碰撞检测算法的探讨

在视景仿真和3d游戏设计中,碰撞检测是必不可少的一部分。通过对碰撞检测算法的现状的研究,在几种碰撞检测算法的基础上,提出了一种经过改进的用于判断三维空间中视点或运动物体与场景的碰撞检测算法。     

基于帧亮度补偿和融合的校园夜间视频增强算法

本文研究了夜间校园视频的增强算法,采用帧亮度的补偿和融合算法。具体作法如下：(1)利用不同时间段白天帧与当前夜间帧背景亮度的比例,采取亮度参数调整的补偿方式对当前夜间视频背景进行补偿;(2)提出一种基于运动物体移动区域融合和差分的算法,对视频中的运动物体进行增强。本文基于亮度融合补偿的算法,较原始校园夜间视频,亮度、对比度和熵都得到了增强。     

三种用于视觉感知系统的算法比较

视觉感知系统的主要功能是对运动物体或目标进行检测和识别,达到某种特定目标的系统,它可以广泛的应用于校园、交通、家庭等方面。软件算法的设计与实现是视觉感知系统的灵魂,适合系统的算法不公可以对图像数据的压缩、去噪、特征提取以及大量图像模式识别,还能够克服了传统算法的复杂度高,方程求解方法单一、求解速度慢等问题。本文针对研究过程中所使用的三种算法进行比较,从而推动视觉感知系统中算法研究的开展。     

基于OPENCV平台的运动物体跟踪与轨迹生成研究

在比赛项目中,对运动员进行跟踪和分析,精确计算运动员的体能消耗和状态是十分必要的。一个新兴的交叉学科SportsIT,就是利用先进的计算机图形图像技术来分析各种比赛时运动员状态。在此背景下,利用OPENCV平台,实现运动物体的实时跟踪,生成轨迹和长度。实现了对艺术体操运动进行识别和追踪,生成运动轨迹。首先采用camshift方法进行跟踪,当遇到相似的背景导致跟踪失败时,采用帧间差分算法对运动物体再次识别,在出现多个候选运动目标中挑选出距离跟踪失败坐标点最近的运动目标,找回跟踪物体。     

静止背景下运动检测的像素线阵分割算法在视频监控中的应用

运动识别和检测在数字视频监控系统中是关键环节。本文提出了一种摄像机作为监控前端,静止背景下运动物体的检测算法。相对于传统的关键桢全画面像素做差算法,它进行了简化和改进,将监控画面进行了线阵处理和划分,只针对特定的几条关键线阵像素进行对比计算。在不影响运动检测准确度的前提下,极大缩短了程序的计算时间,提高了系统工作效率。     

我对相对论之“弯曲空间”的探索

正前言广泛的宇宙空间,分布着无数的运动天体,它们分级组成了各种运动体系,虽然都在旋转运动,强大的离心力没有使众多天体四散开来,牛顿通过相应的探索,认为天体间存在相互吸引作用,以此提出了万有引力理论,并推导计算出了万有引力定律,这已经成为地球人类科学探索的共识。1913年,爱因斯坦提出了引力场的相对论理论,而这个理论不同于牛顿的引力论,它认为,物体间不存在真正的引力,它把引力场归结为物体周围的时空弯曲,把物体     

基于J2ME平台的手机远程监控系统

本系统利用互联网和移动通信网将服务器端和手机端有机地结合起来。采用Aforge．net框架技术实现多路监控功能,采用基于运动估计的运动物体监测算法进行运动物体识别,采用H．264编码算法进行视频压缩,采用Base64编码解码算法和TCP、UDP协议进行图像处理与传输。本系统可以用于家庭远程监控、医院看护病人、店铺仓库实时监测、幼儿园小孩的探视等。     

一种基于背景剪除的视频检测方法

文章主要针对视频监控系统中滞留物体和遗失物体的侦测问题,提出了一种实时的监测方法。该方法主要包括以下步骤:首先,利用背景剪除算法进行目标物体的分割;然后,将提取目标划分为动态或静态物体;最后,采用一种决策模型计算所发生事件的置信度,并且在置信度偏离设定阈值时自动触发警报。实验结果验证文章算法有效性。     

基于区域选择的视频分割

本文提出了一种基于区域选择的视频运动对象分割方法。本方法先以一种简便实用的空间区域分割方法入手,通过运动信息和时空能量模型对所得到的区域进行多重选择,最后通过一些后处理技术得到了准确的分割对象。实验证明本算法具有较好的鲁棒性。     

一物一时空——无需暗物质与暗能量

认为每个物体都拥有其时空体系,任何地方的时空体系是宇宙中所有物体时空体系于该处的综合。星系的时空体系由于受其本身的旋转运动影响而作相应的但并非处处一致的旋转,导致各星球实际的运动速度远小于我们的观察。因此对螺旋星系旋转速度的解释无需暗物质。随着宇宙的膨胀,各星系受其他星系的影响越弱和其独立性越强,实际上速度不变的星系运动体现加速运动的现象。当这种现象超过万有引力的影响时宇宙显现加速膨胀现象。而这也无需暗能量。     

基于多传感器信息融合的单交叉口信号控制

本文介绍了基于多传感器信息融合技术的单交叉口信号控制方法。首先利用多传感器系统对交通流量进行采集，然后用加权平均的数据融合算法将交通流量数据进行处理，得到更可靠的数据，最后将这些数据作为确定交通信号控制参数的依据，运用公式算出控制参数。进而实现了对单交叉口信号的控制。相对于传统的基于单一传感器信号控制而言，谈方法具有信息的完整性、统一性、多样性和容错性等优点。     

Machine learning-based human-robot interaction in ITS

In the last few years, intelligent transport systems (ITS) have drawn growing attention, and these applications would have a clear and more comfortable experience for transportation. ITS provides applications with a chance to address the future condition on the route beforehand. The major issues in ITS to accomplish a precise and effective traffic flow prediction system are essential. Therefore, in this paper, a machine learning-assisted intelligent traffic monitoring system (ML-ITMS) has proposed improving transportation protection and reliability to tackle several challenges. The suggested ML-ITMS uses mathematical models to improve the accuracy estimation of traffic flow and nonparametric processes. The Machine Learning-based (ML) method is one of the best-known methods of nonparametric. It requires less prior information about connections between various traffic patterns, minor estimation limitations, and better suitability of nonlinear traffic data features. Human-Robot Interaction (HRI) helps resolve crucial issues concurrently on both the customers and service supplier levels at both ends of the transport system. Thus the experimental results show the proposed ML-ITMS to enhance traffic monitoring to 98.6% and better traffic flow prediction systems than other existing methods.     

Model studies of the pressure and flow pulses in a viscoelastic arterial conduit

In certain arteries the flow rate of blood can now be quantified by a non-invasive technique based on a newly developed ultrasound velocity profile meter. Clinical applications of this technique indicate that a reliable mathematical model of the circulatory system would facilitate the identification of pathologic patterns of flow rate and the corresponding possible causes. A relatively simple law for the viscoelastic behavior of arterial conduits is hypothesized and its influence on the phasis variations of pressure and flow examined with the aid of the method of characteristics. To test the feasibility of this model, its predictions of the attenuation and dispersion of small sinusoidal pressure waves are compared with data obtained in animal experiments. The results show good agreement and verify the significance of taper in reducing the attenuation of waves propagating towards the periphery and conversely increasing the damping of waves moving towards the heart. Beside this the natural pressure and flow pulses generated by the heart appear to be attenuated in a realistic manner: they no longer exhibit the somewhat exaggerated peaking predicted by the theoretical model when the viscoelasticity of the vessel wall is neglected.     

DNS tunnels detection via DNS-images

DNS tunneling is a typical attack adopted by cyber-criminals to compromise victims’ devices, steal sensitive data, or perform fraudulent actions against third parties without their knowledge. The fraudulent traffic is encapsulated into DNS queries to evade intrusion detection. Unfortunately, traditional defense systems based on Deep Packet Inspection cannot always detect such traffic. As a result, DNS tunneling is one problem that has worried the cybersecurity community over the past decade.In this paper, we propose a robust and reliable Deep Learning-based DNS tunneling detection approach to mine valuable insight from DNS query payloads. More precisely, several features are first extracted by the DNS flow, and then they are arranged as bi-dimensional images. A Convolutional Neural Network is used to automatically and adaptively learn spatial hierarchies of features to be used in a fully connected neural network for traffic classification. The proposed approach may result in an extremely interesting task in predictive security approaches to attack detection.The effectiveness of the proposal is evaluated in several experiments using a real-world traffic dataset. The obtained results show that our approach achieves 99.99% of accuracy and performs better than state-of-the-art solutions.     

我国智能交通系统专利状况分析

专利信息能够从一个侧面反映技术发展的趋势变化。通过中国专利检索系统(CPRS)中公开收录的专利数据,对智能交通系统主要是城市道路智能交通系统中的交通信息采集技术、交通信息处理技术、交通管理技术和交通信息服务技术等4个重点领域的专利申请情况分别进行研究。文章通过对专利申请态势、国内技术分布和国外来华专利布局进行对比分析,发现ITS领域存在的专利机会和风险,提出技术布局策略和发展建议。     

On improving the regional transportation efficiency based on federated learning

In recent years, regional traffic congestion has become increasingly frequent, which seriously affects the safety and efficiency of urban vehicles. Therefore, traffic flow prediction methods based on artificial intelligence are widely used in traffic management. However, the existing traffic flow prediction methods need to collect raw data, which involves risks of vehicle privacy leakage. Federated learning, which shares model updates without exchanging local data, has gradually become an effective solution to achieve privacy protection. A federated learning traffic flow prediction model for regional transportation systems is proposed in this paper. At the same time, due to the emergence of highly intelligent automatic driving vehicles, a vehicle scheduling system, which can control the departure and routes of vehicles in urban regions is developed in the proposed approach. A road weight measurement method combined with real time traffic information is introduced to optimize the driving routes of vehicles to reduce the average travel time. Additionally, departure strategy, is another factor that has a great influence on traffic efficiency, but is usually ignored in the past, and is also carefully compared and studied in this paper. The numerical results illustrate that the proposed schemes can effectively improve the privacy protection ability of model updates, reduce the scheduling completion time by using the traffic flow prediction model, and realize the comparative research between departure strategies, which provides a reference for developing a safe and efficient regional transportation system.     

微观交通仿真跟驰模型影响因子选择研究

在已有的车辆跟驰微观仿真模型中,多数模型的构建是基于对交通现象的感性认识,有些模型对数据进行了统计分析,却未直接涉及到对输入变量选择的研究。本文运用因子分析非线性多元统计方法榨取典型实验数据的有用信息从而寻求车辆跟驰模型的基本结构,寻求能够最大程度反映跟车信息的内生变量作为建立微观仿真模型的基础。     

SNSJam: Road traffic analysis and prediction by fusing data from multiple social networks

The increased popularity of micro-blogging applications together with the widespread of location-aware devices have resulted in the creation of large streams of geo-tagged data. Such data provides a great opportunity for researchers to explore event detection and prediction. In particular, road traffic detection and prediction are of great importance to various applications, i.e. Intelligent Transportation Systems. Current works proposed traffic jam detection from a single data source with a single language. However, for countries where the residents are speaking two, or more, languages and are interacting with more than one online social platform, single-language and single-source systems are insufficient to capture the necessary online information. Therefore, in this paper, we introduce SNSJam, an effective system to detect and predict road traffic jams using cross-lingual (English and Arabic) data collected from multiple dynamic sources, such as Twitter and Instagram. SNSJam classifier not only detect traffic events, but also identifies the causes of traffic jams. To identify the location of a traffic event, a Location Recognizer is developed that extracts locations from text and GPS of the post. Additionally, the Location Recognizer supports user-defined locations, which are common names among people. Our experiments show that by combining Arabic and English data streams, the accuracies of traffic events detection and prediction are significantly improved as compared with that of the individual languages. Additionally, combining data streams from multiple sources (Twitter and Instagram) further improved the accuracies of event detection and prediction over any individual source. A visualization interface was developed to show the detected spatio-temporal traffic events on a dynamic map. The detection and prediction results are validated against ground truth data obtained from the concerned authorities in the UAE.     

关联挖掘研究综述

数据挖掘是一种重要的数据分析方法,旨在发现庞大的数据中隐藏着的、先前未知的并潜在有用的模式和信息,以帮助人们正确理解和认识数据,进行科学决策。关联挖掘是数据挖掘中研究最早也是最活跃的领域,其中,频繁模式挖掘是关联挖掘的核心和基础。对关联挖掘算法的研究和发展进行综述,分析挖掘算法面临的主要挑战,概括最新研究进展。     

沈阳市交通生态足迹的时间序列分析

对沈阳市交通足迹总体形势、各种交通工具的生态效率变化进行了较为详细的分析,研究结果表明：①沈阳市1995年～2004年交通足迹连年增加,且其增长率高于客运量,环境恶化速度快于经济增长速度;②总的看,沈阳市交通的生态效率有所提高,但近几年出现下降趋势,分析其主要原因在于对客运量贡献最大的公共交通生态效率这期间出现了下降的趋势;③无论从总量上还是增长率,小轿车对城市交通足迹均有较显著的影响,是对交通足迹贡献最大的交通工具。由于交通生态效率最低、环境压力指数远高于其他交通工具,小轿车对沈阳市交通环境压力的影响和冲击最显著（其他交通工具相对较小）。通过沈阳市地铁工程运营前后情景预测和对比可知,地铁工程将能缓解沈阳市未来交通环境的压力。