CMU Computer Vision Projects

Implementing computer vision algorithms and applications

Scene Classification System using Bag-of-words Approach with Spatial Pyramid Extension

• Feature Extraction based on Filter Banks
• K Means Clustering
• Visual Word Dictionary
• Scene Classification

Augmented Reality with Planar Homographies

• Direct Linear Transform
• Matrix Decomposition to calculate Homography
• Limitations of Planar Homography
• FAST Detector and BRIEF Descriptors
• Feature Matching
• Compute Homography via RANSAC
• Automated Homography Estimation and Warping
• Augmented Reality Application using Homography

Lucas-Kanade Object Tracking

• Simple Lucas & Kanade Tracker with Naive Template Update
• Lucas & Kanade Tracker with Template Correction

Structure from Motion - 3D Reconstruction

• Fundamental Matrix Estimation using Point Correspondence
• Metric Reconstruction
• Retrieval of Camera Matrices up to a Scale and Four-Fold Rotation Ambiguity
• Triangulation using the Homogeneous Least Squares Solution
• 3D Visualization from a Stereo-Pair by Triangulation and 3D Locations Rendering

Neural Networks for Recognition

• Manual Implementation of a Fully Connected Network
• Training the Implemented Models
• Text Extraction from Images of Handwritten Characters
• Image Compression with Autoencoders

Photometric Stereo

• Calibrated Photometric Stereo
• Uncalibrated Photometric Stereo