激光探测与测量视觉技术在堆取料机全自动控制中的应用

针对散货料场堆取料机人工操作堆取作业随意性大、精度差、效率低等现状,设计了一种堆取料机全自动控制系统。该系统基于激光雷达(Lidar)机器视觉技术,通过3D激光扫描仪实时获取料堆形状的点云数据,并完成对目标料堆的在线实时建模,最后控制堆取料机完成自动作业;提出了一种基于视觉图像处理算法的作业路径规划算法,通过实时提前预测作业轨迹来指导堆取料机自动作业。实践表明该控制系统提高了设备的作业效率,降低了作业成本。     

基于火场信息的地铁车站智能疏散技术研究

火灾是城市轨道交通车站内影响最为严重的事故之一,科学合理的安全疏散方案是突发火灾时确保乘客出行安全的重要保障。然而,目前地铁车站火灾疏散方案中的疏散路线难以根据火场情况动态调整。针对地铁车站疏散路径固定单一的弊端,基于地铁车站内的监控系统,利用计算机视觉技术识别人员分布信息和火灾发生位置,建立空间拓扑模型,利用改进的蚁群算法规划出耗时最短且转弯次数较少的疏散路线,实现站内乘客更科学高效的疏散,最后通过3个场景的案例应用验证本文所提疏散方法的有效性。     

猎豹智能车无人驾驶系统总体设计

介绍猎豹智能车无人驾驶系统总体设计及其硬件和软件的设计特点和实现方法。系统采用机器视觉来识别高速公路车道线,利用拟人控制算法来实现车辆自动驾驶控制,最高时速为95km/h的初步试验结果验证了系统的可行性。     

基于机器视觉的非接触式螺纹参数测量系统

文中采用光机电一体化的思想,将光源、CCD、计算机等有机结合,开发了一种基于面阵CCD技术的石油管螺纹参数智能化测量系统。生产现场测量结果表明：该系统具有重复性好、精度高、检测速度快等优点,此外,此系统具有抗环境光及振动干扰,可操作性强等特点,适用于各种规格钢管外螺纹参数的在线测量。     

基于单目视觉的区域交通智能车辆道路边界检测方法研究

基于单目视觉的道路边界检测由于其在车辆辅助驾驶系统中的重要应用价值成为当前计算机视觉和智能车辆领域最为活跃的研究课题之一。指出图像边缘检测现有算法的不足,采用领域平均法对图像进行平滑处理,根据图像的边缘特征运用Prewitt算子实现边缘增强,以获取精确的边缘信息。使用最大熵算法分割二值化图像进一步减少噪声,从而得到良好的道路特征图像数据。利用道路约束条件,建立视觉系统动态感兴趣区域(DAOI),运用改进的Hough变换最终识别道路边界。试验结果表明:本文所述算法不仅能准确、实时检测出道路板边界,而且能有效地抑制噪声,为区域交通智能车辆的换道和超车提供研究基础。     

基于CapsNet的行人检测方法及评价

为了提高道路环境中行人目标检测的准确率，改善现有检测算法对不同环境视角下漏检率较高、耗时过长、实用性较差等问题，本文提出了一种基于 CapsNet的行人检测模型. CapsNet由神经元所构成的 Capsule组成，通过动态路由协议对物体的实例化参数进行表达和传递，保留了各特征对象间的空间层级，采用 Caltech公开数据库对所提算法的有效性进行验证，并在检测准确率及算法耗时等方面与其他算法进行对比.实验结果表明：相比于其他主流检测算法，本文算法在确保检测效率的前提下，对数平均漏检率最低可降至 9.17%；且在 Caltech、INRIA和 NICTA数据集的交叉验证实验中，也能达到良好的检测效果，具有较好的鲁棒性和泛化能力.     

舰船综合网络视频监控系统设计

本文论述了舰船综合网络视频监控系统的最优化设计及黑光夜视摄像仪在对抗性夜晚环境下的应用。基于黑光夜视摄像仪的特点和现代舰船环境条件的要求,阐述了黑光夜视摄像设备在现代舰船综合网络视频监控系统中的配置和使用。     

Planning with vision: The development of traffic strategies for Melbourne

This paper describes an approach to the development of metropolitan transport strategies based on community needs and values. A search conference and other consultation methods were used to raise community awareness of transport issues and to give the transport planners an understanding of community concerns and values. The collective values were used to develop a vision statement of where Melbourne could be in the future. Transport strategies were then developed which helped achieve the vision. By this approach transport strategies can be integrated with the delivery of other services so that they are complementary and achieve consistent ends. The process encouraged community debate and helped strategy development to focus on what was to be achieved, rather than on particular techniques or interest group agendas. Integrated strategies which have wide interest group and community support can be developed by the process.     

A real-time posture monitoring method for rail vehicle bodies based on machine vision

Monitoring vehicle operation conditions has become significantly important in modern high-speed railway systems. However, the operational impact of monitoring the roll angle of vehicle bodies has principally been limited to tilting trains, while few studies have focused on monitoring the running posture of vehicle bodies during operation. We propose a real-time posture monitoring method to fulfil real-time monitoring requirements, by taking rail surfaces and centrelines as detection references. In realising the proposed method, we built a mathematical computational model based on space coordinate transformations to calculate attitude angles of vehicles in operation and vertical and lateral vibration displacements of single measuring points. Moreover, comparison and verification of reliability between system and field results were conducted. Results show that monitoring of the roll angles of car bodies obtained through the system exhibit variation trends similar to those converted from the dynamic deflection of bogie secondary air springs. The monitoring results of two identical conditions were basically the same, highlighting repeatability and good monitoring accuracy. Therefore, our monitoring results were reliable in reflecting posture changes in running railway vehicles.     

基于机器视觉的钢轨表面检测光学模型的研究

在机器视觉的检测中,图像是整个系统中最重要的原始数据,其质量决定了后期图像处理的效果和速度。为探讨高质量图像的采集,提出一种基于线阵CCD相机和线阵光源的钢轨表面缺陷检测的光学理论模型,分析线阵CCD采集系统中振动模糊的原因,推导出图像灰度值与系统振动幅度和缺陷深度的关系,研究光源照射角度和相机拍摄角度对图像灰度和缺陷区域对比度的影响,并通过实验验证模型的合理性。结果表明:缺陷区域图像灰度值随着钢轨表面缺陷深度增大而降低,采用较低的光源照射角度可增大缺陷与背景的对比度,突出缺陷特征便于后期图像处理的缺陷识别。