Real time detection of driver attention: Emerging solutions based on robust iconic classifiers and dictionary of poses

Real time monitoring of driver attention by computer vision techniques is a key issue in the development of advanced driver assistance systems. While past work mostly focused on structured feature-based approaches, characterized by high computational requirements, emerging technologies based on iconic classifiers recently proved to be good candidates for the implementation of accurate and real-time solutions, characterized by simplicity and automatic fast training stages.In this work the combined use of binary classifiers and iconic data reduction, based on Sanger neural networks, is proposed, detailing critical aspects related to the application of this approach to the specific problem of driving assistance. In particular it is investigated the possibility of a simplified learning stage, based on a small dictionary of poses, that makes the system almost independent from the actual user.On-board experiments demonstrate the effectiveness of the approach, even in case of noise and adverse light conditions. Moreover the system proved unexpected robustness to various categories of users, including people with beard and eyeglasses. Temporal integration of classification results, together with a partial distinction among visual distraction and fatigue effects, make the proposed technology an excellent candidate for the exploration of adaptive and user-centered applications in the automotive field.     

Influence of some vehicle and track parameters on the environmental vibrations induced by railway traffic

A study is performed on the influence of some typical railway vehicle and track parameters on the level of ground vibrations induced in the neighbourhood. The results are obtained from a previously validated simulation framework considering in a first step the vehicle/track subsystem and, in a second step, the response of the soil to the forces resulting from the first analysis. The vehicle is reduced to a simple vertical 3-dof model, corresponding to the superposition of the wheelset, the bogie and the car body. The rail is modelled as a succession of beam elements elastically supported by the sleepers, lying themselves on a flexible foundation representing the ballast and the subgrade. The connection between the wheels and the rails is realised through a non-linear Hertzian contact. The soil motion is obtained from a finite/infinite element model. The investigated vehicle parameters are its type (urban, high speed, freight, etc.) and its speed. For the track, the rail flexural stiffness, the railpad stiffness, the spacing between sleepers and the rail and sleeper masses are considered. In all cases, the parameter value range is defined from a bibliographic browsing. At the end, the paper proposes a table summarising the influence of each studied parameter on three indicators: the vehicle acceleration, the rail velocity and the soil velocity. It namely turns out that the vehicle has a serious influence on the vibration level and should be considered in prediction models.     

Monitoring marine plankton ecosystems: Identification of the most relevant indicators of the state of an ecosystem

The number of variables involved in the monitoring of an ecosystem can be high and often one of the first stages in the analysis is to reduce the number of variables. We describe a method developed for geological purposes, using the information theory, that enables selection of the most relevant variables. This technique also allows the examination of the asymmetrical relationships between variables. Applied to a set of physical and biological variables (plankton assemblages in four areas of the North Sea), the method shows that biological variables are more informative than physical variables although the controlling factors are mainly physical (sea surface temperature in winter and spring). Among biological variables, diversity measures and warm-water species assemblages are informative for the state of the North Sea pelagic ecosystems while among physical variables sea surface temperature in late winter and early spring are highly informative. Although often used in bioclimatology, the utilisation of the North Atlantic Oscillation (NAO) index does not seem to provide a lot of information. The method reveals that only the extreme states of this index has an influence on North Sea pelagic ecosystems. The substantial and persistent changes that were detected in the dynamic regime of the North Sea ecosystems and called regime shift are detected by the method and corresponds to the timing of other shifts described in the literature for some European Systems such as the Baltic and the Mediterranean Sea when both physical and biological variables are considered.     

一种面向海事分支机构的船舶安全管理信息系统的设计

针对直属海事局分支机构船舶安全管理业务的需求，提出一种船舶安全管理信息系统的设计思路。该系统将电子海图平台、船舶交通动态数据和船舶安全管理信息集成，以实现船舶安全管理数字化、信息化、网络化。从系统技术实现角度，对信息管理系统作出详细的设计与分析。     

国内信息

交通部认真做好2008年春节运输工作；交通部开展暴风雷应对准备工作检查确保水上交通安全；交通部公布全国主要港口引航员登轮点。     

信息融合技术在交通流量预测中的应用

交通流量预测是智能运输系统的一个重要组成内容，但传统的数学方法一直未能取得令人满意的预测效果。信息融合技术是最近十多年来新兴的技术。它通过合理协调多源数据，充分综合有用信息，在较短的时间内，以较小的代价获得对未来交通流量的预测。实验证明，借助信息融合理论建立的聚类分析模型和神经网络模型对未来交通流量的预测比较准确，有实际意义。     

An agent-based approach to modelling driver route choice behaviour under the influence of real-time information

This paper presents an agent-based approach to modelling individual driver behaviour under the influence of real-time traffic information. The driver behaviour models developed in this study are based on a behavioural survey of drivers which was conducted on a congested commuting corridor in Brisbane, Australia. Commuters’ responses to travel information were analysed and a number of discrete choice models were developed to determine the factors influencing drivers’ behaviour and their propensity to change route and adjust travel patterns. Based on the results obtained from the behavioural survey, the agent behaviour parameters which define driver characteristics, knowledge and preferences were identified and their values determined. A case study implementing a simple agent-based route choice decision model within a microscopic traffic simulation tool is also presented. Driver-vehicle units (DVUs) were modelled as autonomous software components that can each be assigned a set of goals to achieve and a database of knowledge comprising certain beliefs, intentions and preferences concerning the driving task. Each DVU provided route choice decision-making capabilities, based on perception of its environment, that were similar to the described intentions of the driver it represented. The case study clearly demonstrated the feasibility of the approach and the potential to develop more complex driver behavioural dynamics based on the belief–desire–intention agent architecture.     

新型船舶运动控制平台及海上试验

研制出一艘以水动力学相似准则缩尺的无人驾驶遥控模型船，模型船装有PC／104为主控计算机的船舶控制器，模型船由岸上主PC机遥控，用Honeywell公司的HMR3000碰罗经测量航导，用差分GPS系统定位，自主控制和推进，该遥控篡自治船舶运动控制已经进行了两次海上试验并取得成功，本文介绍该平台的系统设计，控制系统硬件和软件和海上试验经。     

AutoLISP程序设计的若干问题

本文剖析了 AutoLISP 程序的结构特点,运行长大程序的措施和数据文件的组织等三个方面的问题.     

基于SuperMap GIS的公路养护信息系统设计

以SuperMap地理信息系统为基础平台,实现公路养护与施工数据的共享,建立一套管理信息系统,能完成图形、属性、影像、文本高度集成的一体化数据库可视化统一管理,提高公路养护的效率,并能为决策提供支持。