# OAK vs StereoLabs ZED Compared to StereoLabs ZED cameras, OAK cameras feature a ton of on-device features (stereo depth estimation/disparity matching, custom AI models, object tracking, scripting, encoding etc.). ## Overview Here's a quick comparison of on-device capabilities between OAK cameras and ZED cameras. More details can be found at at [On-device feature comparison](#OAK%2520vs%2520StereoLabs%2520ZED-On-device%2520feature%2520comparison). | **On-device capability** | **OAK Cameras** | ZED cameras | | --- | --- | --- | | Camera ISP | ✔️ | ✔️ | | Stereo matching | ✔️ | - | | Stereo postprocessing | ✔️ | - | | AI processing | ✔️ | - | | CV processing | ✔️ | - | | Video encoding | ✔️ | - | Essentially, ZED cameras require a powerful host computer with beefy NVIDIA GPU to process the stereo data and run AI models. OAK cameras can do all the processing on-device, eliminating the need for a powerful host (see [Host requirements](#OAK%2520vs%2520StereoLabs%2520ZED-Host%2520requirements) for details). ## 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 found that among the tested cameras, the OAK-D Long Range delivers the most impressive long-range depth accuracy. Its 15cm baseline significantly reduces depth errors, making it ideal for applications requiring extended-range perception. Camera Performance Overview * OAK-D Long Range: Excels in long-range performance with a 15cm baseline, ensuring great depth accuracy and minimal errors at greater distances. * ZED 2i: Performs well at long ranges, benefiting from a 12cm baseline and high 2K resolution. * OAK-D Pro: Provides a balanced active stereo depth estimation performance across various distances with its 7.5cm baseline. For more details, please visit [Depth Accuracy comparison docs](https://docs.luxonis.com/hardware/platform/depth/depth-accuracy.md). ## Host requirements ### OAK Cameras With most processing occurring on the device, OAK cameras can efficiently run on low-powered host computers like the [Raspberry Pi Zero](https://docs.luxonis.com/hardware/platform/deploy/to-rpi.md). ### ZED Cameras * No Onboard Compute: All AI and depth processing are handled by a connected host, which demands considerably more processing power. * Minimum System Requirements for ZED Series (ZED 2i, etc.): * CPU: Dual-core 2.3GHz or faster * RAM: At least 4GB * GPU: NVIDIA GPU with Compute Capability > 3.0 (required for real-time depth processing) * ZED X Series (ZED X, ZED X Mini) Requirements * Requires NVIDIA Jetson AGX Orin / Orin NX for operation ## 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) | [ZED Mini](https://cdn.sanity.io/files/s18ewfw4/staging/ebcd46896092d1ee6212b7f4d81aaa1c479c2440.pdf/ZED%20Mini%20Datasheet%20v1.1.pdf) | [ZED 2i](https://cdn.sanity.io/files/s18ewfw4/staging/c059860f8fe49f3856f6b8da770eb13cc543ac2c.pdf/ZED%202i%20Datasheet%20v1.2.pdf) 4mm **/** 2.1mm | | --- | --- | --- | --- | --- | --- | | RGB | IMX378 | IMX214 | IMX378 | OV4689 | OV4689 | | RGB HFOV | 66˚ **/** 109˚ | 69˚ | 66˚ | 102˚ | 72˚ **/** 110˚ | | RGB Shutter | Rolling **/** Global | Rolling | Rolling | Rolling | Rolling | | RGB resolution | 12MP | 13MP | 12MP | 4MP | 4MP | | Depth Type | Active Stereo | Passive Stereo | ToF | Passive Stereo | Passive Stereo | | Depth sensor | OV9282 | OV7251 | 33D ToF | OV2740 | OV9282 | | Stereo Shutter | Global | Global | / | Rolling | Rolling | | Stereo baseline | 7.5cm | 7.5cm | / | 6.3cm | 12cm | | Depth HFOV | 72˚ **/** 127˚ | 72˚ | 70˚ | 102˚ | 72˚ **/** 110˚ | | Min Depth | 20 cm | 20 cm | 20 cm | 10 cm | 150 cm **/** 30 cm | | Depth resolution | 1280x800 | 640x480 | 1280x800 | 1920x1080 | 1920x1080 | | IR LED | ✔️ | - | ✔️ | - | - | | ToF | - | - | ✔️ | - | - | | IMU | ✔️ | - | ✔️ | ✔️ | ✔️ | | Barometer | - | - | - | - | ✔️ | ## Modular design Our platform was built from the ground up with the idea of being customizable. All 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 FFC line is 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. ## On-device feature comparison OAK cameras integrate a wide range of advanced processing capabilities directly on-device, eliminating the need for a powerful external host. In contrast, StereoLabs™ ZED cameras rely entirely on host-based processing. Here's a snapshot of what Luxonis offers: * 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).