ITEP-68945 ITEP-68944 Using WebRTC for frames streaming

[Irakus]

📝 Description

Manager app:

• Added WebRTC connection to retrieve video streams for processed and unprocessed camera feed
• Removed live-view button from scene detail view
• Added loading video to play before WebRTC connection is established
• In calibration view, changed source of projection to be video from WebRTC stream
• Removed handling of images with frames from MQTT
• Adjusted calibration messages to use parameters from WebRTC video

DLS Pipeline Server:

• Added frame publishing through WebRTC to Media Server(MediaMTX)
• Added watermark to published frames
• Removed Python code responsible for publishing frames to MQTT
• Changed naming of streams for easy corellation between raw camera feed and dls-processed feed in Media Server
• Removed no-rtsp pipelines as RTSP is needed for WebRTC
• Adjusted all sample pipelines

Media Server (MediaMTX)

• Added config file
• Enabled WebRTC protocol

Coturn:

• Added new component for establishing connection between Media Server and WebRTC receivers

Nginx:

• Added new component to serve as reverse proxy to enable TLS connection between Web app and Media Server
• DLS still uses insecure connection to Media Server
• Added new certificates generation for nginx

Samples:

• Changed mp4->ts conversion script to remove b-frames (WebRTC requirement) and add more keyframes (for WebRTC performance)

Docs:

• Included guides on updating hostfile and CA certificates to enable accessing Scenescape through web.scenescape.intel.com instead of IP
• Updated sample DLS pipelines code snippets

✨ Type of Change

Select the type of change your PR introduces:

• 🐞 Bug fix – Non-breaking change which fixes an issue
• 🚀 New feature – Non-breaking change which adds functionality
• 🔨 Refactor – Non-breaking change which refactors the code base
• 💥 Breaking change – Changes that break existing functionality
• 📚 Documentation update
• 🔒 Security update
• 🧪 Tests
• 🚂 CI

🧪 Testing Scenarios

Describe how the changes were tested and how reviewers can test them too:

• [*] Ran demo
• ✅ Tested manually
• 🤖 Ran automated end-to-end tests

✅ Checklist

Before submitting the PR, ensure the following:

• 🔍 PR title is clear and descriptive
• 📝 For internal contributors: If applicable, include the JIRA ticket number (e.g., ITEP-123456) in the PR title. Do not include full URLs
• 💬 I have commented my code, especially in hard-to-understand areas
• 📄 I have made corresponding changes to the documentation
• ✅ I have added tests that prove my fix is effective or my feature works

[saratpoluri]

We don't need individual license call out for each dependency. Those are done in third-party-programs.txt

[Copilot]

Pull Request Overview

This PR implements WebRTC-based video streaming to replace MQTT-based frame publishing in the SceneScape system. The changes introduce real-time video streaming capabilities through MediaMTX and nginx proxy services, improving performance and user experience.

• Replaced MQTT frame publishing with WebRTC streaming infrastructure
• Added MediaMTX and nginx proxy services for secure TLS connections
• Modified calibration and visualization components to use video streams instead of static images

Reviewed Changes

Copilot reviewed 28 out of 29 changed files in this pull request and generated 2 comments.

Show a summary per file

File	Description
tools/certificates/Makefile	Added certificate generation for MediaMTX proxy service
scene_common/src/transform.py	Added type checking in CameraPose constructor for intrinsics parameter
sample_data/nginx.conf	New nginx configuration for MediaMTX proxy with SSL support
sample_data/mediamtx.yml	MediaMTX configuration with WebRTC and TURN server settings
sample_data/docker-compose-dls-perf.yml	Added MediaMTX, nginx, and coturn services to Docker composition
manager/src/templates/sscape/sceneDetail.html	Replaced image elements with video elements for camera feeds
manager/src/templates/cam/cam_calibrate.html	Updated calibration view to use video instead of images
manager/src/static/js/webrtc_reader.js	New WebRTC reader implementation for video stream handling
manager/src/static/js/viewport.js	Modified projection to use video texture instead of image loading
manager/src/static/js/sscape.js	Removed MQTT image handling and added WebRTC stream initialization
dlstreamer-pipeline-server/user_scripts/gvapython/sscape/sscape_adapter.py	Removed MQTT frame publishing functionality
dlstreamer-pipeline-server/retail-config.json	Updated pipeline configurations with WebRTC destinations and watermarks
docs/user-guide/Getting-Started-Guide.md	Added instructions for hosts file configuration and SSL certificate installation

---

_{Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.}

[Copilot]

Use isinstance() instead of type() for type checking to support inheritance and follow Python best practices.

Suggested change

	if type(intrinsics) != CameraIntrinsics:
	if not isinstance(intrinsics, CameraIntrinsics):

[Copilot]

The 'destination' configuration is placed outside the 'payload' object, which is inconsistent with the structure in other configuration files where it appears inside 'payload'. This should be moved inside the 'payload' object for consistency.

[saratpoluri]

Could you please add a "How to Verify" section in your description or Testing Scenarios section.

[Irakus]

Could you please add a "How to Verify" section in your description or Testing Scenarios section.

So far, I only run demo. I've added new instructions in user guide, aside from that, deployment process looks the same.

[kblaszczak-intel]

doc looks good