https://wiki.jw-tech.eu/index.php?action=history&feed=atom&title=WSAL22641_%E2%80%93_OAK-D-Pro%2FenWSAL22641 – OAK-D-Pro/en - Versionsgeschichte2026-10-23T21:25:39ZVersionsgeschichte dieser Seite in JW Tech WikiMediaWiki 1.43.9https://wiki.jw-tech.eu/index.php?title=WSAL22641_%E2%80%93_OAK-D-Pro/en&diff=2354&oldid=prevJWTechPublisher: Freigegebene technische Dokumentation veröffentlicht; Text-only und noindex2026-09-06T06:02:59Z<p>Freigegebene technische Dokumentation veröffentlicht; Text-only und noindex</p>
<p><b>Neue Seite</b></p><div>__NOINDEX__<br />
'''Documentation notice:''' This technical documentation was independently rewritten from an archived supplier source. Check technical details and commands against the product version and manufacturer documentation before use.<br />
<br />
== Summary ==<br />
The OAK-D-Pro is an upgraded model in the OAK-D line. It combines active stereo vision (IR laser dot matrix) and IR illumination for night vision, runs on an Intel Myriad X VPU (~4 TOPS), captures 12 MP RGB at 60 fps, and supports 4K/30 fps H.265 streaming. The interface is USB 3.0 Type-C via a Y-adapter.<br />
<br />
== Related products at JW Tech ==<br />
* [https://shop.jw-tech.eu/p/WSAL22641 WSAL22641 – OAK-D-Pro, 12MP, OpenCV AI Machine Vision Kit, Depth Measuring, Image Recognition]<br />
<br />
== Technical overview ==<br />
* Active depth system: Belago 1.1 dot-pattern emitter with 4700 dots, 940 nm wavelength, operating range 10–60 °C<br />
* Color camera: Sony IMX378, 12 MP (4032 × 3040 px), rolling shutter, autofocus from 8 cm, aperture f/2.0<br />
* Monochrome cameras: OV9282, 1 MP (1280 × 4800 px per source; unusual aspect ratio), global shutter, fixed focus from 50 cm or 19.6 cm, aperture f/2.2<br />
* Depth measurement range: 0.7–12 m; theoretically up to 35 m, measurement error at 30 m approx. 6–10 %<br />
* Average power consumption: ~2.5 W<br />
* Supported NN frameworks: Caffe, TensorFlow, MXNet – including AlexNet, ResNet, MobileNet, YOLO, SSD<br />
* Development languages: Python and C++<br />
* Enclosure: metal enclosure; laser safety standard EN/IEC 60825-1 (3rd edition, 2014), Class 1<br />
<br />
'''Commands and examples – verify before use:''' <br />
<syntaxhighlight lang="text"><br />
git clone https://gitee.com/oakchina/depthai.git<br />
git clone https://gitee.com/oakchina/depthai-python.git<br />
git clone https://gitee.com/oakchina/depthai-experiments.git<br />
echo 'SUBSYSTEM=="usb", ATTRS{idVendor}=="03e7", MODE="0666"' | sudo tee /etc/udev/rules.d/80-movidius.rules<br />
sudo udevadm control --reload-rules && sudo udevadm trigger<br />
python3 -m pip install -r depthai/requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple<br />
python3 depthai/depthai_demo.py<br />
cd depthai && python3 depthai_demo.py<br />
echo "export OPENBLAS_CORETYPE=ARMV8" >> ~/.bashrc && source ~/.bashrc<br />
</syntaxhighlight><br />
<br />
== Notes and version constraints ==<br />
* The monochrome resolution stated in the source (1280 × 4800 px) appears unusual; verify against the datasheet before publication.<br />
* Linux installation instructions reference Gitee mirrors; availability of these repositories may change.<br />
* The Y-adapter connection (USB + 5 V/2 A) must be physically connected correctly; incorrect wiring can damage the host or device.<br />
* For Jetson, the source explicitly warns against directly running the dependency scripts in the depthai package to avoid overwriting OpenCV.<br />
* Accuracy figures (cm-level, 1–2 cm under 3 m, 2–10 cm under 9 m) depend on object texture and are not a fixed specification.<br />
* No warranty, certifications beyond the laser standard, or pricing information are present in the source.<br />
<br />
== Source and revision record ==<br />
* [https://www.waveshare.com/wiki/OAK-D-Pro OAK - Waveshare Wiki]<br />
* Source revision: 89738<br />
* Captured: 2026-09-03T04:13:08+00:00<br />
* SHA-256: <code>c91049bf524b93b42e5e2fc67b13c02fb99ae1e05d2befea8c1e0d567a86dfbd</code></div>JWTechPublisher