摘要
视觉信息处理是智能机器人研究的一项关键技术.由于传统的视觉传感器存在可视范围小等缺点,为此引入由双曲线旋转体反射镜构成的全向视觉传感器,提出了基于全向视觉传感器的图像解算算法.该算法可以有效地还原全向视觉传感器所获取的扭曲图像,从而实现利用全局性信息进行移动机器人的视觉导航.实验结果表明该方法从原理上是可行的,可以应用到机器人的定位导航中.
Vision information processing is a key technique for the intelligence robot research, Considering that traditional vision sensors has some disadvantages such as very small visible area, the omni-directional camera made up of the hyperbola reflector is introduced. And an image calculation algorithm is presented. This algorithm can restore the distortional image. The experiment results show that this method is feasible theoretically and can be utilized into oriental navigation of robot.
出处
《哈尔滨工业大学学报》
EI
CAS
CSCD
北大核心
2006年第12期2158-2161,共4页
Journal of Harbin Institute of Technology
基金
哈尔滨市留学回国人员基金资助项目(2004AFLXJ009)
