O'Byrne, MichaelMichaelO'ByrnePakrashi, VikramVikramPakrashiSchoefs, FranckFranckSchoefsGhosh, BidishaBidishaGhosh2019-05-082019-05-082017 Compu2018-03Computer-Aided Civil and Infrastructure Engineering1093-9687http://hdl.handle.net/10197/10352Underwater inspections stand to gain from using stereo imaging systems to collect three-dimensional measurements. Although many stereo-matching algorithms have been devised to solve the correspondence problem, that is, find the same points in multiple images, these algorithms often perform poorly when applied to images of underwater scenes due to the poor visibility and the complex underwater light field. This article presents a new stereo-matching algorithm, called PaLPaBEL (Pyramidal Loopy Propagated BELief) that is designed to operate on challenging imagery. At its core, PaLPaBEL is a semiglobal method based on a loopy belief propagation message passing algorithm applied on a Markov random field. A pyramidal scheme is adopted that enables wide disparity ranges and high-resolution images to be handled efficiently. For performance evaluation, PaLPaBEL is applied to underwater stereo images captured under various visibility conditions in a laboratory setting, and to synthetic imagery created in a virtual underwater environment. The technique is also demonstrated on stereo images obtained from a real-world inspection. The successful results indicate that PaLPaBEL is well suited for underwater application and has value as a tool for the cost-effective inspection of marine structures.enThis is the peer reviewed version of the following article: O' Byrne, M. , Pakrashi, V. , Schoefs, F. and Ghosh, B. (2018), A Stereo‐Matching Technique for Recovering 3D Information from Underwater Inspection Imagery. Computer‐Aided Civil and Infrastructure Engineering, 33: 193-208, which has been published in final form at http://onlinelibrary.wiley.com/doi/10.1111/mice.12307. This article may be used for non-commercial purposes in accordance with Wiley Terms and Conditions for Self-Archiving.Underwater inspectionsPaLPaBEL (Pyramidal Loopy Propagated BELief)High-resolution imagesMarine structuresStereo correspondence algorithmA Stereo-Matching Technique for Recovering 3D Information from Underwater Inspection ImageryJournal Article33319320810.1111/mice.123072019-05-0512/RC/2302https://creativecommons.org/licenses/by-nc-nd/3.0/ie/