YOLO-Powered_Robot_Vision

YOLO-Powered_Robot_Vision


Introduction

This is a Pi-based robot to implement visual recognition(by YOLO). The YOLO-Powered vision can recognize many objects such as people, car, bus, fruits, and so on.

  • Hardware: Raspberry-Pi2, Sony PS3 Eye Camera

    (Available to use Logitech C270 USB camera with Raspberry Pi)

  • Software: YOLO(v2), Jupyter-Notebook

Structure.png

My motivation

I was so interested in performance of the image recognition with YOLO-2 on Raspberry Pi. In addition, the Jupyter notebook is really convenient to instantly code as a quick prototype. According to paper, I realised that YOLO is a fast, accurate visual detector, making it ideal for computer vision system. We connect YOLO to a webcam and verify that it maintains real-time performance. So, the Raspberry pi’s processing speed is very slow compare to my laptop.

(Picasso Dataset precision-recall curves: paper)

Perfomance_Picaso.png

(The Architecture: paper)

Architecture_CNN.png

Requirements and Installation

Quick Start

This post will guide you through detecting objects with the YOLO system using a pre-trained model. If you don’t already have Darknet installed, you should install OpenCV2 before on your Raspberry Pi.

  • Install dependencies for OpenCV2
sudo apt-get update

sudo apt-get install build-essential
sudo apt-get install cmake git libgtk2.0-dev pkg-config libavcodec-dev libavformat-dev libswscale-dev python-dev python-numpy libjpeg-dev libpng-dev libtiff-dev libjasper-dev

sudo apt-get install python-opencv
  • Check which version of OpenCV you have in Python
python
import cv2
cv2.__version__
  • Install the darknet for YOLO
git clone https://github.com/pjreddie/darknet
cd darknet
make

Easy!

You already have the config file for YOLO in the cfg/ subdirectory. You will have to download the pre-trained weight file here (258 MB). Or just run this:

wget http://pjreddie.com/media/files/yolo.weights

Then run the detector to test.

./darknet detect cfg/yolo.cfg yolo.weights data/dog.jpg

You will see some output like this:

layer     filters    size              input                output
    0 conv     32  3 x 3 / 1   416 x 416 x   3   ->   416 x 416 x  32
    1 max          2 x 2 / 2   416 x 416 x  32   ->   208 x 208 x  32
    .......
   29 conv    425  1 x 1 / 1    13 x  13 x1024   ->    13 x  13 x 425
   30 detection
Loading weights from yolo.weights...Done!
data/dog.jpg: Predicted in 0.016287 seconds.
car: 54%
bicycle: 51%
dog: 56%

Output

  • Re-name from ‘darknet’ to ‘YOLO-Powered_Robot_Vision’.
mv /home/pi/Documents/darknet /home/pi/Documents/YOLO-Powered_Robot_Vision
cd /home/pi/Documents/YOLO-Powered_Robot_Vision
  • Download ‘YOLO-Powered_Robot_Vision.ipynb’ at /home/pi/Documents/YOLO-Powered_Robot_Vision
wget https://github.com/leehaesung/YOLO-Powered_Robot_Vision/raw/master/YOLO-Powered_Robot_Vision.ipynb

jupyter-notebook

Source Codes

Result of Object Recognition

(Caution!!: I have used the image sources for an educational purpose. Please don’t use any pictures in copyright. So, I am not responsible for any images you use.)

predictions06.png

  • Another examples predictions07.png

predictions08.png

predictions09.png

predictions11.png

Advertisements

Author: iotmaker

I am interested in IoT, robot, figures & leadership. Also, I have spent almost every day of the past 15 years making robots or electronic inventions or computer programs.

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s