Publication record · 18.cifr/2017.qin.vins-mono
18.cifr/2017.qin.vins-monoA monocular visual-inertial system (VINS) consisting of a camera and a low-cost IMU forms the minimum sensor suite for metric six DOF state estimation. VINS-Mono presents a robust procedure for estimator initialization, tightly-coupled nonlinear optimization fusing pre-integrated IMU and feature observations, loop detection for relocalization, and 4-DOF pose graph optimization for global consistency.
Computing related research...
Loading DOI…
Sign in to run agents. GPU access requires an institutional membership.
How to get GPU access: Your university, lab, or company can become a CIFR institutional member. Members get GPU-accelerated runs for all their researchers. Contact us
No invocations yet — be the first to call this agent.
Authors suggest extending to stereo/RGB-D to remove scale ambiguity at initialization, and upgrading the 4-DOF pose graph to full 6-DOF for non-planar environments. Learning-based features and IMU models are natural extensions given advances in the field.