基于Kinect的环境平面特征提取与重构

doi:10.11772/j.issn.1001-9081.2016.05.1366

计算机应用 ›› 2016, Vol. 36 ›› Issue (5): 1366-1370.DOI: 10.11772/j.issn.1001-9081.2016.05.1366

基于Kinect的环境平面特征提取与重构

王梅, 于远芳, 屠大维, 周华

上海大学机电工程与自动化学院, 上海 200072

收稿日期:2015-10-16 修回日期:2015-12-09 出版日期:2016-05-10 发布日期:2016-05-09
通讯作者: 于远芳
作者简介:王梅(1969-),女,辽宁北镇人,讲师,博士,主要研究方向:机器人智能控制、机器视觉;于远芳(1990-),女,河南商丘人,硕士研究生,主要研究方向:服务机器人、机器视觉、三维建模;屠大维(1965-),男,浙江绍兴人,教授,博士生导师,主要研究方向:光机电一体化精密机械、视觉检测;周华(1990-),男,河南信阳人,硕士研究生,主要研究方向:服务机器人、机器人运动仿真。
基金资助:
国家自然科学基金资助项目(51305248,61203351)。

Feature extraction and reconstruction of environmental plane based on Kinect

WANG Mei, YU Yuanfang, TU Dawei, ZHOU Hua

School of Mechatronic Engineering and Automation, Shanghai University, Shanghai 200072, China

Received:2015-10-16 Revised:2015-12-09 Online:2016-05-10 Published:2016-05-09
Supported by:
This work is partially supported by the National Natural Science Foundation of China (51305248,61203351).

摘要/Abstract

摘要： 针对三维场景物体特征识别过程中数据量大、算法复杂等问题,提出一种基于Kinect的环境平面特征提取与重构算法。首先,针对场景的点云分割,采用融合场景几何信息和颜色信息的随机采样一致性(RANSAC)算法,综合二者分割优势,克服几何特征分割过程中分割不足或者过分割,提高分割精度;其次,根据投影变换原理推导出相应的三维坐标变换矩阵,指导分割后独立区域内的三维平面特征信息到二维空间映射,利用凸包概念搜索物体边界信息,实现二维空间的轮廓点提取;最后,通过旋转逆变换,恢复轮廓点的三维信息,完成环境特征重构。采用3组场景数据验证所提算法,实验结果表明,所提算法分割较精确,不容易产生过分割的情况,对不同形状特征的物体,具有较好的重构效果。

关键词: Kinect, 平面分割, 轮廓提取, 平面重构

Abstract: Aiming at the problem of the large amount of data and the complicated algorithm in 3D scene feature recognition process, an feature extraction and reconstruction of environmental plane algorithm based on Kinect was proposed. Firstly, a method of RANdom SAmple Consensus (RANSAC) environment segmentation with the combination of geometrical and color information was proposed, which overcame the over segmentation and lack-segmentation based on geometric characteristic and improved the accuracy. Secondly, according to the principle of perspective projection, the three-dimensional transformation matrix was derived, which guided the 3D environment mapped into a plane. The extraction of contour points in two-dimensional space was realized by searching object boundary information which used convex hull concept. Finally, the 3D information of the contour points was recovered by the rotating inverse transform and the reconstruction of environment features was completed. Three groups of scene data were used to verify the algorithm and the experimental results show the proposed algorithm gains more precise segmentation, reduces over segmentation phenomena, and also has better reconstruction effect for objects with different shape features.

Key words: Kinect, plane segmentation, contour extraction, feature reconstruction

中图分类号:

TP391.41

王梅, 于远芳, 屠大维, 周华. 基于Kinect的环境平面特征提取与重构[J]. 计算机应用, 2016, 36(5): 1366-1370.

WANG Mei, YU Yuanfang, TU Dawei, ZHOU Hua. Feature extraction and reconstruction of environmental plane based on Kinect[J]. Journal of Computer Applications, 2016, 36(5): 1366-1370.

参考文献

[1] QIAN K, MA X, FANG F. 3D environmental mapping of mobile robot using a low-cost depth camera[C]//Proceedings of the 2013 IEEE International Conference on Mechatronics and Automation. Piscataway, NJ:IEEE, 2013:507-512.
[2] HWANG Y S, LEE D J, KIM H W, et al. 3D map building for slopes based on modeling of mobile robot[C]//Proceedings of the 2014 IEEE International Conference on Industrial Technology. Piscataway, NJ:IEEE, 2014:796-799.
[3] 务战威.基于特征信息的场景重构及其在遥操作机器人中的应用[D].绵阳:西南科技大学, 2012:4-8.(WU Z W. Scene reconstruction based on feature information and its application in teleoperation robot[D]. Mianyang:Southwest University of Science and Technology, 2012:4-8.)
[4] 李庆华.基于RGB-D数据的环境特征提取与场景重构[D]. 大连:大连理工大学, 2014:1-10.(LI Q H. Environmental features extraction and scene reconstruction based on RGB-D data[D]. Dalian:Dalian University of Technology, 2014:1-10.)
[5] 叶迪. 移动机器人基于激光测距的三维场景重构[D].大连:大连理工大学, 2008:5-8.(YE D. Mobile robot 3D scene reconstruction based on laser scanning[D]. Dalian:Dalian University of Technology, 2008:5-8.)
[6] YU C H. A new 3D map reconstruction based mobile robot navigation[C]//Proceedings of the 20068th International Conference on Signal Processing. Piscataway, NJ:IEEE, 2006:16-20.
[7] DIFILIPPO N M, JOUANEH M K. Characterization of different Microsoft Kinect sensor models[J]. IEEE Sensors Journal, 2015, 15(8):99-102.
[8] ENDRES F, HESS J, STURM J. 3-D mapping with an RGB-D camera[J]. IEEE Transactions on Robotics, 2014, 30(1):177-187.
[9] SOMLYAI L, VAMOSSY Z. Map building with RGB-D camera for mobil robot[C]//Proceedings of the IEEE 16th International Conference on Intelligent Engineering Systems. Piscataway, NJ:IEEE, 2012:489-493.
[10] 魏永超, 刘长华. 基于曲面分割的三维点云物体识别[J]. 光子学报, 2010, 39(12):2268-2272.(WEI Y C, LIU C H. 3D point cloud object recognition based on surface segmentation[J]. Acta Photonica Sinica, 2010, 39(12):2268-2272.)
[11] 张强. 基于点云库的服务机器人视觉识别[D].合肥:中国科学技术大学, 2014:15-16.(ZHANG Q. Research of visual recognition algorithm for service robot based on PCL[D]. Hefei:University of Science and Technology of China, 2014:15-16.)
[12] DEAN J, GHEMAWAT S. MapReduce:simplified data processing on large clusters[J]. Communications of the ACM, 2008, 51(1):107-113.
[13] 王芳, 钱炜, 李文超.基于数学形态学的图像边缘提取方法[J].机械工程与自动化, 2015(1):46-48.(WANG F, QIAN W, LI W C. Edge detection algorithm based on mathematical morphology[J].Mechanical Engineering & Automation, 2015(1):46-48.)
[14] WANG S, SUN S F. Image edge detection based on rotating Kernel transformation[C]//Proceedings of the 20147th International Congress on Image and Signal Processing. Piscataway, NJ:IEEE, 2014:397-402.
[15] CHIN U, CHHABRA A. A hybrid approach for color based image edge detection[C]//Proceedings of the 2014 Communications and Informatics Communications and Informatics. Piscataway, NJ:IEEE, 2014:2443-2448.
[16] PAVITHRA C, KAVITHA M, KANNAN E. An efficient edge detection algorithm for 2D-3D conversion[C]//Proceedings of the 2014 International Conference on Computation of Power, Energy, Information and Communication. Piscataway, NJ:IEEE, 2014:434-436.
[17] POPPINGA J, VASKEVICIUS N, BIRK A. Fast plane detection and polygonalization in noisy 3D range images[C]//Proceedings of the 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway, NJ:IEEE, 2008:3378-3383.
[18] 曾筝, 陈晓, 周宏, 等. 基于凸包算法的三维表面重建中边缘轮廓提取[J].微机发展, 2004, 14(12):39-42.(ZENG Z, CHEN X, ZHOU H, et al. Extracting contour in 3D surface reconstruction based on convex hull algorithm[J]. Microcomputer Development, 2004, 14(12):39-42.)
[19] 张林. 改进的多边形凸包算法[J].长春工业大学学报, 2013, 34(5):560-563.(ZHANG L. An improved algorithm of polygon convex hull[J]. Journal of Changchun University of Technology, 2013, 34(5):560-563.)

基于Kinect的环境平面特征提取与重构

Feature extraction and reconstruction of environmental plane based on Kinect

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 14

编辑推荐

Metrics

[1]	徐景中, 王佳荣. 基于线特征及迭代最近点算法的地基建筑物点云自动配准方法[J]. 计算机应用, 2020, 40(6): 1837-1841.
[2]	喻露, 胡剑锋, 姚磊岳. 基于人体骨架的非标准深蹲姿势检测方法[J]. 计算机应用, 2019, 39(5): 1448-1452.
[3]	张全贵, 蔡丰, 李志强. 基于耦合多隐马尔可夫模型和深度图像数据的人体动作识别[J]. 计算机应用, 2018, 38(2): 454-457.
[4]	侯荣波, 魏武, 黄婷, 邓超锋. 基于ORB-SLAM的室内机器人定位和三维稠密地图构建[J]. 计算机应用, 2017, 37(5): 1439-1444.
[5]	王红霞, 王坤. 基于加锁机制的静态手势识别方法[J]. 计算机应用, 2016, 36(7): 1959-1964.
[6]	蒋穗峰, 李艳春, 肖南峰. 基于手势识别的工业机器人操作控制方法[J]. 计算机应用, 2016, 36(12): 3486-3491.
[7]	谈家谱, 徐文胜. 基于Kinect的指尖检测与手势识别方法[J]. 计算机应用, 2015, 35(6): 1795-1800.
[8]	侯贺, 吕晓琪, 贾东征, 于荷峰. 基于多平面重建提取冠脉轮廓线的曲面重建算法[J]. 计算机应用, 2015, 35(1): 211-214.
[9]	王丽娜史晓华. 基于Chan-Vese模型的面向多核CPU和GPU的人脸轮廓提取并行算法[J]. 计算机应用, 2014, 34(11): 3121-3125.
[10]	张毅黄聪罗元. 基于改进朴素贝叶斯分类器的康复训练行为识别方法[J]. 计算机应用, 2013, 33(11): 3187-3189.
[11]	杨全彭进业. 基于深度图像信息的手语识别算法[J]. 计算机应用, 2013, 33(10): 2882-2885.
[12]	黎燕李刚. 新的MR-CT图像轮廓提取方法[J]. 计算机应用, 2009, 29(12): 3343-3345.
[13]	陆铖何东健. 基于概率分布图的运动目标轮廓快速提取方法[J]. 计算机应用, 2008, 28(10): 2636-2638.
[14]	刘睿；王晓东. 类肤色背景中提取人脸轮廓的方法研究[J]. 计算机应用, 2005, 25(12): 2855-2857.