POSE POSITIONING METHOD AND RELATED EQUIPMENT OF ACTIVE RIGID BODY IN MULTI-CAMERA ENVIRONMENT

摘要

The present invention relates to the technical field of computer vision, in particular to a pose positioning method and related equipment of an active rigid body in a multi-camera environment. The method comprises: acquiring two-dimensional space point coordinates and two-dimensional spatial point coding of two adjacent frames, and calculating three-dimensional space point coding and three-dimensional space point coordinates; converting all three-dimensional space point coding and three-dimensional space point coordinates into rigid body coordinates; determining an initial pose of the rigid body by solving a pose estimation; using a gradient descent method, and constructing a cost function by using a re-projection error, and minimizing the cost function to obtain a motion pose of the rigid body, and tracking and positioning the rigid body according to the initial pose and the motion pose. After adopting said positioning mode, the present invention simplifies the complex device structure of traditional optical motion capture cameras, reduces the camera cost, and moreover, the rigid body is not easy to wear and destroy, and its use sustainability is greatly improved.