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

Any 3D tracking algorithm has to deal with occlusions: multiple targets getso close to each other that the loss of their identities becomes likely. In thebest case scenario, trajectories are interrupted, thus curbing the completenessof the data-set; in the worse case scenario, identity switches arise,potentially affecting in severe ways the very quality of the data. Here, wepresent a novel tracking method that addresses the problem of occlusions withinlarge groups of featureless objects by means of three steps: i) it representseach target as a cloud of points in 3D; ii) once a 3D cluster corresponding toan occlusion occurs, it defines a partitioning problem by introducing a costfunction that uses both attractive and repulsive spatio-temporal proximitylinks; iii) it minimizes the cost function through a semi-definite optimizationtechnique specifically designed to cope with link frustration. The algorithm isindependent of the specific experimental method used to collect the data. Byperforming tests on public data-sets, we show that the new algorithm produces asignificant improvement over the state-of-the-art tracking methods, both byreducing the number of identity switches and by increasing the accuracy of theactual positions of the targets in real space.

SpaRTA - Tracking across occlusions via global partitioning of 3D clouds of points