Luxonis Oak-D LR – AI kit for Image Recognition
The Luxonis Oak-D LR – AI Kit for Image Recognition is an advanced Spatial AI embedded vision platform. It features three AR0234 2.3 MP global‑shutter color cameras arranged with variable stereo baselines (5 cm, 10 cm, 15 cm), enabling precise depth perception up to approximately 30 m. Powered by the RVC2 module delivering 4 TOPS compute (≈1.4 TOPS reserved for AI), this open‑source kit runs custom neural models, object tracking, and real‑time video encoding (H.264 / H.265 / MJPEG). With a built‑in BNO085 9‑axis IMU, USB‑C and Gigabit Ethernet with PoE support, Gorilla Glass front window, and industrial aluminum housing, Oak‑D LR is ideal for robotics, surveillance, automation, and edge‑AI applications.
Features
- Triple AR0234 2.3 MP global‑shutter cameras with swappable M12 lenses.
- Three stereo baselines (5 cm, 10 cm, 15 cm) for depth sensing from ~20 cm to ~30 m.
- RVC2 vision processor providing 4 TOPS compute (≈1.4 TOPS for AI inference).
- Supports real‑time object tracking (2D/3D), feature tracking, warp/dewarp, resizing, and edge detection.
- AI model compatibility: run any custom neural network model (requires conversion).
- Video encoding up to 4K/30 fps or 1080p/60 fps (H.264, H.265, MJPEG).
- Built‑in BNO085 9‑axis IMU with onboard sensor fusion.
- USB‑C (USB 3.1 Gen1 up to 10 Gbps) and RJ45 port supporting IEEE 802.3af PoE.
- Durable aluminum enclosure with Gorilla Glass, rain‑cover included.
Specifications
| Parameter | Value |
|---|---|
| Camera Sensors | 3 × AR0234 global‑shutter color (1920×1200, 2.3 MP, 3 μm pixels). |
| Stereo Baselines | 5 cm, 10 cm, 15 cm (M12 lenses swappable). |
| Depth Range | ~20 cm to ~16 m accurate (<2–6% error), up to ~30 m full depth (~100 m with narrow lenses). |
| Compute Power | 4 TOPS overall, ~1.4 TOPS AI inference on RVC2. |
| Video Encoding | H.264, H.265, MJPEG – 4K@30 fps or 1080p@60 fps. |
| IMU | BNO085 9‑axis integrated onboard. |
| Connectivity | USB‑C (USB 2/3), RJ45 with PoE support. |
| Power Consumption | ~2.5–3 W streaming; up to ~5.5 W total. |
| Operating Temp. Range | –20 °C to +50 °C (dependent on VPU usage). |
| Housing & Mounting | Aluminum body, Gorilla Glass front, 1/4″ tripod or 75 mm M4 VESA mount. |
| Dimensions (no rain cover) | ~202 × 43 × 40 mm |
| Dimensions (with rain cover) | ~50 × 27 × 22 mm |
| Weight | ~425 g |
Theoretical depth accuracy
| HFOV [°] | < 2% depth error | < 4% depth error | < 8% depth error | MinZ |
|---|---|---|---|---|
| 10 | 54.9 m | 137.2 m | 274.3 m | 1.92 m |
| 20 | 27.2 m | 68.1 m | 136.1 m | 95 cm |
| 30 | 17.9 m | 44.8 m | 89.6 m | 63 cm |
| 40 | 13.2 m | 33.0 m | 65.9 m | 46 cm |
| 50 | 10.3 m | 25.7 m | 51.5 m | 36 cm |
| 60 | 8.3 m | 20.8 m | 41.6 m | 29 cm |
| 70 | 6.9 m | 17.1 m | 34.3 m | 24 cm |
| 80 | 5.7 m | 14.3 m | 28.6 m | 21 cm |
| 82 | 5.5 m | 13.8 m | 27.6 m | 20 cm |
| 90 | 4.8 m | 12.0 m | 24.0 m | 17 cm |
| 100 | 4.0 m | 10.1 m | 20.1 m | 14 cm |
Note: not all of these combinations are tested but rather are calculated theoretical depth errors.
Maximum depth was calculated by using the large (15cm) baseline, while MinZ was calculated by using the small (5cm) baseline of the OAK-D-LR. You can further decrease MinZ by lowering the resolution, or using disparity shift. MinZ values are already using Extended Disparity Mode.
PINOUT
Dimension
Mounting
Applications
- Robotics and automation requiring depth perception and onboard AI inference.
- Surveillance and smart security systems with 2D/3D object tracking.
- Industrial inspection, sorting, and warehouse monitoring.
- Edge-AI for smart city and environmental sensing.
- Custom vision applications leveraging Python/D2I/DepthAI SDK.
Maintenance Guide
Maintenance GuidePackage Contents
- 1x Luxonis Oak-D LR.
- 1x USB 3.1 Type-A to USB‑C cable.
- 1x Ethernet cable with RJ45 plugs.
- 1x Rain Cover.
- 3x Locking rings.
- 1x Lock ring fastening tool.
- 1x Cleaning cloth.
- 1x Start Guide.
Reviews
There are no reviews yet.