In this project, we are going to implement the concept of Stereo Vision. We will be given 3 different datasets, each of them contains 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.
To find the depth in an image by following the stereo vision pipeline.
- Matplotlib
pip install matplotlib - OpenCV
pip install opencv-python - NumPy
pip install numpy - tqdm
pip install tqdm - The dataset used for this project is MiddleBury Stereo Dataset
├───data
│ ├───curule
│ ├───octagon
│ └───pendulum
├───bchukkal_proj3_report.pdf
├───stereo_vision.py
└───results
- Clone the repository
git clone https://github.com/bharadwaj-chukkala/Stereo-Vision-to-estimate-depth-in-an-image.git
- Install Python 3.9 and the libraries mentinoned below prior to running the code
- Go to the root directory from your IDE.
- Please mention the path to the datasets wherever necessary.
- Run the
stereo_vision.pyfile as it is. - Note: if dataset and results are not given, please paste the py file in the folder where dataset is present and also create a results folder in the directory where you run the code.
| Curule | Octagon | Pendulum | |
|---|---|---|---|
| Epipolar geometry (Rectified) |
 |
 |
 |
| Disparity (Heat) |
 |
 |
 |
| Depth Estimation |  |
 |
 |
This project is licensed under the MIT License - see the LICENSE file for details.
Bharadwaj Chukkala
UID: 118341705
Bharadwaj Chukkala is currently a Master's student in Robotics at the University of Maryland, College Park, MD (Batch of 2023). His interests include Machine Learning, Perception and Path Planning.
