[POSTER] Geometric Mapping for Color Compensation Using Scene Adaptive Patches

The SAR technique using a projector-camera system allows us to make various effect on a real scene without physical reconstitution. In order to project contents on a textured scene without color imperfections, geometric and radiometric compensation of a projection image should be conducted as prepro...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2015 IEEE International Symposium on Mixed and Augmented Reality s. 206 - 207
Hlavní autoři: Jong Hun Lee, Yong Hwi Kim, Yong Yi Lee, Lee, Kwan H.
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.09.2015
Témata:
Augmented reality
Calibration
Cameras
Distortion
Image color analysis
Image segmentation
Polynomials
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:The SAR technique using a projector-camera system allows us to make various effect on a real scene without physical reconstitution. In order to project contents on a textured scene without color imperfections, geometric and radiometric compensation of a projection image should be conducted as preprocessing. In this paper, we present a new geometric mapping method for color compensation in the projector-camera system. We capture the scene and segment it into adaptive patch according to the scene structure using the SLIC segmentation. The piece-wise polynomial function is evaluated for each patch to find pixel-to-pixel correspondences between the measured and projection images. Finally, color compensation is performed by using a color mixing matrix. Experimental results show that our geometric mapping method establishes accurate correspondences and color compensation alleviates the color imperfections which is caused by texture of a general scene.
DOI:10.1109/ISMAR.2015.67