OAK vs RealSense™

Compared to RealSense™ stereo cameras, OAK cameras feature a ton of on-device features (custom AI modes, tracking, scripting, encoding etc.).

Depth accuracy comparison

From our own evaluation (details at Stereo cameras accuracy comparison blog post), we have found out that our OAK-D-Pro camera has a slightly better depth accuracy compared to RealSense™ D435i / D455. OAK-D Long Range has much better accuracy at longer distances, as it has wider stereo baseline distance.

For more information, please visit OAK Depth Accuracy comparison docs.

Comparison overview

Specification	OAK-D Pro / -W	OAK-D Lite	OAK ToF	D415	D435	D455
RGB	IMX378	IMX214	IMX378	OV2740	OV2740	OV9782
RGB HFOV	66˚ / 109˚	69˚	66˚	69˚	69˚	90˚
RGB Shutter	Rolling / Global	Rolling	Rolling	Rolling	Rolling	Global
RGB resolution	12MP	13MP	12MP	2MP	2MP	1MP
Depth Type	Active Stereo	Passive Stereo	ToF	Active Stereo	Active Stereo	Active Stereo
Depth sensor	OV9282	OV7251	33D ToF	OV2740	OV9282	OV9782
Stereo Shutter	Global	Global	/	Global	Global	Global
Stereo baseline	75mm	75mm	/	55mm	55mm	95mm
Depth HFOV	72˚ / 127˚	72˚	70˚	65˚	87˚	87˚
Min Depth	20 cm	20 cm	20 cm	45 cm	28 cm	52 cm
Depth resolution	1280x800	640x480	1280x800	1024x768	1280x720	1280x720
IR LED	✔️	-	✔️	-	-	-
ToF	-	-	✔️	-	-	-
IMU	✔️	-	✔️	-	✔️	✔️

3rd party evaluation

A third party (customer) sent us their OAK evaluation results, comparing OAK-D Pro with RealSense™ D435i.

Passive stereo (no IR dot projector)

Active stereo (IR dot projector)

On-device feature comparison

On-Device Capabilities	OAK-D Pro	OAK-D Lite	D415	D430-D435	D450-D455	F450
Custom AI models	✔️	✔️	-	-	-	-
Object detection	✔️	✔️	-	-	-	-
Object tracking	✔️	✔️	-	-	-	-
On-device scripting	✔️	✔️	-	-	-	-
Video/Image Encoding	✔️	✔️	-	-	-	-
Image Manipulation	✔️	✔️	-	-	-	-
Skeleton/Hand Tracking	✔️	✔️	✔️	✔️	✔️	-
Feature Tracking	✔️	✔️	-	-	-	-
OCR	✔️	✔️	-	-	-	-
Face Recognition	✔️	✔️	-	-	-	✔️

Features described

Custom AI models - You can run any AI/NN model(s) on the device, as long as all layers are supported. You can also choose from 200+ pretrained NN models from Open Model Zoo and DepthAI Model Zoo.
Object detection - Most popular object detectors have been converted and run on our devices. DepthAI supports onboard decoding of Yolo and MobileNet based NN models.
Object tracking - ObjectTracker node comes with 4 tracker types, and it also supports tracking of objects in 3D space.
On-device scripting - Script node enables users to run custom Python 3.9 scripts that will run on the device, used for managing the flow of the pipeline (business logic).
Video/Image encoding - VideoEncoder node allows encoding into MJPEG, H265, or H264 formats.
Image Manipulation - ImageManip node allows users to resize, warp, crop, flip, and thumbnail image frames and do type conversions (YUV420, NV12, RGB, etc.)
Skeleton/Hand Tracking - Detect and track key points of a hand or human pose. Geaxgx's demos: Hand tracker, Blazepose, Movenet.
3D Semantic segmentation - Perceive the world with semantically-labeled pixels. DeeplabV3 demo here.
3D Object Pose Estimation - MediaPipe's Objectron has been converted to run on OAK cameras. Video here.
3D Edge Detection - EdgeDetector node uses Sobel filter to detect edges. With depth information, you can get physical position of these edges.
Feature Tracking - FeatureTracker node detects and tracks key points (features).
3D Feature Tracking - With depth information, you can track these features in physical space.
OCR - Optical character recognition, demo here.
Face Recognition - Demo here, which runs face detection, alignment, and face recognition (3 different NN models) on the device simultaneously.

Modular design

Our platform was built from the ground up with the idea of being customizable. Many of our products based on OAK-SoM are open-source so you can easily redesign the board (see Integrating DepthAI into products), for example to change the stereo baseline distance or use a different image sensor (we support a bunch of different sensors).OAK Modules (FFCs) are great for prototyping, as it allows users to use different camera sensors/optics and place them at an ideal stereo baseline distance for their application.Below is a long-range disparity depth visualized over a color frame. This customer used narrow FOV M12 lenses with wide stereo baseline distance (25cm) to achieve such results with our platform.

See stereo depth documentation on max depth perception calculations based on camera intrinsics/baseline distance.

Intel, Intel RealSense and Intel Movidius Myriad are trademarks of Intel Corporation or its subsidiaries.

ON THIS PAGE