The OAK-D W PoE is the ultimate camera for robotic vision that perceives the world like a human by combining a wide stereo depth camera and wide high-resolution color camera with an on-device Neural Network inferencing and Computer Vision capabilities.

PoE connection allows cameras to communicate to other computers via networking protocols (TCP, UDP, HTTP, MQTT, etc.). As our PoE models feature device flash memory, you can also run your programs in standalone mode. OAK PoE cameras are housed in an rugged, IP-rated enclosure, which is required for industrial and outdoor use. It uses PoE for both power and GigE connectivity.

Wide FOV allows you to capture more area in one shot, which can be especially useful for:

Multi-camera setup, to reduce the number of cameras needed to cover the whole area

AMRs, to cover larger area and to get more features for localization and 3D mapping - see VIO/SLAM documentation for more information

Object tracking/counting, for example vehicle or people counting over a larger area

• 150° DFOV for stereo pair, 120° for central camera depending on variant chosen
• 4 TOPS of processing power
• Rugged IP65 rated enclosure
• M12 PoE connector and additionally M8 connector for IO connectivity
  

Features

• 4 TOPS of processing power (1.4 TOPS for AI - RVC2 NN Performance)
• Run any AI model, even custom architectured/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
• IMU (Either BMI270 6-axis or BNO086 9-axis sensor)
• Object tracking: 2D and 3D tracking with ObjectTracker node

Specifications

Documentation

Product Documentation