ASUS Tinker Pack, Includes Setup Guide and Code Edge Smart + AI Kit Listing Comes with ASUS Tinker Edge T board, Google Coral Cameras

ASUS SBC Tinker Edge Smart + AI Kit Pack, Includes ASUS Thinker Edge T + 2 x Google Coral Camera

Bundle Includes;

- ASUS SBC Tinker Edge T Card size SBC, NXP i.MX 8M, 1.5GHz ARM Cortex-A53 Quad
- Google Coral 5 Megapixel Camera MIPI-CSI Interface

ASUS SBC Tinker Edge T Card size SBC, NXP i.MX 8M, 1.5GHz ARM Cortex-A53 Quad - Core SoC, Google Coral Edge TPU, 1GB RAM, 8GB eMMC, HDMI, MIPI-DSI, MIPI-CSI, 12 - 19V DC in

Features:

- ML Capability with google Edge TPU
- 2x MIPI-CSI / MIPIDSI / HDMI
- 40-pin GPIOs for multiple purposes
- 12V~19V DC-in offers stable power delivery (45W Adapter, 65W Adapter)


AI accelerator (Edge TPU)

Tinker Edge T is a single-board computer (SBC) specially designed for AI applications. It features the Google Edge TPU, a machine learning (ML) accelerator that speeds up processing efficiency, lowers power demands and makes it easier to build connected devices and intelligent applications. With this onboard ML accelerator, Tinker Edge T is capable of performing four tera-operations per second (TOPS) using only 0.5 watts per unit of computation. It is also optimized for TensorFlow Lite models, making it easy to compile and run common ML models.

NXP i.MX 8M processor




With its powerful and modern quad-core ARM-based NXP i.MX 8M processor, Tinker Edge T offers a powerful solution for graphics, machine vision, video, audio, voice and safety-critical applications. Tinker Edge T features 1 GB of LPDDR4 dual-channel memory, the 4th generation of low-power DDR DRAM technology, offering faster speeds and even lower power consumption for improved system performance and efficiency. Tinker Edge T also comes equipped with an onboard 8 GB eMMC and SD 3.0 interface that offers significantly faster read and write speeds for the OS, applications and file storage.

Advanced power design

Most SBC motherboards only offer a 15 watt (5V 3A) power design, which can cause device and system instability when there are multiple connected devices. Other SBCs have power designs that lower the performance of their I/O ports. Tinker Edge T has a special power design that, together with a DC head power supply, delivers up to 45 watts of power, enabling stable system operation and full I/O performance, even with multiple connected devices. Additionally, an exclusive power-protection design activates automatically if the supplied current and voltage change significantly, effectively protecting the board and all connected devices.

More connectivity options for makers




Tinker Edge T features a rich I/O interface, including one MIPI-DSI connection for displays and touch screens, and two MIPI-CSI connections for compatible cameras to enable computer vision for applications such as depth measurement, smart vending machine QR code payment systems and interactive advertising.
Tinker Edge T has a maker-friendly design that offers many carefully considered features to provide a superior experience for first-time builders and seasoned hobbyists alike. Programmable LEDs let makers develop custom lighting behaviors, such as system notifications and status indicators, and the color-coded GPIO header makes it easy to recognize respective pin headers.
Tinker Edge T also features a full-size HDMI port, USB Type-A, USB Type-C, gigabit LAN and integrated Wi-Fi and Bluetooth for internet and network connectivity.

Heatsink included

Tinker Edge T includes an active heatsink, which helps improve heat dissipation under heavy loading or in hot ambient environments.

Neural network tools for users




ASUS provides a robust API and SDK that enables users to deploy machine learning models to Tinker Edge T easily for applications such as image classification and object detection.

OS flash tool*

Tinker Edge T comes with a cross-platform OS flash tool that enables easy OS image flashing to SD cards and USB drives, enabling you to get your system up and running quickly.*The feature will be ready from Jan, 2020

Enhanced OS interface*

An intuitive software interface offers makes it easy to navigate the features of Tinker Edge T, and shortcuts provide quick, convenient access to commonly user functions.*The feature will be ready from Jan, 2020

Google Coral 5 Megapixel Camera MIPI-CSI Interface Compatible with Coral boards , Built in ISP, Auto Focus, Dual Lane bring Visual Input into your Mode

The Coral Camera is designed to enable on-device vision intelligence with Coral prototyping boards or other production hardware. The camera attaches to the Coral Dev Board with a 24-pin FFC.

Other features include:

 - ISP function: Automatic exposure control (AEC), automatic white balance (AWB), automatic band filter (ABF), automatic 50/60 Hz lumination, automatic blacklevel calibration (ABLC).
 - Image quality control: color saturation, hue, gamma, sharpness, lens correction, defective pixel canceling, and noise canceling.
 - Support autofocus control (AFC) with embedded AF VCM Driver.

Features:

 - 5-megapixel OmniVision sensor
 - 1.4um x 1.4um pixel
 - Active array size 2582x1933
 - Optical size: �"
 - Field of view: 84.0° / 87.6°
 - F-number: F=2.2 ±5%
 - TV distortion: <1.5%
 - Focal length: 2.5mm
 - Focusing range: 10cm ~ 8
 - Dual lane MIPI output interface
 - Board dimensions: 25 x 25 mm
Connect a camera to the Dev Board (Guide)
To perform real-time inferencing with a vision model, you can connect the Coral Camera to a Dev Board.
Once you connect a camera, try the demo scripts below.

The Coral Camera is designed to enable on-device vision intelligence with Coral prototyping boards or other production hardware.

Compatible with Coral boards
Connects to the Dev Board and Dev Board Mini through the CSI camera connector.

Scalable to production: Designed to scale with your manufacturing needs.

https://coral.ai/docs/camera/datasheet/

Asus Tinker Edge T Mendel 5 Eagle V3.0.2

Asus Tinker Edge T OS Download Website

How to build your first AI Recognition platform by this kit? Please follow the guide below step by step!

Requirements:

Hardware:

 - 1 x ASUS Thinker Edge T
 - 2 x Google Coral Cameras
 - 1 x Power Adapter
 - 1 x Raspberry Pi US Layout Official Grey / Black Keyboard and Hub
 - 1 x Raspberry Pi Official Grey / Black Mouse
 - 1 x Monitor with HDMI port
 - 1 x HDMI Cable
 - 1 x USB C to USB A cable

Connect all of parts above as the photo shown below.

Software:

OS: Tinker Edge T Mendel 5 Eagle V3.0.2

Download and unzip it under a Win10 computer.

Getting Started:

1. Find the Boot Mode Switch (DIP Switch) from back of the ASUS Tinker Edge T board.

2. The boot mode switches are set to eMMC mode, please refer to the table and illustration below for the eMMC mode setting.

3. Flashing the Tinker Edge T.
 - Connect the USB type-c cable to the Tinker Edge T and the host computer.
 - Connect the power adapter to the Tinker Edge T and power on.
 - Check Windows Update on the host computer and Device Manager till ASUS Android Device is recognized as the screenshot shown below.

4. Double click 'flash.cmd' to start the flash process. The flash process should take a few minutes.

5. Connect HDMI Cable to monitor. The Tinker Board T will lead you into system. You can open the terminal by mouse and enter the name of demo app in the terminal. code is below. For moving the camera windows by hold the windows key + mouse left key.

For face detection: edgetpu_face_detect. You should see results like below. Please make sure your face is showing in the front of the cameras. :)

For object detection: edgetpu_object_detect. You should see results like below.

6. Congratulations! You've just got AI Recognition experience from the ASUS Tinker Board T board and the Google Coral Cameras platform.

Find more pre-trained model from below link.

https://github.com/google-coral/project-posenet/tree/master/models/resnet

https://github.com/google-coral/project-posenet/tree/master/models/mobilenet