Full Scaled 3D Visual Odometry from a Single Wearable Omnidirectional Camera

Autores

Gutierrez-Gomez, D; Puig-Morales, L; Guerrero, JJ

Año: 2012

Resumen

In the last years monocular SLAM has been widely used and tested to obtain highly accurate maps and trajectory estimations of a moving camera. However one of the issues of this methodology is that, due to the imposibility of the depth being measured in a single image, global scale is not observable and scene and camera motion can only be recovered up to scale. This problem gets aggravated as we deal with larger scenes since it is more likely that scale drift arises between different map portions and their corresponding motion estimates. To compute the absolute scale we need to know some kind of dimension of the scene (e.g. real size of an element of the scene, velocity of the camera or baseline between two frames) and somehow integrate it in the SLAM estimation. In this paper, we present a method to recover the scale of the scene using an omnidirectional camera mounted on a helmet carried by a person. The high precision of visual SLAM allows the head vertical oscillation during walking to be perceived in the trajectory estimation. By performing a spectral analysis on the camera vertical displacement, we can measure the step frequency. We relate the step frequency to the speed of the camera by an empirical formula based on biomedical experiments on human walking. This velocity measurement is integrated in a Particle Filter to estimate the current scale factor and the 3D motion estimation in real size. We tested our approach on real world image sequences and it has shown to provide a very accurate estimate of the real scaled trajectory being able to cope with scale drift.

Palabras clave

Omnidirectional vision ; catadioptric camera ; Visual SLAM ; feature matching ; Extended Kalman Filter (EKF) ; spectral analysis ; Discrete Fourier Transform (DFT)

Documento pdf: Ver documento