基于视觉特征的大范围地形感知

doi:10.13973/j.cnki.robot.2015.0369

摘要
图/表
参考文献
相关文章 (1)

全文: PDF (935 KB) HTML ( ) 输出: BibTeX \| EndNote (RIS)
引用本文:
张伟东, 张伟, 李振鹏, 顾建军. 基于视觉特征的大范围地形感知[J]. 机器人, 2015, 37(3): 369-375.DOI: 10.13973/j.cnki.robot.2015.0369. ZHANG Weidong, ZHANG Wei, LI Zhenpeng, GU Jianjun. Visual Features for Long-Range Terrain Perception. ROBOT, 2015, 37(3): 369-375. DOI: 10.13973/j.cnki.robot.2015.0369.

摘要

提出了一种基于视觉特征的移动机器人大范围地形感知方法.该方法采用由近及远的学习策略:首先，将获取的图像分割并进行尺度归一化，提取样本中反映颜色的色相特征和反映纹理的局部二值模式(LBP)特征作为描述子；其次，利用双目视觉将近景的一部分地形样本分为障碍与地面，将这些样本作为有标签的训练数据构建分类器分类未知样本；最后，基于后验概率定义可信度，对可疑的样本进行重分类，提高最终分类准确率.实验结果表明，该方法可以准确且稳定地实现大范围地形感知.

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	张伟东
	张伟
	李振鹏
	顾建军

关键词 ：地形感知, 障碍检测, 色相特征, LBP 特征

Abstract：

A visual features based long-range terrain perception method for mobile robots is presented. This approach follows a near-to-far learning procedure. Firstly, the obtained image is segmented and the scale is normalized. Then, hue features for representing the color information and LBP (local binary pattern) features for representing the texture information are extracted. Next, the near field terrain samples are labelled obstacle and ground using stereo vision, and then a classifier is trained with these labelled samples to classify the rest unknown samples. Finally, confidence values are defined based on posterior probability to reclassify the low confident samples for further improving the classification accuracy. Experiment results show that the proposed approach can achieve long-range terrain perception accurately and stably.

Key words： terrain perception obstacle detection hue feature LBP (local binary pattern) feature

收稿日期: 2014-11-25 录用日期: 2015-04-02

TP24

基金资助:

国家自然科学基金(61203253,61233014);山东省优秀中青年科学家科研奖励基金(BS2013DX023);计算智能与信号处理教育部重点实验室开放课题

通讯作者: 张伟,info@vsislab.com E-mail: info@vsislab.com

作者简介: 张伟东(1990--),男,博士生.研究领域:机器视觉,模式识别,机器人.
张伟(1981--),男,博士,副研究员.研究领域:机器视觉,机器学习,人工智能,机器人.
李振鹏(1990--),男,硕士生.研究领域:机器视觉,模式识别,机器人.

链接本文:

https://robot.sia.cn/CN/10.13973/j.cnki.robot.2015.0369 或 https://robot.sia.cn/CN/Y2015/V37/I3/369

[1] Bhoite A, Beke N, Nanduri S, et al. Advanced situational awareness and obstacle detection using a monocular camera[C]// Western New York Image Processing Workshop. Piscataway, USA: IEEE, 2010: 30-33.

[2] Xia Y Q, Zhi J, Huang M, et a1. An obstacle segmentation approach in ALV system[C]//2th International Symposium on Intelligent Information Technology Application. Piscataway, \linebreak USA: IEEE, 2008: 259-262.

[3] Pantilie C D, Nedevschi S. Real-time obstacle detection in complex scenarios using dense stereo vision and optical flow[C]// 13th International IEEE Conference on Intelligent Transportation Systems. Piscataway, USA: IEEE, 2010: 439-444.

[4] Ventroux N, Schmit R, Pasquet F, et al. Stereovision-based 3D obstacle detection for automotive safety driving assistance[C]// 12th International IEEE Conference on Intelligent Transportation Systems. Piscataway, USA: IEEE, 2009: 394-399.

[5] Cong Y, Peng J J, Sun J, et al. V-disparity based UGV obstacle detection in rough outdoor terrain[J]. Acta Automatica Sinica, 2010, 36(5): 667-673.

[6] Zhu X Z, Lu H M, Yang X R, et al. Stereo vision based traversable region detection for mobile robots using U-V-disparity[C]//32th Chinese Control Conference. Piscataway, China: IEEE, 2013: 5785-5790.

[7] Hadsell R, Sermanet P, Ben J, et a1. Learning long-range vision for autonomous off-road driving[J]. Journal of Field Robotics, 2009, 26(2): 120-144.

[8] Procopio M J, Mulligan J, Grudic G. Coping with imbalanced training data for improved terrain prediction in autonomous outdoor robot navigation[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA: IEEE, 2010: 518-525.

[9] Procopio M J, Mulligan J, Grudic G. Learning terrain segmentation with classifier ensembles for autonomous robot navigation in unstructured environments[J]. Journal of Field Robotics, 2009, 26(2): 145-175.

[10] Gevers T, Stokman H. Robust histogram construction from color invariants for object recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(1): 113-118.

[11] van de Weijer J, Schmid C. Coloring local feature extraction[C]//9th European Conference on Computer Vision. Berlin, Germany: Springer-Verlag, 2006: 334-348.

[12] Ojala T, Pietikainen M, Harwood D. Performance evaluation of texture measures with classification based on Kullback discrimination of distributions[C]//12th International Conference on Pattern Recognition. Piscataway, USA: IEEE, 1994: 582-585.

[13] Ojala T, Pietikainen M, Maenpaa T. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(7): 971-987.

[14] Cortes C, Vapnik V. Support-vector networks[J]. Machine Learning, 1995, 20(3): 273-297.

[15] Chang C C, Lin C J. LIBSVM: A library for support vector machines[OL]. (2013-04-04) [2014-11-01]. http://www.csie. ntu.edu.tw/～ cjlin/papers/libsvm.pdf.

[16] Mousazadeh H. A technical review on navigation systems of agricultural autonomous off-road vehicles[J]. Journal of Terramechanics, 2013, 50(3): 211-232.

[17] Procopio M J. An experimental analysis of classifier ensembles for learning drifting concepts over time in autonomous outdoor robot navigation[D]. Boulder, USA: University of Colorado at Boulder, 2007.

[18] 朱效洲,李宇波,卢惠民,等.基于视觉的移动机器人可通行区域识别研究综述 [J].计算机应用研究,2012,29(6):2009-2013.Zhu X Z, Li Y B, Lu H M, et al. Research on vision-based traversable region recognition for mobile robots[J]. Application Research of Computers, 2012, 29(6): 2009-2013.

[19] 王明军,周俊,屠珺,等.基于条件随机场的大范围地形感知框架 [J].机器人,2010,32(3):326-333.Wang M J, Zhou J, Tu J, et a1. Long-range terrain perception based on conditional random fields[J]. Robot, 2010, 32(3): 326-333.

[20] Halatci I, Brooks C A, Iagnemma K. Terrain classification and classifier fusion for planetary exploration rovers[C]//IEEE Aerospace Conference. Piscataway, USA: IEEE, 2007: 1-11.