# 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](https://discuss.luxonis.com/blog/3734-depth-accuracy-comparison-luxonis-oak-vs-stereolab-zed-vs-intel-realsense)), 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](https://docs.luxonis.com/hardware/platform/depth/depth-accuracy.md).

## Comparison overview

| Specification | [OAK-D Pro](https://docs.luxonis.com/hardware/products/OAK-D%2520Pro.md) **/**
[-W](https://docs.luxonis.com/hardware/products/OAK-D%2520Pro%2520W.md) | [OAK-D
Lite](https://docs.luxonis.com/hardware/products/OAK-D%2520Lite.md) | [OAK
ToF](https://docs.luxonis.com/hardware/products/OAK-D%2520ToF.md) | [D415](https://www.intelrealsense.com/depth-camera-d415/) |
[D435](https://www.intelrealsense.com/depth-camera-d435/) | [D455](https://www.intelrealsense.com/depth-camera-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](https://docs.luxonis.com/hardware/products/OAK-D%2520Pro.md) with RealSense™ D435i.

## On-device feature comparison

| **On-Device** Capabilities | [OAK-D Pro](https://docs.luxonis.com/hardware/products/OAK-D%2520Pro.md) | [OAK-D
Lite](https://docs.luxonis.com/hardware/products/OAK-D%2520Lite.md) | [D415](https://www.intelrealsense.com/depth-camera-d415/) |
[D430-D435](https://www.intel.com/content/www/us/en/products/sku/98320/intel-realsense-depth-module-d430/specifications.html) |
[D450-D455](https://www.intelrealsense.com/depth-camera-d455/) |
[F450](https://www.intel.com/content/www/us/en/products/sku/212558/intel-realsense-id-solution-f450/specifications.l) |
| --- | --- | --- | --- | --- | --- | --- |
| 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](https://github.com/openvinotoolkit/open_model_zoo) and [DepthAI Model
   Zoo](https://github.com/luxonis/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](https://docs.luxonis.com/software/depthai-components/nodes/object_tracker.md) node comes with
   4 tracker types, and it also supports tracking of objects in 3D space.
 * On-device scripting - [Script](https://docs.luxonis.com/software/depthai-components/nodes/script.md) 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](https://docs.luxonis.com/software/depthai-components/nodes/video_encoder.md) node allows
   encoding into MJPEG, H265, or H264 formats.
 * Image Manipulation - [ImageManip](https://docs.luxonis.com/software/depthai-components/nodes/image_manip.md) 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](https://github.com/geaxgx/depthai_hand_tracker), [Blazepose](https://github.com/geaxgx/depthai_blazepose),
   [Movenet](https://github.com/geaxgx/depthai_movenet).
 * 3D Semantic segmentation - Perceive the world with semantically-labeled pixels. [DeeplabV3 demo
   here](https://github.com/luxonis/oak-examples/tree/master/gen2-deeplabv3_depth).
 * 3D Object Pose Estimation - MediaPipe's
   [Objectron](https://github.com/google-ai-edge/mediapipe/blob/master/docs/solutions/objectron.md) has been converted to run on
   OAK cameras. Video [here](https://youtu.be/C3M_JOtmQCk).
 * 3D Edge Detection - [EdgeDetector](https://docs.luxonis.com/software/depthai-components/nodes/edge_detector.md) node uses Sobel
   filter to detect edges. With depth information, you can get physical position of these edges.
 * Feature Tracking - [FeatureTracker](https://docs.luxonis.com/software/depthai-components/nodes/feature_tracker.md) 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](https://github.com/luxonis/oak-examples/tree/master/gen2-ocr).
 * Face Recognition - [Demo here](https://github.com/luxonis/oak-examples/tree/master/gen2-face-recognition), 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](https://docs.luxonis.com/hardware/products/OAK-SoM%2520(sets).md) are open-source so you can easily redesign the board
(see [Integrating DepthAI into products](https://docs.luxonis.com/hardware/platform/deploy/oak2-som-development-guide.md)), for
example to change the stereo baseline distance or use a different image sensor (we support [a bunch of different
sensors](https://docs.luxonis.com/hardware/platform/sensors/sensors.md)).

[OAK Modules (FFCs)](https://shop.luxonis.com/collections/oak-modules) 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](https://docs.luxonis.com/software/depthai-components/nodes/stereo_depth.md#max-stereo-depth-distance) 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.