---
name: vision
description: Camera and computer vision on the Arduino Uno Q — MIPI-CSI-2 camera via V4L2/GStreamer and OpenCV on the Linux side. Load this for capturing images/frames, camera pipelines, or running vision on the board.
---

# Vision on the Uno Q (Linux side)

The camera (MIPI-CSI-2) is a **Linux/MPU** device exposed via **V4L2**
(`/dev/video0`). Capture and processing run on the MPU, not the MCU.

## Capture a frame

Use the **`camera`** tool — it runs a single-frame GStreamer pipeline and writes a
JPEG (args: `device`, `width`, `height`, `output` under /tmp, /var/tmp, or $HOME).

Equivalent pipeline it runs:

```sh
gst-launch-1.0 v4l2src device=/dev/video0 num-buffers=1 \
  ! video/x-raw,width=1280,height=720 ! videoconvert ! jpegenc \
  ! filesink location=/tmp/frame.jpg
```

## Processing (Python, MPU)

```python
import cv2
img = cv2.imread("/tmp/frame.jpg")
# detect / annotate / stream ...
```

The Adreno 702 GPU provides hardware H.264/H.265/VP9 encode/decode for streaming.

## Pitfalls

- The camera is not accessible from a sketch — it's a Linux device. Drive vision
  from Python (MPU); use Bridge if a sketch needs the result.
- `output` for `camera` must be an absolute path under /tmp, /var/tmp, or $HOME.