RGB-D视觉SLAM算法的改进及应用

成怡; 白佳奇; 修春波

doi:10.3788/OPE.20172513.0160

您当前的位置：

首页 >

文章列表页 >

RGB-D视觉SLAM算法的改进及应用

信息科学 | 更新时间：2020-08-13

- RGB-D视觉SLAM算法的改进及应用
- Improvement and application of RGB-D vision SLAM algorithm
- 光学精密工程 2017年25卷第10s期页码：160-166
- 作者机构：
  
  1. 天津工业大学电气工程与自动化学院天津,300387
  2. 天津市电工电能新技术重点实验室天津,300387
- 作者简介：
- 基金信息：
  
  国家自然科学基金资助项目（No.61203302）();天津市应用基础与前沿技术研究计划资助项目（No.14JCYBJC18900）()
- DOI：10.3788/OPE.20172513.0160
  中图分类号： TP391.41
- 收稿日期：2017-04-28，
  
  修回日期：2017-06-10，
  
  纸质出版日期：2017-11-25
- 稿件说明：
移动端阅览
成怡, 白佳奇, 修春波. RGB-D视觉SLAM算法的改进及应用[J]. 光学精密工程, 2017,25(10s): 160-166

CHENG Yi, BAI Jia-qi, XIU Chun-bo. Improvement and application of RGB-D vision SLAM algorithm[J]. Editorial Office of Optics and Precision Engineering, 2017,25(10s): 160-166
成怡, 白佳奇, 修春波. RGB-D视觉SLAM算法的改进及应用[J]. 光学精密工程, 2017,25(10s): 160-166 DOI： 10.3788/OPE.20172513.0160.

CHENG Yi, BAI Jia-qi, XIU Chun-bo. Improvement and application of RGB-D vision SLAM algorithm[J]. Editorial Office of Optics and Precision Engineering, 2017,25(10s): 160-166 DOI： 10.3788/OPE.20172513.0160.

摘要

针对传统视觉SLAM算法位置误差积累及计算量大上的突出问题，提出了一种改进的RGB-D的视觉SLAM算法。在提出的算法中采用SURF算法提取特征，利用随机采样一致性和迭代最近点算法根据匹配结果估算并优化运动过程；在后端图优化的过程中，引入半随机的回环检测，通过改变关键帧的提取方法，克服当前帧最近检测与历史帧回环检测的缺点，提高匹配的准确性，同时减少了计算量。通过开源机器人操作系统的实验结果表明，提出的改进RGB-D的视觉SLAM算法处理一帧数据的速度为0.030 s左右，在满足了所得3D点云地图的准确性和完整性的基础上，加快了处理速度，节省了计算量，增强了算法的实时性。

Abstract

An improved visual SLAM algorithm of RGB-D was proposed aimed at prominent problem of accumulative position error and large calculated amount of traditional visual SLAM algorithm under the application background of wheeled mobile robot in the thesis. SURF algorithm was used to extract features

and random sample consensus (Ransac) and iterative closest point (ICP) algorithm were used to estimate and optimize movement process according to matching result in proposed algorithm; semi-random loop detection was introduced in the optimization process of back-end graph. Defects of recent detection of current frame and loop detection of historical frames were overcome by changing extraction method of key frames

which improved accuracy of matching and reduced calculated amount at the same time. Experimental result of open-source robot operating system (ROS) shows that speed of processing one frame data by proposed improved visual SLAM algorithm of RGB-D is 0.030 s approximately

which accelerates processing speed

saves calculated amount and strengthens real-time performance of the algorithm on the basis of satisfying accuracy and completeness of obtained 3D point cloud map.

关键词

Keywords

references

ENDRES F,HESS J,STURM J, et al..3D mapping with an RGB-D camera[C]. Robotics, IEEE Transactions on, 2014, 30(1):1-11.

ALMANSA-VALVERDE S,CASTILLO JC, CABALLER OA. Mobile robot map building from time-of-flight camera[J]. Expert Systems with Applications, 2012, 39:8835-8843.

JO S J,JO H G,JUN S W, et al..3D Environment reconstruction using a ToF camera[c]. Proceedings of the 9th Korea Robotics Society Annual Conference, Buyeo, Korea, 2014.

王欣,袁坤,于晓,等.基于运动恢复的双目视觉三维重建系统设计[J]. 光学精密工程,2014,22(5):1379-1387. WANG X,YUAN K,YU X, et al..Design of binocular vision 3D reconstruction system based on motion recovery[J]. Opt. Precision Eng., 2014, 22(5):1379-1387. (in Chinese)

林义闽, 吕乃光,娄小平,等.用于弱纹理场景三维重建的机器人视觉系统[J]. 光学精密工程,2015,23(2):540-549. LIN Y M, LV N G, LOU X P, et al.. Robot vision system for 3D reconstruction in low texture environment[J]. Opt. Precision Eng., 2015, 23(2):540-549. (in Chinese)

HENRY P, KRAININ M, HERBST E, et al.. RGB-D mapping:Using depth cameras for dense 3D modeling of indoor environments[C]. 12th International Symposium on Experimental Robotics. Berlin, Germany:Springer, 2014:477-491.

DRYANOVSKI I,VALENTI R G,XIAO J Z.Fast visual odometry and mapping from RGB-D data[C]. IEEE International Conference on Robotics and Automation. Piscataway, USA:IEEE, 2013:2305-2310.

ENDRES F,HESS J, ENGELHARD N, et al..An evaluation of the RGB-D SLAM system[C]. IEEE International Conference on Robotics and Automation. Piscataway, USA:IEEE, 2012:1691-1696.

王忠立,赵杰,蔡鹤皋. 大规模环境下基于图优化SLAM的图构建方法[J]. 哈尔滨工业大学学报,2015,1(1):75-85. WANG ZH L, ZHANG J. Method for constructing graph based optimization SLAM in large scale environment[J]. Journal of Harbin Institute of Technology,2015, 1(1):75-85.(in Chinese)

付梦印,吕宪伟,刘彤,等. 基于RGB-D数据的实时SLAM算法[J]. 机器人,2015,37(6):683-692. FU M Y, LIU T. Real time SLAM algorithm based on RGB-D data[J]. Robot, 2015, 37(6):683-692.(in Chinese)

LOWE D G.Distinctive image features from scale-invariant keypoints[J]. In ternational journal of computer vision,2004,60(2):91-110.

曾峦,王元钦,谭久彬. 改进的SIFT特征提取和匹配算法[J]. 光学精密工程,2011,19(6):1391-1397. ZENG L, WANG Y Q, TAN J B, et al..Improved SIFT feature extraction and matching algorithm[J]. Opt. Precision Eng., 2011,19(6):1391-1397. (in Chinese)

BAY H,ESS A,TUYTELAARS T, et al..Speeded-up robust features(SURF)[J]. Computer vision and image understanding, 2008,110(3):346-359.

RUBLEE E, RABAUD V, KONOLIGE K, et al.. ORB:An efficient alternative to SIFT or SURF[C]. IEEE International Conference on Computer Vision. Piscataway, USA:IEEE, 2011:2564-2571.

肖军浩[译], 机器人操作系统(ROS)浅析[M].2013. JASON M.O'Kane.A Gentle Introduction to ROS[M].2013. (in Chinese)

KERL C, STURM J, CREMERS D. Dense Visual SLAM for RGB-D Cameras[C]. In Proc. of the Int. Conf. on Intelligent Robot Systems (IROS), 2013.

SCHERER S A, DUBE D, ZELLl A. Using depth in visual simultaneous localization and mapping[C]. 2012 IEEE International Conference on Robotics and Automation(ICRA),2012:5216-5221.

浏览量

208

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于SURF-OKG特征匹配的三维重建技术