期刊文献+

面向室内动态环境的半直接法RGB-D SLAM算法

Semi-direct RGB-D SLAM Algorithm for Dynamic Indoor Environments
分享 导出
摘要 为了解决室内动态环境下移动机器人的准确定位问题,提出了一种融合运动检测算法的半直接法RGB-D视觉SLAM(同时定位与地图创建)算法,它由运动检测、相机位姿估计、基于TSDF (truncated signed distance function)模型的稠密地图构建3个步骤组成.首先,通过最小化图像光度误差,利用稀疏图像对齐算法实现对相机位姿的初步估计.然后,使用视觉里程计的位姿估计对图像进行运动补偿,建立基于图像块实时更新的高斯模型,依据方差变化分割出图像中的运动物体,进而剔除投影在图像运动区域的局部地图点,通过最小化重投影误差对相机位姿进行进一步优化,提升相机位姿估计精度.最后,使用相机位姿和RGB-D相机图像信息构建TSDF稠密地图,利用图像运动检测结果和地图体素块的颜色变化,完成地图在动态环境下的实时更新.实验结果表明,在室内动态环境下,本文算法能够有效提高相机位姿估计精度,实现稠密地图的实时更新,在提升系统鲁棒性的同时也提升了环境重构的准确性. To solve the accurate positioning problem of mobile robots in dynamic indoor environments, a semi-direct RGBD visual SLAM(simultaneous localization and mapping) algorithm integrating a motion detection algorithm, is proposed. It consists of three parts, including motion detection, camera pose estimation and dense map building based on TSDF(truncated signed distance function) model. Firstly, the primary camera pose can be estimated with the sparse image alignment algorithm by minimizing the photometric residual. Then, the pose estimation of visual odometry is used to compensate for image movement. A Gaussian model is built based on real-time update of the image patch. The moving object in the image can be segmented according to the variance change of each patch. By eliminating the local map points projected on the motion region and minimizing the reprojection error, the camera pose can be optimized again to improve its estimation accuracy.Finally, the dense TSDF map can be built with the camera pose and RGB-D image. Furthermore, the map can be updated in real time in dynamic environments by using the motion detection result and and the color change of voxel patches in the map. Experimental results show that the proposed algorithm can effectively improve the precision of camera pose estimation and implement the real-time update of the dense map in dynamic indoor environments. Therefore, it can improve the system robustness and the scene reconstruction accuracy.
作者 高成强 张云洲 王晓哲 邓毅 姜浩 GAO Chengqiang;ZHANG Yunzhou;WANG Xiaozhe;DENG Yi;JIANG Hao(College of Information Science and Engineering,Northeastern University,Shenyang 110819,China;Faculty of Robot Science and Engineering,Northeastern University,Shenyang 110819,China)
出处 《机器人》 EI CSCD 北大核心 2019年第3期372-383,共12页 Robot
基金 国家自然科学基金(61471110,61733003) 国家重点研发计划(2017YFC0805000/5005,2017YFB1301103) 中央高校基本科研业务专项资金(N172608005) 辽宁省自然科学基金(20180520040) 辽宁省教育厅科技项目(L20150185).
关键词 动态环境 视觉SLAM(同时定位与地图创建) 半直接法 TSDF(truncated SIGNED DISTANCE function)模型 稠密地图 dynamic environment visual SLAM(simultaneous localization and mapping) semi-direct algorithm TSDF(truncated signed distance function) model dense map
作者简介 高成强(1994-),男,硕士生.研究领域:移动机器人VSLAM;通信作者:张云洲(1974-),男,博士,教授.研究领域:智能机器人,计算机视觉,zhangyunzhou@mail.neu.edu.cn;王晓哲(1971-),女,博士,副教授.研究领域:智能机器人,计算机视觉.
  • 相关文献

参考文献2

二级参考文献22

  • 1Grisetti G, Stachniss C, Burgard W. Improved techniques for grid mapping with Rao-Blackwellized particle filters[J]. IEEE Transactions on Robotics, 2007, 23( 1 ): 34-46. 被引量:1
  • 2Dissanayake M W M G, Newman P, Clark S, et al. A solution to the simultaneous localization and map building (SLAM) prob- lem[J]. IEEE Transactions on Robotics and Automation, 2001, 17(3): 229-241. 被引量:1
  • 3Nikolic J, Rehder J, Burri M, et al. A synchronized visual- inertial sensor system with FPGA pre-processing for accu- rate real-time SLAM[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA: IEEE, 2014: 431- 437. 被引量:1
  • 4Hornung A, Phillips M, Jones E G, et al. Navigation in three-dimensional cluttered environments for mobile manipu- lation[C]//IEEE International Conference on Robotics and Au- tomation. Piscataway, USA: IEEE, 2012: 423-429. 被引量:1
  • 5Liu M, Siegwart R. Navigation on point-cloud - A Rie- mannian metric approach[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA: IEEE, 2014: 4088-4093. 被引量:1
  • 6Civera J, Davison A J, Montiel J M M. Inverse depth parametrization for monocular SLAM[J]. IEEE Transactions on Robotics, 2008, 24(5): 932-945. 被引量:1
  • 7Sadat S A, Chutskoff K, Jungic D, et al. Feature-rich path planning for robust navigation of MAVs with mono- SLAM[C]//IEEE International Conference on Robotics and Au- tomation. Piscataway, USA: IEEE, 2014: 3870-3875. 被引量:1
  • 8Khoshelham K, Elberink S O. Accuracy and resolution of kinect depth data for indoor mapping applications[J]. Sensors, 2012, 12(2): 1437-1454. 被引量:1
  • 9H6gman V. Building a 3D map from RGB-D sensors[D]. Stockholm, Sweden: Royal Institute of Technology, 2012. 被引量:1
  • 10Henry P, Krainin M, Herbst E, et al. RGB-D mapping: Us- ing depth cameras for dense 3D modeling of indoor envi- ronments[C]//12th International Symposium on Experimental Robotics. Berlin, Germany: Springer, 2014: 477-491. 被引量:1

共引文献16

投稿分析

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部 意见反馈