The manpower allocation problem with time windows and job-teaming constraints: A branch-and-price approach

In this paper, we consider the manpower allocation problem with time windows, job-teaming constraints and a limited number of teams (m-MAPTWTC). Given a set of teams and a set of tasks, the problem is to assign to each team a sequential order of tasks to maximize the total number of assigned tasks. Both teams and tasks may be restricted by time windows outside which operation is not possible. Some tasks require cooperation between teams, and all teams cooperating must initiate execution simultaneously. We present an integer programming model for the problem, which is decomposed using Dantzig–Wolfe decomposition. The problem is solved by column generation in a branch-and-price framework. Simultaneous execution of tasks is enforced by the branching scheme. To test the efficiency of the proposed algorithm, 12 realistic test instances are introduced. The algorithm is able to find the optimal solution in 11 of the test instances. The main contribution of this article is the addition of synchronization between teams in an exact optimization context.     

RFID技术在铁路列车信息自动识别系统中的应用

无线射频识别技术（RFID Technology）是近些年来发展起来并已得到逐步推广的一种先进的物件识别技术。该文介绍RFID在铁路车辆信息自动识别系统中的应用,主要对该系统的构成和基本工作原理进行了描述。     

基于深度卷积神经网络的车型识别研究

近年来,深度学习中的卷积神经网络已经广泛运用于图像识别领域,它不仅显著提升了识别准确率,同时在特征提取速度方面也优于许多传统方法。本文针对高速公路环境下的车型识别问题,引入卷积神经网络（CNNs）理论,设计相应特征提取算法,并结合SVM分类器构建识别系统。通过对高速公路上主要三种车型（小车、客车、货车）的分类实验显示,本文方法在识别精度及速度上均取得较显著的提高。     

Solution algorithms for synchronous flow shop problems with two dominating machines

In this paper, we present solution algorithms for synchronous flow shop problems with two dominating machines. In such an environment, jobs have to be moved from one machine to the next by an unpaced synchronous transportation system, which implies that the processing is organized in synchronized cycles. This means that in each cycle the current jobs start at the same time on the corresponding machines and after processing have to wait until the last job is finished. Afterwards, all jobs are moved to the next machine simultaneously. Motivated by a practical application, we investigate the special case of two dominating machines where the processing times of all jobs on these two machines are at least as large as the processing times of all jobs on the other machines and hence always determine the cycle times. After formulating the considered problem as a special vehicle routing problem, we propose mixed integer linear programming formulations and a tabu search algorithm. Finally, we present computational results for randomly generated data and show the efficiency of the approaches.     

无人机地面运动控制与仿真

为了解决无人机纠偏刹车系统中实际存在的问题,对无人机地面运动进行了研究,采用前轮转弯、方向舵、差动刹车联合使用模式,以无人机的侧偏角、侧偏距为反馈信号,设计了无人机地面运动纠偏控制律,通过遗传算法的全局优化过程实现其纠偏参数寻优,在Simulink平台建立了无人机纠偏数学模型;试验结果表明,建立的无人机地面运动纠偏数学模型正确有效,能够模拟出无人机地面运动的真实情况;基于遗传算法的控制策略能够实现一定范围内的无人机地面运动纠偏,提高跑道的利用率。     

基于视频的夜间车辆检测与跟踪算法研究

针对夜间高速光照条件差、车灯种类多样、环境因素干扰等导致的车辆难以检测的问题,提出了一种基于视频的夜间车辆的检测与跟踪算法。该方法首先将OTSU与一维最大熵阈值分割算法相结合来实现车灯的提取,剔除非车灯光源;然后利用车灯的时空特性完成车灯的匹配,解决了一车多灯和并排同速车辆的问题;最后利用kalman滤波器完成车灯的预测跟踪。在交通弱光流畅交通、正常光流畅交通和正常光拥堵交通3种应用场景下对所提算法进行应用和结果分析,实验结果表明所提方法在保证实时性的同时具有较高的准确率。     

越野环境下自主车辆导航地图自动创建方法研究*

针对越野环境下的地图创建问题,提出了一种自动创建自主车导航地图的方法。首先将车载摄像机获得的图像投影到车体坐标系,然后结合车辆行驶轨迹信息采用基于标记的分水岭算法判定可通行区域,最后融合局部俯视图信息生成全局一致地图,并在实时导航需求下对地图进行优化得到最终的导航地图。自主车实车实验结果表明,该方法生成的地图满足自主车实时导航需求,提高了路径规划效率。     

运钞车车辆路径规划策略

针对实际运钞网点数每天动态变化问题,提出一种先划分、再优化的动态运钞车路线规划策略。第一阶段先采用Dijkstra算法求出两点之间的最短路径,再利用最近邻算法和均衡工作量因子求出动态需求车辆的车辆数和每条路径上的网点;第二阶段利用前置交叉的改进遗传算法,分别优化每条路径并求出每条路径上的网点顺序,获得距离最短和时间最少的路径。实验结果表明,该策略能有效解决车辆数目和路径根据需求动态变化的问题,达到节约和合理利用资源的目的。     

一种基于小波与形态学的车牌图象分割方法

针对汽车车牌与车身背景的分割问题,给出了一种基于小波分析和数学形态学的图象分割方法。该方法是通过小波多尺度分解提取出纺理清晰,具有不同空间分辨率、不同方向的边缘子图象。其水平方向低频、垂直方向高频的这一细节分量,主要代表车牌的目标区域。然后,用数学形态学方法对小波分解后的细节图象进行一系列的形态运算,进一步消除无用信息和噪声,以找准车牌位置。用该方法对在不同照明条件下所采集到的一系列车头、车尾图象     

车载导航电子地图的路网模型

建立适合于车载导航系统的路网数据是车载导航系统的关键。本文描述了如何表达真实世界的交通要素,并结合实际情况给出数据模型。