Exercise2b - Change detection in videos¶

The goal of this exercise is to create a small program for real-time change detection using OpenCV.

Learning Objectives¶

After completing this exercise, the student should be able to do the following:

Use OpenCV to access a web-camera or the camera or a mobile phone.
Use the OpenCV function cvtColor to convert from color to gray scale,
Convert images from integer to floating point using the img_as_float function.
Convert image from floating point to uint8 using the img_as_ubyte function.
Compute a floating point absolute difference image between a new and a previous image.
Compute the frames-per-second of an image analysis system.
Show text on an image using the OpenCV function putText.
Display an image and zoom on pixel values using the OpenCV function imshow.
Implement and test a change detection program.
Update a background image using a linear combination of the previous background image and a new frame.
Compute a binary image by thresholding an absolute difference image.
Compute the total number of changed pixels in a binary image.
Implement a simple decision algorithm that is based on counting the amount of changed pixels in an image.

Installing Python packages¶

In this exercise, we will be using the popular OpenCV library to perform real-time image analysis.

We will use the virtual environment from the previous exercise (course02503). Start an Anaconda prompt and do:

conda activate course02503
pip install opencv-python

Exercise data and material¶

Download the data you'll need for this exercise by clicking here: Data

Alternatively, you can also fetch the data for the whole course through the Image Analysis GitHub repository. See the Data and GitHub section for more information. If you're using Git, it may be wise run:

git pull

As this will fetch updates to the material, which may happen throughout the course.