摘要
提出在基于单目视觉创建的环境地图中实现移动机器人全局定位.基于KD树的最近邻搜索实现特征匹配.应用尺度不变特征变换(SIFT)方法提取特征,并用多维向量描述,保证了对图像光强变化、尺度缩放、三维视角和噪声具有不变性.提出了一种基于RANSAC的鲁棒定位方法.在实际室内环境Pioneer3机器人上进行的实验表明本文提出方法高效、可靠.
An environmental map built with monocular vision is used to implement mobile robot global localization. The feature matching is implemented with the KD-tree-based nearest search approach. The features are extracted with Scale Invariant Feature Transform （SIFF）, and discribed with highly distinctive multi-dimensional vector, making features be invariant to changes in illumination, scale, 3D viewpoint and noise. A robust localization based on RANSAC （RANdom SAmple Consensus） approach is presented. Experiments on robot Pioneer 3 with monocular CCD camera in our real indoor environment show that our method is of high precision and stability.
出处
《机器人》
EI
CSCD
北大核心
2007年第2期140-144,178,共6页
Robot
基金
国家863计划资助项目(2002AA735041)
国家自然科学基金资助项目(69985002)
关键词
移动机器人
全局定位
KD树
特征提取
RANSAC
单目视觉
mobile robot
global localization
KD-tree
feature extraction
RANSAC （ RANdom SAmple Consensus ）
monocular vision
