[1]牛杰,卜雄洙,钱堃.一种面向移动机器人导航的自然路标提取方法[J].哈尔滨工程大学学报,2019,40(04):844-850.[doi:10.11990/jheu.201709095]
 NIU Jie,BU Xiongzhu,QIAN Kun.A method of extracting natural landmarks for mobile robot navigation[J].hebgcdxxb,2019,40(04):844-850.[doi:10.11990/jheu.201709095]
点击复制

一种面向移动机器人导航的自然路标提取方法(/HTML)
分享到:

《哈尔滨工程大学学报》[ISSN:1006-6977/CN:61-1281/TN]

卷:
40
期数:
2019年04期
页码:
844-850
栏目:
出版日期:
2019-04-05

文章信息/Info

Title:
A method of extracting natural landmarks for mobile robot navigation
作者:
牛杰12 卜雄洙2 钱堃3
1. 常州信息职业技术学院 电子与电气工程学院, 江苏 常州 213164;
2. 南京理工大学 机械工程学院, 江苏 南京 210094;
3. 东南大学 自动化学院, 江苏 南京 210096
Author(s):
NIU Jie12 BU Xiongzhu2 QIAN Kun3
1. School of Electrical and Electronic Engineering, Changzhou College of Information Technology, Changzhou 213164, China;
2. School of Mechanical Engineering, Nanjing University of Science and Technology, Nanjing 210094, China;
3. School of Automation, Southeast University, Nanjing 210096, China
关键词:
视觉注意图像聚类图像分割移动机器人路标检测
分类号:
TP242
DOI:
10.11990/jheu.201709095
文献标志码:
A
摘要:
针对机器人定位和导航应用中人工路标存在的缺陷,本文设计了一种基于频域特性的显著性路标提取方法。该方法利用图像熵理论自适应选取因子平滑图像,在对立色彩空间上,利用频域显著性计算方法得到三通道色彩空间的显著图,并对其进行加权融合。同时考虑到路标一致性和噪声的因素,利用优化的K-means聚类结果,对最终的显著图进行掩膜操作,筛选出可供机器人导航应用的自然路标。实验验证了在常规环境下,相较于特征算子的直接匹配,视觉注意特征提取的显著像素达到了平均80%的检出率,并具有较高的可重复性。基于自然路标的实际机器人导航实验进一步验证了方法的有效性。

参考文献/References:

[1] KUNⅡ Y, KOVACS G, HOSHI N. Mobile robot navigation in natural environments using robust object tracking[C]//2017 IEEE 26th International Symposium on Industrial Electronics. Edinburgh, UK, 2017:1747-1752.
[2] PFRUNDER A, BORGES P V K, ROMERO A R, et al. Real-time autonomous ground vehicle navigation in heterogeneous environments using a 3D LIDAR[C]//2017 IEEE/RSJ International Conference on Intelligent Robots and Systems. Vancouver, BC, Canada, 2017:2601-2608.
[3] BEINHOFER M, MVLLER J, BURGARD W. Effective landmark placement for accurate and reliable mobile robot navigation[J]. Robotics and autonomous systems, 2013, 61(10):1060-1069.
[4] CHOSET H, NAGATANI K. Topological simultaneous localization and mapping (SLAM):toward exact localization without explicit localization[J]. IEEE transactions on robotics and automation, 2002, 17(2):125-137.
[5] ZEIDAN B, DASGUPTA S, WÖRGÖTTER F, et al. Adaptive landmark-based navigation system using learning techniques[M]//DEL POBIL A P, CHINELLATO E, MARTINEZ-MARTIN E, et al. International Conference on Simulation of Adaptive Behavior. Cham:Springer, 2014, 8575:121-131.
[6] LUKE R H, KELLER J M, SKUBIC M, et al. Acquiring and maintaining abstract landmark chunks for cognitive robot navigation[C]//2005 IEEE/RSJ International Conference on Intelligent Robots and Systems. Edmonton, Alta., Canada, 2005:2566-2571.
[7] 吴鹏, 徐洪玲, 李雯霖, 等. 基于区域检测的多尺度Harris角点检测算法[J]. 哈尔滨工程大学学报, 2016, 37(7):969-973.WU Peng, XU Hongling, LI Wenlin, et al. Multi-scale Harris-corner detection algorithm based on region detection[J]. Journal of Harbin Engineering University, 2016, 37(7):969-973.
[8] ZHAO Chunhui, ZHOU Yihui, WEI Yanyan, et al. Visual saliency landmark detection algorithm based on DNN feature extraction[C]//2016 35th Chinese Control Conference. Chengdu, China, 2016:5551-5556.
[9] ACHANTA R, HEMAMI S, ESTRADA F, et al. Frequency-tuned salient region detection[C]//2009 IEEE Conference on Computer Vision and Pattern Recognition. Miami, FL, USA, 2009:1597-1604.
[10] XU Li, LU Cewu, XU Yi, et al. Image smoothing via L0 gradient minimization[J]. ACM transactions on graphics, 2011, 30(6):1-12.
[11] YANG Hanpei, LI Weihai. Edge-aware saliency detection via novel graph model[M]//ZENG B, HUANG Q, EL SADDIK A, et al. Pacific-Rim Conference on Multimedia. Cham:Springer, 2018:45-55.
[12] FRINTROP S, WERNER T, GARCÍA G M. Traditional saliency reloaded:A good old model in new shape[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston, MA, USA, 2015:82-90.
[13] OHASHI T, AGHBARI Z, MAKINOUCHI A. Hill-climbing algorithm for efficient color-based image segmentation[C]//International Conference on Signal Processing, Pattern Recognition, and Applications. ACTA, 2003:17-22.
[14] 钱堃, 马旭东, 戴先中, 等. 基于显著场景Bayesian Surprise的移动机器人自然路标检测[J]. 模式识别与人工智能, 2013, 26(6):571-576.QIAN Kun, MA Xudong, DAI Xianzhong, et al. Natural landmark detection of mobile robots based on bayesian surprise of salient scenes[J]. Pattern recognition and artificial intelligence, 2013, 26(6):571-576.
[15] MONTEMERLO M, THRUN S. FastSLAM:a scalable method for the simultaneous localization and mapping problem in robotics[M]. Berlin:Springer, 2007:63-90.
[16] MUR-ARTAL R, MONTIEL J M M, TARDÓS J D. ORB-SLAM:a versatile and accurate monocular slam system[J]. IEEE transactions on robotics, 2015, 31(5):1147-1163.

备注/Memo

备注/Memo:
收稿日期:2017-09-21。
基金项目:国家自然科学基金项目(61573101);江苏省高校自然科学研究项目(16KJB520048);常州市科技计划项目(CJ20180010);江苏省青蓝工程项目.
作者简介:牛杰,男,副教授;卜雄洙,男,教授,博士生导师.
通讯作者:牛杰,E-mail:niujie@czcit.edu.cn
更新日期/Last Update: 2019-04-03