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

Human gait is one of important biometric characteristics for humanidentification at a distance. In practice, occlusion usually occurs andseriously affects accuracy of gait recognition. However, there is no availabledatabase to support in-depth research of this problem, and state-of-arts gaitrecognition methods have not paid enough attention to it, thus this paperfocuses on gait recognition under occlusion. We collect a new gait recognitiondatabase called OG RGB+D database, which breaks through the limitation of othergait databases and includes multimodal gait data of various occlusions(self-occlusion, active occlusion, and passive occlusion) by our multiplesynchronous Azure Kinect DK sensors data acquisition system (multi-Kinect SDAS)that can be also applied in security situations. Because Azure Kinect DK cansimultaneously collect multimodal data to support different types of gaitrecognition algorithms, especially enables us to effectively obtaincamera-centric multi-person 3D poses, and multi-view is better to deal withocclusion than single-view. In particular, the OG RGB+D database providesaccurate silhouettes and the optimized human 3D joints data (OJ) by fusing datacollected by multi-Kinects which are more accurate in human pose representationunder occlusion. We also use the OJ data to train an advanced 3D multi-personpose estimation model to improve its accuracy of pose estimation underocclusion for universality. Besides, as human pose is less sensitive toocclusion than human appearance, we propose a novel gait recognition methodSkeletonGait based on human dual skeleton model using a framework of siamesespatio-temporal graph convolutional networks (siamese ST-GCN). The evaluationresults demonstrate that SkeletonGait has competitive performance compared withstate-of-art gait recognition methods on OG RGB+D database and popular CAISA-Bdatabase.

A Benchmark for Gait Recognition under Occlusion Collected by Multi-Kinect SDAS