Abstract
The problem of where to position the range sensor next for generating a completely seamless integration of a targeted surface from multiple range datasets acquired at different spatial poses is one of the challenging tasks in machine vision. A new view planning method is proposed for complete reconstruction of the real scene from the minimum number of range datasets. The generated surface model covers approximately all major attributes of the scene with minimal a priori knowledge about its geometry. Finally, the experimental results show the effectiveness of the proposed method.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have