OAK-D Lite brings the superpowers of Spatial AI to the price point necessary to unlock all sorts of applications.
It features 300,000-point stereo depth, an integrated 12.3MP camera capable of 4k video (with onboard encoding), and 1.4 TOPS of neural inference (AI) processing for real-time object detection and semantic segmentation.
- 4 TOPS of processing power (1.4 TOPS for AI)
- Run any AI model, even custom architectured/built ones
- Encoding: H.264, H.265, MJPEG – 4K/30FPS, 1080P/60FPS
- Computer vision: warp/dewarp, resize, crop, edge detection, feature tracking
- Stereo depth perception at 200FPS+ with filtering
- Object tracking: 2D and 3D tracking
- Fixed-Focus : Has the lens fixed in place mechanically and cannot move, whereas Auto-Focus has an electromagnet that controls the lens position dynamically. Fixed-Focus is recommended for heavy-vibration applications (e.g., drones, lawnmowers, bikes w/out suspension, etc.
|CAMERA SPECS||COLOR CAMERA||STEREO PAIR|
|DFOV / HFOV / VFOV||81° / 69° / 54°||86° / 73° / 58°|
|Resolution||13MP (4208×3120)||480P (640×480)|
|Focus||AF: 8cm – ∞ OR FF: 50cm – ∞||Fixed-Focus 6.5cm – ∞|
|Max Framerate||60 FPS||200 FPS|
|F-number||2.2 ± 5%||2.2|
|Lens size||1/3.1 inch||1/7.5 inch|
|Effective Focal Length||3.37mm||1.3mm|
|Distortion||< 1%||< 1.5%|
The Oak-D LITE takes the appealing characteristics of the Oak-D and makes them even better. The smaller and more affordable Oak-D LITE can still be considered the swiss army knife of computer vision. The main difference between the D and the D LITE are lower resolution mono-cameras, no IMU on board, and no power adapter. For most use cases of the Oak-D LITE, the USB Type C port should supply enough power
Much like the rest of the Oak line from Luxonis, the Oak-D LITE works with the OpenCV AI kit and makes for both a great starting point and a professional solution for computer vision.
- OAK-D LITE Documentation and Full Specs
- Board 3D Model (STEP file)
- Enclosure 3D Model (STEP file)
OAK—D. LITE is built on the open-source DepthAI ecosystem, with out-of-the-box supported by the following frameworks, but since the API (and hardware) are open-source, it’s easy to extend support to nearly any language & framework.
Out-of-the-box Python, C++, Java, ROS & ROS2, Roboflow, CEP Support
Any Operating System
Works with any OS. You name it. Pre-built binaries are regularly released for Mac, Windows, Ubuntu, Raspberry Pi OS, and the Jetson series.
And since it’s heavily open source (including being able to download the design files), every day we wake up to some new integration with a new language, or suite of tools, etc.