Accuracy Assessment and Guidelines for Manual Traffic Counts from Pre-Recorded Video Data

Traffic count is the fundamental data source for transportation planning, management, design, and effectiveness evaluation. Recording traffic flow and counting from the recorded videos are increasingly used due to convenience, high accuracy, and cost-effectiveness. Manual counting from pre-recorded video footage can be prone to inconsistencies and errors, leading to inaccurate counts. Besides, there are no standard guidelines for collecting video data and conducting manual counts from the recorded videos. This paper aims to comprehensively assess the accuracy of manual counts from pre-recorded videos and introduces guidelines for efficiently collecting video data and conducting manual counts by trained individuals. The accuracy assessment of the manual counts was conducted based on repeated counts, and the guidelines were provided from the experience of conducting a traffic survey on forty strip mall access points in Baton Rouge, Louisiana, USA. The percentage of total error, classification error, and interval error were found to be 1.05 percent, 1.08 percent, and 1.29 percent, respectively. Besides, the percent root mean square errors (RMSE) were found to be 1.13 percent, 1.21 percent, and 1.48 percent, respectively. Guidelines were provided for selecting survey sites, instruments and timeframe, fieldwork, and manual counts for an efficient traffic data collection survey.

Using microscopic video data measures for driver behavior analysis during adverse winter weather:opportunities and challenges

This paper presents a driver behavior analysis using microscopic video data measures including vehicle speed, lane-changing ratio, and time to collision. An analytical framework was developed to evaluate the effect of adverse winter weather conditions on highway driving behavior based on automated （computer） and manual methods. The research was conducted through two case studies. The first case study was conducted to evaluate the feasibility of applying an au- tomated approach to extracting driver behavior data based on 15 video recordings obtained in the winter 2013 at three dif- ferent locations on the Don Valley Parkway in Toronto, Canada. A comparison was made between the automated approach and manual approach, and issues in collecting data using the automated approach under winter conditions were identified. The second case study was based on high quality data collected in the winter 2014, at a location on Highway 25 in Montreal, Canada. The results demonstrate the effectiveness of the automated analytical framework in analyzing driver behavior, as well as evaluating the impact of adverse winter weather conditions on driver behavior. This approach could be applied to evaluate winter maintenance strategies and crash risk on highways during adverse winter weather conditions.

A Novel Video Data-Source Authentication Model Based on Digital Watermarking and MAC in Multicast

A novel video data authentication model based on digital video watermarking and MAC （message authentication code） in multicast protocol is proposed in this paper, The digital watermarking which composes of the MAC of the significant vid eo content, the key and instant authentication data is embedded into the insignificant video component by the MLUT （modified look-up table） video watermarking technology. We explain a method that does not require storage of each data packet for a time, thus making receiver not vulnerable to DOS （denial of service） attack. So the video packets can be authenticated instantly without large volume buffer in the receivers. TESLA （timed efficient stream loss tolerant authentication） does not explain how to select the suitable value for d, which is an important parameter in multicast source authentication. So we give a method to calculate the key disclosure delay （number of intervals）. Simulation results show that the proposed algorithms improve the performance of data source authentication in multicast.

Optimization-Based Fragmental Transmission Method for Video Data in Opportunistic Networks

Multimedia data have become popularly transmitted content in opportunistic networks. A large amount of video data easily leads to a low delivery ratio. Breaking up these big data into small pieces or fragments is a reasonable option. The size of the fragments is critical to transmission efficiency and should be adaptable to the communication capability of a network. We propose a novel communication capacity calculation model of opportunistic network based on the classical random direction mobile model, define the restrain facts model of overhead, and present an optimal fragment size algorithm. We also design and evaluate the methods and algorithms with video data fragments disseminated in a simulated environment. Experiment results verified the effectiveness of the network capability and the optimal fragment methods.

StreamTune： dynamic resource scheduling approach for workload skew in video data center

Video surveillance applications need video data center to provide elastic virtual machine （VM） provisioning. However, the workloads of the VMs are hardly to be predicted for online video surveillance service. The unknown arrival workloads easily lead to workload skew among VMs. In this paper, we study how to balance the workload skew on online video surveillance system. First, we design the system framework for online surveillance service which con- sists of video capturing and analysis tasks. Second, we propose StreamTune, an online resource scheduling approach for workload balancing, to deal with irregular video analysis workload with the minimum number of VMs. We aim at timely balancing the workload skew on video analyzers without depending on any workload prediction method. Furthermore, we evaluate the performance of the proposed approach using a traffic surveillance application. The experimental results show that our approach is well adaptive to the variation of workload and achieves workload balance with less VMs.

Minimizing Resource Cost for Camera Stream Scheduling in Video Data Center

Video surveillance service, which receives live streams from IP cameras and forwards the streams to end users, has become one of the most popular services of video data center. The video data center focuses on minimizing the resource cost during resource provisioning for the service. However, little of the previous work comprehensively considers the bandwidth cost optimization of both upload and forwarding streams, and the capacity of the media server. In this paper, we propose an efficient resource scheduling approach for online multi-camera video forwarding, which tries to optimize the resource sharing of media servers and the networks together. Firstly, we not only provide a fine-grained resource usage model for media servers, but also evaluate the bandwidth cost of both upload and forwarding streams. Without loss of generality, we utilize two resource pricing models with different resource cost functions to evaluate the resource cost： the linear cost function and the non-linear cost functions. Then, we formulate the cost minimization problem as a constrained integer programming problem. For the linear resource cost function, the drift-plus-penalty optimization method is exploited in our approach. For non-linear resource cost functions, the approach employs a heuristic method to reduce both media server cost and bandwidth cost. The experimental results demonstrate that our approach obviously reduces the total resource costs on both media servers and networks simultaneously.

Human Stress Recognition by Correlating Vision and EEG Data

Because stress has such a powerful impact on human health,we must be able to identify it automatically in our everyday lives.The human activity recognition(HAR)system use data from several kinds of sensors to try to recognize and evaluate human actions automatically recognize and evaluate human actions.Using the multimodal dataset DEAP(Database for Emotion Analysis using Physiological Signals),this paper presents deep learning(DL)technique for effectively detecting human stress.The combination of vision-based and sensor-based approaches for recognizing human stress will help us achieve the increased efficiency of current stress recognition systems and predict probable actions in advance of when fatal.Based on visual and EEG(Electroencephalogram)data,this research aims to enhance the performance and extract the dominating characteristics of stress detection.For the stress identification test,we utilized the DEAP dataset,which included video and EEG data.We also demonstrate that combining video and EEG characteristics may increase overall performance,with the suggested stochastic features providing the most accurate results.In the first step,CNN(Convolutional Neural Network)extracts feature vectors from video frames and EEG data.Feature Level(FL)fusion that combines the features extracted from video and EEG data.We use XGBoost as our classifier model to predict stress,and we put it into action.The stress recognition accuracy of the proposed method is compared to existing methods of Decision Tree(DT),Random Forest(RF),AdaBoost,Linear Discriminant Analysis(LDA),and KNearest Neighborhood(KNN).When we compared our technique to existing state-of-the-art approaches,we found that the suggested DL methodology combining multimodal and heterogeneous inputs may improve stress identification.

Design and Implementation of GIS Data Production System for Expressway Video and Road Infostructure

The expressway is necessary for the development of the modern transportation industry, and the level of expressway construction reflects the overall grade of national or regional economic development. In order to process the expressway road property data information, based on the current mainstream Windows operating system, this study utilizes Geographic Information System (GIS) development technology, road video processing technology, and spatial data mining method to design and develop an expressway video and road infostructure GIS data production system. The system designs a multi-layer distributed application model in accordance with the ideas and methods of GIS engineering and the characteristics of road production data. In addition, according to the characteristics and specification requirements of basic geographic data, the road production database of spatial data and attribute data integrated storage is constructed by combining database and spatial data engine. Through the development of the GIS data production system for expressway video and road infostructure, various functions such as generation of road property data, dynamic management of road infostructure, and visualization of spatial information have been realized. The system focuses on improving the production efficiency and automation level of expressway production data and meets the construction requirements for modernization, informatization, and intelligence of expressways.

Recommendations for Big Data in Online Video Quality of Experience Assessment

Real-time video application usage is increasing rapidly. Hence, accurate and efficient assessment of video Quality of Experience (QoE) is a crucial concern for end-users and communication service providers. After considering the relevant literature on QoS, QoE and characteristics of video trans-missions, this paper investigates the role of big data in video QoE assessment. The impact of QoS parameters on video QoE are established based on test-bed experiments. Essentially big data is employed as a method to establish a sensible mapping between network QoS parameters and the resulting video QoE. Ultimately, based on the outcome of experiments, recommendations/re- quirements are made for a Big Data-driven QoE model.

短视频消费时长能够反映就业率吗?

鉴于现行就业统计方式不能及时、准确反映经济运行形势,如何利用大数据对现有统计指标进行补充成为一个重要问题。鉴于短视频消费已经成为当今社会主要的休闲娱乐方式,文章将短视频消费纳入效用函数,通过失业人员与雇员在时间分配上的差异,揭示全社会用于观看短视频的时间与就业率之间存在的理论联系。通过计量分析,研究发现基于抖音在线人数计算的估计值与描述失业者寻找工作行为的百度搜索指数呈现正相关关系,可以借助短视频观看时长变动说明失业者寻找工作行为的变化。基于抖音在线人数估计的劳动参与率与16—24岁城镇调查失业率存在显著负相关关系,两者的皮尔逊相关系数为-0.862,因此估计的劳动参与率可以作为城镇调查失业率,特别是16—24岁劳动力调查失业率的补充。

基于电力载波与云计算的视频监控系统设计

针对目前视频监控系统不断升级改造存在的布线工作量大、布线成本高、无法存储及计算海量视频文件的问题,该文提出基于电力载波技术和云计算框架的视频监控系统。视频数据经过调制解调、振荡、放大、耦合等过程,利用电力线网络传输到各分控点,通过互联网传送到云端,利用云端强大的存储、计算能对视频数据进行各种处理。设计中硬件部分的ARM11微处理器主要负责视频数据的采集、编码并封包传送到PLC调制解调模块,完成数据收发控制和系统任务调度。软件部分主要包括开发系统搭建、USB摄像头驱动、视频数据采集、LCD实时显示、网络传输和双核数据处理等。该文的设计充分结合电力载波和云计算的特点,在视频监控领域中具有较高的应用价值。

中国石油井下作业数字化监督发展问题与对策

阐述了中国石油井下作业数字化监督在监督人员数字化管理、施工队伍数字化监督、施工作业数字化监督、井场环境数字化监督4个方面的发展现状。分析了井下作业数字化监督发展面临数字化监督管理制度不健全、监督数据标准不统一、数字化智能监督技术不完善、缺少统一的数字化智能监督平台、监督数据价值挖掘不深入5个方面的主要问题。提出了制定井下作业数字化监督管理制度、建立井下作业监督数据标准、攻关数字化智能监督关键技术、研发井下作业数字化智能监督平台、提升监督大数据分析应用水平5项数字化监督发展对策。展望了井下作业数字化监督建设发展后在提升监督人员履职效率、降低监督人力资源成本、提升工程质量、保障施工安全与环保4个方面的预期成效。

视频侦查技术关键及其发展展望

视频侦查技术的核心是通过视频图像的提取、查看、分析和研判来获取侦查线索、固定涉案证据。多年来经过在实战应用中不断地发展创新,视频侦查技术形成了自己独特的关键技术体系:视频信息分析解读技术是侦查应用和证据固定的基础和核心;视频证据固定保全技术的规范是审判中心主义的客观要求,可以获取视频侦查记录报告、视频检验鉴定报告或视频数据关联报告;低质量视频图像的增强恢复技术专业性强,应用范围窄,技术成熟度高,然而它不断面临新的挑战。目前,视频数据的智能应用在大数据背景下变得越来越重要,仍需进一步突破视频自动识别技术的应用范畴,建立完善多层次的视频数据综合应用体系,打造适应不同业务需要的视频数据实战应用模型。

涉Sora等文生视频危害行为的刑法规制

Sora等文生视频的应用将对刑法的法益理论产生重大影响。应将文生视频生成内容纳入作品范围。文生视频是其生成内容的作者但尚不是权利主体,应将相关著作财产权转移给使用人。涉文生视频强制猥亵、侮辱罪所侵害法益应当包括精神损害的内容。文生视频的应用改变了视频创作行业的社会关系,进而会改变相关犯罪行为法益侵害性程度的判断标准。涉文生视频犯罪主要涉及侵犯人身权利类犯罪、侵犯财产权利类犯罪以及寻衅滋事犯罪。司法解释对涉文生视频犯罪相关罪名构成要件的规定应当既有突破也有限制。我国刑法应设立数据安全责任事故罪以追究文生视频研发者、生产者的过失罪过下的刑事责任。应及时完善生成式人工智能产品应用的前置法规定。司法实践中应将文生视频的智能化程度区分为信息的整理、信息的基本加工、信息的深度加工三类,以此合理分配使用者、研发者与生产者所应当承担的涉文生视频犯罪的刑事责任。

基于监控视频数据的城市轨道交通车站闸机设施处行人停滞行为谱特征研究

[目的]为科学设置闸机,改善其实际通行能力,以及减少行人异常停滞行为带来的拥挤风险,需对城市轨道交通车站闸机设施处行人停滞行为谱特征进行研究。[方法]利用视频轨迹追踪技术,采集城市轨道交通车站闸机设施处监控视频中的行人运动参数;确定行人停滞行为表征指标,从闸机类型、行人流及个体停滞行为三类要素构建了城市轨道交通车站闸机设施处行人停滞行为谱,并采用四分位差法确定行人停滞行为谱表征指标上下限阈值;对行人停滞行为起点至闸翼/闸杆中心的纵向距离和横向距离,以及行人停滞范围和停滞时间等4个表征指标的差异性进行了分析,并全面解析了不同闸机类型和不同行人流率下的行人停滞行为谱特征。[结果及结论]行人易在闸机设施正前方停滞,行人停滞行为起点至闸翼/闸杆中心的纵向距离远大于其横向距离;当行人流率为>5~10人次/min时,行人停滞范围波动性最大;随着行人流量的增加,行人可用空间、停滞范围及停滞时间均减小。

车路协同感知技术研究进展及展望

近年来,我国自动驾驶研究逐步从聚焦于单车智能技术向车路协同技术转变,为智能交通产业发展带来了重大机遇;我国在车路协同感知领域的研究虽处于起步阶段,但注重技术推动,未来发展前景广阔。本文致力于深入探讨车路协同感知技术的发展动态,梳理了车路协同感知基础支撑技术的特性和发展现状,厘清了车路协同感知技术的研究进展,探讨了其技术发展趋势,并针对推动车路协同感知技术发展提出了一系列建议。研究表明,车路协同感知技术正朝着多源数据融合方向发展,主要集中在纯视觉协同感知技术优化、激光雷达点云处理技术升级、多传感器时空信息匹配与数据融合技术发展以及车路协同感知技术标准体系构建等方面。为进一步促进我国车路协同自动驾驶产业的迅速成长,研究建议,加大对多模态车路协同感知技术的研发投入、深化行业间的合作、制定统一的感知数据处理技术标准并加速技术应用普及,以期推动我国在全球自动驾驶竞争中赢得主动,推动自动驾驶行业稳定持续发展。

决策树码率自适应算法的无数据蒸馏框架

码率自适应(Adaptive Bit-Rate,ABR)算法是流媒体视频传输中至关重要的技术.该算法根据当前网络情况和播放状态等因素,为下一个视频块选择合适的码率,以确保用户获得良好的体验质量(QoE).其中,基于学习的ABR算法因其不依赖传统模型和从头学习策略的特点,表现出良好的性能,并逐渐取代需要繁琐调优的启发式ABR算法,成为研究领域的热点.然而,这些算法使用神经网络推理,导致模型参数较多,整体计算量较大,使得在实际场景中难以部署.因此,以往的研究提出了决策树蒸馏方案,即使用轻量级的决策树来提取基于学习的ABR算法的专家策略,并在线上部署这些决策树.然而,本文的实验结果表明,过去的蒸馏框架忽略了训练环境对蒸馏后策略的影响,导致策略的泛化能力较差.因此,本文提出了一种名为NIA(data-free Network-environmental Imitationbased rate Adaptation framework)的新型无数据蒸馏框架,用于生成具有更好泛化性能的决策树A BR算法.NIA通过网络环境生成模块构建多个人工网络环境,并在每次迭代训练前使用环境选择模块来选择适合的网络场景,然后与该场景进行交互,利用基于学生驱动的模仿学习算法完成决策树的蒸馏过程.本文还设计了完整的评测平台测试NIA的性能.实验表明,NIA在各种带宽数据集上展现出良好的QoE性能和泛化性能:(1)相较于启发式算法,在QoE指标上提升了1%~46%;(2)与以往的决策树蒸馏方案相比,在低带宽场景下表现相当,但在高带宽场景下提升了近1倍;(3)总体性能接近甚至超过基于学习的算法(即专家策略)的表现.

基于多模态知识主动学习的视频问答方案

视频问答是人工智能领域的一个热点研究问题.现有方法在特征提取方面缺乏针对视觉目标运动细节的获取,从而会导致错误因果关系的建立.此外,在数据融合与推理过程中,现有方法缺乏有效的主动学习能力,难以获取特征提取之外的先验知识,影响了模型对多模态内容的深度理解.针对这些问题,首先,设计了一种显性多模态特征提取模块,通过获取图像序列中视觉目标的语义关联以及与周围环境的动态关系来建立每个视觉目标的运动轨迹.进一步通过动态内容对静态内容的补充,为数据融合与推理提供了更加精准的视频特征表达.其次,提出了知识自增强多模态数据融合与推理模型,实现了多模态信息理解的自我完善和逻辑思维聚焦,增强了对多模态特征的深度理解,减少了对先验知识的依赖.最后,提出了一种基于多模态知识主动学习的视频问答方案.实验结果表明,该方案的性能优于现有最先进的视频问答算法,大量的消融和可视化实验也验证了方案的合理性.

基于眼动追踪技术的教学视频眼动分析系统

设计了可兼容大部分眼动仪的教学视频眼动分析系统,并从眼动数据记录、动态兴趣区定义、眼动分析3个模块,探讨了教学视频眼动分析系统的实现机制。该系统有助于提高眼动分析在教育领域应用的普适性,降低研究者在眼动相关方向的研究成本。

基于VideoCharger视频点播系统的设计与实现

探讨了VideoCharger的逻辑组成、交互与配置方式 ,及详细的资源需求分析 ,给出了据此建立VOD系统的系列解决方案。