一种基于BIM和单目相机的室内定位方法

An indoor positioning method based on BIM and monocular camera

传统的室内定位与跟踪需要在环境中安装大量的辅助设施,这在一些特定的场合中存在很大的局限性。针对以上问题,提出了一种基于建筑信息模型(BIM)和单目相机的室内定位及跟踪方法。该方法利用手机等移动设备上的相机获取现场图像,使用坎尼(Canny)算法进行边缘检测,结合BIM提供的几何信息实现对目标的定位,并通过改进卡尔曼滤波算法对运动轨迹进行优化,最终实现了高精度的定位跟踪。本文所提算法在实际的数据集上进行了测试,实验结果表明,本算法满足室内定位的要求。

Traditional indoor positioning and tracking requires the installation of a large number of auxiliary facilities in the environment, which has great limitations in some specific situations. Aiming at the above problems, this paper innovatively proposes an indoor positioning and tracking method based on Building Information Modeling(BIM) and monocular camera. In this method, the camera on mobile devices such as mobile phones is used to obtain field images. Canny algorithm is used to detect edges and the target location is realized by combining the geometric information provided by BIM. The motion trajectory is optimized by an improved Kalman filter algorithm, and the high-precision location tracking is finally realized. The proposed algorithm is testified on realistic data sets. At last the experimental results show that the algorithm meets the requirements of indoor positioning.