摘要
提出了一种移动机器人快速定位方法。该方法在水平面假设的前提下,采用Harris Laplace算子并结合快速均值漂移和立体视觉方法,构建了一个障碍物地平角点提取算法取得特征角点,再以提取的障碍物地平角点为路标点,利用自适应粒子滤波方法融合路标点的深度和位置信息,实现了移动机器人高效快速和较为精确的定位。由于路标点(障碍物地平角点)数量大幅度减少,大大降低了定位算法计算的复杂度。实验的结果证明了上述方法是行之有效的。
Using the assumption of the horizontal plane, a method of fast localization for mobile robot is presented. This method addresses an Obstacle-Ground-Comer extraction algorithm combined with the Harris-Laplace operator, fast mean shift and stereo vision, and then uses the obstacle ground comers as landmarks. The adaptive particle filtering method is used to fusion the landmarks depth and position to a- chieve an efficient and more accurate fast localization, the computational complexity of localization algo- rithm is greatly reduces due to the use of a small number of landmarks. The results of experiment illustra- ted the effectiveness of this method.
出处
《中山大学学报（自然科学版）》
CAS
CSCD
北大核心
2013年第5期45-50,共6页
Acta Scientiarum Naturalium Universitatis Sunyatseni
基金
国家自然科学基金资助项目(61201087)
