EyeCloudAI CDK

by EyeCloud

An open edge-AI camera kit compatible with OpenVINO and based on the Intel Myriad X

$3,114 raised

of $1 goal

Funded! Order Below

Product Choices

$134

EyeCloud AI CDK - Core Board

A dev board based on Intel's Movidius Myriad X VPU with 8 Gb of DDR and two neural-computing engines. Measures 38 x 38 mm and comes with a 30 cm USB Type-C cable


$154

EyeCloudAI CDK with eMMC Expansion Board

A variant of the EyeCloudAI CDK core board designed for independent, stand-alone operation. Includes an 8 GB eMMC expansion board that allows it to boot from local storage. Measures 38 x 38 mm and comes with a 30 cm USB Type-C cable.


$25

2 MP RS Sensor Module

An independent 2 MP rolling-shutter sensor with a changeable M 12 lens. If your applications do not require high-speed capture or high-resolution imagery, this is a good, cost-efficient option. Requires an EyeCloudAI CDK Core Board. Measures 38 x 38 mm.


$92

2 MP GS Sensor Module

An independent 2 MP global-shutter sensor, based on the Onsemi AR0234CS, that captures up to 120 frames per second through a changeable M 12 Lens. Recommended for applications that involve production lines, transportation systems, and other scenarios that require the ability to capture fast-moving objects. Requires an EyeCloudAI CDK Core Board. Measures 38 x 38 mm.


$61

8 MP RS Sensor Module

An 8 MP rolling-shutter sensor with a changeable M 12 Lens. Recommended for applications that require high-resolution imagery. Requires an EyeCloudAI CDK Core Board. Measures 38 x 38 mm.

Details

Recent Updates


As Featured In

Optional eMMC & Three ISP-Ready Sensor Modules

EyeCloudAI CDK is an open source edge-AI camera development kit for applications where privacy, real-time performance, reliability, and flexibility are paramount. With this camera-development kit (CDK), developing and deploying custom edge-AI camera solutions is easy. We’ve taken care of the AI optimization, sensor tuning, optics, tooling, and supply chain management so you can focus on your application.

EyeCloudAI CDK is based on the Intel Movidius Myriad X VPU and is compatible with the Intel Distribution of OpenVINO Toolkit. We are offering two versions of our core board. The first model is designed to be used while connected to an external host device or integrated into a larger system, be it a laptop, a single-board computer (SBC), a robot, or something else. The second model supports independent, stand-alone operation by allowing the CDK to boot from an 8 GB eMMC expansion board and access AI models stored there.

You can pair either version of the core board with any of three image signal processor (ISP) sensor modules: a 2 MP rolling-shutter module for normal applications, an 8 MP rolling shutter module for high-resolution applications, or a 2 MP global-shutter module (based on the ON Semi AR0234) for high-speed applications.

Each camera module is an independent, 38 x 38 mm board that connects to the EyeCloudAI CDK core board by means of an FFC cable. This design provides maximum flexibility while reducing the amount of work required to integrate these sensors into your final product.

Use Pre-Trained Models, Custom Models, or Two Models in Series!

The Intel Distribution of OpenVINO Toolkit allows you to take advantage of most pre-trained models from the OpenVINO Model Zoo or to create your own models, which you can then load onto EyeCloudAI CDK with our SDK or our easy-to-use Windows- and Linux-compatible graphical software. If you are working with the version that includes an 8 GB eMMC expansion board, you can update both the firmware and the set of available AI models using any UVC-compatible tool.

In addition, EyeCloudAI CDK allows you to deploy two convolutional neural network (CNN) models to a single core board and configure them to operate in series. By using the output of the first model as input to the second, EyeCloudAI CDK can produce complex results independently, without having to move data to and from a computer. In the example shown below, a license-plate recognition camera passes the output of a plate-detection model to a license-recognition model automatically.

Features

  • High Compute Capacity: 4 trillion operations per second (TOPS)
  • Three ISP-Ready Sensor Modules: Up to 8 MP, Up to 120 FPS, Rolling Shutter or Global Shutter
  • Hardware Video Encoding: H.264/H.265 at 2 MP (30 FPS) & MJPEG at 2MP (30 FPS)
  • Flexible Connectivity: USB Type-C 3.0 & 2.0 selectable by cable orientation
  • Versatile Design: built for prototyping and for integration into new products
  • Capable of Running Two CNN Models in Series: Use one model's output as another model's input
  • Rich Interfaces Available for Customization: GPIO, I²C, SPI, SD/SDIO, UART, 2x two-lane DSI (up to 2.5 Gbps per lane)
  • Compatibility: Works with computers, ARM devices, and Raspberry Pi SBCs
  • Available Variant With 8 GB of eMMC: Allows booting from ROM and local storage of AI models
  • Lightweight & Compact: Each board weighs 9 - 12 g and measures 38 x 38 mm
  • Open Source: Schematic and open source client software

Technical Specifications

Core Board

Core Board
VPUIntel Movidius Myriad X MA2085
Vector Processors16 SHAVEs
Vision Accelerators20+
Neural Network CapabilityTwo neural compute engines (up to 4 TOPS)
RAM8 Gbits, LPDDR4 (1600 MHz, 32-bit)
Power Supply5 V / 2 A
Input Data InterfaceMIPI 4 lane
Output Data InterfaceUSB Type-C 3.0 & 2.0 selectable by cable orientation
Expansion InterfacesGPIO, I²C, SPI, SD/SDIO, UART, 2x two-lane DSI (up to 2.5 Gbps per lane)
Dimensions38 mm x 38 mm
Weight9 g
Cable30 cm USB Type-C

Sensor Modules

2MP RS Sensor Module2MP GS Sensor Module8MP RS Sensor Module
SensorSmartSens SC200AION Semi AR0234CSSmartSens SC8238H
Frame Rate30 FPS120 FPS at 1 MP or 60 FPS at 2 MP30 FPS
Resolution1920 x 1080 (2K)1920 × 1080 (2K)3872 × 2180 (4K)
ShutterRolling shutterGlobal shutterRolling shutter
LensM12M12M12
Field of ViewDiagonal 60°Diagonal 63°Diagonal 58°
Output Data InterfaceMIPI 2 laneMIPI 4 laneMIPI 4 lane
Dimensions38 x 38 mm38 x 38 mm38 x 38 mm
Weight12 g12 g12 g
Cable4 cm FFC4 cm FFC4 cm FFC

Comparisons

EyeCloudAI CDKOAK-1Intel NCS2
Manufacturer EyeCloud, Inc Luxonis Intel
Camera Sensor(s) Semi AR0234CS, SmartSens SC200AI, or SC8238H IMX378 No
NPU Performance4 TOPS 4 TOPS 4 TOPS
Neural Compute Engine2 x 2 x 2 x
SHAVE Cores16 16 16
Output Data InterfaceUSB Type-C 3.0 & 2.0 selectable by cable orientation USB 3 USB 3.0 Type-A
Reserved Interfaces for CustomizationGPIO, I²C, SPI, SD/SDIO, UART, 2x two-lane DSI (up to 2.5 Gbps per lane) No No
Camera Sensor ResolutionSelectable from 2 MP (1920 x 1080) to 8 MP (3872 x 2180) Fixed 12 MP (4056x3040) No
Hardware Video EncodingH.264/H.265 at 2MP (30 PFS) & MJPEG at 2MP (30 FPS) 4K H.265 encoding at 30 FPS No
Max Framerate120 FPS 60 FPS No
User-Friendly Software to Update Firmware & AI ModelsYes No No
eMMCVia expansion board No No
Bootable From ROMVia expansion board No No
Capable of Running Two CNN Models in SeriesYes No No
Weight9 - 12 g per board 56.7 g 77.8 g
Size38 x 38 mm 45 x 30 mm 27 x 72.5 mm
Open SourceSchematic + software Hardware + software No
PriceStarting at $148 with sensor module Starting at $149 $79

Software

EyeCloudAI CDK works with Intel’s distribution of OpenVINO Toolkit and is compatible with frameworks such as ONNX, TensorFlow, Caffee, MXNet, Kaldi, and PaddlePaddle. Our SDK is compatible with Raspberry Pi flavors of Linux for ARMv7 and ARMv8.

EyeCloudAI CDK Demos

Car Detection & License Plate Recognition

Optical Character Recognition

Pet Detection & Monitoring

Video Conference Tracking

Support & Documentation

You can find the EyeCloudAI CDK documentation, software, and hardware design files in our GitHub repository. If you have a question, please reach out using the Ask a technical question link on our campaign page.

Manufacturing Plan

Our team has been designing, producing, and shipping products for decades, and we’ve already manufactured several small batches of EyeCloudAI CDK boards, here in China, at the same facility we intend to use for production. In addition, we have already begun to gather components for a 200-board run. Due to component scarcity, some orders may be delayed if we end up shipping more than 100 units of any given EyeCloudAI CDK board.

Fulfillment & Logistics

After testing and packaging the first production batch of EyeCloudAI CDK boards, we will send them on to Crowd Supply’s fulfillment partner, Mouser Electronics, who will distribute them to backers worldwide. You can learn more about Crowd Supply’s fulfillment service under Ordering, Paying, and Shipping in their guide.

Risks & Challenges

Having run several small EyeCloudAI CDK production runs, we are confident in our process. Our biggest concerns at the moment have to do with the volatility of component pricing and the persistent availability issues that are plaguing hardware projects all over the world. While our supply chains are well tested, we could still face delays if demand is such that we find ourselves unable to source sufficient quantities of critical parts. Regardless, we will be in touch by way of regular, weekly campaign updates.


Credits

EyeCloud

We are a leading supplier of open AI vision solutions. We help developers overcome the integration and production challenges of delivering edge-AI vision products through our expertise in custom hardware production, embedded software, IoT management, and cloud services.


Po Yuan

Johanna Shi

Timotei Redis

See Also

Subscribe to the Crowd Supply newsletter, highlighting the latest creators and projects: