In this work we deal with the matching process problem using stereo images from real world terrains taken with a Videre STH-DCSG 9mm stereoscopic system. A series of matching algorithms are used, as part of the global stereoscopic process, with the purpose of creating a 3D reconstruction for robotic autonomous navigation in natural and non-structured environments. First, a study about the effects of applying homomorphic filtering to the input images previous to the matching process is carried out. Using this method, a significant enhancement in the disparity map is achieved, obtaining a greater number of true correspondences in relation to applying no filtering at all. Then, a filtering process over the disparities map driven by clusters and based in a spatial continuity premise dismisses false positives or wrong correspondences. Both filtering processes are the main contribution of this work. © 2013 CEA.
Correal, R., Pajares, G., & Ruz, J. J. (2013). Mejora del proceso de correspondencia en imágenes estereoscópicas mediante filtrado homomórfico y agrupaciones de disparidad. RIAI - Revista Iberoamericana de Automatica e Informatica Industrial, 10(2), 178–184. https://doi.org/10.1016/j.riai.2013.03.008