Region of interest–based segmented tiled adaptive streaming using head-mounted display tracking sensing data

Abstract

To support 360 virtual reality video streaming services, high resolutions of over 8K and network streaming technology that guarantees consistent quality of service are required. To this end, we propose 360 virtual reality video player technology and a streaming protocol based on MPEG Dynamic Adaptive Streaming over HTTP Spatial Representation Description to support the player. The player renders the downsized video as the base layer, which has a quarter of the resolution of the original video, and high-quality video tiles consisting of tiles obtained from the tiled-encoded high-quality video (over 16K resolution) as the enhanced layer. Furthermore, we implemented the system and conducted experiments to measure the network bandwidth for 16K video streaming and switching latency arising from changes in the viewport. From the results, we confirmed that the player has a switching latency of less than 1000 ms and a maximum network download bandwidth requirement of 100 Mbps.

Real-time wildfire detection with semantic explanations

“…Even with the advance of deep learning methods in which the latent features are learned automatically, these features still lack the ability to generate rich semantic explanations, especially with streaming data. On the other hand, lightweight models (Kim & Yang, 2019) rely on threshold-based predicates over spectral indexes, which are somewhat understandable for domain experts. However, they often yield a lower prediction power in practice.…”

A Survey on Adaptive 360° Video Streaming: Solutions, Challenges and Opportunities

“…The authors showed that differentiated quality streaming results in a bandwidth saving of 72% in comparison to a baseline approach. Kim and Yang [123] used an enhanced version of MPEG-DASH SRD to choose between quality variable tile layers. The researchers designed 15 https://github.com/tnomedialab/dash-srd.js and implemented a multilayer rendering enabled 360 • VR player based on their previous work [124] to support highresolution and low latency streaming for highly unpredictable head motion data.…”