MaskCam on Jetson Nano

Hardware required: Jetson Nano 4GB, JetPack 4.6, USB camera, Docker with nvidia runtime, docker-compose. MaskCam detects face mask compliance and streams annotated video over RTSP.

Execution model

Run one phase at a time. After each phase:

• Relay all command output to the user.
• If output contains [STOP] → stop immediately, consult the failure decision tree below.
• If output ends with [OK] → tell the user "Phase N complete" and proceed to the next phase.

Prerequisites

Phase 1 — Pull Docker image

sudo docker pull maskcam/maskcam-beta

Verify:

sudo docker images | grep maskcam
# Expected: maskcam/maskcam-beta listed with a recent tag

[OK] when the image appears in docker images. [STOP] if pull fails — see failure decision tree.

Phase 2 — Get device IP address

sudo ifconfig
# Note the inet address for your active interface (e.g. eth0 or wlan0)
# Example: inet 192.168.1.42

[OK] when you have the Jetson's IP address noted. You will use it to access the RTSP stream in Phase 4.

Phase 3 — Run MaskCam

sudo docker run --runtime nvidia -it --rm \
  --network host \
  -v /tmp/argus_socket:/tmp/argus_socket \
  maskcam/maskcam-beta

Expected: container starts and prints initialization logs, then begins processing camera frames. You should see inference output in the terminal.

[OK] when the container is running and printing frame inference results. [STOP] if the container exits immediately or errors — see failure decision tree.

Phase 4 — View RTSP stream

With MaskCam running, open the stream in VLC or any RTSP-capable player on another machine:

rtsp://<jetson-ip>:8554/maskcam

Replace <jetson-ip> with the address noted in Phase 2.

In VLC: Media -> Open Network Stream -> paste the URL above.

[OK] when the annotated video stream is visible with mask detection overlays.

Failure decision tree

Reference files

• references/source.body.md — full Seeed Wiki tutorial with screenshots and additional context (reference only)