Title :
GPU-Based Background Illumination Correction for Blue Screen Matting
Author :
Ley, Nicolas ; Weigel, Christian ; Mehnert, Markus
Author_Institution :
Tech. Univ. Ilmenau, Ilmenau
Abstract :
Separation of foreground objects from an almost constant backing color for video applications is still a common problem ([1]). For non-realtime situations there is a wide variety of different powerful mathematical approaches that can deal with most of the matting problems. For SD/HD studio realtime keyers most solutions are not applicable due to their algorithm complexity or high effort in user interaction. Excellent hardware keyers, such as Ultimattetrade work on most occasions, but even under controlled lighting in a blue-/greenscreen matting problems may occur, or creativity is limited by necessary lighting conditions. As a preprocessing algorithm for traditional chroma keying systems, we present a simple background illumination correction based approach for avoiding matting problems due to uneven or poor lit blue-/greenscreens. Using the computational power of GPU computing (GPGPU [2]) the presented algorithm is realtime capable and offers an improvement for achievable mattes quality.
Keywords :
colour graphics; computer graphic equipment; image colour analysis; GPU-based background illumination correction; blue screen matting; chroma keying systems; constant backing color; foreground object separation; lighting condition; preprocessing algorithm; Color; Degradation; Frequency estimation; Hardware; High definition video; Kernel; Lighting control; Motion pictures; Production; TV; blue screen matting; illumination correction; illumination estimation; inpainting;
Conference_Titel :
Consumer Electronics, 2007. ISCE 2007. IEEE International Symposium on
Conference_Location :
Irving, TX
Print_ISBN :
978-1-4244-1109-2
Electronic_ISBN :
978-1-4244-1110-8
DOI :
10.1109/ISCE.2007.4382150