Computer Vision

Description:

Computer Vision is concerned about the algorithms and models that enable machines to extract information automatically from images. The goal of this course is to provide an introduction to computer vision through the study of three main aspects of the domain: image processing at pixel level, modeling and estimation of 2D and 3D geometry, machine learning of visual models. Each topic will be associated to practical programming laboratories with applications such as image segmentation, object tracking and object recognition.

Download flyer: [PDF]

Prerequisites:

• CCOM3034 Data Structures

Content:

1. Image processing (15h)

   • Image representation and manipulation
   • Filtering
   • Segmentation

2. Geometry modeling and estimation (15h)

   • Camera modeling and image formation
   • Feature based (SIFT, SURF...) image alignment
   • Object tracking
   • Multiview geometry and stereovision

3. Machine learning of visual models (15h)

   • Visual features extraction
   • Object and scene recognition
   • Deep learning and convolutional networks

Teaching strategy and ressources:

Concepts and theory presented in lectures and in class discussion. Hands on labs using Python and computer vision libraries (OpenCV, skimage, sklearn...). Mini-projects.

Books:

• No textbook required, as the content will be mostly self-contained (slides, documents, and online resources). Specific chapters of the following books will be used (documents available online):
• Richard Szeliski. "Computer Vision: Algorithms and Applications". Springer 2010. ISBN 1848829345. Available online: http://szeliski.org/Book/
• Ian Goodfellow, Yoshua Bengio and Aaron Courville. "Deep Learning". MIT Press, 2016. Available online: http://www.deeplearningbook.org/
• Jan Erik Solem. "Programming Computer Vision with Python: Tools and algorithms for analyzing images". O'Reilly, 2012. ISBN 1449316549. Draft available online: http://programmingcomputervision.com/downloads/ProgrammingComputerVision_CCdraft.pdf
• Wilhelm Burger and Mark J. Burge, Principles of Digital Image Processing: Fundamental Techniques, Springer, 2011. ISBN 1848001908.
• Fletcher Dunn, Ian Parberry, 3D Math Primer for Graphics and Game Development, 2nd Edition. CRC Press, 2011. ISBN 1568817231.

Links:

• OpenCV official page: http://opencv.org/ and its documentation http://docs.opencv.org/3.2.0/
• Scikit-image documentation: http://scikit-image.org/docs/dev/
• Scikit-learn documentation: http://scikit-learn.org/stable/documentation.html
• Matlab - Image Processing and Computer Vision System Toolboxes: https://www.mathworks.com/products/image.html, https://www.mathworks.com/help/vision/
• Vector Math for 3D Computer Graphics: http://chortle.ccsu.edu/vectorlessons/vectorindex.html