PIVO: Probabilistic Inertial-Visual Odometry for Occlusion-Robust Navigation
This addresses navigation challenges for mobile devices in real-world conditions, though it appears incremental as it builds on existing fusion frameworks with enhanced coupling.
The paper tackles the problem of robust visual-inertial odometry in occlusion and feature-poor environments by proposing a probabilistic fusion method that propagates uncertainties across inertial and visual data, achieving improved performance as demonstrated on iPhone data and benchmarks like EuRoC.
This paper presents a novel method for visual-inertial odometry. The method is based on an information fusion framework employing low-cost IMU sensors and the monocular camera in a standard smartphone. We formulate a sequential inference scheme, where the IMU drives the dynamical model and the camera frames are used in coupling trailing sequences of augmented poses. The novelty in the model is in taking into account all the cross-terms in the updates, thus propagating the inter-connected uncertainties throughout the model. Stronger coupling between the inertial and visual data sources leads to robustness against occlusion and feature-poor environments. We demonstrate results on data collected with an iPhone and provide comparisons against the Tango device and using the EuRoC data set.