Odometria Visual por Fluxo Óptico Integrada a um Sistema de Localização Multi-sensor para Veículos de Mineração

Abstract

This paper presents a method for estimating odometry for vehicles in mining environments, where GNSS-based localization systems often fail. The method relies on visual odometry from a camera directed towards the ground. Captured images are used to calculate the optical flow, which describes the movement of pixels in a sequence of images. This movement is combined with data from an IMU to determine the camera’s movement (Visual-Inertial Odometry). The optical flow is calculated using the Gunnar Farneback’s GPU processing method to accurately and efficiently determine camera motion. An analysis of four localization implementations is conducted: (1) Wheel Odometry, (2) Visual-Inertial Odometry, (3) fusion of Wheel Odometry and IMU using Extended Kalman Filter (EKF), and (4) fusion using EKF of Visual-Inertial Odometry, Wheel Odometry, and IMU. Results obtained in the simulation illustrate that the proposed multi-sensor localization system can be effectively used to assist in the localization of mining vehicles in field tasks.