高速公路场景下的电子稳像技术研究

为了去除高速公路监控视频中自身位置不稳定的事物给全局运动矢量估计带来误差,先通过Canny算子检测图像中的直线,并根据车道边界的特征筛选出道路边界,确定道路区域。再检测道路区域内的Harris角点信息,并与背景图中道路区域内的角点位置进行匹配,从而得到全局运动矢量,并计算出稳定的图像。实验表明,该算法能够满足高速公路场景下的稳像需求。     

基于动态时间调整的时空图卷积路网交通流量预测

为深入挖掘交通流数据的复杂时空特征并建立其依赖关系,提高交通流参数的预测精度, 本文提出一种新的交通流量预测模型——基于注意力机制和残差网络的时空关系图卷积网络 (TSARGCN)。TSARGCN对输入数据进行切片,实现多分支建模,挖掘数据的时间周期性特征; 引入残差网络保证网络中信息传递的完整性;利用DTW (Dynamic Time Warping)算法计算路网 中节点之间交通流量序列在时间维度的相似程度大小,提出时间图的概念,结合路网结构中各节 点的邻近关系,提出时空关系图的概念;基于时空关系图,在每个分支结合注意力机制分别进行图卷积和时间维度卷积,捕获交通流的时空特征及其依赖关系,实现对路网交通流量数据时空关系的建模。经过在公开数据集PEMSD4上进行实验,结果表明：TSARGCN在交通流量预测中的平均绝对误差 (MAE) 达 到 19.24,均方根误差 (RMSE) 达到 27.09,比 ARIMA(Autoregressive Integrated Moving Average model),Conv-LSTM(Convolution Long short-term memory)及 ASTGCN (Attention based Spatial-temporal Graph Convolutional Network)等知名交通流量预测算法具有更高的预测精度。     

考虑行驶时间不确定性的合乘路径鲁棒优化方法

为应对实际合乘过程中时间不确定性带来的负面影响,本文研究不确定行驶时间下的合乘问题。采用预算不确定集合描述时间变量,引入不确定性水平可调节的预算系数,构建以车辆总里程最短和车辆数最少为目标的合乘路径鲁棒优化模型。并设计两阶段算法求解,第1阶段以两乘客间的可行合乘路径为基础,从车辆总里程节省率和乘客时间窗匹配灵活性两方面设计公式量化合乘匹配机会,以匹配机会为权重构建乘客图网络并聚类乘客需求;第2阶段设计以顺序插入启发式方法构造初始解的禁忌搜索算法求解。案例数据实验结果表明：本文聚类方法能保证优化质量并提高85%以上的计算效率,同时能缩减乘客等车时间和绕行距离;增大预算系数时解的鲁棒性逐渐提高,但会增加10%~40%的车辆数并降低1%~10%的里程节省率;大规模乘客案例和窄时间窗案例的合乘路径对不确定时间的敏感性更高,宽时间窗案例无需增加过多额外车辆和总里程就能达到较高水平的路径鲁棒性。     

基于路网可达性的城市交通离散网络设计模型及算法

根据城市交通路网分区理论,把分成的子区看成一个节点,考虑所有节点的可达性,以此度量整个路网的可达性,设计了基于路网可达性最大为目标的城市交通离散网络设计模型。采用粒子群算法,并给出一个简单的算例,算例表明,合理的添加路段,能使城市路网可达性达到最大。     

Camera calibration and vehicle tracking: Highway traffic video analytics

We describe a real-time highway surveillance system (RHSS), which operates autonomously to collect statistics (speed and volume) and generates incident alerts (e.g., stopped vehicles). The system is designed to optimize long-term real-time performance accuracy. It also provides convenient integration to an existing surveillance infrastructure with different levels of service. Innovations include a novel 3-D Hungarian algorithm which is utilized for object tracking and a practical, hands-off mechanism for camera calibration. Speed is estimated based on trajectories after mapping/alignment with respect to dominant paths learned based on an evolutionary dynamics model. The system, RHSS, is intensively evaluated under different scenarios such as rain, low-contrast and high-contrast lightings. Performance is presented in comparison to a current commercial product. The contribution is innovation of new technologies that enable hands-off calibration (i.e., automatic detection of vanishing points) and improved accuracy (i.e., illumination balancing, tracking via a new 3-D Hungarian algorithm, and re-initialization of background detection on-the-fly). Results indicate the capability and applicability of the proposed system in real-time and real-world settings.     

Train rescheduling model with train delay and passenger impatience time in urban subway network

This paper considers the train rescheduling problem with train delay in urban subway network. With the objective of minimizing the negative effect of train delay to passengers, which is quantified with a weighted combination of travel time cost and the cost of giving up the planned trips, train rescheduling model is proposed to jointly synchronize both train delay operation constraints and passenger behavior choices. Space–time network is proposed to describe passenger schedule‐based path choices and obtain the shortest travel times. Impatience time is defined to describe the intolerance of passengers to train delay. By comparing the increased travel time due to train delay with the passenger impatience time, a binary variable is defined to represent whether the passenger will give up their planned trips or not. The proposed train rescheduling model is implemented using genetic algorithm, and the model effectiveness is further examined through numerical experiments of real‐world urban subway train timetabling test. Duration effects of the train delay to the optimization results are analyzed. Copyright © 2017 John Wiley & Sons, Ltd.     

Multi-objective re-synchronizing of bus timetable: Model,complexity and solution

This work is originally motived by the re-planning of a bus network timetable. The existing timetable with even headways for the network is generated using line by line timetabling approach without considering the interactions between lines. Decision-makers (i.e., schedulers) intend to synchronize vehicle timetable of lines at transfer nodes to facilitate passenger transfers while being concerned with the impacts of re-designed timetable on the regularity of existing timetable and the accustomed trip plans of passengers. Regarding this situation, we investigate a multi-objective re-synchronizing of bus timetable (MSBT) problem, which is characterized by headway-sensitive passenger demand, uneven headways, service regularity, flexible synchronization and involvement of existing bus timetable. A multi-objective optimization model for the MSBT is proposed to make a trade-off between the total number of passengers benefited by smooth transfers and the maximal deviation from the departure times of the existing timetable. By clarifying the mathematical properties and solution space of the model, we prove that the MSBT problem is NP-hard, and its Pareto-optimal front is non-convex. Therefore, we design a non-dominated sorting genetic (NSGA-II) based algorithm to solve this problem. Numerical experiments show that the designed algorithm, compared with enumeration method, can generate high-quality Pareto solutions within reasonable times. We also find that the timetable allowing larger flexibility of headways can obtain more and better Pareto-optimal solutions, which can provide decision-makers more choice.     

大型客运站调机运用优化模型及算法

对铁路客运站调机运用进行科学合理的优化分析,对于提高客运站工作效率及保证旅客列车正点到发具有非常重要的意义。通过对客运站调机作业分析,建立客运站调机作业运用优化决策模型,将调机作业顺序模型转化为车辆数固定的、带时间窗口的车辆路径问题。采用模拟退火算法,实现调机运用的合理优化,并对模型和算法进行验证,得出优化效果明显的结论。     

铁路桥梁梁端伸缩装置的结构特点探讨

铁路桥梁梁端伸缩装置是大跨度桥梁的重要部件,为实现轨道的连续性和平顺性,需要具备滑动和支撑功能。对国内各种铁路桥梁梁端伸缩装置的结构特点、工作原理以及各自优缺点进行分析对比,目的在于分析出国内自主研发的梁端伸缩装置需要改进的思路和方向。我国要实现铁路桥梁梁端伸缩装置完全自主化,需要吸收国外先进的技术和经验,同时提升自身的制造精度和水平。     

预应力混凝土槽形梁静力行为研究

为了解槽形梁静力行为,进行了一片预制预应力混凝土槽形梁的模型试验,分别考虑跨中最大弯矩及梁端最大剪力两种荷载工况对试验模型进行加载,测试了试验模型的控制断面的应力、变形.并采用非线性有限元分析方法对槽形梁的力学特性进行了研究.试验和研究得到了如下结论:该槽形梁的剪力滞效应较为突出,具有明显的开口薄壁杆件特征,底板的空间板效应明显,在设计荷载作用下结构处于线弹性状态,具有一定的安全储备.