🤖 AI Summary
To address challenges in distributed orchestration, lack of standardization, and insufficient elasticity for multimedia workflows in cloud–edge collaborative environments, this paper proposes and implements a cloud-native networked multimedia workflow system. The system introduces the first open-source implementation supporting the ISO/IEC 23090-8 NBMP international standard, and adopts a declarative microservice architecture built atop Kubernetes to uniformly abstract end-to-end media processing tasks—including ingestion, transcoding, packaging, and distribution. Leveraging NBMP-standardized APIs and containerized resource scheduling, it enables dynamic cross-environment deployment, fine-grained elastic scaling, and load balancing across cloud and edge infrastructures. Experimental evaluation in a real-world hybrid cloud–edge setting demonstrates sub-500 ms end-to-end latency for live streaming, a 40% throughput improvement, and strong scalability and engineering deployability.
📝 Abstract
Before media playback is possible, live and video-on-demand content alike usually undergoes various operations described as tasks within a multimedia workflow. Where previously ingest, transcode, packaging and delivery tasks might have run on a single machine, today's workflows are significantly more complex distributed systems. Describing and implementing multimedia workflows is challenging and requires new approaches.
A standards-based multimedia workflow system is described in ISO/IEC 23090-8 Network-Based Media Processing (NBMP) developed by MPEG. This technical report discusses details of nagare media engine, our open source research prototype implementation of NBMP. Built upon the Kubernetes platform, nagare media engine provides a cloud- and edge-native solution that meets today's requirements for multimedia workflow systems.