纸质出版日期:2013,
网络出版日期:2013-7-25
扫 描 看 全 文
引用本文
阅读全文PDF
视觉定位是移动机器人视觉导航的关键问题之一。定位的实时性对视觉导航的性能有较大的影响。在确保定位有效性前提下,提出一种快速的视觉定位方法:采用BRISK(Binary Robust Invariant Scalable Key Points)特征作为局部不变性特征点,基于集合理论将场景图像简化为物种种群集合,采用种群相似系数索雷申系数测量场景的相似性,避免繁杂的计算过程,力求简洁快速有效地完成视觉定位。仿真和仿人机器人实验结果表明:在非结构化室内环境下,视觉定位有效性达到99%,场景相似性测量的平均时间003 s(每秒33幅图像),验证了该方法的有效性、鲁棒性和良好的实时性。
Visual location is one of the most important issues in robot visual navigation. The locating efficiency has a large impact on the performance of the visual navigation. A fast visual location method is proposed: BRISK is employed as the local invariant features, the scene model based on aggregate is described and the similarity of the scenes is measured by Sorensen coefficient to avoid complex computation for efficiency. The method has been verified by simulation and experiment with a humanoid robot in indoor environment. The effectiveness is 99% and the average measuring time is 003 s (33 fps). The result demonstrates that the method has good performance in terms of effectiveness, robustness and real time.
848
浏览量
559
下载量
0
CSCD
相关文章
相关作者
相关机构