透视图(图形)
计算机科学
同时定位和映射
离群值
点(几何)
人工智能
计算机视觉
增强现实
方向(向量空间)
姿势
数学
移动机器人
机器人
几何学
标识
DOI:10.23919/ccc52363.2021.9549863
摘要
Determining the position and orientation of the camera is a crucial problem with the rapidly developing technology in visual Simultaneous Localization and Mapping (SLAM), augmented reality and 3D reconstruction. Solving the PnP (perspective-n-point) problem is an effective method to calculate the pose of the camera and is also the most widely used method in many applications. In this paper, the methods for PnP problem, including special PnP problem and general PnP problem are summarized firstly. Then, due to importance of performing PnP methods in practical applications, ability to handle outliers for PnP methods is studied. Finally, the main problems of the current researches on PnP problem are presented.
科研通智能强力驱动
Strongly Powered by AbleSci AI