Skip to content

Latest commit

 

History

History
82 lines (69 loc) · 3.8 KB

README.md

File metadata and controls

82 lines (69 loc) · 3.8 KB
Raw

Course Projects in Computer Vision at CMU

Any Copying from the work of another person is a violation of Carnegie Mellon University Policy on Academic Integrity.

0. Color Channel Alignment and Image Warping

1. 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
  • Hyperparameters Tuning
  • CNN Implementation

2. 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
  • Real-Time Augmented Reality with High FPS
  • Panorama Generation based on Homography

3. Lucas-Kanade Object Tracking

  • Simple Lucas & Kanade Tracker with Naive Template Update
  • Lucas & Kanade Tracker with Template Correction
  • Two-dimensional Tracking with a Pure Translation Warp Function
  • Two-dimensional Tracking with a Plane Affine Warp Function
  • Lucas & Kanade Forward Additive Approach
  • Lucas & Kanade Inverse Compositional Approach

4. 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
  • Bundle Adjustment
    • Estimated fundamental matrix through RANSAC for noisy correspondences
    • Jointly optmized reprojection error w.r.t 3D estimated points and camera matrices
    • Non-linear optimization using SciPy least square optimizer

5. Neural Networks for Recognition

  • Manual Implementation of a Fully Connected Network
  • Text Extraction from Images of Handwritten Characters
  • Image Compression with Autoencoders
  • PyTorch Implementation of a Convolutional Neural Network
  • Fine Tuning of SqueezeNet in PyTorch
  • Comparison between Fine Tuning and Training from Scratch

6. Photometric Stereo

  • Calibrated Photometric Stereo
  • Uncalibrated Photometric Stereo
  • Generalized Bas-Relief Ambiguity