Multi-target tracking on confidence maps: An application to people tracking

We propose a generic online multi-target track-before-detect (MT-TBD) that is applicable on confidence maps used as observations. The proposed tracker is based on particle filtering and automatically initializes tracks. The main novelty is the inclusion of the target ID in the particle state, enabling the algorithm to deal with unknown and large number of targets. To overcome the problem of mixing IDs of targets close to each other, we propose a probabilistic model of target birth and death based on a Markov Random Field (MRF) applied to the particle IDs. Each particle ID is managed using the information carried by neighboring particles. The assignment of the IDs to the targets is performed using Mean-Shift clustering and supported by a Gaussian Mixture Model. We also show that the computational complexity of MT-TBD is proportional only to the number of particles. To compare our method with recent state-of-the-art works, we include a postprocessing stage suited for multi-person tracking. We validate the method on real-world and crowded scenarios, and demonstrate its robustness in scenes presenting different perspective views and targets very close to each other.     

基于梯形模糊数的不确定性河道生态需水模型及其应用

将模糊数引入河道生态需水估算方法中,建立了模糊生态流速和模糊生态水力半径的概念。以抛物线型过水断面河道为例,在扩展原理的基础上,建立了流量与模糊生态流速、模糊生态水力半径的函数关系,提出了基于梯形模糊数的不确定性河道生态需水模型,设计了算法流程。以杜柯河壤塘站为例进行研究,计算并给出了其不确定性河道生态需水量的结果。最后利用Tennant法对所建模型的实用性进行了验证,并对计算结果的表达形式进行了分析。结果表明本文方法得到的结果更合理,效果更好。     

Design of a Rotary Ring APP Information Capturer for Sightseeing PlacemSpecialized Tourism Services for Sun-Moon Lake

The APP （Application） store at the Android market is very popular and attractive for most of current smart phone users. A rotary ring type of APP named as Loving SML （Loving Sun-Moon Lake--＂爱上日月谭＂） is an instant information capturer to capture the instant traffic tourism information （info） services and serve as an interactive device for user to know the instant traffic information of SML area where you may want to go. The tourism service is specialized on i3 travel, which is identified as innovation, intelligent, and interesting for all of the visitors coming from all over the world. The captured instant information is provided by the sightseeing cloud from SML-NSA （National Scenic Area） with the integration of infrastructure of VD （vehicle detector）, CMS or VMS （changeable （or variable） message sign）, CCTV （closed circuit television）, AVI （automatic vehicle identification）. The technique of AR （augmented reality） is also used to identify how many sparkling places in front of you that you may visit. One can easily know the road performance ahead from you before you plan a trip.     

基于多源信息融合的小电流接地系统故障选线方法研究

针对小电流接地系统故障选线难的问题,提出了一种基于多源信息融合的小电流接地系统故障选线方法。该方法以可能发生故障的线路集合、各线路故障特征集合和各线路故障特征规定的量域作为可拓融合的物元三要素,以故障角的大小为权重,把在小故障角下选线准确的能量选线法和大故障角下选线准确的小波包选线法有效融合,并结合重合闸技术实现了准确选线。仿真结果验证了该方法的有效性和合理性。     

可拓K近邻算法在数据聚类分析中的应用

针对区间值数据的数据聚类问题,根据可拓学关联函数的定义,提出可拓距离的概念来度量数据之间的距离,利用K近邻的思想,根据可拓距离的大小对数据集的目标属性进行投票选择进行分类,设计了可拓K近邻算法（Extension K Nearest Neighbor,EKNN）。最后利用UCI的两个基准数据集Iris植物样本数据和糖尿病数据库PIDD进行验证,首先通过免疫网络约简算法对条件属性进行最小属性约简,然后利用EKNN算法分析和比较不同最小约简属性下的分类准确率。     

现场总线在烘丝控制系统中的应用

系统采用现场总线完成过程控制,即可保证现场就地实时控制,又可以完成整线连锁控制,节约现场布线,降低成本,保证系统工艺控制精度和整线控制可靠性。     

公路隧道监控系统中的本地控制器和网络

本文主要介绍了我国目前隧道监控系统的构成,给出了作为其核心的区域控制器和通信网络的选型以及整体解决方案,具体说明了隧道监控系统的应用方案,最后提出了隧道监控系统现阶段存在的问提和注意点。     

基于主题短语的搜索引擎结果聚类

为了解决搜索引擎检索结果中的主题混杂现象,帮助用户快速准确地定位到有价值的信息,提出基于主题短语的搜索引擎结果聚类方法。首先从检索结果中提取查询词并与相邻词语组成主题短语,建立包含高频独立词语及主题短语的混合向量空间模型,同时引入同义词词林对特征项进行语义扩充,最后采用改进的k-means聚类算法对搜索结果进行聚类,并为各个类别提取类别标签。实验结果表明,该算法能有效提高聚类结果的准确率。     

浅谈如何掌握邮件合并功能并发挥它的妙用

本文通过介绍Word邮件合并功能的操作步骤并掌握它学会进行知识的迁移,因不同工作岗位的需要,学会举一反三,在日常的生活工作当中,巧用Word邮件合并功能,从重复劳动中解脱。     

基于FPGA的RAID6硬件加速器的实现

设计了基于FPIGA的RAID6磁盘阵列的硬件加速器,将占用大量CPU周期的RAID6校验算法,用FPGA硬件实现并设计了软件与加速器的交互接口,将CPU从繁重的计算任务中解放出来,系统的处理速度和响应速度得到很大提升.