- Description
- Product diagram
- Technical Specifications
- Package includes
- Files
OAK-D Pro is the ultimate camera for robotic vision that perceives the world like a human by combining active stereo depth camera and high-resolution color camera with an on-device Neural Network inferencing and Computer Vision capabilities. It also features night vision for perceiving low-light and no-light environments. OAK-D Pro uses USB-C for both power and USB3 connectivity.
Pro version is advised for application that require high-quality and reliable stereo depth perception in any kind of environment, including low-light, and texture-less scenes, where traditional passive stereo approach struggles.
For a smooth getting started experience with the USB camera, we recommend following USB deployment guide.
This OAK device is built on top of the RVC2 architecture, with main features being:
- 4 TOPS of processing power (1.4 TOPS for AI - RVC2 NN Performance)
- Active stereo: IR dot projector improves depth perception, especially for low-visual-interest surfaces by projecting thousands of IR dots to the scene.
- Night vision: IR illumination LED enables running your AI and CV algorithms in low-light or no-light environments
- Run any AI model, even custom architected/built ones (models need to be converted)
- Encoding: H.264, H.265, MJPEG - 4K/30FPS, 1080P/60FPS
- Computer vision: warp (undistortion), resize, crop via ImageManip node, edge detection, feature tracking. You can also run custom CV functions
- Stereo depth perception with filtering, post-processing, RGB-depth alignment, and high configurability
- Object tracking: 2D and 3D tracking with ObjectTracker node
- Base line: 75 mm
- Ideal depth range: 70cm - 12m. See technical specifications.
- Power consumption: Up to 7.5W. See technical specifications
- Industrial grade aluminum housing with Front Gorilla Glass
- 1/4" tripod mount and 75mm M4 Vesa mount
- Dimensions: 97x29.5x22.9 mm
- Weight: 91g
Camera Specifications
The OAK-D Pro is available in three camera variants: standard versions IMX378 Fixed-Focus and IMX378 Auto-Focus and special version OV9782 Fixed-Focus. The Fixed-Focus variant has the lens fixed in place mechanically, whereas the Auto-Focus has an electromagnet that controls the lens position dynamically. All variants can clearly see objects 50 cm and beyond.
- Auto-Focus cameras are recommended for close objects between 8 cm to 50 cm of the device (see video). They can also be manually set to a specific focus position utilizing the DepthAI API.
- Fixed-Focus cameras are recommended for heavy-vibration applications, such as drones, lawnmowers, or vehicles (see video).
- OV9782 Fixed-focus cameras feature a special sensor OV9782
Need a Wide FOV option? Check OAK-D-Pro W
Sensors Specifications:| Color camera | Stereo Pair | |||
|---|---|---|---|---|
| Variant | Auto-Focus | Fixed-Focus | OV9782 | All |
| Sensor | IMX378 (PY004) | IMX378 (PY052) | OV9782 (PY074) | OV9282 (PY044) |
| FOV (D/H/V) | 78° / 66° / 54° | 82° / 69° / 55° | 89.5° / 80° / 55° | 89.5° / 80° / 55° |
| Resolution | 12MP (4056x3040) | 12MP (4056x3040) | 1MP (1280x800) | 1MP (1280x800) |
| Focus | AF: 8cm - ∞ | FF: 50cm - ∞ | FF: 19.6cm - ∞ | FF: 19.6cm - ∞ |
| Max Framerate | 60 FPS | 60 FPS | 120 FPS | 120 FPS |
| Spectral range | Visible + 940nm | Visible + 940nm | Visible + 940nm | Visible + 940nm |
| Shutter Type | Rolling | Rolling | Global | Global |
| Sensor size | 1/2.3” | 1/2.3” | 1/4” | 1/4” |
| F-number | 1.8 ± 5% | 1.8 ± 5% | 2.0 ± 5% | 2.0 ± 5% |
| Effective Focal Length | 4.81mm | 4.81mm | 2.35mm | 2.35mm |
| Pixel size | 1.55µm | 1.55µm | 3.0µm | 3.0µm |
IR perception
This product is classified as a Class 1 Laser Product under the EN/IEC 60825-1, Edition 3 (2014) internationally. More information about IR perception and laser safety can by found here.
Active stereo- Uses Ams Belago 1.1 Dot-Pattern Infrared Illuminator
- IR dot projector improves depth perception, especially for low-visual-interest surfaces by projecting thousands of IR dots to the scene.
- IR illumination LED enables running your AI and CV algorithms in low-light or no-light environments
Power consumption
Most of the power is consumed by the RVC2, so the power consumption mostly depends on the workload of the VPU:
- Base consumption + camera streaming: 2.5W - 3W
- AI subsystem consumption: Up to 1W
- Stereo depth pipeline subsystem: Up to 0.5W
- Video Encoder subsystem: Up to 0.5W
Illumination LED and laser dot projector
Power is configurable (more power - more brightness):
- Dot projector (active stereo): Up to 1W
- Illumination LED (night vision): Up to 1W
So the total power consumption can be up to ~7.5W if you are using all the features at 100% at the same time. To reduce the power consumption, you can reduce FPS of the whole pipeline - that way, subsystems won’t be utilized at 100% and will consume less power.
If the hosting system is not able to provide sufficient power, you can use included Y-adapter to connect additional 5V power source.
Stereo depth perception
This OAK camera has a baseline of 7.5cm - the distance between the left and the right stereo camera. Minimal and maximal depth perception (MinZ and Max) depends on camera FOV, resolution, and baseline - more information here.
- Ideal depth range: 70cm - 12m
- MinZ: ~20cm (400P and extended), ~35cm (400P OR 800P, extended), ~70cm (800P)
- below 4m: below 2% absolute depth error
- 4m - 7m: below 4% absolute depth error
- 7m - 10m: below 6% absolute depth error
This OAK camera has an integrated BNO085, a 9-axis IMU (Inertial Measurement Unit). See IMU node for the API details on how to use it.
Operating characteristics
The ambient operating temperature of RVC2 based devices is between -20°C and 50°C when fully utilizing the VPU. To find out more, see our operative temperature range documentation.
Our cameras are tested for vibration tolerance according to the EN 60068-2-6:2008 standard. More information about the testing you can find here.
- OAK-D-Pro camera
- Y-adapter
- Cable USB-CA-1m
