Development of Height Indicators using Omnidirectional Images and Global Appearance Descriptors

Abstract

Nowadays, mobile robots have become a useful tool that permits solving a wide range of applications. Their importance lies in their ability to move autonomously through unknown environments and to adapt to changing conditions. To this end, the robot must be able to build a model of the environment and to estimate its position using the information captured by the different sensors it may be equipped with. Omnidirectional vision sensors have become a robust option thanks to the richness of the data they capture. These data must be analysed to extract relevant information that permits estimating the position of the robot taking into account the number of degrees of freedom it has. In this work, several methods to estimate the relative height of a mobile robot are proposed and evaluated. The framework we present is based on the global appearance of the scenes, which has emerged as an efficient and robust alternative comparing to methods based on local features. All the algorithms have been tested with some sets of images captured under real working conditions in several indoor and outdoor spaces. The results prove that global appearance descriptors provide a feasible alternative to estimate topologically the relative altitude of the robot.

Relative Altitude Estimation Using Omnidirectional Imaging and Holistic Descriptors

“…Second, among the methods presented in [40], those based on the use of the orthographic view present the best performance, similar to the performance of the Radon transform. However, the computation time necessary to describe and compare the reference and the test images is substantially higher in [40] than in the present paper, where this time is around 0.2 s. Finally, the method based on Radon transform has been compared with the benchmarking method described in Section 4.2. First of all, as far as the computational time is concerned, the method based on local features takes, on average, 1.3 s when SURF is used and 6.1 s when ASIFT is used.…”

“…It is important to highlight the fact that, since the global appearance of the images is used and a topological approach is considered, the calibration of the camera and the stability of its parameters are not critical. Comparing to a previous work that used global appearance descriptors to estimate relative height [40], the present work presents some advantages. First, the orientation of the robot can be different for the reference and the test images, because POC is able to calculate and compensate this difference in orientation.…”

“…First, the orientation of the robot can be different for the reference and the test images, because POC is able to calculate and compensate this difference in orientation. In [40], the images have to be equally orientated to estimate correctly the relative height. Second, among the methods presented in [40], those based on the use of the orthographic view present the best performance, similar to the performance of the Radon transform.…”

“…In [40], the images have to be equally orientated to estimate correctly the relative height. Second, among the methods presented in [40], those based on the use of the orthographic view present the best performance, similar to the performance of the Radon transform. However, the computation time necessary to describe and compare the reference and the test images is substantially higher in [40] than in the present paper, where this time is around 0.2 s. Finally, the method based on Radon transform has been compared with the benchmarking method described in Section 4.2.…”