype.