Computer Vision

Lecture Curricula:

Introduction and Image Classification pipeline

Loss Functions and Optimization

Neural Networks and Backpropagation

Convolutional Neural Networks

Hardware and Software for CNN

Training Neural Networks

CNN Architectures

Detection and Segmentation

Projective Geometry

Stereovision

Corner Detectors

SIFT / SURF Features

Optical Flow

Point Cloud Segmentation

 

Textbooks and references:

1. Convolutional Neural Networks for Visual Recognition,  http://cs231n.stanford.edu/

2. David Forsyth, Jean Ponce “Computer Vision A Modern Approach”, Pearson, 2002

3. S. Nedevschi, R. Danescu, F. Oniga, T. Marita, “Tehnici de viziune artificiala in conducerea automata a autovehiculelor“, Editura UT Press,  2012

4. Daniel Scharstein, Richard Szeliski, “A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms”, IJCV

5. Heiko Hirschmuller, “Stereo Processing by Semiglobal Matching and Mutual Information”, IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. 30, NO. 2, FEBRUARY 2008

6. Raphael Labayrade and Didier Aubert, “IN-VEHICLE OBSTACLES DETECTION AND CHARACTERIZATION BY STEREOVISION”

7. Zhencheng Hu, Francisco Lamosa and Keiichi Uchimura,”A Complete U-V-Disparity Study for Stereovision Based 3D Driving Environment Analysis”

8. Ciprian Pocol, Sergiu Nedevschi, Marc-Michael Meinecke, “Obstacle Detection Based on Dense Stereovision for Urban ACC Systems, WIT 2010, Hamburg, Germany

9. IEEE Transactions on Pattern Analyses and Machine Intelligence

10. IEEE Transactions on Intelligent Transportation Systems
11. IEEE Transactions on Image Processing
12. CVPR publications