Book Image

Raspberry Pi Computer Vision Programming - Second Edition

By : Ashwin Pajankar
5 (1)
Book Image

Raspberry Pi Computer Vision Programming - Second Edition

5 (1)
By: Ashwin Pajankar

Overview of this book

Raspberry Pi is one of the popular single-board computers of our generation. All the major image processing and computer vision algorithms and operations can be implemented easily with OpenCV on Raspberry Pi. This updated second edition is packed with cutting-edge examples and new topics, and covers the latest versions of key technologies such as Python 3, Raspberry Pi, and OpenCV. This book will equip you with the skills required to successfully design and implement your own OpenCV, Raspberry Pi, and Python-based computer vision projects. At the start, you'll learn the basics of Python 3, and the fundamentals of single-board computers and NumPy. Next, you'll discover how to install OpenCV 4 for Python 3 on Raspberry Pi, before covering major techniques and algorithms in image processing, manipulation, and computer vision. By working through the steps in each chapter, you'll understand essential OpenCV features. Later sections will take you through creating graphical user interface (GUI) apps with GPIO and OpenCV. You'll also learn to use the new computer vision library, Mahotas, to perform various image processing operations. Finally, you'll explore the Jupyter Notebook and how to set up a Windows computer and Ubuntu for computer vision. By the end of this book, you'll be able to confidently build and deploy computer vision apps.
Table of Contents (15 chapters)

Combining Mahotas and OpenCV

Just like OpenCV, Mahotas uses NumPy arrays to store and process images. We can also combine OpenCV and Mahotas. Let's see an example of this, as follows:

import cv2
import numpy as np
import mahotas as mh
cap = cv2.VideoCapture(0)
while True:
    ret, frame = cap.read()
    frame = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
    T_otsu = mh.otsu(frame)
    output = frame > T_otsu
    output = output.astype(np.uint8) * 255
    cv2.imshow('Output', output)
    if cv2.waitKey(1) == 27:
        break
cv2.destroyAllWindows()
cap.release()

In the preceding program, we converted a live frame into a grayscale version. Then, we applied a Mahotas implementation of Otsu's binarization, which converted the frame from the live video feed into a Boolean binary image. We need to convert this to the np.uint8 type and multiply it by 255 (all of which takes the form of ones in binary 8-bit) so that we can use it with cv2.imshow(). The output is...