Systems and methods for parallax detection and correction in images captured using array cameras that contain occlusions using subsets of images to perform depth estimation

作者: Florian Ciurea , Dan Lelescu , Kartik Venkataraman , Gabriel Molina

DOI:

关键词: Confidence mapPixelParallaxSimilarity (geometry)GeographyParallax mappingPosition (vector)Artificial intelligenceComputer vision

摘要: Systems in accordance with embodiments of the invention can perform parallax detection and correction images captured using array cameras. Due to different viewpoints cameras, results variations position objects within scene. Methods provide an accurate account pixel disparity due between cameras array, so that appropriate scene-dependent geometric shifts be applied pixels when performing super-resolution processing. In several embodiments, detecting involves competing subsets estimate depth a location image from reference viewpoint. number generating estimates considers similarity multiple spectral channels. certain confidence map indicating reliability estimates.

参考文章(194)
Marc-Antoine Drouin, Sébastien Roy, Non-Uniform Hierarchical Pyramid Stereo for Large Images. vision modeling and visualization. pp. 403- 410 ,(2002)
Joey Shah, Jeffrey McKee, HDR/AB on multi-way shared pixels ,(2005)
J Duparré, P Dannberg, A Bräuer, R Völkel, T Scharf, None, Microoptical artificial compound eyes - two different concepts for compact imaging systems microoptics conference. ,(2006)
Darryl Sato, Richard Olsen, Feng-Qing Sun, Solid state camera optics frame and assembly ,(2007)
Donn Carlton, Syamal Ghosh, Darryl Miller, Forming information transfer lens array ,(2002)
Bennett Wilburn, Michal Smulski, Kelin Lee, Mark A. Horowitz, The Light Field Video Camera Defense Technical Information Center. ,(2000) , 10.21236/ADA419717