close

A Guide to Set Up Raspberry Pi for Computer Vision

Object Detection

A Guide to Set Up Raspberry Pi for Computer Vision

Sabina Pokhrel / January 31, 2020

In this post, I will show you how to set up a Raspberry Pi for computer vision.

The Raspberry Pi is a series of low-cost, single-board computers, that are as small as your credit card. They have been very popular amongst hobbyists and makers around the world since the first version came out in 2012. That same year Raspberry Pi won T3’s Innovation of the Year award. 

Around 30 million Raspberry Pis were sold by the end of the year 2019. — The Inquirer

In eight years, the Raspberry Pi has gone through a lot of iterations and improvements. Below is a table showing different models of Raspberry Pi that have been released.

Generations of released Raspberry Pi Models

Projects Using Raspberry Pi

Here is a list of some interesting projects that use Raspberry Pi, to give you some ideas on how people are using it:

Home Automation

Basic Object and Motion Detection

Making DashCams

Setting up a Media Streaming Server

WhatsApp Surveillance Video Camera with IR Proximity Sensors

In this post, I will show you how to set up your Raspberry Pi 3B+ model so that you can start using it to create your own projects.

Raspberry Pi 3B+

Raspberry Pi 3B+ Specifications

Raspberry Pi 3B+ is the final version of the Raspberry Pi 3 range.

Processor: Broadcom BCM2837B0, Cortex-A53 64-bit SoC @ 1.4GHz
Memory: 1GB LPDDR2 SDRAM
Networking: Gigabit Ethernet over USB 2.0 (maximum throughput 300 Mbps), 2.4GHz and 5GHz IEEE 802.11.b/g/n/ac wireless LAN
Bluetooth: Bluetooth 4.2, Bluetooth Low Energy (BLE)
GPU: Broadcom Videocore-IV
Storage: Micro-SD
GPIO: 40-pin GPIO header, populated
Ports: HDMI, 3.5mm analogue audio-video jack, 4x USB 2.0, Ethernet, Camera Serial Interface (CSI), Display Serial Interface (DSI)
Dimensions: 82mm x 56mm x 19.5mm, 50g
Operating temperature: 0–50°C
Production Lifetime: will remain in production until at least January 2023

Things You Will Need:

Raspberry Pi 3B+

SD card

SD card reader

Ethernet Cable

Operating System You Will Need to Download:

1. Raspbian Buster: This is the operating system we will be installing on our Raspberry Pi 3B+. Please download Raspbian Buster with desktop and recommended software.

Software that You Will Need to Download:

Etcher Software

1. Etcher: Etcher is a free and open-source utility used for writing image files such as .iso and .img onto storage media to create live SD cards and USB flash drives.

VNC Viewer

2. VNC viewer: VNC viewer is software that allows remote access and control of a device that has VNC server enabled.

Steps to Set Up Your Raspberry Pi for Computer Vision:

1. Insert the SD card into your PC/laptop using the SD card reader.

2. Format the SD card.

3. Use Etcher software to burn the Raspbian Buster image file to the SD card.

Select image to burn in Etcher
Select target to burn the image
Flash image

4. Now from remote access, connect it to wifi so that you can access it without having to connect it to the PC using an ethernet cable.

Add ssh file to root directory of SD card

5. Eject the SD card from the PC/laptop, insert it into the Raspberry Pi, and turn the Raspberry Pi on by connecting it to power.

6. Connect the Raspberry Pi to the PC/laptop using an ethernet cable.

Raspberry Pi 3B+ with ethernet cable and power cable connected

7. SSH into the Pi from your PC using terminal. Enter the following command:

8. You will be prompted to enter a password. Enter the default password (raspberry).

9. Now enable vncserver on the Raspberry Pi using the following command:

10. From your PC, open VNC viewer and add the IP address of the Raspberry Pi to remotely connect to it.

11. Now from remote access, connect it to wifi so that you can access it without having to connect it to the PC using an ethernet cable.

All done! You now know how to set up a Raspberry Pi for computer vision, and your Raspberry Pi 3B+ is ready to be used.

If you’re looking to implement real-time face detection on a Raspberry Pi, then check out this post, or this one to implement real-time face tracking.

Spread the love

About the Author

    Sabina is an AI Specialist and Machine Learning Engineer. She is a Writer and a former Editorial Associate at Towards Data Science.

Trusted by

Xailient’s commercial partners

Press releases

March 14, 2022

Xailient specializes in extremely efficient low-power computer vision. Intel's OpenVINO specializes in maximizing the performance and speed of computer vision AI workloads. OpenVINO improved Xailient FPS 9.5x on Intel hardware to 448 FPS. Together, Xailient-Intel outperforms the comparable MobileNet_SSD by 80x. Even after Intel worked the OpenVINO magic on MobileNet_SSD, Xailient-OpenVINO is 14x faster.

November 29, 2021

Xailient’s Face Recognition enables high-speed edge AI processing with low-power consumption using Sony’s IMX500 – a chip so small it can fit on the tip of your finger.

OnEdge Newsletter

A weekly newsletter with the best hand-picked resources about Edge AI and Computer Vision

OnEdge is a free weekly newsletter that keeps you ahead of the curve on low-powered Edge devices and computer vision AI.

 

You’ll get insights and resources into:

  • Edge computing use cases.
  • Market trends in Edge computing.
  • Computer Vision AI at the Edge.
  • Machine learning at the Edge.
Cookie Policy