Many Computer Vision Lectures (full PDFs) are available below for free!

DESCRIPTION

Our dream to make machines sense and perceive (notably see) comes true: nowadays Computer Vision enables diverse applications:

  1. Autonomous Systems (cars, drones, vessels) Perception,
  2. Robotics Perception and Control,
  3. Intelligent Human-Machine Interaction,
  4. Anthropocentric (human-centered)Computing,
  5. Smart Cities/Buildings and Assisted living.

Computer Vision, coupled with AI (notably Machine Learning and Deep Neural Network) advances hit the news almost every day.

This CVML Web Module focuses on Computer Vision and its applications in the above-mentioned diverse domains and new challenges ahead. First an introduction to computer vision is made, to be complemented with a formal presentation of digital images and videos, image/video sampling and color theory. After reviewing image acquisition, camera structure, camera geometry (mapping the 3D world on a 2D image plane) and camera calibration are presented. Stereo and multi-view imaging systems are presented for recovering 3D world geometry from 2D images. This is complemented by Structure from Motion (SfM) towards Simultaneous Localization and Mapping (SLAM) for vehicle and/or target localization. Then semantic 3D world mapping is overviewed, coupling 3D geometry and semantics. 3D object/target localization is then presented, encompassing Visual 3D object localization using 3D maps, GPS object localization, multisensor object localization and multi-view object localization. Object pose is then defined and its estimation by deep neural regression is presented. Computational Cinematography is a new topic in computer vision, encompassing visual shot framing types and shot feasibility issues, under shooting constraints.

LECTURE LIST

  1. Introduction to Computer Vision
  2. Digital Images and Videos
  3. Image acquisition
  4. Camera Geometry
  5. Stereo and Multiview Imaging
  6. Neural Semantic 3D World Modeling and Mapping
  7. Structure from Motion
  8. Simultaneous Localization and Mapping
  9. Neural SLAM
  10. 3D Object Localization
  11. Object Pose Estimation
  12. Computational Cinematography
CVML WEB LECTURE MODULE SCHEDULE

This module has been designed to be mastered within 1 month (or less), if you have proper background (at least early undergraduate student in an EE, ECE, CS, CSE or any Engineering or Exact Sciences Department).
We propose that you follow the above mentioned  Lecture order. You may want to skip few Lectures that might not be of immediate interest to you for later study.

On average you can study 4 lectures per week. The related effort is as follows:
1) Lecture pdf study and filling the related understanding questionnaire: 1-2 hours per lecture (on average, depending on your background)
2) Tutorial exercise (if available): 1/2 hour on average (more if you do not have theoretical skills). We strongly recommend to try solve them yourself, before resorting to the existing solution.
3) Programming exercise (if available): 3-4 hours on average (more if you do not have good programming skills). We strongly recommend to try program them yourself, before resorting to the existing code.

The following lectures are accompanied by programming or tutorial exercises:

  1. Image Acquisition (1 Tutorial Exercise)
  2. Camera Geometry (1 Tutorial Exercise)