89
edits
Metropolis Microservices/RidgeRun Microservices Demo/Demo Description: Difference between revisions
Metropolis Microservices/RidgeRun Microservices Demo/Demo Description (view source)
Revision as of 03:19, 26 June 2024
, 26 Juneno edit summary
No edit summary |
No edit summary |
||
| Line 7: | Line 7: | ||
This system is made up of the following Microservices: | This system is made up of the following Microservices: | ||
NVIDIA Metropolis Microservices: | '''NVIDIA Metropolis Microservices:''' | ||
#'''Video Storage Toolkit (VST):''' VST NVIDIA microservice auto-discovers ONVIF-S compliant IP cameras, and allows use of custom IP stream as video source. It then allows for video to be stored, played back at various speeds, or paused at any frame | #'''Video Storage Toolkit (VST):''' VST NVIDIA microservice auto-discovers ONVIF-S compliant IP cameras, and allows use of custom IP stream as video source. It then allows for video to be stored, played back at various speeds, or paused at any frame | ||
#'''Deepstream AI Microservice:''' Metropolis Microservices provide a DeepStream application for real-time processing of various camera streams presented by VST. The processing includes object detection, and object tracking. The output of the application is metadata based on metropolis schema sent to Redis message bus using msgbroker plugin. | #'''Deepstream AI Microservice:''' Metropolis Microservices provide a DeepStream application for real-time processing of various camera streams presented by VST. The processing includes object detection, and object tracking. The output of the application is metadata based on metropolis schema sent to Redis message bus using msgbroker plugin. | ||
| Line 15: | Line 15: | ||
{{Review|Add links to the respective MS nvida website|mortigoza}} | {{Review|Add links to the respective MS nvida website|mortigoza}} | ||
RidgeRun Microservices: | '''RidgeRun Microservices:''' | ||
#'''PTZ Microservice:'''The PTZ Microservice is designed to receive 360-degree equirectangular RTSP video streams and outputs an RTSP stream with the performed PTZ operations over the equirectangular videos using RidgeRun libpanorama. | #'''PTZ Microservice:'''The PTZ Microservice is designed to receive 360-degree equirectangular RTSP video streams and outputs an RTSP stream with the performed PTZ operations over the equirectangular videos using RidgeRun libpanorama. | ||
#'''Detection Microservice:''' Detection Microservice detects in the input stream the target objects described in a text prompt.The microservice use the NanoOwl generative AI model that allows open vocabulary detection. Meaning that the user can provide a list of objects that are not bounded to any specific classes. For example, it is possible to indicate: search for dogs. | #'''Detection Microservice:''' Detection Microservice detects in the input stream the target objects described in a text prompt.The microservice use the NanoOwl generative AI model that allows open vocabulary detection. Meaning that the user can provide a list of objects that are not bounded to any specific classes. For example, it is possible to indicate: search for dogs. | ||
#'''AI Agent:''' AI Agent Microservice allows a natural communication between the user and other microservices. This service | #'''AI Agent:''' AI Agent Microservice allows a natural communication between the user and other microservices. This service | ||
uses the Hugging Face LLM Trelis/Llama-2-7b-chat-hf-function-calling-v3 to convert text commands into API | uses the Hugging Face LLM Trelis/Llama-2-7b-chat-hf-function-calling-v3 to convert text commands into API calls, processes the LLM result and calls the correspoding API request. For example, it is possible to request: move the camera 30 degrees to the Right. | ||
calls, processes the LLM result and calls the correspoding API request. For example, it is possible to request: move the camera 30 degrees to the Right. | |||
#'''Analytics:''' This Microservice 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. | #'''Analytics:''' This Microservice 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. | ||
#'''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. | #'''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. | ||