基于全景相机的3D坐标测量方法

全景相机通过一次成像获取其周围3600场景,是一种大视场快速图像采集装置。研究了应用双鱼眼全景相机获取三维空间点的方法,研究了单鱼眼镜头成像模型,双鱼眼全景相机成像模型及图像变换原理。研究了鱼眼镜头成像畸变等校模型参数的标定方法,实现了对鱼眼畸变图像的矫正。提出了由全景图像数据解算任意方向等效鱼眼镜头成像数据的数学模型。最后应用平行光轴双目立体视觉技术,获得了被测场景的3D坐标数据。研究结果表明,应用这种方法在4 m×3 m×3 m的测量范围内精度可达13 mm。     

Binocular Spherical Stereo

A fish-eye camera has a wide field of view (FOV), and the realization of a binocular fish-eye stereo for sensing the surrounding 3-D information of the environment around a vehicle is useful for safe driving. However, since a fish-eye camera may have a wider-than-hemispherical FOV, the conventional stereo approach of obtaining a perspective image based on the pinhole camera model cannot directly be applied. However, using a spherical camera model and defining the disparity of a spherical stereo, the conventional binocular stereo problem is reformulated as a binocular spherical stereo problem. A binocular spherical stereo is a generalized paradigm that can cope with cameras having any FOV, including conventional cameras and fish-eye cameras. Moreover, by transforming the rectified spherical images to latitude–longitude representation, the feature point matching of the spherical stereo images can be sped up by using the processing used for perspective stereo images. The effectiveness of this approach is demonstrated by realizing a binocular spherical stereo using a pair of fish-eye cameras. Finally, the application of the proposed approach to vehicles in the future is considered.      

Autonomous Navigation of Vehicles from a Visual Memory Using a Generic Camera Model

In this paper, we present a complete framework for autonomous vehicle navigation using a single camera and natural landmarks. When navigating in an unknown environment for the first time, usual behavior consists of memorizing some key views along the performed path to use these references as checkpoints for future navigation missions. The navigation framework for the wheeled vehicles presented in this paper is based on this assumption. During a human-guided learning step, the vehicle performs paths that are sampled and stored as a set of ordered key images, as acquired by an embedded camera. The visual paths are topologically organized, providing a visual memory of the environment. Given an image of the visual memory as a target, the vehicle navigation mission is defined as a concatenation of visual path subsets called visual routes. When autonomously running, the control guides the vehicle along the reference visual route without explicitly planning any trajectory. The control consists of a vision-based control law that is adapted to the nonholonomic constraint. Our navigation framework has been designed for a generic class of cameras (including conventional, catadioptric, and fisheye cameras). Experiments with an urban electric vehicle navigating in an outdoor environment have been carried out with a fisheye camera along a 750-m-long trajectory. Results validate our approach.     

基于组合式传感器的智能监视节点设计

设计了一种新颖的组合式地面传感器智能监视网络节点,该节点由新型热释电红外传感器、微波感应位移模块和微型串口摄像机组成。其中,红外传感器和微波传感器分别用于检测横向和纵向移动目标,二者输出的脉冲信号用于触发串口摄像机抓拍目标图像,以避免耗电量较大的摄像机连续工作。此外,微波传感器采用脉冲供电,进一步降低节点功耗。实验结果表明:本红外传感器和微波传感器的目标探测距离均达到40 m,与带有红外补光和图像压缩的大焦距镜头串口摄像机的作用距离相匹配,从而实现了体积小、功耗低、高集成度、适用于野外或室内无人值守的地面传感器节点的设计目标。     

基于DSP的SVM算法实现鱼眼镜头畸变校正

鱼眼镜头应用于全方位视觉跟踪导航系统中,但其产生的畸变如不加以精确实时的校正必然导致定位错误和偏差。本文创新地采用鱼眼镜头所采集的图像特征点训练支持向量机(SVM),使其产生回归径向距离的模型并生成坐标映射,然后通过查表法实时的校正采集的图像,用TMS320DM642处理鱼眼镜头畸变的实时校正。结果证实,该方法校正效果好,响应速度快,满足图像处理的实时性要求;并且用DSP代替以往PC运算,可简化整体结构,压缩系统体积。     

Estimation of image scale variations in monocular visual odometry systems

Reliable estimation of the vehicle position is the main prerequisite in all autonomous mobile robotic applications. Image‐scale uncertainty in correlation‐based monocular visual odometry systems negatively affects the accuracy of the vehicle motion estimation. This paper presents the development of a new technique and algorithm to estimate image‐scale variations due to camera height fluctuations when the vehicle is driven on uneven terrains or when the height of vehicle from ground changes as a result of changes in load or number of passengers in the vehicle. This technique depends on marking the image frames by two red laser points, as independent reference points, which have a certain distance between them. The image‐scale variations can be estimated by monitoring the variations in the distance between these two reference points. The proposed technique eliminates the need for camera recalibration and the use of sensors to measure the variations of camera height from ground, such as laser range finders and acceleration sensors. The developed system uses a single downward‐facing monocular camera supported by a lighting module and installed underneath the test vehicle to avoid the negative effect of directional sunlight and shadows, which can disturb the correlation. Indoor and outdoor experiments have proven the efficiency of the suggested technique in resolving image‐scale uncertainty and ensuring an image‐scale‐invariant correlation‐based matching, with only less than 5% additional computational time. © 2016 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.     

Ground-Texture-Based Localization for Intelligent Vehicles

Localization is a critical problem in the research of intelligent vehicles. Although it can be achieved by using a real-time kinematic global positioning system (RTK-GPS, or fused with other methods such as dead reckoning), it may be unfeasible if every vehicle has to be equipped with such an expensive sensor. This paper proposes a ground-texture-based map-matching approach to address the localization problem. To reduce the effect of complicated illumination in outdoor environments, a camera is fixed downward at the bottom of a vehicle, and controllable lights are also equipped around the camera for consistent illumination. The proposed approach includes two steps: 1) mapping and 2) localization. RTK-GPS is only used in the mapping, and other sensor data from camera and odometry are captured with time stamps to create a global ground texture map. A multiple-view registration-based optimization algorithm is applied to improve map accuracy. In the localization step, vehicle pose is estimated by matching the current camera frame with the best submap frame and by fusion strategy. Results with both synthetic and real experiments prove the feasibility and effectiveness of the proposed approach.     

基于概率路线图法的窄道采样与轨迹优化

提出一种结合莱维飞行和概率路线图法(Lévy-probabilistic roadmap, LPRM)的路径规划算法。将莱维飞行方法应用于窄道采样,障碍物中的随机点通过莱维飞行走至自由空间,并延长碰撞测试来确保采样点位于窄道内,提升狭窄区域的采样质量与效率;为避免大量无效点的生成,在采样前先对地图进行预处理,膨胀障碍并对其进行边界提取,根据边界信息计算狭窄区域采样点数量,保证了全图采样的合理分布;进一步考虑移动机器人的实际工作情况,采用分段贝塞尔曲线对路径轨迹进行优化使其符合运动学约束,提高移动机器人的机动性。仿真实验在不同环境地图下对比了LPRM、传统概率路线图(PRM)和桥测试3种算法,结果表明LPRM算法相较两者在单一窄道环境下规划效率分别提升35.1%和32.2%,在复杂环境下其规划效率分别提升32.9%和15.5%,且提前400和100个采样点达到收敛,规划效率和成功率显著提高,总体耗时更短、路径更优,能减少移动机器人本身的能耗,提高整体工作效率。     

LED location beacon system based on processing of digital images

This paper is in the field of vehicle positioning technology for the intelligent transportation systems. The ideas of an innovative light-emitting diode (LED)-based location beacon system are developed and verified. The system developed is a combination of several latest technologies which include a CMOS vision sensor, high brightness LED, and digital image processing techniques. It belongs to a new kind of simplex communication link. A digital camera is used to capture images contained in the LED beacon signal. The captured digital images are processed by the algorithms developed and a location code is extracted. The location code can be used for calibration of a vehicle positioning system which may consist of a GPS, inertial navigation system (INS) and other sensors. The issues examined include the structure of the transmitter and the receiver, the signaling method, the transmission protocol of the LED panel, the relationship between the camera capturing rate and the LED pattern update rate, the digital camera exposure technology, and the efficiency of the image processing algorithms. Experiments using a prototype transmitter and a receiver were performed. The experimental results provide a good demonstration of the viability of the ideas and methodologies developed     

Detection and classification of vehicles

This paper presents algorithms for vision-based detection and classification of vehicles in monocular image sequences of traffic scenes recorded by a stationary camera. Processing is done at three levels: raw images, region level, and vehicle level. Vehicles are modeled as rectangular patches with certain dynamic behavior. The proposed method is based on the establishment of correspondences between regions and vehicles, as the vehicles move through the image sequence. Experimental results from highway scenes are provided which demonstrate the effectiveness of the method. We also briefly describe an interactive camera calibration tool that we have developed for recovering the camera parameters using features in the image selected by the user     

基于红外技术的变电站温度监控

针对变电站各发热点温度测量和监控问题,提出利用红外摄像机代替昂贵的红外热像仪对电力设备进行实时非精确的温度监控设计方案。该方案基于自源无线红外温度传感器,利用微型太阳能电池为测温和发射设备提供电源;发射端把测温传感器测得的温度量转化为红外信号并发射;接收端的红外监控摄像机对传感器扫描接收;监控中心对提取的红外图像处理、分析后,给出温度指示和异常报警信号。解决了变电站内高温高压强干扰问题。并开发了软件界面进行实时监控,做到各被测点的温度实时显示。通过实际检验,所设计的方案获得满意的效果。     

Dynamic camera calibration of roadside traffic management cameras for vehicle speed estimation

In this paper, we present a new three-stage algorithm to calibrate roadside traffic management cameras and track vehicles to create a traffic speed sensor. The algorithm first estimates the camera position relative to the roadway using the motion and edges of the vehicles. Given the camera position, the algorithm then calibrates the camera by estimating the lane boundaries and the vanishing point of the lines along the roadway. The algorithm transforms the image coordinates from the vehicle tracker into real-world coordinates using our simplified camera model. We present results that demonstrate the ability of our algorithm to produce good estimates of the mean vehicle speed in a lane of traffic.     

高帧频DVI接口彩色CMOS数字相机系统设计

针对高帧频彩色CMOS图像传感器在机器视觉高速成像领域中的应用,本文介绍利用高性能可编程逻辑器件FPGA实现CMOS图像传感器MI-MV13的高速驱动时序的设计,并且在FPGA内部设计了高速FIFO缓存器和双口RAM来完成Bayer彩色阵列图像数据的实时同步转换输出RGB彩色分量。最终由2片专用DVI接口集成芯片SiI178实现了DVI-IDualLink模式的高帧频高分辨率彩色图像输出,DVI接口方便显示终端和高速存储设备链接。该相机系统具有集成度高、低功耗、接口通用紧凑、传输带宽高的优点。     

A compact integrated visual motion sensor for ITS applications

We have developed a prototype of a compact integrated visual sensor which detects direction and velocity of motion on a focal plane in a wide brightness range in real time with a newly devised motion measurement method. The sensor is composed of a lens and a single-chip very large scale integration whose die size is 2 mm /spl times/ 2 mm that was fabricated with a 1.5-/spl mu/ standard CMOS process. The spatial resolution is 10 /spl times/ 2. As a result of performance evaluation of the prototype sensor, it was confirmed that the sensor can detect motion direction and velocity up to an on-chip image velocity of 100 mm/s in a response time of 10 /spl mu/s under an illuminance range between 100 and 100,000 lux. Furthermore, we have demonstrated effectiveness of the visual sensor by applying the sensor to running vehicle detection on a road and blind-corner monitoring at a road junction.     

基于两灭点法的摄像机标定方法研究

在计算机视觉当中,要对物体进行三维重建,需要实现对相机进行标定,即获得相机的的焦距(内参数)、旋转矩阵以及偏移向量(外参数)。为提高场景摄像机的标定精度和标定效率,研究了一种基于2个灭点的快速摄像机标定方法。该方法利用灭点理论,只要求被标定相机拍摄的图像中有2组相互正交的平行线,且这2组平行线与成像平面不平行,由此可以获得2个灭点;为计算平移向量,图像中某个平行线方向上的一段直线的实际长度需已知。根据灭点的几何投影特性计算相机内外参数。利用监控摄像机进行试验验证,验证结果表明,该方法相对于传统的标定方法操作简单并且精度较高,具有一定的理论意义和实用价值。     

多GigE相机高速视觉系统的架构与处理速度研究

提出了一种高精度大视场的高速并行处理系统,采用GigE相机并行检测,所有相机排列成线性阵列,通过千兆Ethernet网络与主机连接,并行检测将各单个相机视场合并为一个大视场,在保持单个相机检测分辨率不变的同时扩大检测的范围;并行检测系统可根据图像数据量的变化灵活配置每台相机采集的图像由单台或多台计算机进行处理;数据传输上整个系统采用非碰撞的确定延时网络传输处理结果以确保实时性。通过使用网络延迟理论和OPNET仿真验证得到系统处理的延迟时间不大于162.8μs。     

Robust image-based detection of activity for traffic control

An important application of image processing and computer vision is the development of intelligent systems for traffic monitoring, management and optimization. This paper presents a system for real-time detection of moving vehicles approaching an intersection from sequences of colour images acquired by a stationary camera. The proposed approach is developed in the context of traffic-light control systems. As the system is dedicated to outdoor applications, efficient and robust vehicle detection under various weather and illumination conditions must be achieved. To deal with these ever-changing conditions, the vehicle detection relies on motion segmentation with dynamic background representation and on an original switching algorithm using hue-saturation-value (HSV) colour mapping to achieve feature space segmentation. Experimental results using real outdoor image sequences demonstrate the systems robustness under various and difficult environmental conditions.     

路面病害巡检评估系统中的裂缝检测技术

由于使用手持设备的网络型混凝土路面病害巡检评估系统与车载道路检测系统的病害图片处理方法不同,针对使用手持设备的网络型混凝土路面病害巡检评估系统提出一种基于图像处理的可纠正图像畸变的混凝土路面裂缝检测技术。1)使用张定友法对摄像头进行标定,获得摄像头内外参数;2)对路面病害图像进行预处理;然后,通过阈值分割法检测出路面裂缝,根据背景连通域数量的差异,实现了裂缝分类;通过投影法对出横、纵和斜向裂缝实现分类。3)对线性裂缝提取裂缝骨架细化并根据实际版块长宽,求出裂缝长度、平均宽度等病害参数;对于网状裂缝通过求其最小外接矩形计算其破损面积。     

基于机器视觉的孔类零件尺寸在线检测

应用机器视觉技术对孔类零件进行尺寸测量,采用边加工边测量的方式进行在线检测,可有效缩短零件的生产周期,提高生产效率.通过分析零件的工艺特征,选用CMOS相机与高精度远心镜头,对有倒角的特征采用环形光源照明,对未倒角的特征采用同轴光源照明,提高了硬件平台的柔性化.针对图像采集与传输过程中的椒盐噪声与高斯噪声,对采集后的灰...     

Spectroscopic Measurements of Oxygen Saturation in the Retina

We introduce a new type of retinal oximeter able to capture multiple spectroscopic sensitive images of the retina in a single snapshot. The core of our apparatus is a multiaperture camera that can be easily interfaced with a fundus camera system. A lenslet array divides the image collected by a fundus camera into identical subimages. A bandpass filter array in front of the lens system is used to collect the subimages only at the wavelengths of interest. Two different instruments were designed based on this simple principle. The first system can collect six different images, while the second system can collect up to 18 different images in a single snapshot.