Low Latency High-definition Video Streaming for Real-time Teleoperation Platform
Laine, Joona (2017)
Laine, Joona
2017
Tietotekniikka
Tieto- ja sähkötekniikan tiedekunta - Faculty of Computing and Electrical Engineering
This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited.
Hyväksymispäivämäärä
2017-06-07
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:tty-201705241474
https://urn.fi/URN:NBN:fi:tty-201705241474
Tiivistelmä
Teleoperation is the remote controlling of machines using a real-time video stream to support the controlling decisions. The key components of a teleoperation system are video streaming through a network to enable the control, low enough latency to ensure real-time control and latency - bandwidth - resolution balance of the streaming system. In general, a low latency means high bandwidth consumption and the used resolution relates also straight to the bandwidth. Using the modern video coding method H.264/AVC allows for the reduction of bandwidth and latency by selecting a suitable H.264 profile.
This thesis studies the possibility and effect of maximizing the usage of a graphics processing unit (GPU) in the streaming pipeline of a teleoperation platform and presents measurements to show the impact on the streaming latency. An open source multimedia framework GStreamer is used in the pipeline construction of the platform. The thesis presents the creation of two teleoperation platforms and examines their features. Latency measurements between an existing system and one of the developed systems are compared and results discussed. The results show that employing a GPU in the streaming pipeline greatly improves the performance of the system and allows the streaming of multiple simultaneous low latency high resolution video streams.
This thesis studies the possibility and effect of maximizing the usage of a graphics processing unit (GPU) in the streaming pipeline of a teleoperation platform and presents measurements to show the impact on the streaming latency. An open source multimedia framework GStreamer is used in the pipeline construction of the platform. The thesis presents the creation of two teleoperation platforms and examines their features. Latency measurements between an existing system and one of the developed systems are compared and results discussed. The results show that employing a GPU in the streaming pipeline greatly improves the performance of the system and allows the streaming of multiple simultaneous low latency high resolution video streams.