Cruz García, Jesús Manuel de laHerrera Caro, Pedro JavierPajares Martínsanz, GonzaloGuijarro Mata-García, María2023-06-202023-06-202011-070957-417410.1016/j.eswa.2011.01.066https://hdl.handle.net/20.500.14352/43934© 2011 Elsevier. The authors wish to acknowledge to the Council of Education of the Autonomous Community of Madrid and the Social European Fund for the research contract with the author P. Javier Herrera. Also to Drs. Fernando Montes and Isabel Canellas from the Forest Research Centre (CIFOR, INIA) for his support and the imaged material supplied.We present a novel strategy for computing disparity maps from omni-directional stereo images obtained with fish-eye lenses in forest environments. At a first segmentation stage, the method identifies textures of interest to be either matched or discarded. Two of them are identified by applying the powerful Support Vector Machines approach. At a second stage, a stereovision matching process is designed based on the application of four stereovision matching constraints: epipolarity, similarity, uniqueness and smoothness. The epipolarity guides the process. The similarity and uniqueness are mapped once again through the Support Vector Machines, but under a different way to the previous case; after this an initial disparity map is obtained. This map is later filtered by applying the Discrete Simulated Annealing framework where the smoothness constraint is conveniently mapped. The combination of the segmentation and stereovision matching approaches makes the main contribution. The method is compared against the usage of simple features and combined similarity matching strategies. (C) 2011 Elsevier Ltd. All rights reserved.engjournal articlehttp://link.springer.com/chapter/10.1007/978-3-642-25489-5_56#page-1http://www.sciencedirect.comopen access004Image SegmentationOptimizationRelaxationTextureColorInformática (Informática)1203.17 Informática