/Camera_Pose_Estimation

This project aims to estimate camera pose using homography for a given video. Steps involved are designing an image processing pipeline to extract paper's corners, computing homography between real-world points and pixel coordinates of the corners, and decomposing the homography matrix to obtain rotation and translation parameters.

Primary LanguagePython

Camera Pose Estimation

gif image1 image2 image3 image4

File Tree

Camera_Pose_Estimation
+-figures
  +- 8 images
+-project2.avi
+-Problem_1
+-README.md
+-report.pdf

Installation and Running

  1. Download and extract the files.

  2. Run the code Problem.py using the following command in your terminal python3 Problem.py Two pop up windows: window 1: Roll, Pitch and Yaw versus time graph. window 2: Tx, Ty, Tz versus time graph. The terminal displays the following:

  • The frame which is currently being read and the coordinates of the corners of the sheet of paper in that frame.

For plotting graphs directly uncomment the corners

Have stored the co-ordinates from all the frames in a list obtained by once running the code

  1. A detailed report of the entire project is given in report.pdf