English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Learning-based visual ego-motion estimation is promising yet not ready fornavigating agile mobile robots in the real world. In this article, we proposeCUAHN-VIO, a robust and efficient monocular visual-inertial odometry (VIO)designed for micro aerial vehicles (MAVs) equipped with a downward-facingcamera. The vision frontend is a content-and-uncertainty-aware homographynetwork (CUAHN) that is robust to non-homography image content and failurecases of network prediction. It not only predicts the homography transformationbut also estimates its uncertainty. The training is self-supervised, so that itdoes not require ground truth that is often difficult to obtain. The networkhas good generalization that enables "plug-and-play" deployment in newenvironments without fine-tuning. A lightweight extended Kalman filter (EKF)serves as the VIO backend and utilizes the mean prediction and varianceestimation from the network for visual measurement updates. CUAHN-VIO isevaluated on a high-speed public dataset and shows rivaling accuracy tostate-of-the-art (SOTA) VIO approaches. Thanks to the robustness to motionblur, low network inference time (~23ms), and stable processing latency(~26ms), CUAHN-VIO successfully runs onboard an Nvidia Jetson TX2 embeddedprocessor to navigate a fast autonomous MAV.

CUAHN-VIO: Content-and-Uncertainty-Aware Homography Network for Visual-Inertial Odometry