The Raven initiative is Fluendo’s strategic research framework designed to navigate and lead the convergence of Multimedia Processing and Edge Artificial Intelligence. By transforming complex video streams into actionable, real-time insights, Raven establishes a robust foundation for next-generation AI SDKs, tailored consultancy services, and scalable hardware-accelerated products.
The rapid evolution of Artificial Intelligence is reshaping the multimedia landscape, creating unprecedented architectural demands and business opportunities. However, the sheer density of emerging technologies, frameworks, and market inputs requires a structured, data-driven approach.
The Raven initiative was born to bridge this gap. It serves as Fluendo’s specialized research line dedicated to gathering objective market intelligence and technical data. By analyzing industry trends, hardware constraints, and evolving customer needs, Raven removes ambiguity from AI integration. This initiative ensures that Fluendo’s transition into the AI ecosystem is backed by rigorous validation, ultimately transforming our proven multimedia expertise into high-performance, edge-optimized intelligence.
The rapid evolution of Artificial Intelligence is reshaping the multimedia landscape, creating unprecedented architectural demands and business opportunities. However, the sheer density of emerging technologies, frameworks, and market inputs requires a structured, data-driven approach.
The Raven initiative was born to bridge this gap. It serves as Fluendo’s specialized research line dedicated to gathering objective market intelligence and technical data. By analyzing industry trends, hardware constraints, and evolving customer needs, Raven removes ambiguity from AI integration. This initiative ensures that Fluendo’s transition into the AI ecosystem is backed by rigorous validation, ultimately transforming our proven multimedia expertise into high-performance, edge-optimized intelligence.
What we did
Driven by our AI Engine, these production-ready, hardware-agnostic ai powered plugins feature a fully GPU-driven pipeline, keeping rendering, inference, and image processing on the GPU to maximize performance across heterogeneous computing platforms.
Accelerate your media processing with ultra-low-latency AI video analyzer solutions, optimized for edge performance where milliseconds matter.
our use cases
These use cases present conceptual examples of how our ideas and technologies could address real-world industry challenges.
DaaS & VDI administrators currently lack a reliable, non-intrusive way to measure real-time video quality perceived by users. Traditional reference-based metrics (e.g., VMAF, PSNR, SSIM) require an original source stream that is unavailable in most production desktops, making live monitoring impractical.
Subjective methods (e.g., MOS following ITU BT.500/P.910) are costly, offline, and cannot operate continuously. Meanwhile, transport-level metrics (latency, loss, jitter, bitrate) do not consistently correlate with users’ visual experience, so degradations are detected late, after productivity and satisfaction have already dropped.
An approach that estimates perceived quality without a reference and runs continuously inside real environments would close this gap.
Historic sports footage represents a valuable asset for broadcasters, clubs, sports federations, and media archives. However, many classic matches were recorded in low resolutions, analog formats, or early digital standards, resulting in blurry visuals, limited detail, and reduced viewing quality on modern displays.
Manually restoring and enhancing these recordings is complex, time-consuming, and often requires specialized post-production workflows. As demand grows for remastered sports content, documentaries, digital archives, and modern streaming platforms, improving the quality of historic footage has become increasingly important.
With advancements in AI-based superresolution, computer vision models can reconstruct missing details and upscale legacy sports videos to higher resolutions. By processing video frames automatically, such systems can transform historic recordings into clearer, sharper versions suitable for modern screens while preserving the authenticity of the original footage.
Youth and academy sports organizations increasingly record matches and training sessions for performance analysis, coaching review, and player development. However, these recordings often include minors, spectators, and staff members, creating important privacy and regulatory challenges, particularly under frameworks such as GDPR and child protection policies.
Manually anonymizing individuals in sports footage is time-consuming and difficult to scale, especially when clubs, academies, or federations manage large volumes of recorded matches, training sessions, and archived content.
With advances in AI-based person detection, tracking, and segmentation, computer vision systems can automatically detect individuals appearing in sports video and apply anonymization techniques such as face blurring or body masking. At the same time, the system can preserve useful movement and positional metadata, enabling coaches and analysts to study gameplay, tactics, and player behavior without exposing personal identities.
Sports clubs, broadcasters, and analytics teams increasingly rely on data-driven insights to understand player performance, tactical behavior, and match dynamics. Traditionally, these metrics are collected using dedicated tracking systems or manual annotation workflows, which can be costly, complex to deploy, and difficult to integrate into existing video infrastructures.
Recent advances in AI-based computer vision enable sports analytics to be derived directly from video. By analyzing match footage frame by frame, AI models can estimate player positioning, movement trajectories, and spatial relationships across the field.
These insights can be transformed into valuable performance metrics such as distance traveled, top speed, positioning patterns, and heatmaps, enabling coaches, analysts, and media teams to better understand player behavior and team dynamics.
When combined with modern multimedia pipelines, these AI-generated insights can be embedded directly into the video stream as structured metadata, enabling downstream systems to access analytics data in real time without requiring separate data pipelines.
Sports clubs and academies increasingly produce live video streams, interviews, commentary shows, and behind-the-scenes content for digital platforms and social media. These broadcasts often take place in training grounds, stadiums, or mixed media areas, where children, staff members, and spectators may appear in the background.
This creates important privacy and safeguarding challenges, particularly in youth sports environments where minors must not be publicly identifiable without explicit consent.
Manual editing or post-production anonymization is not feasible for live broadcasts or real-time streaming, where video must be processed instantly before distribution.
With advances in AI-based person and face detection, video processing systems can automatically identify individuals appearing in the background of a live stream and apply anonymization techniques such as face blurring or masking in real time. This allows sports organizations to safely broadcast interviews, live shows, and training content while protecting the identity of children and other individuals present in the scene.
Bits & Bytes
Explore our blog, one byte at a time. Our team unpack our latest news, industry insights and in-depth articles to connect you with the multimedia world.Blog
Read more about our work
Real-time 4K face anonymization benchmark (GStreamer plugin)
broadcasting, video-surveillance, automotive, multimedia-edge-ai, gstreamer, events, fluendo-ai-plugins, anonymizer, ravenPerformance benchmark analysis of real-time 4K AI video anonymization.
Virtual avatars optimized for AMD GPUs in video games
hardware-manufacturer, multimedia-edge-ai, gstreamer, outsource, ravenAI-based 3D virtual avatars rendering application for video games and Twitch.
Fluendo awarded SPIRIT Open Call 2 grant: Introducing AIVATAR
daas-vdi, gstreamer, codecs, fluendo-codec-pack, fluendo-ai-plugins, remote-desktop-coding-tools, raven, lynxFluendo selected for SPIRIT grant to develop AI-powered avatar telepresence.
Privacy-preserving AI video surveillance with edge intelligence
video-surveillance, multimedia-edge-ai, gstreamer, events, fluendo-ai-plugins, ravenGDPR-compliant AI video surveillance with real-time edge intelligence.