Samodejna koregistracija trirazse nih modelov stavb z grafi nimi gradniki na podobah : Automatic coregistration of three-dimensional building models with image features

Namen na e raziskave je samodejna dolo itev tekstur streh in fasad stavb z infrarde ih (IR) posnetkov za teksturiranje obstoje ega trirazse nega (3D) modela stavb. Za to je treba izbolj ati natan nosti neposredno izmerjenih parametrov zunanje orientacije IR-kamere, pritrjene na mobilno platformo. Ta prispevek opisuje metodo, razvito za izbolj anje parametrov zunanje orientacije, ki temelji na ujemanju to k samodejno zaznanih grafi nih gradnikov z IR-videoposnetka in i nega modela stavb. Najprej prou imo zaznavo razli nih tipov grafi nih gradnikov na testnem IR-posnetku. F rstnerjeve in prese i ne to ke izberemo kot primerne grafi ne gradnike za predstavitev obravnavanih zna ilnosti stavb na IR-posnetku. 3D-model stavb projiciramo na vsak posamezen posnetek videosekvence ob upo tevanju orientacijskih parametrov, od katerih so parametri zunanje orientacije podani s pribli nimi vrednostmi. Nato izvedemo samodejno koregistracijo 3D-modela stavb, projiciranega na videoposnetek, in grafi nih gradnikov, zaznanih z istega IR-videoposnetka. Samodejno ujemanje 3D-modela stavb in zaznanih grafi nih gradnikov poteka iterativno in skupaj z izravnavo parametrov zunanje orientacije z metodo najmanj ih kvadratov. Razvito metodologijo za koregistracijo in izravnavo zunanjih orientacijskih parametrov smo preizkusili na strnjenem poseljenem obmo ju. Kakovost metodologije ocenimo s petimi parametri: u inkovitostjo metodologije, popolnostjo in pravilnostjo algoritmov za ujemanje in zaznavo grafi nih gradnikov ; The aim of this article is to investigate methods for the automatic extraction of the infrared (IR) textures for the roofs and facades of existing building models. We focus on the correction of the measured exterior orientation parameters of the IR camera mounted on a mobile platform. The developed method is based on point-to-point matching of the features extracted from IR images with a wire-frame building model. Firstly, the extraction of different feature types is studied on a sample IR image; F rstner and intersection points are chosen for a representation of the image features. Secondly, the three-dimensional (3D) building model is projected into each frame of the IR video sequence using orientation parameters; only coarse exterior orientation parameters are known. Then the automatic co-registration of a 3D building model projection into the image sequence with image features is carried out. The matching of a model and extracted features is applied iteratively, and exterior orientation parameters are adjusted with least square adjustment. The method is tested