一种基于改进NMS的牛脸检测方法

针对牲畜牛身份认证的多牛脸检测场景，本文给出一种基于改进Faster R-CNN的牛脸检测方法。使用Inception v2替换ZF网络作为Faster R-CNN的基础网络，模型精度得到显著提升；针对多牛检测场景对NMS（Non-Maximum Suppression）进行相应优化，使模型的召回率得到显著提升。通过和其他目标检测模型对比实验，本文的改进模型在精确率和召回率上均优于其他模型。     

深度学习识别光网络单元故障的设计与应用

为解决依赖装维上门鉴别光网络单元故障带来的不便,可以从机器视觉入手实现自动化故障识别。近年,ImageNet挑战赛的成功推动了物体识别技术的跨越式发展,特别是基于卷积的深度学习技术在视觉识别方面已经达到人类水平,为光网络单元故障的自动识别提供了技术基础。文章对识别光网络单元的工作状态进行了研究,将设备工作状态分为7个场景,提出了利用手机APP采集图片识别故障的解决方案并投入了实际生产;重点阐述了深度学习模块的设计与实现,提出一种通过算法整合的方式综合运用物体检测和图像分类算法,分3阶段逐步求精,解决了图片过滤,光网络单元型号和状态识别等问题,实现了基于计算机视觉自动识别光网络单元故障。从数据上看产品的端到端准确率超过84%,识别速度达到10 FPS,月均提供服务超过1万人次,在减少用户等待的同时节约了人力资源。     

网络安全等级保护测评中测评结论的度量方法优化

文章分析了网络安全等级保护2.0时期国家标准的新变化对等级测评结论可能产生的影响,并用实际案例和数据论述了以往描述的基于测评指标和基于测评对象的定量分析方法存在的局限性。根据网络安全等级保护国家标准结构和内容的新特点,结合新的等级测评结论表述方法,文章提出了调整和优化定量计算产生等级测评结论的思路,给出了缺陷扣分的原理和缺陷扣分的定量计算方法,并比较了各种定量计算方法在计算结果上的差异,提出了适合新标准的测评结论定量计算公式。     

Cloud asset for urban flood control

The performance of physical assets has become a major determinant success factor for urban flood control. However, managing these assets is always challenging as there are a huge number of diverse assets involved, which are distributed throughout the city, and owned by different agencies. Aiming at improving the management efficiency of these assets, and ensuring their performance, this paper proposes the concept of cloud asset based on cloud computing, mobile agent, and various smart devices. Through hardware integration and software encapsulation, cloud asset could sense its real-time status, adapt to varied working scenarios, be controlled remotely, and shared among agencies. It enables accurate real-time control of every asset, and thus improves the management efficiency and effectiveness. This paper first presents the concept of cloud asset with its technical architecture, and then analyses the software agent model for cloud asset, which is the key enabler to realize UPnP (Universal Plug and Play) management of assets, and provides mobility and intelligence for them. After that, the framework of cloud asset-enabled workflow management is built, in which cloud asset could be easily found and dynamically invoked by different workflows. Finally, a demonstrative case is provided to verify the effectiveness of cloud asset.     

Expert system for problem solving in distance university education: The successful case of the subject “operations management”

Acquiring the skills needed to solve certain types of problems is one of the main challenges of distance university education, demanding extra motivation from students to tackle it. New technology should be one of our great allies in addressing these problems. This article proposes an expert system with a web‐based problem‐solving simulator for a multidevice environment in order to allow students to access an unlimited number of problems with their corresponding solutions, immediately, anytime and anywhere. The types of problems that can be used are those based on quantitative methods with a fixed methodology to be followed. A successful case study was carried out for the subject Operations Management at the Distance University of Madrid (UDIMA), with three different problem simulators having been developed. The results were very satisfactory compared with previous academic years in terms of motivation. A decrease in students that did not sit the final examination was observed, as was an increase in the number of visits to the Moodle classroom. Students also responded positively in their assessments of the initiative.     

多先验融合的图像显著性目标检测算法

为了更加准确地检测出图像中的显著性目标，提出了多先验融合的显著性目标检测算法。针对传统中心先验对偏离图像中心的显著性目标会出现检测失效的情况，提出在多颜色空间下求显著性目标的最小凸包交集来确定目标的大致位置，以凸包区域中心计算中心先验。同时通过融合策略将凸包区域中心先验、颜色对比先验和背景先验融合并集成到特征矩阵中。最后通过低秩矩阵恢复模型生成结果显著图。在公开数据集MSRA1000和ESSCD上的仿真实验结果表明，MPLRR能够得到清晰高亮的显著性目标视觉效果图，同时F，AUC，MAE等评价指标也比现有的许多方法有明显提升。     

小尺度交通信号灯的检测与状态识别

交通信号灯识别包括检测和状态识别，在智能交通系统中发挥重要作用。基于YOLOv3算法提出了一种交通信号灯检测与状态识别模型。针对交通信号灯相较于交通场景中其他目标具有尺度小的特性进行了算法的设计：降低骨干网络的下采样倍率以增加小尺度目标的特征描述能力；通过增大特征图的尺度来改进多尺度特征融合；引入广义交并比作为检测任务的损失函数来改进目标边界框的回归效果。同时，根据交通信号灯本身的特性，使用颜色和形状约束的方法对信号灯进行状态识别和类别验证。最后在公开的Bosch交通信号灯数据集上和实际的城区道路进行了实验验证。实验结果表明，所提出的算法能够提升交通信号灯识别的精度和召回率，识别准确率可以达到90%左右。     

Robust Mapping for Mobile Robot Based on Immobile Area Grid Map Considering Potential Moving Objects

Mobile robots need Simultaneous Localization and Mapping (SLAM) for autonomous movement in human living environments. The occupancy grid map used in SLAM is a conventional method which makes a map by an occupancy probability in each grid. This method renews a map based on whether an object is observed or not. In order to remove moving objects from a map, an additional method is required. However, conventional methods deal only with actually moving objects, and potential moving objects (e.g., standing humans) are mapped as static objects. Furthermore, only binary states, used or not used, are given to each object in map updating. This paper proposes the immobility area grid map to represent a map by an immobility probability in each grid. The proposed method renews a map based on the identification of observed objects by a robot's sensors, in addition to whether an object is observed or not. We introduce the map update parameter, which is set adaptively from the certainty of identification result of the object. Observed objects can take continuous states, truly static—unknown—truly moving, according to the parameter value. Potential moving objects are not mapped if the parameter takes values corresponding to moving objects. The experimental results show robust mapping in dynamic environments including potential moving objects.     

基于内隐测量的APP交互流程可用性评估方法

目的 研究内隐测量用于交互流程评估的普遍方法，选取适合的参考指标建立评估标准，旨在提出一套完整且通用的评估策略。方法 以带有拍摄功能的宠物社交类APP为载体，提出两种不同的交互流程，建立交互原型，并提取两套原型中差异较大的流程进行对比实验，采用眼动仪收集被测的无意识行为，依据首次注视时间、兴趣区域注视率，注视点图等指标分析实验数据，并与外显测量结果相结合，衡量用户操作情况以及APP的交互性能。结果 根据实验和数据分析，得出以拍摄界面为主页是更适合宠物社交APP的交互方式。结论 内隐测量评估作为一种新兴的产品可用性评估方式，不仅在交互界面设计评估上得到了广泛的应用，还可作为产品交互流程的评估方法，并具有深度挖掘的意义。