一种用于多摄像机无重叠视域环境下的车辆跟踪系统

针对当前交通监控系统中自动化程度较低、过多依赖人力进行监控的现状,文章设计了一种用于多摄像机无重叠视域环境下的车辆跟踪系统.该系统为中心-分布式结构,中心服务器与分布在前端的智能摄像机节点通过GPRS相连,与传统的功能单一的摄像头相比,基于DM642的智能节点可以在前端完成目标检测、跟踪以及分类等工作,并将抽象化后的目标特征信息通过GPRS传输给中心服务器,大大减轻了网络传输的压力.中心服务器根据节点传送来的目标信息,对不同摄像机视域下的目标进行匹配,实现了目标的连续跟踪,获得了更为全面的目标信息.试验表明,文章设计的车辆跟踪系统可以在较大监控范围内有效地跟踪目标车辆.     

Robust Principal Component Test in Gross Error Detection and Identification

Principle component analysis (PCA) based chi-square test is more sensitive to subtle gross errors and has greater power to correctly detect gross errors than classical chi-square test. However, classical principal component test (PCT) is non-robust and can be very sensitive to one or more outliers. In this paper, a Huber function liked robust weight factor was added in the collective chi-square test to eliminate the influence of gross errors on the PCT. Meanwhile, robust chi-square test was applied to modified simultaneous estimation of gross error (MSEGE) strategy to detect and identify multiple gross errors. Simulation results show that the proposed robust test can reduce the possibility of type II errors effectively. Adding robust chi-square test into MSEGE does not obviously improve the power of multiple gross error identification, the proposed approach considers the influence of outliers on hypothesis statistic test and is more reasonable.     

临江破碎地层基坑涌水综合分析方法研究

岩溶破碎地层是地铁基坑水害的常见地质条件,复杂的水文地质条件是灾害频发的主要原因。以南京上元门车站为例,运用水文地质资料、地球物理探测及连通试验手段对南京上元门车站基坑岩性、岩溶裂隙发育特征及相对富水性进行深入研究。根据薄弱地层围岩及裂隙类型,可将基坑划分为4个区域,并提出针对性的治理措施,形成临江破碎地层基坑涌水综合分析方法。最后通过选择适当的注浆材料和配套工艺对临江破碎带进行综合治理,取得较好的治理效果,验证了此方法的可行性,同时实现了临江破碎地层治理的信息化施工。实践表明,该方法能有效减少注浆治理的盲目性,大大降低治理成本,保证注浆治理的效果。     

基于Faster R-CNN的高速公路抛落物检测

采用传统的基于图像处理的检测方法对高速公路抛落物进行检测不仅耗时耗力,而且检测效果不理想,为解决该问题,提出一种基于Faster R-CNN的深度学习检测方法.在原始Faster R-CNN的基础上,采用残差网络Resnet101代替传统的VGG-16网络和ZFNet网络,作为图像特征提取网络;采用尺寸为4像素、8像素和16像素的锚框代替原始锚框,得到高速公路抛落物检测模型.采用自制的高速公路抛落物数据集对该检测方法的有效性进行验证,结果显示,采用该方法检测的平均准确率达到了91.75％,相比原始的Faster R-CNN算法和yolov3算法,分别提高了7.02％和11.13％.     

Spatial-temporal traffic flow pattern identification and anomaly detection with dictionary-based compression theory in a large-scale urban network

Traffic flow pattern identification, as well as anomaly detection, is an important component for traffic operations and control. To reveal the characteristics of regional traffic flow patterns in large road networks, this paper employs dictionary-based compression theory to identify the features of both spatial and temporal patterns by analyzing the multi-dimensional traffic-related data. An anomaly index is derived to quantify the network traffic in both spatial and temporal perspectives. Both pattern identifications are conducted in three different geographic levels: detector, intersection, and sub-region. From different geographic levels, this study finds several important features of traffic flow patterns, including the geographic distribution of traffic flow patterns, pattern shifts at different times-of-day, pattern fluctuations over different days, etc. Both spatial and temporal traffic flow patterns defined in this study can jointly characterize pattern changes and provide a good performance measure of traffic operations and management. The proposed method is further implemented in a case study for the impact of a newly constructed subway line. The before-and-after study identifies the major changes of surrounding road traffic near the subway stations. It is found that new metro stations attract more commute traffic in weekdays as well as entertaining traffic during weekends.     

Use of magnetic monitoring of vehicles for proactive strategy development

The proactive operational strategy in the transport system which is a parallel concept associated with the Intelligent Transportation System (ITS) seems to be modern and right direction of development. However, the basis for its operation is the “information” in the broad sense of the term, on the functioning of the transport system itself. As new technologies develop, there emerge new opportunities of putting to use a wide array of sensors which can deliver more complete traffic data but using complex matrix of sensors is often unjustified economically and confusing. The paper proposes use of magnetometers as an interesting alternative to pass the requirements of simplicity of application, minimum costs and maximum of acquired information. The process of obtaining the information requires analysis of the quantitative and qualitative changes of the magnetic field. The conducted analyses demonstrate the possibility of using the passive magnetic methods for the purpose of monitoring of vehicles. Placement of the magnetic sensor bear out an important issue and was also discussed. During the experimental research it has been proven that passive magnetic methods enable obtaining the information on the movement of a vehicle as well as on the vehicle itself. Estimations of such values as: vehicle’s moving direction, velocity, dimensions, clearance or mass having ferromagnetic properties and even the state of strain in a vehicle’s structure were confirmed in practice. In addition thanks to magneto-mechanical effects the theoretical possibility of assessing the stress occurring in the components of vehicles, which could be indicative of the volume of cargo carried. Moreover, the crash experiment showed the possibility of a collision detection using magnetic signal. The need for obtaining information increases from year to year, with information becoming the biggest asset which enables both development and effective use of the transport system. Included researches, proofs emerging opportunity of more extensive use of magnetic sensors and the passive magnetic methods which could be applied in the modern transportation system.     

新型机车信号检测环线安装方法探究

针对目前传统的机车信号测试环线安装在钢轨内侧腰部存在一定的磁屏蔽、安装相对不是很容易、施工钢轨穿孔困难等缺点,结合具体施工等实际因素,设计并实现了一种成本较为低廉、安装方便、削弱构成磁屏蔽的一种机车信号测试环线支架法。该方法采用自主设计,特定加工的环线支架固定在钢轨上,环线通过支架安装在钢轨外侧,高度基本与钢轨高度水平。实践证明,这种环线支架法较之前传统的安装方式使用效果良好、信号检测稳定,设计经过实践检验基本合理,能满足机车信号的正常检测,在一定程度上优化了设计,方便了施工,达到了预期目标。     

基于PCA和随机Hough变换的调车信号灯检测

针对传统信号灯检测方法中存在的弊端,提出了一种主成分分析(Principal Component Analysis,PCA)和圆拟合与分段随机Hough变换(Randomized Hough Transform,RHT)圆检测相结合的信号灯检测方法。该方法利用主成分分析结合圆拟合来简化图像的复杂背景,然后通过随机Hough变换进行分段圆检测,得到信号灯的准确位置,最后结合线路特征及信号灯的颜色特点,确定本股道有显示的调车信号灯。对调车信号灯图像进行仿真实验,结果表明,该方法检测准确度高,实时性好,并对有颜色信号灯的检测具有良好的检测效果,适合于对复杂环境中调车信号灯的准确检测和定位。     

桥梁状态检测评估技术研究

由于桥梁的先天弱点和老化现象等原因,对桥梁进行检测,建立合适的评估方法已成为当务之急。明确桥梁状态检测评估的内容与依据,对桥梁外观、材料、结构等的检测评估进行探讨。     

基于高分辨率摄像机的机动车违法检测系统

在目前应用的机动车视频违法检测系统中,广泛采用的是多摄像机分别拍摄违法行为全景及违法车辆车牌特写的技术方案。针对其存在证据性弱、系统调试复杂等缺点,设计并实现了一种基于高分辨率摄像机的视频违法检测系统,重点阐述了系统设计方案、软件结构、实现方法和实验结果。