基于视觉SLAM的任意路径场景重建的优化  

Scene Reconstruction Optimization along the Free Trajectory Based on the Vision SLAM

作　　者：杜振龙 马芸 李晓丽 DU Zhenlong;MA Yun;LI Xiaoli(School of Computer Science and Technology,ISanjing Technology University,Nanjing 211816,China)

机构地区：[1]南京工业大学计算机科学与技术学院,江苏南京211816

出　　处：《信息与控制》2020年第6期667-672,共6页Information and Control

基　　金：国家自然科学基金资助项目(61672279);江苏省“六大人才高峰”资助项目(2012-WLW-023);水文水资源与水利工程科学国家重点实验室开放基金资助项目(2016491411)。

摘　　要：同时定位与地图构建(SLAM)在计算机视觉和机器人领域有着重要作用,也为VR/AR应用提供了基础技术支持.在面对特征较为单一或复杂的景物时,传统SLAM系统的前端特征匹配模块因特征点过于稀疏或过于稠密,较难生成准确的相机轨迹和场景重构结果.本文提出一种基于视觉SLAM的任意路径场景重建改进算法,前端线程采用Hessian矩阵对图像进行特征提取和匹配,对感兴趣区域施以仿射变换识别相邻帧特征点以提高匹配效率,进而降低相机轨迹和场景重构的原始误差;后端优化线程减小标记点次数优化特征点数目,并运用局部和全局BA(bundle adjustment)方法对相机运动轨迹分段优化,降低系统误差,提高相机轨迹优化效率.所提方法可在场景实时添加三维物体.实验结果表明,改进的视觉SLAM算法比传统的SLAM算法具有更好的实时性能.Simultaneous localization and mapping( SLAM) plays an important role in the field of computer vision and robotics,and provides basic technical support for VR/AR application development. Traditional SLAM has difficulty and inefficiently handles scenarios with relatively simple and sparse features. In this paper,we propose an improved algorithm for reconstructing an arbitrary trajectory based on visual SLAM. The front-end thread employs a Hessian matrix for extracting and matching the feature point among neighboring frames. By applying affine transformation to regions of interest to rapidly identify feature points,the errors associated with point-cloud reconstruction and the camera trajectory are reduced. To improve the efficiency of camera trajectory optimization,the back-end thread optimizes a limited number of feature points. Local and global BA strategies are used to optimize the camera trajectory to reduce system errors,thereby improving the optimization efficiency. Moreover,3 D models can be introduced in real-time. The experimental results show that the improved visual SLAM algorithm achieves better real-time performance than the traditional SLAM.

关 键 词：同时定位与地图构建 特征匹配 路径优化 场景重建 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]