Skip to content

Implementing the concept of Stereo Vision. We are given 3 different datasets, each of them containing 2 images of the same scenario but taken from two different camera angles. By comparing the information about a scene from 2 vantage points, we can obtain the 3D information by examining the relative positions of objects.

Notifications You must be signed in to change notification settings

omkarchittar/Stereo_Depth_Estimation

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Stereo Depth Estimation

Overview

The code estimates the depth by creating a disparity map using the frames of a scene observed by a stereo-camera setup. This is done by correcting the epi-lines.

image1 image2 image3 image4 image5

File Tree

+-data
  +- artroom
    +- 2 images and calibration data
  +- chess
    +- 2 images and calibration data
  +- ladder
    +- 2 images and calibration data
+-main
+-README.md
+-report.pdf

Note - Please make changes in the main.py for variable "data" as "1", or "2", or "3" for artroom, chess and ladder repectively.

Installation and Running

  1. Download and extract the files.

  2. Run the code main.py using the following command in your terminal python3 main.py The terminal displays the following:

  • Fundamental Matrix

  • Essential Matrix

  • Rotation

  • camera center

  • Rectification homographies

  • 1st pop up window: matching features on the two images.

  • 2nd pop up window: reprojected points

  • 3rd pop up window:

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

About

Implementing the concept of Stereo Vision. We are given 3 different datasets, each of them containing 2 images of the same scenario but taken from two different camera angles. By comparing the information about a scene from 2 vantage points, we can obtain the 3D information by examining the relative positions of objects.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages