Build Vision AI on RTSP Camera Streams

RTSP is how most IP cameras and NVRs share live video. Paste in a camera's RTSP URL, and Roboflow runs your vision model on the stream in the cloud or on an edge device next to the camera.

Computer vision object detection bounding box identifying a shrink-wrapped wooden pallet of boxes in a warehouse loading dock.

RTSP Cameras AI Vision Solution

RTSP (Real-Time Streaming Protocol) is the IETF standard cameras use to set up and control live video. The current version, RTSP 2.0 (opens in a new tab), is defined in RFC 7826. RTSP handles the session, the video itself travels over RTP, and the default port is 554. Because almost every IP camera and NVR exposes an RTSP URL, one Roboflow pipeline works across brands: if a camera has an RTSP URL, Roboflow can read it.

Already have cameras on site? Start with those. IP cameras from Axis, Reolink, Amcrest, and Dahua all stream over RTSP, and each brand has its own setup guide.

How to Connect an RTSP Camera to Roboflow

  • Find the URL: most cameras use the form rtsp://user:password@camera-ip:554/path. The path differs by maker, so check the camera's manual or find the stream with ONVIF
  • Run it in the cloud: install the Roboflow Connector on a computer near your cameras, and it sends their RTSP streams to Roboflow Cloud Streaming over an outbound-only connection, so your network stays closed
  • Run it at the edge: pass the RTSP URL to InferencePipeline in Roboflow Inference on a server or edge device on the same network. One pipeline can take several streams at once
  • Manage a fleet: Enterprise teams can add an RTSP Stream in Deployment Manager (opens in a new tab), pick a Workflow, and monitor every stream and device from one dashboard

Then train a model on footage from your own cameras, so it learns your scenes, angles, and lighting. Label frames in Roboflow, train, and deploy the model back to the same streams. Send results to your alerting, MES, or business systems, and retrain as conditions change.

Run vision models on Roboflow hardware

Roboflow Edge computers and the AI1 Smart Camera arrive ready to run your models. Each one ships with RoboflowOS, the operating system we build and maintain, so fixes and security patches reach your devices over the air without a site visit.

Roboflow Edge computers
  • Settings that survive a restart

    RoboflowOS rebuilds static addresses, gateway, DNS and camera-port tuning from a persistent store each time the device starts.

  • Updates over the air

    Security patches, camera driver fixes and NVIDIA platform upgrades come in from the Roboflow platform, separate from your models and Workflows.

  • Tested on the hardware you get

    We build the inference runtime too, so we test every OS image against it on the same boards we ship.

  • Locked down by default

    The OS image is read-only and ships without SSH, a desktop or a local login. Your team reads logs, checks streams and views telemetry in Deployment Manager, the Roboflow tool for managing devices remotely.

  • Five years of updates included

    Every appliance comes with five years of RoboflowOS updates from the purchase date, plus a one-year hardware warranty.

RoboflowOS on NVIDIA Jetson

  • Smart Camera

    AI1

    The AI1 puts a camera, a light and a computer in one housing. It pairs an 8 MP (3840 x 2160) camera and LED ring with an NVIDIA Jetson Orin NX 8GB. Teams use it to prove out an edge vision project on a fixed inspection view, counting parts a few inches away or spotting defects dozens of feet away.

    Memory
    8 GB
    Cameras and networking
    Integrated 8 MP camera and LED ring1 x GbE
    1 stream
  • Roboflow Edge

    RF-NX16

    The RF-NX16 handles stations with several cameras. It has six PoE ports on a shared 150 W budget, two more GbE ports and an NVIDIA Jetson Orin NX 16GB.

    Memory
    16 GB
    Cameras and networking
    6 x GbE PoE with a 150 W total budget2 x GbE
    1–4 streamsRF-NX16 Spec Sheet
  • Roboflow Edge

    RF-AGX64

    The RF-AGX64 runs higher-resolution cameras and bigger models. It has 64 GB of memory on an NVIDIA Jetson AGX Orin, four PoE ports and two 10 GbE ports.

    Memory
    64 GB
    Cameras and networking
    4 x GbE PoE2 x 10 GbE
    4+ streams, line scanRF-AGX64 Spec Sheet
  • Roboflow Edge

    RF-THOR128

    The RF-THOR128 is our most powerful appliance and runs on the NVIDIA Jetson T5000 with 128 GB of memory. It has one 5 GbE port and a 100 GbE QSFP28 port that breaks out to four 25 GbE links, and its cameras connect through a PoE switch.

    Memory
    128 GB
    Cameras and networking
    1 x 5 GbE and 1 x 100 GbE QSFP28Breaks out to 4 x 25 GbE
    8+ streams, edge VLM inferenceRF-THOR128 Spec Sheet

One GbE PoE camera port

Not sure which one fits your line?

Send us your cameras, Workflow and line rate, and we’ll create a recommendation for you.

AI for RTSP Cameras Workflows

Have RTSP cameras? Explore Workflows you can get started with to create computer vision apps in minutes. Try the top open and closed source models on frames from your cameras for free, then run a Workflow on your RTSP streams with Roboflow Cloud Streaming or Roboflow Inference.

How to Setup RTSP Cameras with AI

RTSP cameras connect to Roboflow Cloud Streaming through the Roboflow Connector, or to Roboflow Inference on a server or edge device on the same network. Paste in the camera's RTSP URL and run a model or Workflow on the live stream.

“Achieving positive results using AI in a lab environment is easy, but the real challenge comes when scaling the solution across a network like ours without disrupting day-to-day operations. Our partnership with Roboflow is allowing us to do just that.”

Asim Ghanchi

AVP of Technology, BNSF

Speak with an AI expert

Our team will help you start solving business problems on the first call.

Ask us about:

  • Solution architecting
  • Live demonstration
  • Pricing and specifications
  • Feasibility assessment

Over 80,000 organizations build with Roboflow.

  • Rivian
  • Pella
  • Chobani
  • USG Corporation
  • BNSF Railway
  • American Woodmark
Start where you are

Additional resources

  • Vision AI for Logistics

    See how logistics teams use Vision AI to track packages, verify loads, and monitor safety across warehouses and yards.

  • Vision AI for Warehouses

    See how warehouses use Vision AI to improve productivity, track inventory, and keep workers safe around forklifts and docks.

  • Vision AI in Industrial Manufacturing

    Learn how manufacturers deploy Vision AI for quality control, worker safety, and process automation at scale.