Description
Lab 1: Hough Transform: The goal of this assignment is to write a code to use Hough transform
to detect checkerboard in an image.
Prelab work:
Familiarize yourself with opencv functions for Canny edge detection and Hough transform
Familiarize yourself with opencv and python functions to draw points, lines, and plot.
Familiarize yourself with opencv read and write images
Read Szeliski section 2.1.1
Procedure:
1. Download the zip file called lab1 and extract it to your home directory.
From windows start menu, open anaconda command prompt and install opencv library
using running the following command: pip install opencv-contrib-python
2. Open spyder for anaconda 3 as the python editor and open the sample code in Lab1.py.
3. Read the implementation of the code and understand what each part does and then run the code
4. As you have seen in different test images that results are not great and sometimes even the
detected angles are not correct (try image test4.jpg). You can remove some of the false results by
increasing the threshold in HoughLines function. Feel free to come up with a different idea to
improve the results.
5. Group the detected lines into horizontal and vertical lines and then find intersections of the
horizontal and vertical lines.
6. Extend the code to make able to run on a video. It should process every 30th frame and display
the results for that frame then pause. To read video, you can use cv2.VideoCapture function.
COMPUTER VISION, LAB 1, FEB. 08, 2021
Instructions:
Submit your codes and results as a zip file through the drop box folder for lab 1. You can upload
several versions, however, the most recent submission will be the only one marked
General guidelines for programming assignments:
The marking of the implemented functions is based on the following general scheme:
– Correctness and logic 80%: the program logic should be correct and code is compiled without
errors.
– Style 10%: codes should have comments and properly formatted.
– Optimization and simplicity 10%: codes should have reasonable implementation and should not
be too complicated.