[1]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 Zi-xing,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.
点击复制
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
1
期数:
2006年第1期
页码:
52-56
栏目:
学术论文—机器感知与模式识别
出版日期:
2006-03-25
- Title:
-
Corner clustering based detection and recognition of natural landmark for mobile robot
- 文章编号:
-
1673-4785(2006)01-0052-05
- 作者:
-
蔡自兴,王 勇,王 璐
-
中南大学信息科学与工程学院,湖南长沙410083
- Author(s):
-
CAI Zi-xing, WANG Yong, WANG Lu
-
School of Information Science and Engineering, Central South University, Changsha 410083,China
-
- 关键词:
-
未知环境; 移动机器人; 角点聚类; 双目视觉; 局部特征; 匹配算法
- Keywords:
-
unknown environment; mobile robot; corner cluste ring; stereo vision; local feature; matching algorithm
- 分类号:
-
TP242.6+2
- 文献标志码:
-
A
- 摘要:
-
针对未知环境中机器人视觉导航的自然路标检测,提出了一种基于角点聚类的自然路标局部特征提取、不变性表示及其匹配算法.用SUSAN算子提取左右视图中的角点,在极线约束下对左右视图的角点进行匹配,消除遮挡或噪声引起的角点;同时应用立体视觉计算角点视差,进一步筛选角点.根据角点聚类策略提取自然路标局部特征,并提出不随距离、角度变化的局部特征不变性表示及匹配方法.理论分析和实验结果表明,该算法具有较好的鲁棒性,在一定距离和角度变换下能够对路标进行正确识别.
- Abstract:
-
Aiming at the detection of the natural landmarks for mobile robot nav igation based on vision system in unknown environment, this paper presented a no v el method based on corner clustering method to build the invariant model of loca l feature of unknown natural landmark and recognize it. Firstly, SUSAN operator was used to detect corners in the left and right pictures. Then those corners we re matched in the two pictures, so that occluded points could be deleted. Then, cor ners were clustered according to the corner clustering strategy to build the inv a riant model of local features of unknown natural landmark. Lastly, the method wa s given to match the model, and experiments showed that the method was effective to build the invariant model of natural landmark and could also be recognized when viewpoint and scale were changed.
更新日期/Last Update:
2009-04-07