Skip to content

Add UVC camera input example - #866

Merged
klemen1999 merged 2 commits into
mainfrom
feat/uvc-input-example
Sep 22, 2026
Merged

klemen1999 merged 2 commits into
mainfrom
feat/uvc-input-example

Conversation

@mtramsak-luxonis

Copy link
Copy Markdown
Contributor

Purpose

Add a reference tutorial demonstrating how to capture frames from an external USB UVC camera and inject them as ImgFrame messages into a DepthAI v3 pipeline. This enables external OpenCV/V4L2 cameras to feed nodes such as ImageManip, neural networks, and detection networks in both host and RVC4 standalone workflows.

Specification

Adds UVC discovery and capture, configurable camera settings, ImageManip processing, Visualizer output, standalone packaging, and
documentation.

Dependencies & Potential Impact

OpenCV, and NumPy dependencies. No breaking changes expected. Requires an external UVC camera.

Deployment Plan

/

Testing & Validation

Tested locally on OAK4-D with a webcam connected to the usb-c port. (using usb-c -> usb-a adapter)

AI Usage

Assisted-by: Codex:GPT-5

Submitted code was reviewed by a human: YES

The author is taking responsibility for the contribution: YES

@mtramsak-luxonis mtramsak-luxonis added the testable PR is ready to be tested label Sep 15, 2026

@klemen1999 klemen1999 left a comment

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Generally LGTM, I tested with an RVC2 and RVC4 device in peripheral mode. Can't test in standalone mode since I don't have physical access to RVC4.

Comment thread tutorials/uvc-camera-input/requirements.txt Outdated
@klemen1999
klemen1999 merged commit aa9f7a4 into main Sep 22, 2026
9 checks passed
@klemen1999
klemen1999 deleted the feat/uvc-input-example branch September 22, 2026 11:41
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

testable PR is ready to be tested

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants