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。     

基于目标空间分布特征的无人机航拍车辆实时检测技术研究

针对无人机航拍视角下存在整体图像分辨率高但占比较高的小尺度车辆检测特征点稀少这一问题,从卷积网络检测器针对性优化与基于目标分布特征的航拍图像自适应切分2个角度综合考虑,提出一种基于目标空间分布特征的无人机航拍车辆检测网络DF-Net。以单阶段目标检测框架SSD为基础,引入深度可分离卷积和抗混叠低通滤波器对网络结构进行优化搭建E-SSD,为后续检测网络搭建提供高效检测器;接着基于条件生成对抗CGAN思想构建密度估计网络生成器,从而得到航拍图像中车辆的准确分布特征,生成高质量的车辆密度图;将E-SSD与车辆密度估计网络结合,对车辆密度图进行自适应切分,并将切分后的局部图像与全局图像一同输入E-SSD,最后在决策层融合检测结果,由此实现对航拍视角道路交通场景下车辆目标的精确高效检测。在试验中,一方面将设计的基于目标空间分布特征的无人机航拍车辆检测网络DF-Net与E-SSD进行对比分析,另一方面将DF-Net与航拍目标检测领域表现较为优秀的网络进行比较。研究结果表明：设计的方法对于2个试验在均值平均精度指标上均有提升,与E-SSD网络对比时提升了至少4.4%,与航拍目标检测领域优秀网络比较时也有一定提升,并保持了较好的实时性。     

连续-钢桁组合结构钢桁下节点安装定位施工工艺

以西宁跨兰西高速公路特大桥(80+168+80)m连续-钢桁组合结构钢桁下节点安装定位工程施工为例,详细介绍了下节点在连续梁砼施工过程中如何精确定位和安装,确保在连续梁施工完成后下节点的精度满足钢桁结构的安装要求,保证连续-钢桁组合结构的整体施工要求。     

浅谈渐开线花键的检测方法的应用

本文对渐开线花键的检测方法进行介绍分析,为渐开线花键的生产检验及零件验收提供理论依据和参考。     

基于弹性波CT的大体积混凝土检测应用

现代土木工程时常涉及大体积混凝土,其施工及养护过程极易出现质量问题,因此项目实施过程中检测工作始终贯穿于各个环节。常规混凝土无损检测方法一般无法对混凝土内部大截面进行直观评判,而弹性波CT则一次性重构截面波速分布,经反演后直接推定剖面内缺陷存在与否以及缺陷的位置及规模。通过弹性波CT在大体积混凝土检测中的应用,并结合超声法等验证手段,验证了该方法分辨率高、可靠性好、图像直观等优点,为其他相关类型项目提供了有益的参考。     

声波 CT 技术在旧桥粘钢加固评价中的应用

在役桥梁运营维护中，粘钢加固技术由于其经济、便捷等特点是保证桥梁安全运营的重要手段。但由于现有检测手段的不足，旧桥粘钢加固后修复效果是未知的。为弥补检验修复效果这一空白，将CT技术引入旧桥粘钢加固评价当中，以安徽某大桥的工程为例，用声波CT技术可以检测加固区域混凝土整体质量，得到定性、定量的检测结果，为旧桥加固修复情况提供客观评价，且可增强后续处治的针对性，并节约维修成本。     

Adhesion estimation at the wheel–rail interface using advanced model-based filtering

The railway industry in the UK is currently expanding the use of condition monitoring of railway vehicles. These systems can be used to improve maintenance procedures or could potentially be used to monitor current vehicle running conditions without the use of cost prohibitive sensors. This paper looks at a novel method for the online detection of areas of low adhesion in the wheel/rail contact that cause significant disruption to the running of a network, particularly in the autumn season. The proposed method uses a Kalman–Bucy filter to estimate the creep forces in the wheel–rail contact area; post-processing is then applied to provide information indicative of the actual adhesion level. The algorithm uses data that, in practice, would be available from a set of modest cost inertial sensors mounted on the vehicle bogie and wheel-sets. The efficacy of the approach is demonstrated using simulation data from a nonlinear dynamic model of the vehicle and its track interface.     

Contents Index Volume 35 and 36

Active safety systems would benefit from tyre force and friction potential information. Different sensor concepts, including, among others, the EU–funded Apollo–project developed tyre sensor based on optical position detection, are being studied. The sensor can measure tyre carcass deflections with respect to the rim. The carcass deflections can be used to calculate tyre forces and they may be exploited in the estimation of friction potential. The waveforms of the sensor signal are illustrated. The vertical and lateral force estimations are presented with unavoidable compensation parts. The tyre sensor measurements were compared to the measurement–vehicle results and good correlations achieved. Continuing activities are concerned with the estimation of friction potential and the detection of aquaplaning.     

From Twitter to detector: Real-time traffic incident detection using social media data

The effectiveness of traditional incident detection is often limited by sparse sensor coverage, and reporting incidents to emergency response systems is labor-intensive. We propose to mine tweet texts to extract incident information on both highways and arterials as an efficient and cost-effective alternative to existing data sources. This paper presents a methodology to crawl, process and filter tweets that are accessible by the public for free. Tweets are acquired from Twitter using the REST API in real time. The process of adaptive data acquisition establishes a dictionary of important keywords and their combinations that can imply traffic incidents (TI). A tweet is then mapped into a high dimensional binary vector in a feature space formed by the dictionary, and classified into either TI related or not. All the TI tweets are then geocoded to determine their locations, and further classified into one of the five incident categories.We apply the methodology in two regions, the Pittsburgh and Philadelphia Metropolitan Areas. Overall, mining tweets holds great potentials to complement existing traffic incident data in a very cheap way. A small sample of tweets acquired from the Twitter API cover most of the incidents reported in the existing data set, and additional incidents can be identified through analyzing tweets text. Twitter also provides ample additional information with a reasonable coverage on arterials. A tweet that is related to TI and geocodable accounts for approximately 5% of all the acquired tweets. Of those geocodable TI tweets, 60–70% are posted by influential users (IU), namely public Twitter accounts mostly owned by public agencies and media, while the rest is contributed by individual users. There is more incident information provided by Twitter on weekends than on weekdays. Within the same day, both individuals and IUs tend to report incidents more frequently during the day time than at night, especially during traffic peak hours. Individual tweets are more likely to report incidents near the center of a city, and the volume of information significantly decays outwards from the center.