[1]李新德,金晓彬,张秀龙,等.一种基于BoW物体识别模型的视觉导航方法[J].东南大学学报(自然科学版),2012,42(3):393-398.[doi:10.3969/j.issn.1001-0505.2012.03.001]
 Li Xinde,Jin Xiaobin,Zhang Xiulong,et al.Visual navigation method based on BoW object recognition model[J].Journal of Southeast University (Natural Science Edition),2012,42(3):393-398.[doi:10.3969/j.issn.1001-0505.2012.03.001]
点击复制

一种基于BoW物体识别模型的视觉导航方法()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
42
期数:
2012年第3期
页码:
393-398
栏目:
自动化
出版日期:
2012-05-20

文章信息/Info

Title:
Visual navigation method based on BoW object recognition model
作者:
李新德 金晓彬 张秀龙 戴先中
东南大学复杂工程系统测量与控制教育部重点实验室, 南京 210096
Author(s):
Li Xinde Jin Xiaobin Zhang Xiulong Dai Xianzhong
Key Laboratory of Measurement and Control of CSE of Ministry of Education, Southeast University, Nanjing 210096, China
关键词:
移动机器人 物体识别 手绘地图 视觉导航
Keywords:
mobile robot object recognition hand-drawn-route-map visual navigation
分类号:
TP24
DOI:
10.3969/j.issn.1001-0505.2012.03.001
摘要:
针对复杂的室内环境,提出一种新的动态环境下的移动机器人视觉导航方法.该方法以室内常见物体作为自然路标,通过单目视觉建立识别模型来认知环境中的各种物体.首先对室内常见物体建立图像库,并对库中的大量图像采集SIFT特征; 然后通过BoW模型来描述各幅图像,针对每类物体利用线性支持向量机(SVM)训练出物体识别模型; 最后借助交互的手绘地图描述室内环境,移动机器人从中获得辅助路径以及自然路标的大概位置,从而完成导航任务.通过大量实验,从自然路标变化、目的区域变化、手绘地图偏差等多角度验证该方法的鲁棒性.实验结果表明,该导航方法操作简单高效,并具有人机交互性强、动态环境下适应能力高的优点.
Abstract:
A new visual navigation method for mobile robot to navigate in dynamic environment is proposed. This method relies on some natural landmarks, which are common objects in indoor environment. Robot can establish recognition model and cognize various objects in the environment by monocular camera. Firstly, an image database of indoor common objects is established, and the SIFT(scale invariant feature transform)features are extracted from these images. Then, each image in the database is described as a bag of words(BoW)model. The linear SVM(support vector machine)is used to discriminate every class of images. Finally, An interactive hand-drawn-route-map is used to describe the dynamic indoor environment, where robot can get auxiliary route and natural landmark location and navigate successfully. The robustness of this method was verified by experiments in different aspects including the natural landmark change, destination area change and hand-drawn map deviation. A lot of experiments in the indoor environment show that the proposed method is very simple and highly effective, and has the advantage of high man-machine interaction and high adaptability to the dynamic environment.

参考文献/References:

[1] Bonin-Font B,Ortiz A,Oliver G.Visual navigation for mobile robots:a survey[J].Journal of Intelligent and Robotic Systems,2008,53(3):263-296.[DOI:10.1007/s10846-008-9235-4]
[2] 许俊勇,王景川,陈卫东.基于全景视觉的移动机器人同步定位与地图创建研究[J].机器人,2008,30(4):289-297.
  Xu Junyong,Wang Jingchuan,Chen Weidong.Omni-vision-based simultaneous localization and mapping of mobile robots[J].Robot,2008,30(4):289-297.(in Chinese)
[3] Guo Yang,Xu Xinhe.Color landmark design for mobile robot localization[C]//IMACS Multi Conference on Computational Engineering in Systems Applications.Beijing,China,2006:1868-1874.
[4] Hu Huosheng,Gu Dongbing.Landmark-based navigation of industrial mobile robots[J].International Journal of Industry Robot,2000,27(6):458-467.[DOI:10.1108/01439910010378879]
[5] Hayet J B,Lerasle F,Devy M.A visual landmark framework for indoor mobile robot navigation[C] //Proceedings of ICRA’02 Robotics and Automation.Washington DC,USA,2002,4:3942-3947.
[6] Blanc G,Mezouar Y,Martinet P.Indoor navigation of a wheeled mobile robot along visual routes[C] //IEEE International Conference on Robotics and Automation.Barcelona,Spanish,2005:3354-3359.
[7] Madhavan R,Durrant-Whyte H F.Natural landmark-based autonomous vehicle navigation[J].Robotics and Autonomous Systems,2004,46(2):79-95.[DOI:10.1016/j.robot.2003.11.003]
[8] 蔡自兴,王勇,王璐.基于角点聚类的移动机器人自然路标检测与识别[J].智能系统学报,2006,1(1):52-56.
  Cai Zixing,Wang Yong,Wang Lu.Corner clustering based detection and recognition of natural landmark for mobile robot[J].CAAI Transactions on Intelligent Systems,2006,1(1):52-56.(in Chinese)
[9] 李新德,吴雪建,朱博,等.一种基于手绘地图的动态环境视觉导航方法[J].机器人,2011,33(4):490-501.
  Li Xinde,Wu Xuejian,Zhu Bo,et al.A visual navigation method using a hand-drawn-route-map in dynamic environments[J].Robot,2011,33(4):490-501.(in Chinese)
[10] Csurka G,Dance C,Fan L,et al.Visual categorization with bags of keypoints[C] //ECCV’04 Workshop on Statistical Learning in Computer Vision.Prague,Czech,2004:59-74.
[11] Zhao R,Grosky W I.Narrowing the semantic gap-improved text-based web document retrieval using visual features[J].IEEE Transactions on Multimedia,2002,4(2):15-42.[DOI:10.1109/TMM.2002.1017733]
[12] David G L.Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision,2004,60(2):91-110.[DOI:10.1023/B:VISI.0000029664.99615.94]

相似文献/References:

[1]涂刚毅,金世俊,祝雪芬,等.基于粒子滤波的移动机器人SLAM算法[J].东南大学学报(自然科学版),2010,40(1):117.[doi:10.3969/j.issn.1001-0505.2010.01.022]
 Tu Gangyi,Jin Shijun,Zhu Xuefen,et al.Particle filter SLAM method for mobile robot[J].Journal of Southeast University (Natural Science Edition),2010,40(3):117.[doi:10.3969/j.issn.1001-0505.2010.01.022]
[2]房芳,马旭东,戴先中.一种新的移动机器人Monte Carlo自主定位算法[J].东南大学学报(自然科学版),2007,37(1):40.[doi:10.3969/j.issn.1001-0505.2007.01.010]
 Fang Fang,Ma Xudong,Dai Xianzhong.New Monte Carlo algorithm for mobile robot self-localization[J].Journal of Southeast University (Natural Science Edition),2007,37(3):40.[doi:10.3969/j.issn.1001-0505.2007.01.010]
[3]尚文,马旭东,戴先中.融合多传感器信息的移动机器人自定位方法[J].东南大学学报(自然科学版),2004,34(6):784.[doi:10.3969/j.issn.1001-0505.2004.06.015]
 Shang Wen,Ma Xudong,Dai Xianzhong.Mobile robot self-localization based-on multi-sensory information fusion[J].Journal of Southeast University (Natural Science Edition),2004,34(3):784.[doi:10.3969/j.issn.1001-0505.2004.06.015]
[4]周波,戴先中.基于SR-UKF的移动机器人主动故障检测和容错控制[J].东南大学学报(自然科学版),2011,41(5):1002.[doi:10.3969/j.issn.1001-0505.2011.05.021]
 Zhou Bo,Dai Xianzhong.SR-UKF based active fault detection and tolerant control of mobile robots[J].Journal of Southeast University (Natural Science Edition),2011,41(3):1002.[doi:10.3969/j.issn.1001-0505.2011.05.021]
[5]房芳,马旭东,戴先中.基于混合模型的移动机器人同时定位与环境建模[J].东南大学学报(自然科学版),2009,39(5):923.[doi:10.3969/j.issn.1001-0505.2009.05.011]
 Fang Fang,Ma Xudong,Dai Xianzhong.Mixed-model based simultaneous localization and mapping approach for mobile robot[J].Journal of Southeast University (Natural Science Edition),2009,39(3):923.[doi:10.3969/j.issn.1001-0505.2009.05.011]
[6]周波,樊帅权,戴先中.基于集员滤波的移动机器人动态环境建模[J].东南大学学报(自然科学版),2011,41(1):107.[doi:10.3969/j.issn.1001-0505.2011.01.021]
 Zhou Bo,Fan Shuaiquan,Dai Xianzhong.Dynamic environment modeling of mobile robots based on set membership filter[J].Journal of Southeast University (Natural Science Edition),2011,41(3):107.[doi:10.3969/j.issn.1001-0505.2011.01.021]

备注/Memo

备注/Memo:
作者简介: 李新德(1975—),男,博士,副教授,xindeli@seu.edu.cn.
基金项目: 国家自然科学基金资助项目(60804063,61175091)、江苏省自然科学基金资助项目(BK2010403)、图像信息处理与智能控制教育部重点实验室开放基金资助项目(200902)、东南大学优秀青年教师教学与科研资助计划资助项目(3208001203)、东南大学创新基金资助项目(3208000501).
引文格式: 李新德,金晓彬,张秀龙,等.一种基于BoW物体识别模型的视觉导航方法[J].东南大学学报:自然科学版,2012,42(3):393-398. [doi:10.3969/j.issn.1001-0505.2012.03.001]
更新日期/Last Update: 2012-05-20