基于分级关键帧筛选的RGB-D SLAM算法研究

利用关键帧求解SLAM算法(simultaneous localization and mapping)能够提高SLAM系统的实时性与精确度。针对现存关键帧筛选算法中存在的计算复杂度高、图像帧冗余以及鲁棒性较差等问题,提出一种分级关键帧筛选方法。该算法考虑了SLAM系统在不同运行阶段时对关键帧的要求,首先结合旋转度指数与地图点跟踪筛选出一级关键帧用于后端优化与回环检测,再利用相邻帧在空间上的相对运动距离筛选出二级关键帧用于三维地图构建,最后,实现了基于此二级筛选算法的RGB-D SLAM系统。实验表明,一级关键帧算法能提高SLAM系统的定位和建图精度,二级关键帧算法则有效减少了数据冗余,提高了建图效率。     

室内动态环境下基于网格分割与双地图耦合的RGB-D SLAM算法

为解决室内动态环境下现有RGB-D SLAM（同步定位与地图创建）系统定位精度低、建图效果差的问题,提出一种基于网格分割与双地图耦合的RGB-D SLAM算法。基于单应运动补偿与双向补偿光流法,根据几何连通性与深度图像聚类结果实现网格化运动分割,同时保证算法的快速性。利用静态区域内的特征点最小化重投影误差对相机进行位置估计。结合相机位姿、RGB-D图像、网格化运动分割图像,同时构建场景的稀疏点云地图和静态八叉树地图并进行耦合,在关键帧上使用基于网格分割和八叉树地图光线遍历的方法筛选静态地图点,更新稀疏点云地图,保障定位精度。公开数据集和实际动态场景中的实验结果都表明,本文算法能够有效提升室内动态场景中的相机位姿估计精度,实现场景静态八叉树地图的实时构建和更新。此外,本文算法能够实时运行在标准CPU硬件平台上,无需GPU等额外计算资源。     

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.     

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。     

How to localize humanoids with a single camera?

In this paper, we propose a real-time vision-based localization approach for humanoid robots using a single camera as the only sensor. In order to obtain an accurate localization of the robot, we first build an accurate 3D map of the environment. In the map computation process, we use stereo visual SLAM techniques based on non-linear least squares optimization methods (bundle adjustment). Once we have computed a 3D reconstruction of the environment, which comprises of a set of camera poses (keyframes) and a list of 3D points, we learn the visibility of the 3D points by exploiting all the geometric relationships between the camera poses and 3D map points involved in the reconstruction. Finally, we use the prior 3D map and the learned visibility prediction for monocular vision-based localization. Our algorithm is very efficient, easy to implement and more robust and accurate than existing approaches. By means of visibility prediction we predict for a query pose only the highly visible 3D points, thus, speeding up tremendously the data association between 3D map points and perceived 2D features in the image. In this way, we can solve very efficiently the Perspective-n-Point (PnP) problem providing robust and fast vision-based localization. We demonstrate the robustness and accuracy of our approach by showing several vision-based localization experiments with the HRP-2 humanoid robot.     

面向半稠密三维重建的改进单目ORB-SLAM

构建更详细的地图以及估计更精准的相机位姿一直都是同时定位与地图构建（Simultaneous Localization And Mapping,SLAM）技术所追求的目标,但是以上目标与实时性要求、较低的计算代价和受限的计算资源条件是相矛盾的。提出一种在单目ORB-SLAM（Oriented FAST and Rotated BRIEF-SLAM）方法的基础上利用关键帧中提取到的直线特征进行半稠密三维重建的方法。由ORB-SLAM实时提供一组关键帧及其对应的相机位姿信息和一系列地图点,提出一种关键帧再剔除算法进一步减少冗余帧数目,使用直线段提取方法提取各帧中的直线段,使用纯几何约束方法对以上检测得到的直线段进行匹配,生成一个由直线段构成的半稠密三维场景模型。实验结果表明新方法持续稳定的运行,能在低计算代价条件下快速地在线三维重建。     

单目同时定位与建图中的地图恢复融合技术

目的 传统的单目视觉SLAM（simultaneous localization and mapping）跟踪失败后需要相机重新回到丢失的位置才能重定位并恢复建图,这极大限制了单目SLAM的应用场景。为解决这一问题,提出一种基于视觉惯性传感器融合的地图恢复融合算法。方法 当系统跟踪失败,仅由惯性传感器提供相机位姿,通过对系统重新初始化并结合惯性传感器提供的丢失部分的相机位姿将丢失前的地图融合到当前的地图中;为解决视觉跟踪丢失期间由惯性测量计算导致的相机位姿误差,提出了一种以关键帧之间的共视关系为依据的跳跃式的匹配搜索策略,快速获得匹配地图点,再通过非线性优化求解匹配点之间的运动估计,进行误差补偿,获得更加准确的相机位姿,并删减融合后重复的点云;最后建立前后两个地图中关键帧之间与地图点之间的联系,用于联合优化后续的跟踪建图过程中相机位姿和地图点位置。结果 利用Euroc数据集及其他数据进行地图精度和地图完整性实验,在精度方面,将本文算法得到的轨迹与ground truth和未丢失情况下得到的轨迹进行对比,结果表明,在SLAM系统跟踪失败的情况下,此方法能有效解决系统无法继续跟踪建图的问题,其精度可达厘米级别。在30 m²的室内环境中,仅有9 cm的误差,而在300 m²工厂环境中误差仅有7 cm。在完整性方面,在相机运动较剧烈的情况下,恢复地图的完整性优于ORB_SLAM的重定位算法,通过本文算法得到的地图关键帧数量比ORB_SLAM多30%。结论 本文提出的算法在单目视觉SLAM系统跟踪失败之后,仍然能够继续跟踪建图,不会丢失相机轨迹。此外,无需相机回到丢失之前的场景中,只需相机观察到部分丢失前场景,即可恢复融合所有地图。本文算法不仅保证了恢复地图的精度,还保证了建图的完整性。与传统的重定位方法相比,本文算法在系统建图较少时跟踪失败的情况下效果更好。     

A novel constrained texture mapping method based on harmonic map

In this paper, we present a novel constrained texture mapping method based on the harmonic map. We first project the surface of a 3D model on a planar domain by an angle-based-flattening technique and perform a parametrization. The user then specifies interactively the constraints between the selected feature points on the parametric domain of the 3D model and the corresponding pixels on the texture image; the texture coordinates of other sample points on the 3D model are determined based on harmonic mapping between the parametric domain of the model and the texture image; finally we apply an adaptive local mapping refinement to improve the rendering result in real-time. Compared with other interactive methods, our method provides an analytically accurate solution to the problem, and the energy minimization characteristic of the harmonic map reduces the potential distortion that may result in the constrained texture mapping. Experimental data demonstrate good rendering effects generated by the presented algorithm.     

面向嵌入式平台的单目ORB-SLAM稠密化建图实现

针对现有方法在机器人室内定位中无法同时满足高精度定位、快速处理及稠密地图重建的问题,在拥有跟踪、地图构建和回环检测三线程的ORB-SLAM3系统基础上设计了三维稠密地图构建算法,分别在跟踪阶段、局部光束法平差阶段（bundle adjustment,BA）和全局BA阶段,对满足需求的关键帧进行二次采样和位姿更新,然后通过关键帧和对应位姿计算得到三维点云,最终获得稠密地图。实验结果表明,所提方法在Jetson AGX Xavier嵌入式平台上对TUM数据集的定位速度达到了10.8 frame/s,均方根误差仅有0.213%,验证了该系统的高精度与快速性,可以满足机器人室内定位与建图需求。     

医学图像三维重建及实时性研究

使用VTK工具包和MC重建算法开发了一套医学影像三维重建系统,并着重对实时性进行研究。由于重建后图像数据的处理时间和存储代价与三角形网格中三角形数量成正比,过于复杂和细节化的网格会给图像数据的存储、传输、计算和实时绘制等带来负担,故采用了顶点合并的三角形网格简化方法来减少三角形数量。另外,网格存储中存在公共顶点的大量重复存储,故提出了三角形网格的哈希映射存储方法,消除了顶点的重复存储。     

Robust dense reconstruction by range merging based on confidence estimation

Although the stereo matching problem has been extensively studied during the past decades, automatically computing a dense 3D reconstruction from several multiple views is still a difficult task owing to the problems of textureless regions, outliers, detail loss, and various other factors. In this paper, these difficult problems are handled effectively by a robust model that outputs an accurate and dense reconstruction as the final result from an input of multiple images captured by a normal camera. First, the positions of the camera and sparse 3D points are estimated by a structure-from-motion algorithm and we compute the range map with a confidence estimation for each image in our approach. Then all the range maps are integrated into a fine point cloud data set. In the final step we use a Poisson reconstruction algorithm to finish the reconstruction. The major contributions of the work lie in the following points: effective range-computation and confidence-estimation methods are proposed to handle the problems of textureless regions, outliers and detail loss. Then, the range maps are merged into the point cloud data in terms of a confidence-estimation. Finally, Poisson reconstruction algorithm completes the dense mesh. In addition, texture mapping is also implemented as a post-processing work for obtaining good visual effects. Experimental results are presented to demonstrate the effectiveness of the proposed approach.     

基于混合位姿估计模型的移动机器人三维地图创建方法

针对室内复杂环境下的稠密三维建模问题, 提出一种基于RGB-D 相机的移动机器人同时定位与三维地图创建方法. 该方法利用架设在移动机器人上的RGB-D 相机获取环境信息, 根据点云和纹理加权模型建立结合局部纹理约束的混合位姿估计方法, 确保定位精度的同时减小失败率. 在关键帧选取机制下, 结合视觉闭环检测方法, 运用树结构网络优化(TORO) 算法最小化闭环误差, 实现三维地图的全局一致性优化. 在室内环境下的实验结果验证了所提出算法的有效性和可行性.

     

基于流应用中的哈希查表性能研究

基于流应用中采用哈希查表进行报文分类具有成本低、扩展性好等优点,但是其查表性能受到诸多因素影响,制约了它的应用范围。该文采用理论分析和仿真的方法研究了在均匀映射和非均匀映射情况下,哈希查表性能的一些规律,对于具体应用具有一定的指导作用。     

面向MIC协处理器的OLAP外键连接算法

众核架构协处理器Xeon Phi成为新兴的主流高性能计算平台.对于数据库应用而言,内存分析处理是一种计算密集型负载,其主要的性能取决于大事实表与维表之间的内存外键连接性能.本文关注于一种相对于缓存相关的分区哈希连接算法和缓存不相关的无分区哈希连接算法的缓存友好型外键连接算法,以适应Xeon Phi协处理器较小的LLC和高并发线程的特点.通过挖掘OLAP模式中的代理键特征,基于键值匹配的哈希探测操作可以进一步简化为事实表与维表之间基于主-外键参照完整性约束的代理键参照访问,因此复杂的哈希表和CPU代价较高的哈希探测操作可以简化为通过映射外键值为代理键向量内存偏移地址的方法对代理向量直接访问.基于代理向量参照访问的外键连接算法能够简单并高效地应用于Xeon Phi协处理器平台,通过更多的核心和高并发线程来掩盖内存访问延迟.实验中对传统的哈希连接算法（无分区哈希连接算法和基数分区哈希连接算法）和基于代理向量参照技术的外键连接算法在Xeon E5-2650 v3 10核处理器平台和Xeon Phi 5110P 60核协处理器平台进行性能测试和比较,实验结果给出了主流的内存外键连接算法在不同数据集和不同平台上全面的性能特征.     

Detection of Geometric Temporal Changes in Point Clouds

Detecting geometric changes between two 3D captures of the same location performed at different moments is a critical operation for all systems requiring a precise segmentation between change and no‐change regions. Such application scenarios include 3D surface reconstruction, environment monitoring, natural events management and forensic science. Unfortunately, typical 3D scanning setups cannot provide any one‐to‐one mapping between measured samples in static regions: in particular, both extrinsic and intrinsic sensor parameters may vary over time while sensor noise and outliers additionally corrupt the data. In this paper, we adopt a multi‐scale approach to robustly tackle these issues. Starting from two point clouds, we first remove outliers using a probabilistic operator. Then, we detect the actual change using the implicit surface defined by the point clouds under a Growing Least Square reconstruction that, compared to the classical proximity measure, offers a more robust change/no‐change characterization near the temporal intersection of the scans and in the areas exhibiting different sampling density and direction. The resulting classification is enhanced with a spatial reasoning step to solve critical geometric configurations that are common in man‐made environments. We validate our approach on a synthetic test case and on a collection of real data sets acquired using commodity hardware. Finally, we show how 3D reconstruction benefits from the resulting precise change/no‐change segmentation.     

融合双目视觉与惯导信息的高效视觉里程计算法

为提高视觉里程计(VO)在大尺度环境下运行的实时性,提出一种融合双目视觉与惯导信息的视觉里程计算法,主要由前端位姿跟踪和后端局部地图优化两个线程组成.位姿跟踪线程首先使用惯导信息辅助光流法进行帧间特征点跟踪并估计相机初始位姿;接着通过最小化图像光度误差获取当前帧像素点与局部地图点的对应关系;而后最小化当前帧上局部地图点的重投影误差和惯性测量单元(IMU)预积分误差,得到当前帧准确的位姿估计.后端局部地图优化线程对滑动窗口内的关键帧提取特征点并三角化新地图点,使用光束平差法(BA)对逆深度参数化表示的地图点位置、关键帧位姿、速度以及陀螺仪和加速度计零偏进行滑窗优化,为前端提供更加精确的局部地图相机位姿和环境信息.在EuRoC数据集上的实验表明,相比于ORB-SLAM2、ORB-SLAM3算法,该融合双目视觉与惯导信息的视觉里程计算法的定位精度略有下降,但可以较大程度地提高位姿跟踪的实时性.     

Large-scale 3D Semantic Mapping Using Stereo Vision

In recent years, there have been a lot of interests in incorporating semantics into simultaneous localization and mapping (SLAM) systems. This paper presents an approach to generate an outdoor large-scale 3D dense semantic map based on binocular stereo vision. The inputs to system are stereo color images from a moving vehicle. First, dense 3D space around the vehicle is constructed, and the motion of camera is estimated by visual odometry. Meanwhile, semantic segmentation is performed through the deep learning technology online, and the semantic labels are also used to verify the feature matching in visual odometry. These three processes calculate the motion, depth and semantic label of every pixel in the input views. Then, a voxel conditional random field (CRF) inference is introduced to fuse semantic labels to voxel. After that, we present a method to remove the moving objects by incorporating the semantic labels, which improves the motion segmentation accuracy. The last is to generate the dense 3D semantic map of an urban environment from arbitrary long image sequence. We evaluate our approach on KITTI vision benchmark, and the results show that the proposed method is effective.     

面向持久化键值数据库的自适应热点感知哈希索引

针对现有键值数据库存储系统缺乏热点意识,导致系统在高度倾斜的工作负载下性能较差且不可靠,提出了一种自适应热点感知哈希索引模型,该模型基于key值摘要信息实现了一个高性能哈希表。首先,利用key的摘要信息代替key值,压缩key的存储空间,优化哈希表中桶的数据结构;其次,利用CPU的数据级并行技术以及CPU cache line,对哈希表的探查操作进行优化;最后,为解决摘要信息导致key值无法精准比较,需要额外磁盘I/O的问题,设计了一种自适应key值调度算法,该算法根据当前可用内存大小、哈希索引负载以及访问热点情况动态地调整key值的存储位置。在YCSB仿真数据集上进行了实验,实验表明,相较于最先进的哈希表,自适应热点感知哈希索引在相同内存使用率的情况下,将速度提升至1.2倍。     

Approach to Nonrigid Body Metamorphosis UsingGeneralized Morph-translation

An approach of morphing by decomposing two objects into sets of individual convex sub objects respectively and contructing the mapping between two sets is presented The Minkvski addition of two convex sub-objects according to their mapping ralationship is calculated, then all the Minkovski additions are combined to obtain the final result. Nonrigid body motion can be divided into nonrigid body metamorphosis and rigid body rotation A novel method for describing nonrigid body motion based on generalized morph-translation is proposed. This method can solve the metamorphosis problem of two non-homotopic objects. Experiments show tha this method can generate natural, high quality metamorphosis results with simple computation. This method can also be used in interpolation between two keyframes in 2D and 3D computer animation automatically.     

基于立体视觉的在线实时测量系统设计与实现

为了满足深空探测器实时测量天体表面形貌的需求,设计并实现了一套基于立体视觉的在线实时测量原型系统。该系统通过立体相机实时获取空间天体的立体影像,利用每次观测的一组立体影像来重建其局部表面形状;再对每次重建的局部模型进行连接,得到空间天体完整的表面形貌模型。通过仿真实验验证了该系统的可行性,数据处理的速度与精度可以满足对深空目标进行实时测量的需要。