| 内容提要: |
Indoor localization is an essential problem for various location-based applications. It is now widely accepted that single sensor’s performance is not good enough, the hybridization of different sensors for accurate positioning is the tendency of this field. An improved Kalman filter can achieve the integrated system. Experimental results demonstrate that it can produce a high localization accuracy. It can control the cumulative errors of the inertial approach effectively. At the same time, it can also solve the interference problems of the visual approach in challenging scenarios such as people entering/exiting the scene and the sudden scene changes. |