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

Video-based gait recognition has achieved impressive results in constrainedscenarios. However, visual cameras neglect human 3D structure information,which limits the feasibility of gait recognition in the 3D wild world. Insteadof extracting gait features from images, this work explores precise 3D gaitfeatures from point clouds and proposes a simple yet efficient 3D gaitrecognition framework, termed LidarGait. Our proposed approach projects sparsepoint clouds into depth maps to learn the representations with 3D geometryinformation, which outperforms existing point-wise and camera-based methods bya significant margin. Due to the lack of point cloud datasets, we built thefirst large-scale LiDAR-based gait recognition dataset, SUSTech1K, collected bya LiDAR sensor and an RGB camera. The dataset contains 25,239 sequences from1,050 subjects and covers many variations, including visibility, views,occlusions, clothing, carrying, and scenes. Extensive experiments show that (1)3D structure information serves as a significant feature for gait recognition.(2) LidarGait outperforms existing point-based and silhouette-based methods bya significant margin, while it also offers stable cross-view results. (3) TheLiDAR sensor is superior to the RGB camera for gait recognition in the outdoorenvironment. The source code and dataset have been made available athttps://lidargait.github.io.

LidarGait: Benchmarking 3D Gait Recognition with Point Clouds