Asynchronous Optimisation for Event-based Visual Odometry
This work addresses the challenge of monocular visual odometry for robotics using event cameras, offering an incremental improvement over existing methods by enabling map-free and sensor-free operation in SE(3).
The paper tackles the problem of event-based visual odometry without a known map or sensor fusion, proposing an asynchronous optimization back-end that uses Gaussian Process motion modeling and incremental inference. The result is a robust method that outperforms frame-based approaches by processing each event individually, though no concrete performance numbers are provided.
Event cameras open up new possibilities for robotic perception due to their low latency and high dynamic range. On the other hand, developing effective event-based vision algorithms that fully exploit the beneficial properties of event cameras remains work in progress. In this paper, we focus on event-based visual odometry (VO). While existing event-driven VO pipelines have adopted continuous-time representations to asynchronously process event data, they either assume a known map, restrict the camera to planar trajectories, or integrate other sensors into the system. Towards map-free event-only monocular VO in SE(3), we propose an asynchronous structure-from-motion optimisation back-end. Our formulation is underpinned by a principled joint optimisation problem involving non-parametric Gaussian Process motion modelling and incremental maximum a posteriori inference. A high-performance incremental computation engine is employed to reason about the camera trajectory with every incoming event. We demonstrate the robustness of our asynchronous back-end in comparison to frame-based methods which depend on accurate temporal accumulation of measurements.