Contour-based focus of attention mechanism to speed up object detection and labeling in 3D scenes

In this paper, a contour-based focus of attention approach is presented. Fast to compute, contour based features are extracted from 3D scenes and matched to model parts of objects. Local reference frames associated with the features induce a translation and rotation, resulting in a vote being cast for the presence of the object in a certain position within the scene. In these positions, HoG features are extracted and SVM classification is applied. Detection results and computation times are compared to those corresponding to a sliding window approach.     

Selecting and assessing challenge problems

Abstract

Organisations conducting research programs often focus the work of their scientists and technologists on challenge problems (CPs). These challenges are designed to ensure that progress is measurable and relevant to the goals of the program sponsor. Generating and selecting pertinent CPs is difficult, as is assessing their value. We describe a method of generating and selecting CPs and its application in a highly collaborative, multi-organisation research program. Thirty-eight biologists, chemists, mathematicians and computer scientists across academic, commercial and government organisations generated and ranked their top choices from among 12 richly described candidate challenge problems. A ranked-choice voting formula was applied. Five CPs were highly scored; the remaining seven were distributed across a lower range of scores. The program sponsor subsequently directed researchers to address six CPs, including the elected five. Analysis of the rationales that participants offered for their CP rankings revealed four domain-independent dimensions of value: capability, speed, impact and synergy. These dimensions of value can help managers of interdisciplinary research programs systematically select a portfolio of CPs that will efficiently apply utilise resources towards program goals and facilitate measurement of scientific progress.     

Dust particle detection in traffic surveillance video using motion singularity analysis

Dust particle detection in video aims to automatically determine whether the video is degraded by dust particle or not. Dust particles are usually stuck on the camera lends and typically temporally static in the images of a video sequence captured from a dynamic scene. The moving objects in the scene can be occluded by the dusts; consequently, the motion information of moving objects tends to yield singularity. Motivated by this, a dust detection approach is proposed in this paper by exploiting motion singularity analysis in the video. First, the optical model of dust particle is theoretically studied in by simulating optical density of artifacts produced by dust particles. Then, the optical flow is exploited to perform motion singularity analysis for blind dust detection in the video without the need for ground truth dust-free video. More specifically, a singularity model of optical flow is proposed in this paper using the direction of the motion flow field, instead of the amplitude of the motion flow field. The proposed motion singularity model is further incorporated into a temporal voting mechanism to develop an automatic dust particle detection in the video. Experiments are conducted using both artificially-simulated dust-degraded video and real-world dust-degraded video to demonstrate that the proposed approach outperforms conventional approaches to achieve more accurate dust detection.     

Efficient image matching using weighted voting

Spectral decomposition subject to pairwise geometric constraints is one of the most successful image matching (correspondence establishment) methods which is widely used in image retrieval, recognition, registration, and stitching. When the number of candidate correspondences is large, the eigen-decomposition of the affinity matrix is time consuming and therefore is not suitable for real-time computer vision. To overcome the drawback, in this letter we propose to treat each candidate correspondence not only as a candidate but also as a voter. As a voter, it gives voting scores to other candidate correspondences. Based on the voting scores, the optimal correspondences are computed by simple addition and ranking operations. Experimental results on real-data demonstrate that the proposed method is more than one hundred times faster than the classical spectral method while does not decrease the matching accuracy.     

A model for the dc electrical behavior of bulk-barrier diodes

Contents  This paper presents an analytical model for the dc electrical behavior of bulk barrier diodes (BBD's). The proposed model extends previously published models, and includes analytical expressions for all significant quantities of the device dc performance, i.e. barrier height, current density and ideality factor, with respect to the technological parameters and the applied voltage in both bias conditions. The analytical results have been compared with those obtained using the 2-D device simulator S-PISCES, which takes into account the drift–diffusion theory, as well as a concentration and field dependent mobility, the Shockley–Read–Hall and Auger carrier recombination, and the band gab narrowing. Good agreement was obtained between theory and simulation. The device simulation played a very important role in best understanding BBD's behavior, because it could easily take into account parameters strongly affecting the behavior of BBD's, e.g. the free carrier presence in depletion layers, which was very difficult for the analytical model to include. Received: 15 January 2001     

磁耦合元胞自动机逻辑器件的形状可重配置结构

磁耦合元胞自动机逻辑器件(即纳磁体逻辑器件)是后CMOS时代的一种极具潜力的新技术,具有无引线集成、极低功耗和天然非易失性等优点.纳磁体逻辑器件由纳米级单畴磁体构成,而磁体的形状是其一个重要的器件特征参数.本文研究了不同特殊形状纳磁体的转换特性,获得了改变特殊形状器件状态的时钟场值.提出了基于不同尺寸特殊形状纳磁体的可重配置择多逻辑门,采用OOMMF软件验证了形状择多逻辑门的输入可重配置性,得到了顺序配置不同输入组合所需的时钟场.该可重配置门结构的提出为磁性可编程逻辑计算电路的实现奠定了重要的理论基础.     

非交互式可公开认证的电子选举策略

基于椭圆曲线上离散对数的难解问题提出了一种非交互式公开可认证协议,设计了非交互式零知识证明协议,用这两个协议作为基本工具构造出一个简单且有效的非交互式公开可认证的电子选举策略,任何人对投票者和计票者的数据都能进行认证．该策略可防欺诈,适用于小规模的网络选举．     

影响最大化问题中基于K-truss的投票改进算法

在社交网络的影响最大化（IM）问题中,近似算法通过大量的Monte-Carlo模拟计算节点集的影响范围,导致时间复杂度提高,而多数启发式算法在具有不同拓扑结构的图上存在稳定性较差的问题。提出基于K-truss的改进投票算法TrussVote。在投票阶段,通过引入K-truss的相关理论及算法定义节点的有效投票能力,用于表示节点对其不同邻居的投票倾向,同时在计算得票分数时考虑边的传播概率,提高解决IM问题的效率。在每轮投票结束后,将得票分数最高的节点选为种子节点。在更新阶段,结合节点间的相似性指标定义衰减因子,以有效区分邻居节点投票能力的弱化程度。此外,基于IC模型下的原始传播结果,提出传播差异作为传播范围的等价分析指标。在不同规模真实网络数据集上的实验结果表明,相比RNR、VoteRank++等算法,该算法不仅能有效降低时间复杂度,而且可在最短的时间内感染更多的节点,具有广泛的影响范围。     

Nonlinear diffusion for orientation estimation

This letter presents an image orientation estimation method which is based on a combination of two techniques： quadrature filtering and nonlinear diffusion. The quadrature filters are used to get the orientation tensors for edges, then the orientation tensors are smoothed through nonlinear diffusion. Experimental resuits and analysis show the robustness of the proposed method.     

基于兴趣点的图像检索

在基于内容的图像检索中,往往使用颜色、纹理以及形状的全局特征来描述图像,然而全局特征不能描述图像的细节,丢失了图像的空间信息。文章利用兴趣点来灵活描述图像的局部信息,提取兴趣点周围的颜色矩作为局部特征,通过兴趣点的匹配和带权投票来进行相似度量,几何哈希技术的使用增强了兴趣点间的正确匹配。实验证明了这种方法的有效性,具有旋转、平移和部分的尺度不变性。