Abstract
The fringe projection profilometry (FPP) has been regarded as a classical and mature technique for 3D shape measurement. However, in practical applications, shadow is un-avoided in the imaging process and causes errors in many FPP systems. In this paper, the errors in FPP systems caused by shadow are first analyzed. Then, a direction-aware spatial context module based network is proposed for detecting the shadow regions of a fringe image. Further, a repairment method is developed based on a generative adversarial network combining some simple processes. The training datasets are rendered by a graphic software to easy the training of the networks. The proposed method can repair the shadow regions successfully with only one fringe image and so it can be applied in varieties of FPP systems. The feasibility and the accuracy of improved by the proposed method have been illustrated by abundant experiments.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.