Tracking in a Dense Crowd Using Multiple Cameras

Tracking people in a dense crowd is a challenging problem for a single camera tracker due to occlusions and extensive motion that make human segmentation difficult. In this paper we suggest a method for simultaneously tracking all the people in a densely crowded scene using a set of cameras with overlapping fields of view. To overcome occlusions, the cameras are placed at a high elevation and only people’s heads are tracked. Head detection is still difficult since each foreground region may consist of multiple subjects. By combining data from several views, height information is extracted and used for head segmentation. The head tops, which are regarded as 2D patches at various heights, are detected by applying intensity correlation to aligned frames from the different cameras. The detected head tops are then tracked using common assumptions on motion direction and velocity. The method was tested on sequences in indoor and outdoor environments under challenging illumination conditions. It was successful in tracking up to 21 people walking in a small area (2.5 people per m²), in spite of severe and persistent occlusions.     

智能搜索算法教学软件的设计与开发

为提高人工智能导论课程的教学质量,协调好教与学的双边关系,结合教学实践,在Microsoft Visual Studio2005环境中用C++语言开发了智能搜索算法的教学软件,设计了A*算法、模拟退火算法和遗传算法的演示程序和验证程序,提供了这些算法的核心代码,方便学生开展各算法的自主实验设计。     

体验设计乐趣 增强环保意识——在初中美术设计课中渗透绿色设计理念的教学探究

当今,环境问题的日益突出,绿色设计越来越引起了人们的重视,已成为一种全新的设计理念。作为一名初中美术教师,应该将这一全新的理念通过初中美术设计课渗透到每个学生的头脑中,这对于他们了解现代设计,曾强环保意识显得尤为重要。文章中提出了几点在初中美术设计课中切实可行的做法,将绿色设计理念渗透到设计课教学的各个环节,旨在把环境教育寓于美术教学中,使学生曾强社会责任感,强化环保行为。     

面向集装箱字符识别的预处理算法

由于光照,油污,采集图像受天气影响等原因,使集装箱箱号图像背景复杂,给分割识别带来困难.为解决这些问题,主要研究集装箱箱号图像预处理算法.根据原始图像特点,先利用形态学腐蚀运算、膨胀运算滤除噪声,在此基础上运用简单统计法结合Prewitt边缘检测算子的方法对具有复杂背景的集装箱箱号图像二值化,使用基于特征值公式的集装箱箱号字符分割方法准确分割字符.试验结果表明,此方法较好完成对集装箱箱号原始图像的预处理.     

Design of a performance-oriented workplace e-learning system using ontology

E-learning is emerging as a popular learning approach utilized by many organizations. Despite the ever increasing practices of e-learning in the workplace, most e-learning applications fail to meet learners’ needs or serve organization’s quests for success. Significant gaps exist between organizational interests and individual needs when they come to e-learning, which make e-learning applications less goal-effective. To solve this problem, a performance-oriented approach is presented in this study. Key performance indicators (KPIs) are set up to clarify organizational training needs, and help learners establish rational learning objectives. In addition, ontology is used for constructing formal and machine-understandable conceptualization of the performance-oriented learning environment. Using this approach, a KPI-oriented learning ontology and prototype system have been developed and evaluated to demonstrate the effectiveness of the approach.     

Fire detection model in Tibet based on grey-fuzzy neural network algorithm

The fire signals are much weaker in low oxygen concentration and low pressure environment such as Tibet. Fire detectors which were calibrated in correlating standard conditions cannot work well in such condition. This paper presents a synthesis method of GM(1, 1) grey prediction model and adaptive neuro-fuzzy inference system (ANFIS) in advance to detect fire and to make it work in the environment. The theoretical analysis of the algorithm and experimental evaluation in Tibet are presented. In this process, the grey GM(1, 1) predict model can anticipate the development of fire signals without any assumption, thus allowing earlier fire alarm than traditional fire detection equipments, meanwhile, ANFIS can make sure the data processing more accurate to avoid false alarms. This work will supply useful suggestions with the fire detectors design in low ambient pressure and low oxygen concentration such as Tibet, etc.     

一种基于人工神经网络的快速超分辨率方法

图像的超分辨率是指利用一幅或者多幅的低分辨率图像,通过相应的算法来获得一幅对应的清晰的高分辨率图像.针对现有的基于学习的超分辨率方法低效率的问题,提出一种基于人工神经网络的快速超分辨率方法,该方法试图利用人工神经网络学习到高分辨率图像和低分辨率图像之间的函数关系,其理论基础来自于人工神经网络能够很好地求解流形学习中高维流形和低维流形之间的映射关系.     

基于抽象特征检测变形恶意代码

传统的恶意代码检测方法通常以固定的指令或字节序列这些具体特征作为检测依据,因此难以检测变形恶意代码.使用抽象特征是解决该问题的一个思路.本文针对恶意代码常用的变形技术,即等价指令替换、垃圾代码插入以及指令乱序进行研究.定义了一种抽象特征,同时提出了依据该抽象特征检测变形恶意代码的方法.最后,以典型变形病毒Win32.Evol为对象进行了实验,将该方法与其它方法进行了对比.实验结果验证了该方法的有效性.     

面向汽车零部件产业链云服务平台的采购订单整合技术

针对汽车零部件产业链供应商企业群的订单整合集成问题,提出了面向云服务平台订单整合的技术方案.在抽象出订单整合多级映射关系的基础上,建立了多层级订单映射树模型.采用弹性化的动态可配置接口,构建出面向汽车零部件产业链云服务平台的映射规则库,将复杂映射转换为直接映射.运用订单映射树的层级关系,采用映射整合算法,将来自不同整车厂的大批量异构订单整合为供应商企业群所需的零部件生产计划集.结果表明,运用多层级订单映射树模型能支撑面向汽车零部件产业链云服务平台订单整合的扩展应用.