Abstract
We present a novel strategy for computing disparity maps from hemispherical 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. This is achieved by applying a pattern recognition strategy based on the combination of two classifiers: Fuzzy Clustering and Bayesian. At a second stage, a stereovision matching process is performed based on the application of four stereovision matching constraints: epipolar, similarity, uniqueness and smoothness. The epipolar constraint guides the process. The similarity and uniqueness are mapped through a decision making strategy based on a weighted fuzzy similarity approach, obtaining a disparity map. This map is later filtered through the Hopfield Neural Network framework by considering the smoothness constraint. 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.
Highlights
This paper presents the combination of a segmentation process for identifying three kinds of textures and a stereovision matching process, where the WFS approach allows the mapping of the similarity and uniqueness constraints obtaining an initial disparity map
Once the disparity map is obtained according to the above process, we try its improvement based on the Hopfield Neural Network (HNN) paradigm
After mapping the energy function onto the Hopfield neural network, the filtering of the disparity map is achieved by letting the network evolve so that it reaches a stable state, i.e., when no change occurs in the states of its nodes during the updating procedure
Summary
One important task in forest analysis is to determine the volume of wood in an area for different purposes, such as to control the degree of growth of the trees or to determine the resources that must be applied for maintenance. As the images are captured in two positions separated a certain distance (base-line), the tree’s crowns are located at different positions with respect each camera position and the incident rays of the sun produce important lighting variability between the pixels locations and surrounding areas in both images for the same structure in the scene; this makes the matching process a difficult task. This observation is applicable for the whole images. The colour is the unique attribute where the neighbourhood is not involved
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.