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

Monocular person following (MPF) is a capability that supports many usefulapplications of a mobile robot. However, existing MPF solutions are notcompletely satisfactory. Firstly, they often fail to track the target at aclose distance either because they are based on a visual servo or they need theobservation of the full body by the robot. Secondly, their targetRe-IDentification (Re-ID) abilities are weak in cases of target appearancechange and highly similar appearance of distracting people. To remove theassumption of full-body observation, we propose a width-based tracking module,which relies on the target width, which can be observed even at a closedistance. For handling issues related to appearance variation, we use a globalCNN (convolutional neural network) descriptor to represent the target and aridge regression model to learn a target appearance model online. We adopt asampling strategy for online classifier learning, in which both long-term andshort-term samples are involved. We evaluate our method in two datasetsincluding a public person following dataset and a custom-built one withchallenging target appearance and target distance. Our method achievesstate-of-the-art (SOTA) results on both datasets. For the benefit of thecommunity, we make public the dataset and the source code.

Following Closely: A Robust Monocular Person Following System for Mobile Robot