北斗卫星定位系统与VSLAM融合的目标定位方法

Target Positioning Method of Beidou Satellite Positioning System and VSLAM Fusion

针对智能仿生机械狗视觉目标定位精度不高的问题,提出一种单目视觉同步定位与建图和北斗定位信息相结合的定位方法.采用VSLAM算法对每帧图像进行特征点提取匹配,并将二维图像信息转换为所需要的三维空间信息;对从北斗卫星导航系统获取的实时经纬度信息进行处理得到每段时间的位移信息;将单目相机的估计距离和北斗卫星导航系统获取的位移信息进行融合处理,得到CGCS2000坐标系下的相机位姿;通过反投影手段获取感兴趣目标点在空间坐标系下的实际坐标,调取北斗卫星导航系统查询该点的经纬度坐标,从而获取机械狗视觉目标的定位信息;通过试验测试验证了本文方法的有效性、精确性与实时性.

Aiming at the visual target location of intelligent bionic mechanical dog,a location method combining monocular VSLAM and Beidou information is proposed.Firstly,VSLAM algorithm is used to extract and match the feature points of each frame image,and the two-dimensional image information is transformed into the required three-dimensional spatial information.Secondly,the real-time longitude and latitude information obtained from BDS is processed to obtain the displacement information of each period of time.Finally,the estimated distance of monocular camera and the displacement information obtained by BDS are fused to gain the camera pose in CGCS2000 coordinate system.The actual coordinates of the target point of interest in the spatial coordinate system are obtained by back projection,and the longitude and latitude coordinates of the point are queried by BDS,so as to obtain the positioning information of the visual target of the mechanical dog.Experiments show that the method is effective,accurate and real-time.