Group Actions
Engagement
  • Author Author: fyaocn
  • Date Created: Date Created
  • Views 438 views
  • Likes 5 likes
  • Comments 0 comments
Related
Recommended

AI vision Reflective Telescope #2 Install OpenVINO on Raspbian

fyaocn

Install OpenVINO on Raspbian

Table of Contents

1 RaspberryPi Spec

Even known well by most electric engineers, the technical spec shall be listed below to see how powerful it is,

  • Broadcom BCM2711, Quad core Cortex-A72 (ARM v8) 64-bit SoC @ 1.8GHz
  • 2GB SDRAM out of 1GB, 2GB, 4GB or 8GB LPDDR4-3200 SDRAM,
  • 2.4 GHz and 5.0 GHz IEEE 802.11ac wireless, Bluetooth 5.0, BLE
  • Gigabit Ethernet
  • 2 USB 3.0 ports; 2 USB 2.0 ports.
  • 2 × micro-HDMI ports (up to 4kp60 supported)
  • 2-lane MIPI DSI display port
  • 2-lane MIPI CSI camera port
  • 4-pole stereo audio and composite video port
  • OpenGL ES 3.1, Vulkan 1.0

Refer to https://www.raspberrypi.com/products/raspberry-pi-4-model-b/

I buy one case and  fit in.

image

2 Raspbian OS

There are many choice for OS. download image file and flash SD card with Rufus. Another good choice is Raspberry Image Writer, to select OS and just press write without thinking more. Refer to https://www.raspberrypi.com/documentation/

But I this version of OS can not support high-resolution Display up to 1920x1600, it turn black during setup stage, I have to reuse one old laptop LCD panel.

3 OpenVINO runtime

OpenVINO is strong and easy to use, with runtime version installed. Coding with AI can be very efficient.

3.1 Create an installation folder for OpenVINO.

sudo mkdir -p /opt/intel

download OpenVINO Runtime archive file for Debian from

cd ~/Downloads/
sudo wget https://storage.openvinotoolkit.org/repositories/openvino/packages/2022.3/linux/l_openvino_toolkit_debian9_2022.3.0.9052.9752fafe8eb_arm64.tgz -O openvino_2022.3.0.tgz

Extract the archive file and move it to the installation folder

sudo tar -xf openvino_2022.3.0.tgz
sudo mv l_openvino_toolkit_debian9_2022.3.0.9052.9752fafe8eb_arm64 /opt/intel/openvino_2022.3.0

Install required system dependencies on Linux. , Run the following command and create a symbolic link

sudo -E ./install_dependencies/install_openvino_dependencies.sh

sudo ln -s openvino_2022.3.0 openvino_2022

4 Next to do

Now, software development environment is ready.

There are two blocks ,one for vision AI for star-reading and the other for servo control for star tracing. Of course, the reflective telescope shall be design and build before coding.