Implementation of simple block matching, block matching with dynamic programming and Stereo Matching using Belief Propagation algorithm for stereo disparity estimation

Compute disparity map from stereo image with semi global matching algorithm.

Pothole Detection Based on Disparity Transformation and Road Surface Modeling (T-IP)

Stereo matching algorithms implemented in MATLAB

A stereo vision system project (with calibration) using the MATLAB toolboxes.

In this repository, 8-point algorithm is used to find the fundamental matrix based on SVD. Disparity map is generated from left and right images. In addition, RealSense depth camera 435i is used to estimate object center depth. Image thresholding and object detection are implemented. It is apart of Assignment3 in Sensing, Perception and Actuatio…

Project Repository of the course "EE 702: Computer Vision"

Study of stereo photogrammetry implementation in Matlab using disparity map and feature triangulation to reconstruct the scene and Structure from Motion to estimate the camera pose

It compares the disparity map generated by our algorithm against the ground truth disparity map that provided in the dataset.

A Matlab implementation of Loopy Belief Propagation for stereo matching. It uses the "Min-Sum" version of the algorithm and the "Accelerated" (Right-Left-Down-Up pass) message update schedule.

A Matlab implementation of Block Matching Algorithm for stereo matching. It uses matrix operations to make the code faster.

MATLAB implementation of fast stereo disparity estimator.

Software to evaluate depth estimation of ZED and ZED Mini stereo cameras for measurement purposes as part of the Master Thesis Project: Sparse Stereo Visual Odometry with Local Non-Linear Least-Squares Optimization for Navigation of Autonomous Vehicles

A Matlab implementation of Dynamic Programming Algorithm for stereo matching. It provides vertical smoothness by trying to keep the current path close to the former path using an additional discontinuity cost.

An optimized Matlab implementation of Loopy Belief Propagation for stereo matching that focuses on speed. It uses matrix operations and other techniques to make the program run even faster.

A Matlab implementation of Semi-Global Matching (SGM) for stereo matching. It uses the two-pass 8-directions version of the algorithm with a small improvement for better results.

Computer Vision, CSE 6367, projects. Class is taken during Spring 2019, taught by Dr. William Beksi.

A Matlab implementation of Loopy Belief Propagation for stereo matching. It uses the "Max-Product" variation of the algorithm and the "Synchronous" message update schedule.

A Matlab implementation of Semi-Global Matching (SGM) for stereo matching. It uses the 8-direction version of the algorithm with a small improvement for better results.