Skip to content

Aadiv1999/reconstruct_3D

Repository files navigation

3D Recontruction Using Stereo Vision

This Project consists implementation of creating 3D pointclouds from the Left and Right Images of a Stereo Camera. The main idea is to use the epipolar geometry and Simple Pinhole Camera model to estimate the depth of points in the Image. A disparity map is created using feature matching algorithms like SIFT, SURF, ORB etc. In this we have used the OpenCv function to Stereo_BM to create the disparity map. The depth map is then created using the Camera parameters data.

DATASET USED: https://vision.middlebury.edu/stereo/data/scenes2014/

Dataset Sample

The file 3D_Reconstruction.ipynb consists the complete implementation of the project.

The output point clouds are saved in .pcd file format which is then visualized using MATLAB.

Outputs

Disparity

Depth PointClouds

output1 output2

About

3D Reconstruction from Vision

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 4

  •  
  •  
  •  
  •