> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/vss/dev/system-components/vision-microservices/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/vss/_mcp/server.

# Vision Microservices

The Vision Microservices extract rich visual features, semantic embeddings, and natural
language understanding from video. Each is a standalone, GPU-accelerated microservice
with documented REST and MCP interfaces, and can be deployed independently or composed
into an agent workflow.

* [Object Detection and Tracking](/system-components/vision-microservices/object-detection-and-tracking) - Real-time object detection, classification, and multi-object tracking on single or multi-camera streams.
* [Real-Time VLM](/system-components/vision-microservices/real-time-vlm) - Vision Language Models that generate captions, detect incidents, and identify anomalies in video streams.
* [Video Embedding Generation](/system-components/vision-microservices/video-embedding-generation) - Semantic embeddings from video, images, and live RTSP streams for search and similarity matching.
* [Video Summarization](/system-components/vision-microservices/video-summarization) - Analysis and summarization of extended video recordings through chunking and aggregation of dense captions.

## Docs

- [Object Detection and Tracking](https://docs.nvidia.com/vss/dev/system-components/vision-microservices/object-detection-and-tracking.md): 
- [API Reference](https://docs.nvidia.com/vss/dev/system-components/vision-microservices/object-detection-and-tracking/api-reference.md): REST endpoints for the Real Time Video Intelligence CV (RTVI-CV) microservice.
- [MV3DT Standalone Deployment](https://docs.nvidia.com/vss/dev/system-components/vision-microservices/object-detection-and-tracking/mv3dt-standalone-deployment.md): Deploy RT-CV-3D standalone: RT-DETR detection with Multi-View 3D Tracking (MV3DT) and BEV fusion, using Docker Compose.
- [Real-Time VLM](https://docs.nvidia.com/vss/dev/system-components/vision-microservices/real-time-vlm.md): 
- [API Reference](https://docs.nvidia.com/vss/dev/system-components/vision-microservices/real-time-vlm/api-reference.md): 
- [Video Embedding Generation](https://docs.nvidia.com/vss/dev/system-components/vision-microservices/video-embedding-generation.md): 
- [API Reference](https://docs.nvidia.com/vss/dev/system-components/vision-microservices/video-embedding-generation/api-reference.md): REST endpoints for the Real-Time Embedding microservice.
- [Video Summarization](https://docs.nvidia.com/vss/dev/system-components/vision-microservices/video-summarization.md): 
- [API Reference](https://docs.nvidia.com/vss/dev/system-components/vision-microservices/video-summarization/api-reference.md):