摘要
For reverse engineering a CAD model, it is necessary to integrate measured points from several views of an object into a common reference frame. Given a rough initial alignment of point cloud in different views with point-normal method, further refinement is achieved by using an improved iterative closest point (ICP) algorithm. Compared with other methods used for mult-view registration, this approach is automatic because no geometric feature, such as line, plane or sphere needs to be extracted from the original point cloud manually. A good initial alignment can be acquired automatically and the registration accuracy and efficiency is proven better than the normal point-point ICP algorithm both experimentally and theoretically.
For reverse engineering a CAD model, it is necessary to integrate measured points from several views of an object into a common reference frame. Given a rough initial alignment of point cloud in different views with point-normal method, further refinement is achieved by using an improved iterative closest point (ICP) algorithm. Compared with other methods used for mult-view registration, this approach is automatic because no geometric feature, such as line, plane or sphere needs to be extracted from the original point cloud manually. A good initial alignment can be acquired automatically and the registration accuracy and efficiency is proven better than the normal point-point ICP algorithm both experimentally and theoretically.
基金
the National Natural Science Foundation of China (59990470) and the NationalOutstanding Young Scientist Foundation of China (
