Relative Height Estimation using Omnidirectional Images and a Global Appearance Approach
Yerai Berenguer, Luis Payá, Adrián Peidró, Óscar Reinoso · 2015
This work presents a height estimation method that uses visual information. This method is based on the global appearance of the scenes. Every omnidirectional scene is described with a global appearance descriptor without any other transformation. This approach is tested with our own image database. This database is generated synthetically based on two different virtual rooms. One of the advantages of generating the images synthetically is that noise or occlusions can be added to test the robustness of the algorithms. This database is formed by a set of omnidirectional images captured from different points of these rooms and at different heights. With these scenes we build the descriptor of each image and we use our method to estimate the relative height of the robot. The experimental results show the effectiveness and the robustness of the method.