基于图像处理的前方行驶车辆速度测量方法

车辆超速行驶是造成高速公路交通事故的主要原因之一,依赖于固定摄像机的传统视频测速系统测速区域十分有限.通过车载双目电荷耦合器件(CCD)摄像头获取车辆行驶过程中前方车辆的行驶状态,提出了一种测量前方行驶车辆速度的方法.利用改进Hough变换识别车道线,提取感兴趣区域,以车底阴影特征为基础完成车辆检测,通过在车载视频图像中选取适当的图像帧,获得车辆的相对位移及对应的时间间隔,获得前方车辆的行驶速度.经测试,算法能得到较高精度的速度测量结果.     

基于视频车流轨迹的虚拟车道划分方法

针对车道线磨损、临时改道以及非结构化道路等情况下的车道划分问题,在利用YOLOv3得到车辆检测模型前提下,提出基于视频车流轨迹的虚拟车道划分方法。密度矩阵统计时间t内由车辆检测模型得到车流量密度分布,运用三维坐标系对其进行分析;使用EM算法对一元混合高斯模型求解;建立虚拟车道宽度数学模型,运用3σ准则得到车道边界点集合,利用最小二乘法对边界点进行曲线拟合,完成虚拟车道线划分。该方法可以有效避免环境和天气因素对车道线检测的影响,具有一定的鲁棒性和灵活性。实验结果表明,该方法在不同道路中能够取得88.7%的准确率。     

Longitudinal control algorithm for automated vehicle merging

This paper considers longitudinal control of automated vehicle merging in a mathematical approach for automated highway systems. Merging manoeuvre is defined as one vehicle in the merging lane to be inserted in the middle between two vehicles in the main lane at fixed merging point which is the intersection of those two lanes. The main lane vehicles can change speed. To achieve this, the merging vehicle must properly adjust its speed and acceleration such that it reaches the merging point at the right time with the same speed and acceleration as the main lane vehicles. This problem is a little similar to but different from the well-known missile interception problem. The longitudinal control problem is proposed for different road layouts, based on which a unified mathematical model is established. Then a new concept, virtual platooning, is introduced, which effectively avoids a two-point boundary value problem . Based on this concept, an analytic solution with mathematical proof is provided. It is also discretized as a recursive algorithm for real-time use. A dynamic real-time simulation is published at PATH website. This algorithm has been successfully implemented with automated cars.     

基于光流法的快速车道线识别算法研究

为提取无人驾驶车前方车道线信息,提出一种使用光流法的快速车道线识别算法。首先,根据连续视频帧之间的时间相关性,运用光流法检测车辆前方背景的相对移动。然后,利用车辆背景中特征点的移动方向和距离,对本帧图像中车道线的位置进行粗略定位,从而缩小本帧图像中车道线的检测区域,加速车道线识别算法。最后,通过对车道线像素点的处理,给出车道线类型信息。该算法提升了车道线检测算法的效率,降低了复合算子车道线检测算法的时间复杂度。在720*480像素下,算法实现了13.5Hz的处理速度,相较仅使用复合算子的处理算法提升了39.6%的处理速度,且算法检测效果良好。实车实验证明了算法的有效性和实时性。     

开放道路中匹配高精度地图的在线相机外参标定

目的 相机外参标定是ADAS（advanced driver-assistance systems）等应用领域的关键环节。传统的相机外参标定方法通常依赖特定场景和特定标志物,无法实时实地进行动态标定。部分结合SLAM（simultaneous localization and mapping）或VIO（visual inertia odometry）的外参标定方法依赖于点特征匹配,且精度往往不高。针对ADAS应用,本文提出了一种相机地图匹配的外参自校正方法。方法 首先通过深度学习对图像中的车道线进行检测提取,数据筛选及后处理完成后,作为优化问题的输入;其次通过最近邻域解决车道线点关联,并在像平面内定义重投影误差;最后,通过梯度下降方法迭代求解最优的相机外参矩阵,使得像平面内检测车道线与地图车道线真值重投影匹配误差最小。结果 在开放道路上的测试车辆显示,本文方法经过多次迭代后收敛至正确的外参,其旋转角精度小于0.2°,平移精度小于0.2 m,对比基于消失点或VIO的标定方法（精度为2.2°及0.3 m）,本文方法精度具备明显优势。同时,在相机外参动态改变时,所提出方法可迅速收敛至相机新外参。结论 本文方法不依赖于特定场景,支持实时迭代优化进行外参优化,有效提高了相机外参精确度,精度满足ADAS需求。     

智能交通系统车道保持纵横向耦合控制

考虑车辆纵横向运动之间的相互影响,采用位置预瞄和固定车辆间距跟随策略,对基于一列车队的自动化公路系统车道保持纵横向耦合控制进行了研究.利用车载前后双位置传感器检测车辆位置偏差,基于车辆纵横向动力学耦合模型,推导了基于预瞄的车道保持控制系统数学模型;采用非奇异的终端滑模控制技术,设计了车道保持纵横向耦合控制规律.通过构造李雅普诺夫函数,结合相平面方法,分析了控制系统的有限时间收敛性.采用6车辆编队,通过计算机仿真,对文中设计的控制规律进行了验证.仿真结果显示,车队中每个被控车辆在纵向上跟随期望状态的同时能够实现对期望车道轨迹的理想跟踪,跟踪误差精度不超过0.05 m.     

Reactive navigation in dynamic environment using a multisensorpredictor

A reactive navigation system for an autonomous mobile robot in unstructured dynamic environments is presented. The motion of moving obstacles is estimated for robot motion planning and obstacle avoidance. A multisensor-based obstacle predictor is utilized to obtain obstacle-motion information. Sensory data from a CCD camera and multiple ultrasonic range finders are combined to predict obstacle positions at the next sampling instant. A neural network, which is trained off-line, provides the desired prediction on-line in real time. The predicted obstacle configuration is employed by the proposed virtual force based navigation method to prevent collision with moving obstacles. Simulation results are presented to verify the effectiveness of the proposed navigation system in an environment with multiple mobile robots or moving objects. This system was implemented and tested on an experimental mobile robot at our laboratory. Navigation results in real environment are presented and analyzed.     

Collision-avoidance systems PRORETA: Situation analysis and intervention control

After a discussion of passive and active safety systems for automobiles and accident statistics it follows that a further progress in the reduction of accidents can be especially expected by next-generation driver-assistance systems with a sequence of warnings and active interventions. PRORETA is an Industry–University research project with the goal to develop steps towards accident-free driving. The first project considers two vehicles moving in the same direction. The other vehicle is detected by a fusion of LIDAR and camera data providing the system with relative speeds and distance. If the driver does not react to an obstacle on the own lane, the system automatically triggers an emergency braking and/or swerving to avoid a collision. This includes e.g. a fast and precise evasive trajectory control by automatic steering.The second project is dedicated to vehicles moving in opposite directions performing an overtaking maneuver on rural roads. The own vehicle detects the velocities and distances to the preceding and oncoming vehicle by RADAR and lane markings, etc. with a camera. The measured data of the two sensors undergo a sensor fusion with Kalman filters. The overtaking maneuver is predicted by using the measured data of all three vehicles. If an accident-free overtaking is in danger, warnings are given to the driver and if the driver does not react in time a full braking of the own vehicle is triggered such that the driver can turn back behind the overtaken vehicle.The contribution gives a survey on the developed strategies and some basic calculated features and control systems. Measured data are shown and give an impression of the driving experiments on the runway of an air field.     

基于视觉的车道跑偏检测方法研究及仿真

为了保证辅助驾驶技术行车的安全,在分析了基于视觉的车道跑偏检测方法的具体步骤的基础上,首先提出了利用由计算机视觉获得的车道标志线来进一步获得车-路关系的方法,并推导了几种车道跑偏判据TLC(time to lane crossing)的计算公式;然后利用“预瞄最优曲率模型”来仿真人-车-路的关系,并验证了当人的状态发生变化时,TLC判据可以有效地提供报警的效果;最后在红旗自主驾驶样车的视觉导航系统中进行了实验,实验结果表明,上述分析和仿真是可行的。     

Automatic Lane-Level Intersection Map Generation using Low-Channel Roadside LiDAR

A lane-level intersection map is a cornerstone in high-definition(HD) traffic network maps for autonomous driving and high-precision intelligent transportation systems applications such as traffic management and control, and traffic accident evaluation and prevention. Mapping an HD intersection is time-consuming, labor-intensive, and expensive with conventional methods. In this paper, we used a low-channel roadside light detection and range sensor(LiDAR) to automatically and dynamically generate...     

A Fuzzy-Logic-Based Approach for Mobile Robot Path Tracking

One important problem in autonomous robot navigation is the effective following of an unknown path traced in the environment in compliance with the kinematic limits of the vehicle, i.e., bounded linear and angular velocities and accelerations. In this case, the motion planning must be implemented in real-time and must be robust with respect to the geometric characteristics of the unknown path, namely curvature and sharpness. To achieve good tracking capability, this paper proposes a path following approach based on a fuzzy-logic set of rules which emulates the human driving behavior. The input to the fuzzy system is represented by approximate information concerning the next bend ahead the vehicle; the corresponding output is the cruise velocity that the vehicle needs to attain in order to safely drive on the path. To validate the proposed algorithm two completely different experiments have been run: in the first experiment, the vehicle has to perform a lane-following task acquiring lane information in real-time using an onboard camera; in the second, the motion of the vehicle is obtained assigning in real-time a given time law. The obtained results show the effectiveness of the proposed method     

Dynamic calibration of pan-tilt-zoom cameras for traffic monitoring.

Pan-tilt-zoom (PTZ) cameras have been widely used in recent years for monitoring and surveillance applications. These cameras provide flexible view selection as well as a wider observation range. This makes them suitable for vision-based traffic monitoring and enforcement systems. To employ PTZ cameras for image measurement applications, one first needs to calibrate the camera to obtain meaningful results. For instance, the accuracy of estimating vehicle speed depends on the accuracy of camera calibration and that of vehicle tracking results. This paper presents a novel calibration method for a PTZ camera overlooking a traffic scene. The proposed approach requires no manual operation to select the positions of special features. It automatically uses a set of parallel lane markings and the lane width to compute the camera parameters, namely, focal length, tilt angle, and pan angle. Image processing procedures have been developed for automatically finding parallel lane markings. Interesting experimental results are presented to validate the robustness and accuracy of the proposed method.     

Estimation of moving vehicle locations using wheel shape information in single 2-D lateral vehicle images by 3-D computer vision techniques

An approach to the estimation of moving lateral vehicle locations for driving assistance using wheel shape information in single 2-D vehicle images by 3-D computer vision techniques is proposed. The location scheme is supposed to be performed on a vehicle with a camera mounted on the front bumper. An analytical solution is applied to estimate locations of the lateral vehicle. Firstly, the rear wheel shape of a lateral vehicle moving in a nearby lane is imaged. By using the Hough transform, the projected wheel shape, which is an ellipse, is detected. Secondly, the equation of the detected ellipse is used to infer the orientation angle of the lateral vehicle with respect to the camera view direction. Finally, the center of the ellipse shape is used to determine the relative position of the lateral vehicle with respect to the camera lens center. Moreover, an edge-point verification algorithm is utilized to extract the ellipse shape more precisely in the image processing stage. Both computer simulated and real images are tested and good experimental results show the effectiveness of the proposed approach for estimating lateral vehicle locations. The results are useful for driving assistance and vehicle collision avoidance and are discussed in detail.     

Optimal phase searching of PTS using modified genetic algorithm for PAPR reduction in OFDM systems

In this paper,a novel genetic algorithm assisted partial transmit sequence(NGA-PTS)is proposed to reduce the peak-to-average power ratio(PAPR)of orthogonal frequency division multiplexing(OFDM).However,the search complexity of the optimum PTS(OPTS)scheme is too large for the typical number of sub-blocks.Therefore,some artificial intelligence methods,such as genetic algorithm technique,and particle swarm optimization,are introduced to reduce the complexity.As traditional GA-PTS(TGA-PTS)technique risks finding a suboptimal solution,how to avoid this disadvantage of TGA-PTS is an interest topic.In order to obtain a better suboptimal solution,a phase factor optimal pair technique and an abandon/introduction new chromosome technique are proposed in GA here.Simulation results show that the proposed scheme achieves a significant improvement over the TGA-PTS scheme in PAPR.Furthermore,by use of the inherent diversity of constellation for each OFDM candidate,in the receiver part,the proposed scheme enables data recovery without any side information.Simulation results show the efficiency of the proposed scheme.     

Profile based routing in vehicular ad-hoc networks

One of the main problems in the VANET(vehicular ad-hoc network)routing algorithms is how to establish the stable routes.The link duration in these networks is often very short because of the frequent changes in the network topology.Short link duration reduce the network efficiency.Different speeds of the vehicles and choosing different directions by the vehicles in the junctions are the two reasons that lead to link breakage and a reduction in link duration.Several routing protocols have been proposed for VANET in order to improve the link duration,while none of them avoids the link breakages caused by the second reason.In this paper,a new method for routing algorithms is proposed based on the vehicles trips history.Here,each vehicle has a profile containing its movement patterns extracted from its trips history.The next direction which each vehicle may choose at the next junction is predicted using this profile and is sent to other vehicles.Afterward each vehicle selects a node the future direction of which is the same as its predicted direction.Our case study indicates that applying our proposed method to ROMSGP(receive on most stable group-path)routing protocol reduces the links breakages and increases the link duration time.     

高速公路云台相机的自动标定

目的 云台相机因监控视野广、灵活度高,在高速公路监控系统中发挥出重要的作用,但因云台相机焦距与角度不定时地随监控需求变化,对利用云台相机的图像信息获取真实世界准确的物理信息造成一定困难,因此进行云台相机非现场自动标定方法的研究对高速公路监控系统的应用具有重要价值。方法 本文提出了一种基于消失点约束与车道线模型约束的云台相机自动标定方法,以建立高速公路监控系统的图像信息与真实世界物理信息之间准确描述关系。首先,利用车辆目标运动轨迹的级联霍夫变换投票实现纵向消失点的准确估计,其次以车道线模型物理度量为约束,并采用枚举策略获取横向消失点的准确估计,最终在已知相机高度的条件下实现高速公路云台相机标定参数的准确计算。结果 将本文方法在不同的场景下进行实验,得到在不同的距离下的平均误差分别为4.63%、4.74%、4.81%、4.65%,均小于5%。结论 对多组高速公路监控场景的测试实验结果表明,本文提出的云台相机自动标定方法对高速公路监控场景的物理测量误差能够满足应用需求,与参考方法相比较而言具有较大的优势和一定的应用价值,得到的相机内外参数可用于计算车辆速度与空间位置等。     

Dual-eyes Vision-based Docking System for Autonomous Underwater Vehicle: an Approach and Experiments

A critical challenge for autonomous underwater vehicles (AUVs) is the docking operation for applications such as sleeping under the mother ship, recharging batteries, transferring data, and new mission downloading. The final stage of docking at a unidirectional docking station requires the AUV to approach while keeping the pose (position and orientation) of the vehicle within an allowable range. The appropriate pose therefore demands a sensor unit and a control system that have high accuracy and robustness against disturbances existing in a real-world underwater environment. This paper presents a vision-based AUV docking system consisting of a 3D model-based matching method and Real-time Multi-step Genetic Algorithm (GA) for real-time estimation of the robot’s relative pose. Experiments using a remotely operated vehicle (ROV) with dual-eye cameras and a separate 3D marker were conducted in a small indoor pool. The experimental results confirmed that the proposed system is able to provide high homing accuracy and robustness against disturbances that influence not only the captured camera images but also the movement of the vehicle. A successful docking operation using stereo vision that is new and novel to the underwater vehicle environment was achieved and thus proved the effectiveness of the proposed system for AUV.     

Dynamic Calibration of Pan–Tilt–Zoom Cameras for Traffic Monitoring

Pan–tilt–zoom (PTZ) cameras have been widely used in recent years for monitoring and surveillance applications. These cameras provide flexible view selection as well as a wider observation range. This makes them suitable for vision-based traffic monitoring and enforcement systems. To employ PTZ cameras for image measurement applications, one first needs to calibrate the camera to obtain meaningful results. For instance, the accuracy of estimating vehicle speed depends on the accuracy of camera calibration and that of vehicle tracking results. This paper presents a novel calibration method for a PTZ camera overlooking a traffic scene. The proposed approach requires no manual operation to select the positions of special features. It automatically uses a set of parallel lane markings and the lane width to compute the camera parameters, namely, focal length, tilt angle, and pan angle. Image processing procedures have been developed for automatically finding parallel lane markings. Interesting experimental results are presented to validate the robustness and accuracy of the proposed method.     

梯形视野结构化道路视觉识别方法研究

本文对基于机器视觉的路径识别方法进行了研究。通过对采集的路面图像进行中值滤波、边缘增强、动态阈值二值化,获得良好的路标图像。根据道路特征识别出道路标识线,并拟合出车辆运动的引导线。使用梯形小视野直线拟合法,减少图像处理时间和提高道路识别的可靠性。通过自制小车的实验表明,该算法具有良好的实时性、可靠性。     

Virtual 3D City Model for Navigation in Urban Areas

In this paper, we propose to study the integration of a new source of a priori information, which is the virtual 3D city model. We study this integration for two tasks: vehicles geo-localization and obstacles detection. A virtual 3D city model is a realistic representation of the evolution environment of a vehicle. It is a database of geographical and textured 3D data. We describe an ego-localization method that combines measurements of a GPS (Global Positioning System) receiver, odometers, a gyrometer, a video camera and a virtual 3D city model. GPS is often consider as the main sensor for localization of vehicles. But, in urban areas, GPS is not precise or even can be unavailable. So, GPS data are fused with odometers and gyrometer measurements using an Unscented Kalman Filter (UKF). However, during long GPS unavailability, localization with only odometers and gyrometer drift. Thus, we propose a new observation of the location of the vehicle. This observation is based on the matching between the current image acquired by an on-board camera and the virtual 3D city model of the environment. We also propose an obstacle detection method based on the comparison between the image acquired by the on-board camera and the image extracted from the 3D model. The following principle is used: the image acquired by the on-board camera contains the possible dynamic obstacles whereas they are absent from the 3D model. The two proposed concepts are tested on real data.