Demo Description

< >

‎

Metropolis Microservices for NVIDIA Jetson

Table of Contents [Sticky]

• Introduction
  • Introduction
  • Get Started
• AI Stack
• Platform Services
  • Starting and Stopping
  • Video Storage Toolkit
  • Redis
  • API Gateway (Ingress)
  • Monitoring
  • IO Gateway
• RidgeRun Services
  • PTZ
  • Detection
  • AI Agent
  • Analytics
• RidgeRun SmartSeek360 Demo
  • Demo Description
  • Getting the Code
  • Running the Demo
  • Performance and Footprint
• Tools
  • NVStreamer
  • API Usage
• Contact Us

The SmartSeek360 search for objects specified by the user in a 360-degree video stream, once the object is found the system follows it trough the video leveraging the PTZ functions, and triggers video recording at the same time.

This system is made up of the following Microservices:

NVIDIA Metropolis Microservices:

1. Video Storage Toolkit (VST): a NVIDIA microservice that makes it possible to discover, ingest, manage, stream, and record video streams.
2. Deepstream AI Microservice: by using the NVIDIA DeepStream Microservices it is possible to obtain real-time processing of multiple video (camera) and sensor streams through deep learning based inference using pluggable models, tracking and custom CV algorithms.
3. REDIS: The use of the NVIDIA Redis Microservice allows to obtain a message broker for metadata output created by the inference microservices such as Deepstream.
4. Analytics: This NVIDIA microservice is used to create metrics and to emit alerts based on the Analytics microservice configuration.

RidgeRun Microservices:

1. PTZ Microservice: This RidgeRun Microservice encapsulates the GstPTZR GStreamer element that can be used to provide Pan Tilt and Zoom operation in the incoming video stream, the PTZ microservice is designed to receive a 360 degree video and perform PTZ operation in equirectangular projected videos. The PTZ Microservice can receive 360-degree equirectangular RTSP video streams and outputs an RTSP stream with the performed PTZ operations over the equirectangular videos using RidgeRun libpanorama.
2. Detection Microservice: This microservice accepts one or multiple text queries to search for and detect target objects described in text, for example, it is possible to use the AI-Agent to request the Detection microservice, for example, it is possible to indicate: search for bottles.
3. AI Agent: This service uses an LLM model capable of converting text commands in API calls, this service allows direct communication to other services more naturally via text commands, for example it is possible to request: move the camera 30 degrees to the Right.
4. Analytics: This service reads detection metadata provided by the REDIS NVIDIA microservice and moves the camera to the detected object position using PTZ and starts video recordings using the NVIDIA VST microservice.
5. BIPS: This microservice can be used to handle direct memory buffer transfers, currently this is work in progress and it is not included in the Demo.