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

Pedestrian dead reckoning is a challenging task due to the low-cost inertialsensor error accumulation. Recent research has shown that deep learning methodscan achieve impressive performance in handling this issue. In this letter, wepropose inertial odometry using a deep learning-based velocity estimationmethod. The deep neural network based on Res2Net modules and two convolutionalblock attention modules is leveraged to restore the potential connectionbetween the horizontal velocity vector and raw inertial data from a smartphone.Our network is trained using only fifty percent of the public inertial odometrydataset (RoNIN) data. Then, it is validated on the RoNIN testing dataset andanother public inertial odometry dataset (OXIOD). Compared with the traditionalstep-length and heading system-based algorithm, our approach decreases theabsolute translation error (ATE) by 76%-86%. In addition, compared with thestate-of-the-art deep learning method (RoNIN), our method improves its ATE by6%-31.4%.

Deep Learning-based Inertial Odometry for Pedestrian Tracking using Attention Mechanism and Res2Net Module