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

In this work, we are dedicated to multi-target active object tracking (AOT),where there are multiple targets as well as multiple cameras in theenvironment. The goal is maximize the overall target coverage of all cameras.Previous work makes a strong assumption that each camera is fixed in a locationand only allowed to rotate, which limits its application. In this work, werelax the setting by allowing all cameras to both move along the boundary linesand rotate. In our setting, the action space becomes much larger, which leadsto much higher computational complexity to identify the optimal action. To thisend, we propose to leverage the action selection from multi-agent reinforcementlearning (MARL) network to prune the search tree of Monte Carlo Tree Search(MCTS) method, so as to find the optimal action more efficiently. Besides, wemodel the motion of the targets to predict the future position of the targets,which makes a better estimation of the future environment state in the MCTSprocess. We establish a multi-target 2D environment to simulate the sportsgames, and experimental results demonstrate that our method can effectivelyimprove the target coverage.

Multi-Target Active Object Tracking with Monte Carlo Tree Search and Target Motion Modeling