Reinforcement learning for pan-tilt-zoom camera control, with focus on drone tracking

Simple item page
dc.contributor.authorWisniewski, Mariusz
dc.contributor.authorRana, Zeeshan A.
dc.contributor.authorPetrunin, Ivan
dc.date.accessioned2023-05-05T10:45:00Z
dc.date.available2023-05-05T10:45:00Z
dc.date.issued2023-01-19
dc.description.abstractReliable detection and tracking of objects using pan-tilt-zoom (PTZ) cameras is an unsolved problem. We attempt to answer whether the use of reinforcement learning (RL) is an appropriate tool for solving it. We present an environment for training RL agents to track a drone using a (PTZ) camera. We also present an agent trained using this environment, which learns to correctly pan, tilt, and zoom the camera to follow a randomly moving drone, using continuous actions. The input into the agent is the RGB image observed by the camera. The agent is rewarded for correctly tracking the drone, and penalized if it loses it from its viewport. We use the recurrent proximal policy optimization (PPO) algorithm with a long short-term memory (LSTM) layer. We find that the agent reliably learns ways of tracking the drone after around 1.4 million steps of training.en_UK
dc.identifier.citationWisniewski M, Rana ZA, Petrunin I. (2023) Reinforcement learning for pan-tilt-zoom camera control, with focus on drone tracking. In: AIAA SciTech Forum 2023, 23-27 January 2023, National Harbor, Maryland, USA. Paper number AIAA 2023-0194en_UK
dc.identifier.urihttps://doi.org/10.2514/6.2023-0194
dc.identifier.urihttps://dspace.lib.cranfield.ac.uk/handle/1826/19616
dc.language.isoenen_UK
dc.publisherAIAAen_UK
dc.rightsAttribution-NonCommercial 4.0 International*
dc.rights.urihttp://creativecommons.org/licenses/by-nc/4.0/*
dc.titleReinforcement learning for pan-tilt-zoom camera control, with focus on drone trackingen_UK
dc.typeConference paperen_UK

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
stereo_pan_tilt_zoom_camera_control-2023.pdf
Size:
593.49 KB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.63 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Staff publications (SATM)