This paper addresses multi-view point cloud registration, which is one of the major techniques to develop a robust visual tracking system. The proposedalgorithm first uses Kinect camera to capture point clouds of an ...
详细信息
ISBN:
(纸本)9781479923847;9781479923830
This paper addresses multi-view point cloud registration, which is one of the major techniques to develop a robust visual tracking system. The proposedalgorithm first uses Kinect camera to capture point clouds of an object-of-interest or a complex environment with different view points. Then, a novel RANSAC rgb-d mapping algorithm is developed to efficiently and accurately align the multiple point clouds. Based on the aligned point cloud of the object, a CAd model can possibly be created to achieve the purpose of three-dimensional object pose estimation, which helps improving the robustness of visual tracking systems.
暂无评论