【摘要】 回环检测算法对于视觉SLAM系统修正累积误差具有重要意义。传统的回环检测方法基于图像检索的方式,难以解决视角差异较大情况下的图像匹配问题。文章提出基于几何信息的回环检测方法,融合图像和周边环境的三维几何信息构建虚拟关键帧和描述子,完成大视角差异情况下的回环检测。在自建回环检测测试数据集中,文中方法在精确度达到100%情况下,召回率比传统方法提升了29.6%,对提升视觉SLAM系统的回环检测能力有极大帮助。更多还原

【Abstract】 Loop-closing methods play an important role in SLAM systems to eliminate the accumulative error. Existing loop-closing methods are based on the image retrieval which however easily fails to recognize the same scene viewed from different directions due to large perspective distortions. This paper proposes a novel loop-closing method to address this issue. The key idea is to fully explore the 3 D structure reconstructed by the Visual SLAM system,to render virtual views from which the feature descriptors are extracted. We conduct extensive tests on self-collected datasets. The experimental results show that the recall rate of the approach is increased by 29. 6% comparing with the existing method,while both methods achieve a precision rate of 100%.更多还原