基于深度卷积神经网络的视觉里程计研究

视觉里程计利用视频信息来估计相机运动的位姿参数，实现对智能体的定位。传统视觉里程计方法需要特征提取、特征匹配/跟踪、外点剔除、运动估计、优化等流程，解算非常复杂，因此，提出了基于卷积神经网络的方法来实现端对端的单目视觉里程计。借助卷积神经网络对彩色图片自动学习提取图像帧间变化的全局特征，将用于分类的卷积神经网络转化为帧间时序特征网络，通过三层全连接层输出相机的帧间相对位姿参数。在KITTI数据集上的实验结果表明，提出的Deep-CNN-VO模型可以较准确地估计车辆的运动轨迹，证明了方法的可行性。在简化了复杂模型的基础上，与传统的视觉里程计系统相比，该模型的精度也有所提高。     

Point-to-hyperplane ICP: fusing different metric measurements for pose estimation

The objective of this article is to provide a generalized framework of a novel method that investigates the problem of combining and fusing different types of measurements for pose estimation. The proposed method allows to jointly minimize the different metric errors as a single measurement vector in n-dimensions without requiring a scaling factor to tune their importance. This paper is an extended version of previous works that introduced the Point-to-hyperplane Iterative Closest Point (ICP) approach. In this approach, an increased convergence domain and a faster alignment were demonstrated by considering a four-dimensional measurement vector (3D Euclidean points + Intensity). The method has the advantages of the classic point-to-plane ICP method, but extends this to higher dimensions. For demonstration purposes, this paper will focus on a RGB-D sensor that provides colour and depth measurements simultaneously and an optimal error in higher dimensions will be minimized from this. Results on both, simulated and real environments will be provided and the performance of the proposed method will be carried on real-time visual SLAM.     

基于惯性测量单元辅助的激光里程计求解方法

在同步定位与建图(SLAM)问题中,里程计部分的求解精度对后续建图起着至关重要的作用,惯性测量单元(IMU)可以为SLAM中里程计求解提供良好辅助。在考虑平面移动机器人运动特点及室内环境特征的基础上提出一种基于IMU松耦合的激光里程计求解方法,实现里程计部分的精准定位。第1阶段,机器人运动过程中实时处理点云信息,将地面点分割并提取有效关键点;第2阶段,将IMU信息引入卡尔曼滤波器,为帧间匹配提供位姿先验;第3阶段,滤波器输出位姿估计值后,利用非线性优化方法进行点云帧间匹配,实现里程计运动的求解。实验表明,所提方法在激光点云处理、运动求解,具有良好的稳定性和准确性,可将偏移量误差控制在0.4%以内,为后续建图提供有力数据保障。     

Quadratic modeling of wheeled moving platforms on planes

Planar motion of wheeled moving platforms, on which a camera is installed to capture videos, is common in real‐world scenarios. For a general planar motion, Scaramuzza et al. proposed a linear one‐point model to recover motions from a video under a potential assumption that the camera needs to be placed somewhere between the rear wheels of a moving platform. However, the assumption is too restricted for researchers and manufacturers, because the camera is generally fixed either on the front top of vehicles for a broad view or near the left/right mirrors because of the requirement of mechanical design. In this paper, we focus on motion modeling of wheeled moving platforms without the restriction of cameras' location on a vehicle, and propose a quadratic motion model to circumvent the limitation. Newton's iterative method and bounded quadratic least squares are used to solve the quadratic optimization problem. We test our model on both the synthetic data and the real data, and conclude that the tradeoff between model error and computational error and that between performance and computational cost are the main concerns in the practice of visual odometry. © 2015 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.     

基于不确定性分析的视觉里程计优化

通过推导视觉里程计中运动参数估计的不确定度,分析了视觉里程计的定位精度.采用矩阵扰动理论,准确计算了基于最小二乘法运动估计算法给出的6个自由度运动参数估计的不确定性,此方法的计算复杂度为O(1).采用扩展卡尔曼滤波器对视觉里程计和惯性测量单元数据进行融合优化,获得了更加准确的机器人定位和姿态信息.融合实验结果表明,融合后的闭合误差比单一的视觉里程计闭合误差减少近49.5%.     

室内环境下基于平面与线段特征的RGB-D视觉里程计

针对室内环境的结构特点,提出一种使用平面与线段特征的RGB-D视觉里程计算法．首先根据RGB-D扫描点的法向量对3D点云进行聚类,并使用随机抽样一致（RANSAC）算法对每簇3D点集进行平面拟合,抽取出环境中的平面特征;随后利用边缘点检测算法分割出环境中的边缘点集,并提取出环境中的线段特征;然后提出一种基于平面与线段几何约束的特征匹配算法,完成特征之间的匹配．在平面与线段特征匹配结果能提供充足的位姿约束的条件下,利用特征之间的匹配关系直接求解RGB-D相机的位姿;若不能,则利用匹配线段的端点以及线段点集来实现RGB-D相机位姿的估计．在TUM公开数据集中的实验证明了选择平面与线段作为环境特征可以提升视觉里程计估计和环境建图的精度．特别是在fr3/cabinet数据集中,本文算法的旋转、平移的均方根误差分别为2.046°/s、0.034m/s,要显著优于其他经典的视觉里程计算法．最终将本文系统应用到实际的移动机器人室内建图中,系统可以建立准确的环境地图,且系统运行速度可以达到3帧/s,满足实时处理的要求．     

基于CarSim和Matlab的智能车辆视觉里程计仿真平台设计

基于特征的视觉里程计系统主要由特征检测与跟踪模块以及位姿计算模块两部分组成。为分析车载视觉里程计系统中引入车辆运动学约束的位姿计算算法性能,根据摄像机成像及视觉几何学原理,采用Matlab结合车辆动力学仿真软件CarSim建立车载视觉里程计仿真平台。该仿真平台由车辆运动仿真模块、成像仿真模块、数据显示与分析模块组成,仿真平台的测试对象为视觉里程计的位姿估计算法模块。该仿真平台充分考虑车载视觉定位系统的运动特性,为研究车辆运动学约束在视觉里程计系统中的应用提供新的思路和工具。对提出的一种全新的基于车辆运动学约束的位姿估计内层算法,在此仿真平台上进行性能验证。仿真结果表明,该算法在计算精度与效率上都能够满足实时车载视觉定位的要求。     

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.     

A review of visual inertial odometry from filtering and optimisation perspectives

Visual inertial odometry (VIO) is a technique to estimate the change of a mobile platform in position and orientation overtime using the measurements from on-board cameras and IMU sensor. Recently, VIO attracts significant attentions from large number of researchers and is gaining the popularity in various potential applications due to the miniaturisation in size and low cost in price of two sensing modularities. However, it is very challenging in both of technical development and engineering implementation when accuracy, real-time performance, robustness and operation scale are taken into consideration. This survey is to report the state of the art VIO techniques from the perspectives of filtering and optimisation-based approaches, which are two dominated approaches adopted in the research area. To do so, various representations of 3D rigid motion body are illustrated. Then filtering-based approaches are reviewed, and followed by optimisation-based approaches. The links between these two approaches will be clarified via a framework of the Bayesian Maximum A Posterior. Other features, such as observability and self calibration, will be discussed.