[1]CAI Jun,CHEN Keyu,ZHANG Yi.Improved V-SLAM for mobile robots based on Kinect[J].CAAI Transactions on Intelligent Systems,2018,13(5):734-740.[doi:10.11992/tis.201705018]
Copy

Improved V-SLAM for mobile robots based on Kinect

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 13 Number of periods: 2018 5 Page number: 734-740 Column: 学术论文—智能系统 Public date: 2018-09-05
Title:
Improved V-SLAM for mobile robots based on Kinect
Author(s):
CAI Jun;  CHEN Keyu;  ZHANG Yi
Chongqing Information Accessibility and Service Robot Engineering Technology Research Center, Chongqing University of Posts and Telecommunications, Chongqing 400065, China
Keywords:
mobile robot; Kinect; SLAM; ICP; key-frame; RANSAC; pose estimate; three-dimensional reconstruction
CLC:
TP242.6
DOI:
10.11992/tis.201705018
Abstract:
Given that the traditional iterative closest points (ICP) algorithm easily falls into the local optimum and has a large matching error, a novel double restriction method containing Euclidean distance and angle threshold is proposed. To realize this, an indoor mobile robot RGB-D SLAM (simultaneous localization and mapping) using a Kinect camera was developed. First, the Kinect camera was used to get color information and depth information for the indoor environment. Through the image feature extraction and matching procedure, the relationship between two 3D point clouds was established by combining the camera intrinsic parameters and pixel depth values. Then, the initial registration was completed using the random sample consensus (RANSAC) algorithm to remove outliers. Meanwhile, accurate registration was completed using the improved ICP algorithm. Finally, the weight was introduced into the selection of the key frames, and the general graph optimization (g2o) algorithm was used to optimize the pose of the robot. The experimental results prove effectiveness and feasibility of the method, and this method improves the accuracy of the 3D point cloud map and estimates the trajectory of the robot.
References:
[1] ENDRES F, HESS J, STURM J, et al. 3-D mapping with an RGB-D camera[J]. IEEE transactions on robotics, 2014, 30(1):177-187.
[2] KERL C, STURM J, CREMERS D. Dense visual SLAM for RGB-D cameras[C]//Proceedings of 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems. Tokyo, Japan, 2014:2100-2106.
[3] HOU Yi, ZHANG Hong, ZHOU Shilin. Convolutional neural network-based image representation for visual loop closure detection[C]//Proceedings of 2015 IEEE International Conference on Information and Automation. Lijiang, China, 2015:2238-2245.
[4] 解则晓, 徐尚. 三维点云数据拼接中ICP及其改进算法综述[J]. 中国海洋大学学报:自然科学版, 2010, 40(1):99-103 XIE Zexiao, XU Shang. A survey on the ICP algorithm and its variants in registration of 3D point clouds[J]. Periodical of ocean university of China, 2010, 40(1):99-103
[5] LIN C C, TAI Y C, LEE J J, et al. A novel point cloud registration using 2D image features[J]. Eurasip journal on advances in signal processing, 2017, 2017:5.
[6] 杨扬, 曹其新, 朱笑笑, 等. 面向机器人手眼协调抓取的3维建模方法[J]. 机器人, 2013, 35(2):151-155 YANG Yang, CAO Qixin, ZHU Xiaoxiao, et al. A 3D modeling method for robot’s hand-eye coordinated grasping[J]. Robot, 2013, 35(2):151-155
[7] ROSTEN E, PORTER R, DRUMMOND T. Faster and better:a machine learning approach to corner detection[J]. IEEE transactions on pattern analysis and machine intelligence, 2010, 32(1):105-119.
[8] LOWE D G. Distinctive image features from scale-invariant keypoints[J]. International journal of computer vision, 2004, 60(2):91-110.
[9] BAY H, ESS A, TUYTELAARS T, et al. speeded-up robust features (SURF)[J]. Computer vision and image understanding, 2008, 110(3):346-359.
[10] MUJA M, LOWE D G. Scalable nearest neighbor algorithms for high dimensional data[J]. IEEE transactions on pattern analysis and machine intelligence, 2014, 36(11):2227-2240.
[11] 陈胜勇, 刘盛. 基于OpenCV的计算机视觉技术实现[M]. 北京:科学出版社, 2008.
[12] DANIEL H C, KANNALA J, HEIKKILÄ J. Joint depth and color camera calibration with distortion correction[J]. IEEE transactions on pattern analysis and machine intelligence, 2012, 34(10):2058-2064.
[13] 朱德海, 郭浩, 苏伟. 点云库PCL学习教程[M]. 北京:北京航空航天大学出版社, 2012.
[14] KUMMERLE R, GRISETTI G, STRASDAT H, et al. G2o:a general framework for graph optimization[C]//Proceedings of 2011 IEEE International Conference on Robotics and Automation. Shanghai, China, 2011:3607-3613.
Similar References:

Memo

-

Last Update: 2018-10-25

Copyright © CAAI Transactions on Intelligent Systems