基于机器视觉的交叉口特种车辆快速通行技术研究

交叉口是道路网络中重要的交通节点,容易产生交通堵塞问题,为了在保证通行安全的情况下提高特种车辆的通行效率,研究基于机器视觉的交叉口特种车辆快速通行技术。优化通行基础采用图像采集及预处理、检测识别和通行控制作为技术框架结构,利用机器视觉技术采集交叉口实时交通图像,通过图像滤波、图像增强等步骤,实现初始图像的预处理。利用Car-YOLO网络识别交叉口通行能力,规划快速通行路线,考虑前车行驶状态,求解特种车辆通行速度,针对车辆所占车道,通过绿灯早启、绿灯周期时间延长等方式控制交叉口信号灯,实现交叉口特种车辆快速通行。实验结果表明:在拥堵和正常通行场景下,优化设计技术的特种车辆通过时间的平均值分别为18.2s、10.1s,事故发生概率分别低于2%、1.4%,具有较好的应用效果。     

Intelligent traffic light systems using edge flow predictions

In this paper, we propose a novel graph-based semi-supervised learning approach for traffic light management in multiple intersections. Specifically, the basic premise behind our paper is that if we know some of the occupied roads and predict which roads will be congested, we can dynamically change traffic lights at the intersections that are connected to the roads anticipated to be congested. Comparative performance evaluations show that the proposed approach can produce comparable average vehicle waiting time and reduce the training/learning time of learning adequate traffic light configurations for all intersections within a few seconds, while a deep learning-based approach can be trained in a few days for learning similar light configurations.     

Fuzzy logic steering control of autonomous vehicles inside roundabouts

The expansion of roads and the development of new road infrastructures have increased in recent years, linked to the population growing in large cities. In the last two decades, roundabouts have largely replaced traditional intersections in many countries. They have the advantage of allowing drivers continuous flow when traffic is clear, without the usual delay caused by traffic lights. Although roundabouts with and without traffic-signal control have been widely used and considered in the literature, driverless control on roundabouts has not been studied in depth yet. The behavior of autonomous vehicles in roundabouts can be divided into three stages: entrance, inside, and exit. The first and last may be handled as an extension of intersections. However, autonomous driving on the roundabout requires special attention. In this paper, the design and implementation of a fuzzy logic system for the steering control of autonomous vehicles inside the roundabout is proposed. Cascade architecture for lateral control and parametric trajectory generation are used. Fuzzy control has proved to be easy to define using expert knowledge. Experiments with a real prototype have been carried out, taking into account different speed profiles and lane change maneuvers inside the roundabout, with very satisfactory results.     

Automatic detection of traffic lights,street crossings and urban roundabouts combining outlier detection and deep learning classification techniques based on GPS traces while driving

The automatic generation of street networks is attracting the attention of research and industry communities in areas such as routable map generation. This paper presents a novel mechanism that focuses on the automatic detection of street elements such as traffic lights, street crossings and roundabouts which could be used to generate street maps and populate them with traffic influencing infrastructural elements such as traffic lights. In order to minimize the system requirements and simplify the data collection from many users with minimal impact for them, only traces of GPS data from a mobile device while driving are used. Speed and acceleration time series are derived from the GPS data. An outlier detection algorithm is used first in order to detect abnormal driving locations (which can be due to infrastructural elements or particular traffic conditions). Using deep learning, speed and acceleration patterns are automatically analyzed at each outlier in order to extract relevant features which are then classified into a traffic light, street crossing, urban roundabout or other element. The classification results are enhanced by adding the degree of atypicity for each point calculated as the percentage of times that a particular location is detected as an outlier in several drives. The proposed algorithm achieves a combined recall of 0.89 and a combined precision of 0.88 for classification.     

Traffic lights detection and recognition based on multi-feature fusion

Many traffic accidents occurred at intersections are caused by drivers who miss or ignore the traffic signals. In this paper, we present a method dealing with automatic detection of traffic lights that integrates both image processing and support vector machine techniques. Firstly, based on the color characteristics of traffic lights, the paper proposes a method of traffic light segmentation in RGB and HSV color space. And then, according to the geometric features and backplane color information of traffic lights, we design an algorithm to remove false targets in images. Moreover, in order to solve traffic lights diffusion problem, we apply a strategy that we first map the candidate regions onto the original image, then using Otsu algorithm re-extract the target region. Finally, HOG features are extracted from the target regions, and recognized by the trained SVM classifier. Experimental results show that the proposed method has relatively high detection rate and recognition accuracy in different natural scenarios, and is able to meet real-time requirements.     

基于改进YOLOv5s的交通信号灯识别方法

交通信号灯的检测与识别是提升无人驾驶系统安全性的关键技术,传统基于深度学习的识别方法不能在精度和速度之间达到较好的平衡,难以满足实际环境下的检测要求。YOLOv5具有网络规模小的优势,适合在交通场景下进行交通信号灯检测。对YOLOv5网络进行改进,提出TL-YOLOv5s网络用于交通信号灯识别。通过简化主干网络中卷积层的数量提高特征提取效率,同时对残差组件进行密集连接和多层次跨连接,得到2种新的CSP残差结构替换原网络中的残差结构,增强网络特征融合能力,提高识别精度。考虑到交通信号灯的小目标属性,在网络中保留中小目标检测尺度而去除大目标检测尺度,进一步提升识别速率。在法国巴黎LaRA信号灯数据集上进行实验,结果表明,TL-YOLOv5s网络mAP值达到70.1%,相比于基线网络YOLOv5提升6.3个百分点,且检测速度达到22.4 frame/s,能够满足现实环境下的实时性要求。     

城市环境中交通信号灯准确识别与状态估计

根据交通信号灯灯板颜色和形状定位图像中的灯板位置. 将灯板区域的彩色图像转换到YCbCr 空间, 分割灯板区域中的红、黄、绿三色区域, 利用交通信号灯的形态特性定位交通灯位置. 用Gabor 小波和2 维独立分量分析提取感兴趣区域的特征, 送入最近邻分类器分类信号灯的类型. 用代表性的观测序列建立隐马尔科夫模型, 并结合识别和跟踪结果估计信号灯状态. 实验结果表明, 该算法能可靠、准确地识别出信号灯, 并有效地估计出信号灯的状态.     

基于全方位视觉传感器的车辆违章检测系统的设计

探讨了利用全方位视觉传感器(ODVS)以及计算机视觉等技术来实现对交岔路口的车辆违章智能视频监控,采用ODVS来获取整个交岔路口的全景视频图像;通过混合高斯模型提取在全景视频图像中的车辆对象前景;使用camshift跟踪算法跟踪行驶车辆对象;依据交通法规,通过对比红绿灯、车道和车辆运动等状态来判断车辆对象是否有违章行为;实验结果表明,所设计的违章检测系统能自动检测出多种车辆违章行为,为交通执法部门提供了一种智能化的检测手段。     

Detection and classification of traffic lights for automated setup of road surveillance systems

Traffic light plays an important role in controlling the traffic flow to maintain order. The state of the traffic light is used in automatic detection of illegal motions against traffic rules. In this paper, a video based-method is proposed to tackle the problem of detection and classification of traffic lights in the scenes, thus providing an automated setup of road surveillance systems in intelligent transportation systems (ITS). Firstly, the proposed method localizes the regions of traffic lights by detecting the regularity in which the traffic light colors change, and then classify the traffic lights by an SVM classifier on their shape features. This method is insensitive to illumination changing and adaptable to various kinds of shape settings. Finally, the experimental results show that this method is efficient and effective in automatically recognizing traffic lights.     

交通灯运行时间自适应算法及其控制系统

城市交通拥堵具有严重的危害性, 直接导致时间延误、能源浪费和废弃物排放增加, 降低居民生活水平. 现阶段, 基于平面交叉路口交通灯切换时间相对固定, 恶劣天气或发生交通事故时路口经常发生交通堵塞的实际情况, 本文提出了一种平面交叉口交通拥堵多方向交通灯运行时间自适应算法, 采取视频图像处理算法判断道路交通拥堵情况, 根据路况设置交通灯的工作时间, 并设计了相应的控制系统. 仿真结果表明, 在高峰期时段, 此自适应算法的车辆通行效率高于传统的交通灯运行时间控制方法.     

Parametric-based path generation for automated vehicles at roundabouts

Urban environments are becoming more and more complex because several factors as consecutive crossroads or lanes changes. These scenarios demand specific infrastructures—i.e. roundabouts, for improving traffic flow compared with traditional intersections. A roundabout removes timeouts associated with traffic lights at crossroads and trajectory conflicts among drivers. However, it is a challenging scenario for both humans and automated vehicles. This work presents a path planning method for automated vehicle driving at roundabouts. The proposed system achieves a G¹ continuous path, minimizing curvature steps to increase smoothness, dividing the driving process in three stages: entrance maneuver, driving within the roundabout and exit maneuver. Parametric equations are generated to deal with automated roundabout driving. This approach allows a real time planning considering two-lane roundabouts, taking different exits. Tests in simulated environments and on our prototype platform—Cybercar—validate the system on real urban environments, showing the proper behavior of the system.     

A crosswalk pedestrian recognition system by using deep learning and zebra-crossing recognition techniques

Pedestrian detection is essential for improving pedestrian safety in an intelligent traffic system. The efficiency of the system is affected by real-time processing and the error rate of detection. These concerns have not been completely addressed in previous studies. Therefore, this study proposes a real-time pedestrian recognition system that ensures high accuracy by using a deep learning classifier and zebra-crossing recognition techniques. The proposed system was designed to improve pedestrian safety and reduce accidents at intersections. Environmental feature vectors were first used to detect zebra crossings and to determine crossing areas. An adaptive mapping technique was then used to map the pedestrian waiting area based on the crossing area. A dual camera mechanism was used to maintain detection accuracy and improve system fault tolerance. Finally, the you-only-look-once model was used to recognize pedestrians at intersections. A system prototype was implemented to verify the feasibility of the proposed system. The results revealed that the proposed scheme outperforms the conventional histogram of oriented gradients and Haarcascade schemes.     

基于网络流跟踪的信号灯检测方法

结合信号灯信息对机动车行进速度进行引导,减少机动车启停次数,可有效减少废气排放,缓解其造成的污染问题。针对信号灯转换时刻的获取问题,提出了一种基于网络流跟踪的信号灯检测方法。首先,该方法在数据集中引入辅助信号灯类别进行训练,将视频序列中该类目标检测结果关联为踪片,并通过踪片建模多目标跟踪任务。其次,该方法将多目标跟踪任务转换为最小费用流优化任务,以踪片作为节点建立最小费用流网络,提出了适合于信号灯的费用构建方式,通过最短路径算法求解,得到视频序列中辅助信号灯的多条轨迹。最后,基于求解的轨迹结果和图像分类技术,实现信号灯检测性能的提升。该方法的跟踪性能相较于对比算法有大幅提升,并将小目标信号灯检测响应的mAP提升至94.35%。实验结果表明,基于网络流的建模方式能极大地提升信号灯的跟踪准确率,结合跟踪轨迹还能大幅提高视频序列中小目标信号灯的检测准确率,并可有效确定信号灯状态的转换时刻。     

基于交通流量自适应控制的路口子系统

在经济快速发展、道路建设不足等多重压力下,城市交通负担越来越重.在现有的资源条件下,如何提高道路资源的利用效率和道路的通行效率是缓解交通问题的重要途径.本文以设计一种基于交通流量自适应控制的路口子系统为目标,首先分析、研究了交通管控系统的相关算法和相关信息系统的现状,在综合现有系统的基础上,设计了一个交通管控系统的体系结构,系统包括路口子系统、区域中心和信息与控制中心等3部分.通过路口子系统实现交通流数据的实时采集和路口本地的智能控制;设计并实现了路口子系统的检测方案,路口子系统的数据采集和本地的智能控制是云数据存储,以及实时的交通信息平台发布的关键,同时对于实现多个路口的协调管控具有重要的意义.     

基于车前灯的夜间车辆视频检测研究

针对夜间车辆视频检测和车流量统计的难题，提出了一种改进的基于视频图像处理提取车前灯的算法。通过分析夜间车辆视频的特点，利用梯度滤波法消除地面反射光对车灯的干扰，实现图像增强，并将分水岭分割算法和直方图双峰法相结合提取车前灯的信息。利用车灯配对匹配原则设计了一种新的匹配算法和跟踪算法实现车灯的配对与跟踪，最终准确地实现了车辆检测和车流量的统计功能。     

基于区域特征和连接成分的地图规范化算法

地图图像规范化算法是使地图图像同类型对象的某种属性具有相同的表现形式的一种方法或过程,它是地理信息识别的一个重要步骤。根据彩色栅格城市交通地图图像中各类地理要素的特征,提出一种基于区域特征和连接成分的地图图像规范化算法。首先对地图图像中的区域特征进行分析,并建立区域识别测度,实现了区域颜色规范化;再通过对非区域对象的连接成分进行分析,并建立道路识别测度,在区域颜色规范化的基础上,实现了道路颜色规范化。实验结果表明,对于彩色城市交通地图图像,该算法取得了良好的效果。     

基于区域特征和连接成分的地图规范化算法

地图图像规范化算法是使地图图像同类型对象的某种属性具有相同的表现形式的一种方法或过程，它是地理信息识别的一个重要步骤。根据彩色栅格城市交通地图图像中各类地理要素的特征，提出一种基于区域特征和连接成分的地图图像规范化算法。首先对地图图像中的区域特征进行分析，并建立区域识别测度，实现了区域颜色规范化；再通过对非区域对象的连接成分进行分析，并建立道路识别测度，在区域颜色规范化的基础上，实现了道路颜色规范化。实验结果表明，对于彩色城市交通地图图像，该算法取得了良好的效果。     

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。     

交通流量数据的分类规则挖掘

概述了数据挖掘的分类算法,并简要介绍了C5.0决策树算法。以北京市“三横两纵”主干道交通流量数据为例,采用C5.0决策树算法提取交通流量的分类规则,用于分析交通流量规律、信息模式和数据趋势,并对分类树进行量化,为交通信号设计、路网规划、道路设计、路网节点设计等提供决策支持。     

A dynamic and automatic traffic light control expert system for solving the road congestion problem

Traffic congestion is a severe problem in many modern cities around the world. To solve the problem, we have proposed a framework for a dynamic and automatic traffic light control expert system combined with a simulation model, which is composed of six submodels coded in Arena to help analyze the traffic problem. The model adopts interarrival time and interdeparture time to simulate the arrival and leaving number of cars on roads. In the experiment, each submodel represents a road that has three intersections. The simulation results physically prove the efficiency of the traffic system in an urban area, because the average waiting time of cars at every intersection is sharply dropped when the red light duration is 65 s and the green light time duration is 125 s. Meanwhile, further analysis also shows if we keep the interarrival time of roads A, B, and C, and change that of roads D, E, and F from 1.7 to 3.4 s and the interdeparture times at the three intersections on roads A, B, and C are equal to 0.6 s, the total performance of the simulation model is the best. Finally, according to the data collected from RFID readers and the best, second and third best traffic light durations generated from the simulation model, the automatic and dynamic traffic light control expert system can control how long traffic signals should be for traffic improvement.