融合深度和颜色信息的图像物体分割算法

讨论立体图对的图像分割问题,提出一种基于深度和颜色信息的图像物体分割算法。该算法首先利用基于聚类的Mean-shift分割算法对目标图像进行适度的过分割,同时借助双目立体视觉算法获取立体图对的稠密深度图,并依据深度不连续性从过分割结果中选取用于继续进行“精致”分割的种子点集,接着对未分配种子标签的区域用图割算法分配标签,并对彼此之间没有深度不连续边界但具有不同标签的相邻区域进行融合。相比于传统图像分割算法,该算法可有效克服过分割和欠分割问题,获取具有一定语义的图像分割结果。相关的对比实验结果验证了该算法的有效性。     

Tightly-coupled stereo vision-aided inertial navigation using feature-based motion sensors

A tightly-coupled stereo vision-aided inertial navigation system is proposed in this work, as a synergistic incorporation of vision with other sensors. In order to avoid loss of information possibly resulting by visual preprocessing, a set of feature-based motion sensors and an inertial measurement unit are directly fused together to estimate the vehicle state. Two alternative feature-based observation models are considered within the proposed fusion architecture. The first model uses the trifocal tensor to propagate feature points by homography, so as to express geometric constraints among three consecutive scenes. The second one is derived by using a rigid body motion model applied to three-dimensional (3D) reconstructed feature points. A kinematic model accounts for the vehicle motion, and a Sigma-Point Kalman filter is used to achieve a robust state estimation in the presence of non-linearities. The proposed formulation is derived for a general platform-independent 3D problem, and it is tested and demonstrated with a real dynamic indoor data-set alongside of a simulation experiment. Results show improved estimates than in the case of a classical visual odometry approach and of a loosely-coupled stereo vision-aided inertial navigation system, even in GPS (Global Positioning System)-denied conditions and when magnetometer measurements are not reliable.     

Multimodal localization: Stereo over LiDAR map

In this paper, we present a real‐time high‐precision visual localization system for an autonomous vehicle which employs only low‐cost stereo cameras to localize the vehicle with a priori map built using a more expensive 3D LiDAR sensor. To this end, we construct two different visual maps: a sparse feature visual map for visual odometry (VO) based motion tracking, and a semidense visual map for registration with the prior LiDAR map. To register two point clouds sourced from different modalities (i.e., cameras and LiDAR), we leverage probabilistic weighted normal distributions transformation (ProW‐NDT), by particularly taking into account the uncertainty of source point clouds. The registration results are then fused via pose graph optimization to correct the VO drift. Moreover, surfels extracted from the prior LiDAR map are used to refine the sparse 3D visual features that will further improve VO‐based motion estimation. The proposed system has been tested extensively in both simulated and real‐world experiments, showing that robust, high‐precision, real‐time localization can be achieved.     

基于立体视觉的移动机器人导航算法

移动机器人立体视觉系统不仅提供三维地形图用于障碍规避和路径规划,其结果还可以用于视觉导航。以移动机器人立体视觉系统为基础,研究了基于前后两个位置上立体图对的视觉测量算法用于移动机器人的连续导航,讨论了影响导航精度的因素和改进方法;研究了基于局部和全局三维地形图的地形匹配算法用于定期校正位置误差,算法实现简便,定位精度取决于地形图精度。实验结果证明了两种方法的有效性,可以兼顾近距离和中远距离导航任务。     

基于立体视觉运动速度检测系统的研究及实现

介绍了一种基于立体视觉的运动速度检测系统的结构框架。系统在采集卡自带的软件开发包的基础上进行二次软件开发,加入了摄像机标定和图像处理分析部分。整个检测系统主要包括图像采集和运动检测两大环节;涵盖摄像机标定、图像获取及预处理、目标分割、3D定位、速度求取5个功能模块,并具有友好的操作界面,方便用户使用。文章重点针对目标分割和定位中所采用的技术方法展开了讨论。该系统可以具体应用在车辆和游乐设施等的运动速度检测上,在设备的安全运行以及交通监管方面有重要意义。     

集成RGB-D语义分割网络的室内语义地图构建

针对传统视觉SLAM准确度低、实时性差、缺乏语义的问题,提出一种全新的RGB-D语义分割网络,利用室内场景中受光照等条件影响较小的深度信息来提高分割的准确性,并且设计了轻量级多尺度残差模块（MRAM）和空间金字塔池化模块（ASPP）来轻量化分割网络、提高分割的精度。首先输入的图像序列进入ORB-SLAM2网络进行关键帧筛选,之后关键帧送入语义分割网络得到二维语义标签,再将二维语义信息映射到三维点云空间,最后使用贝叶斯算法更新三维地图得到全局一致的三维点云语义地图。实验采用NYUv2数据集验证语义分割网络性能,采用TUM数据集构建点云语义地图,结果表明,提出的语义分割网络性能和速度优于现有的模型,且此语义分割网络与视觉SLAM相结合可以满足高精度、实时的稠密三维语义点云地图构建要求。     

Binocular matching constraints from motion

Structure from motion and structure from stereo are two vision cues for achieving 3D reconstruction. The two cues have complementary strengths; while 3D reconstruction is accurate but correspondence establishment is difficult in the stereo cue, the reverse is true in the motion cue. This paper addresses how to combine the two cues when a stereo pair of cameras are available to capture image data for 3D reconstruction. The work is distinct in that, in contrast with the previous ones, it is not to exploit the redundancy in the image data for boosting the reconstruction accuracy, but to make the two vision cues complementary, preserving their strengths and avoiding their weaknesses. A mechanism is introduced that allows dense motion correspondences in the two separate image streams be transferred to dense binocular correspondences across the image streams, so that 3D can be reconstructed from the latter and accurate reconstruction is possible even with short motions of the stereo rig. Both the stereo correspondences and the motion of the stereo rig are assumed to be unknown in this work. Experiments involving real image data are presented to indicate the feasibility and robustness of the approach.     

Probabilistic voxel mapping using an adaptive confidence measure of stereo matching

In this paper, we describe a probabilistic voxel mapping algorithm using an adaptive confidence measure of stereo matching. Most of the 3D mapping algorithms based on stereo matching usually generate a map formed by point cloud. There are many reconstruction errors. The reconstruction errors are due to stereo reconstruction error factors such as calibration errors, stereo matching errors, and triangulation errors. A point cloud map with reconstruction errors cannot accurately represent structures of environments and needs large memory capacity. To solve these problems, we focused on the confidence of stereo matching and probabilistic representation. For evaluation of stereo matching, we propose an adaptive confidence measure that is suitable for outdoor environments. The confidence of stereo matching can be reflected in the probability of restoring structures. For probabilistic representation, we propose a probabilistic voxel mapping algorithm. The proposed probabilistic voxel map is a more reliable representation of environments than the commonly used voxel map that just contains the occupancy information. We test the proposed confidence measure and probabilistic voxel mapping algorithm in outdoor environments.     

Slip-compensated path following for planetary exploration rovers

A system that enables continuous slip compensation for a Mars rover has been designed, implemented and field-tested. This system is composed of several components that allow the rover to accurately and continuously follow a designated path, compensate for slippage and reach intended goals in high-slip environments. These components include visual odometry, vehicle kinematics, a Kalman filter pose estimator and a slip-compensated path follower. Visual odometry tracks distinctive scene features in stereo imagery to estimate rover motion between successively acquired stereo image pairs. The kinematics for a rocker–bogie suspension system estimates vehicle motion by measuring wheel rates, and rocker, bogie and steering angles. The Kalman filter processes measurements from an inertial measurement unit and visual odometry. The filter estimate is then compared to the kinematic estimate to determine whether slippage has occurred, taking into account estimate uncertainties. If slippage is detected, the slip vector is calculated by differencing the current Kalman filter estimate from the kinematic estimate. This slip vector is then used to determine the necessary wheel velocities and steering angles to compensate for slip and follow the desired path.     

Map building through pseudo dense scan matching using visual sonar data

This paper presents a novel approach to the vision based grid map building and localization problem that works in a complex indoor environment with a single forward viewing camera. Most existing visual SLAM has been limited to the feature-based method and only a few researchers have proposed visual SLAM methods for building a grid map using a stereo vision system which has not been popular in practical application. In this paper, we estimate the planar depth by applying a simple visual sonar ranging technique to the single camera image and then associating sequential scans through our own pseudo dense adaptive scan matching algorithm reducing the processing time compared to the standard point-to-point correspondence based algorithm and finally produce a grid map. To this end, we construct a Pseudo Dense Scan (PDS) which is an odometry based temporal accumulation of the visual sonar readings emulating omni-directional sensing in order to overcome the sparseness of the visual sonar. Moreover, in order to obtain a much more refined map, we further correct the slight trajectory error incurred in the PDS construction step using Sequential Quadratic Programming (SQP) which is a well-known optimization scheme. Experimental results show that our method can obtain an accurate grid map using a single camera without the need for a high price range sensors or stereo camera.

立体视觉里程计中基于微粒群优化的初始运动估计和内点检测

初始运动估计和内点检测是影响立体视觉里程计定位精度的重要因素.目前,立体视觉里程计都采用基于3点线性运动估计的随机采样一致性(random sample consensus,RANSAC)方法.本文分析了随机采样一致性方法在初始运动估计中的性能:该方法对排除误匹配点是有效的,但在一定采样次数下采样到特征点提取误差和立体匹配误差都很小的匹配点的概率是很小的,所以通过该方法得到的初始运动参数和匹配内点不够精确。本文提出了采用微粒群优化的初始运动估计和内点检测新方法,该方法收敛速度快,搜索精确解的能力强,能够获得高精度的运动参数和匹配内点.立体视觉里程计仿真实验和真实智能车实验表明:和随机采样一致性方法相比,本文方法在运行时间、定位精度方面都更优越.     

一种结合光流追踪的双目视觉里程计算法

针对特征点法视觉里程计频繁计算和匹配描述子导致系统实时性能变差的问题,提出一种结合光流追踪的双目视觉里程计算法;首先进行初始化,生成初始的关键帧和地图点,随后在追踪线程中使用光流追踪特征点获取匹配关系,计算并优化相机位姿;满足生成关键帧的条件后,将当前帧设置为关键帧,提取图像的ORB特征点,并使用描述子匹配获取与上一关键帧特征点的匹配关系,三角化生成新的地图点;最后在优化线程中将新的关键帧和地图点使用滑动窗口算法进行优化,剔除冗余关键帧和地图点;在KITTI数据集上的实验结果表明,所提出的算法轨迹误差与双目模式下的ORB-SLAM3算法处于同一水平,同时实时性能有大幅度提高,追踪每一帧图像的平均时间从52ms降至16ms,在保证高精度的情况下运行速度大大提高,具有较高的实用价值.     

Multi-modal object detection and localization for high integrity driving assistance

Much work is currently devoted to increasing the reliability, completeness and precision of the data used by driving assistance systems, particularly in urban environments. Urban environments represent a particular challenge for the task of perception, since they are complex, dynamic and completely variable. This article examines a multi-modal perception approach for enhancing vehicle localization and the tracking of dynamic objects in a world-centric map. 3D ego-localization is achieved by merging stereo vision perception data and proprioceptive information from vehicle sensors. Mobile objects are detected using a multi-layer lidar that is simultaneously used to identify a zone of interest to reduce the complexity of the perception process. Object localization and tracking is then performed in a fixed frame which simplifies analysis and understanding of the scene. Finally, tracked objects are confirmed by vision using 3D dense reconstruction in focused regions of interest. Only confirmed objects can generate an alarm or an action on the vehicle. This is crucial to reduce false alarms that affect the trust that the driver places in the driving assistance system. Synchronization issues between the sensing modalities are solved using predictive filtering. Real experimental results are reported so that the performance of the multi-modal system may be evaluated.     

深度卷积神经网络图像语义分割研究进展

在计算机视觉领域中,语义分割是场景解析和行为识别的关键任务,基于深度卷积神经网络的图像语义分割方法已经取得突破性进展。语义分割的任务是对图像中的每一个像素分配所属的类别标签,属于像素级的图像理解。目标检测仅定位目标的边界框,而语义分割需要分割出图像中的目标。本文首先分析和描述了语义分割领域存在的困难和挑战,介绍了语义分割算法性能评价的常用数据集和客观评测指标。然后,归纳和总结了现阶段主流的基于深度卷积神经网络的图像语义分割方法的国内外研究现状,依据网络训练是否需要像素级的标注图像,将现有方法分为基于监督学习的语义分割和基于弱监督学习的语义分割两类,详细阐述并分析这两类方法各自的优势和不足。本文在PASCAL VOC（pattern analysis, statistical modelling and computational learning visual object classes）2012数据集上比较了部分监督学习和弱监督学习的语义分割模型,并给出了监督学习模型和弱监督学习模型中的最优方法,以及对应的MIoU（mean intersection-over-union）。最后,指出了图像语义分割领域未来可能的热点方向。     

基于双目相机的视觉里程计

针对移动机器人视觉导航定位需求,提出一种基于双目相机的视觉里程计改进方案。对于特征信息冗余问题,改进ORB(oriented FAST and rotated BRIEF)算法,引入多阈值FAST图像分割思想,为使误匹配尽可能减少,主要运用快速最近邻和随机采样一致性算法;一般而言,运用的算法主要是立体匹配算法,此算法的特征主要指灰度,对此算法做出改进,运用一种新型的双目视差算法,此算法主要以描述子为特征,据此恢复特征点深度;为使所得位姿坐标具有相对较高的准确度,构造一种特定的最小二乘问题,使其提供初值,以相应的特征点三维坐标为基础,基于有效方式对相机运动进行估计。根据数据集的实验结果可知,所提双目视觉里程具有相对而言较好的精度及较高的实时性。     

基于视觉惯性融合的半直接单目视觉里程计

针对半直接单目视觉里程计缺乏尺度信息并且在快速运动中鲁棒性较差的缺点,设计了一种融合惯性测量信息的半直接单目视觉里程计,通过IMU（惯性测量单元）信息弥补视觉里程计的缺陷,有效提高跟踪精度与系统鲁棒性．本文联合惯性测量信息与视觉信息进行初始化,较准确地恢复了环境尺度信息．为提高运动跟踪的鲁棒性,提出一种IMU加权的运动先验模型．通过预积分获取IMU的状态估计,根据IMU先验误差调整权重系数,使用IMU先验信息的加权值为前端提供精确的初值．后端构建了紧耦合的图优化模型,融合惯性、视觉以及3维地图点信息进行联合优化,同时在滑动窗口中使用强共视关系作为约束,在消除局部累积误差的同时提高优化效率与优化精度．实验结果表明,本文的先验模型优于匀速运动模型与IMU先验模型,单帧先验误差小于1 cm．后端优化方法改进后,计算效率提高为原来的1.52倍,同时轨迹精度与优化稳定性也得到提高．在EuRoC数据集上进行测试,定位效果优于OKVIS算法,轨迹均方根误差减小为原视觉里程计的1/3．     

融合双目视觉和2D激光雷达的室外定位

高精度的定位对于自动驾驶至关重要. 2D激光雷达作为一种高精度的传感器被广泛应用于各种室内定位系统.然而在室外环境下,大量动态目标的存在使得相邻点云的匹配变得尤为困难,且2D激光雷达的点云数据存在稀疏性的问题,导致2D激光雷达在室外环境下的定位精度极低甚至无法实现定位.为此,提出一种融合双目视觉和2D激光雷达的室外定位算法.首先,利用双目视觉作为里程计提供相对位姿,将一个局部时间窗口内多个时刻得到的2D激光雷达数据融合成一个局部子图;然后,采用DS证据理论融合局部子图中的时态信息,以消除动态目标带来的噪声;最后,利用基于ICA的图像匹配方法将局部子图与预先构建的全局先验地图进行匹配,消除里程计的累积误差,实现高精度定位.在KITTI数据集上的实验结果表明,仅利用低成本的双目相机和2D激光雷达便可实现较高精度的定位,所提出算法的定位精度相比于ORB-SLAM2里程计最高可提升37.9%.     

基于拉普拉斯分布的双目视觉里程计EI北大核心CSCD

针对相机在未知环境中定位及其周围环境地图重建的问题,本文基于拉普拉斯分布提出了一种快速精确的双目视觉里程计算法.在使用光流构建数据关联时结合使用三个策略:平滑的运动约束、环形匹配以及视差一致性检测来剔除错误的关联以提高数据关联的精确性,并在此基础上筛选稳定的特征点.本文单独估计相机的旋转与平移.假设相机旋转、三维空间点以及相机平移的误差都服从拉普拉斯分布,在此假设下优化得到最优的相机位姿估计与三维空间点位置.在KITTI和New Tsukuba数据集上的实验结果表明,本文算法能快速精确地估计相机位姿与三维空间点的位置.     

三维视觉前沿进展

在自动驾驶、机器人、数字城市以及虚拟/混合现实等应用的驱动下,三维视觉得到了广泛的关注。三维视觉研究主要围绕深度图像获取、视觉定位与制图、三维建模及三维理解等任务而展开。本文围绕上述三维视觉任务,对国内外研究进展进行了综合评述和对比分析。首先,针对深度图像获取任务,从非端到端立体匹配、端到端立体匹配及无监督立体匹配3个方面对立体匹配研究进展进行了回顾,从深度回归网络和深度补全网络两个方面对单目深度估计研究进展进行了回顾。其次,针对视觉定位与制图任务,从端到端视觉定位和非端到端视觉定位两个方面对大场景下的视觉定位研究进展进行了回顾,并从视觉同步定位与地图构建和融合其他传感器的同步定位与地图构建两个方面对同步定位与地图构建的研究进展进行了回顾。再次,针对三维建模任务,从深度三维表征学习、深度三维生成模型、结构化表征学习与生成模型以及基于深度学习的三维重建等4个方面对三维几何建模研究进展进行了回顾,并从多视RGB重建、单深度相机和多深度相机方法以及单视图RGB方法等3个方面对人体动态建模研究进展进行了回顾。最后,针对三维理解任务,从点云语义分割和点云实例分割两个方面对点云语义理解研究进展进行了回顾。在此基础上,给出了三维视觉研究的未来发展趋势,旨在为相关研究者提供参考。