2021 Advanced Topics in Computer Vision

Font size  SML

Register update notification mail Add to favorite lecture list
Academic unit or major
Graduate major in Artificial Intelligence
Instructor(s)
Kawakami Rei  Sato Ikuro  Sekikawa Yusuke 
Course component(s)
Lecture    (ZOOM)
Day/Period(Room No.)
Tue7-8()  Fri7-8()  
Group
-
Course number
ART.T552
Credits
2
Academic year
2021
Offered quarter
2Q
Syllabus updated
2021/4/1
Lecture notes updated
-
Language used
English
Access Index

Course description and aims

Computer vision is a field of research that uses computers to extract information of interest from data acquired by visual sensor. This course introduces special topics about image understanding and image generation. This course aims to develop ability to study frontiers of computer vision researches.

Student learning outcomes

- To be able to explain and implement basic object recognition and tracking methods.
- To be able to explain about the selected topics covered in this course.

Course taught by instructors with work experience

Applicable How instructors' work experience benefits the course
The instructors have been using methods of image recognition in the automotive industry.

Keywords

Image Retrieval, Generic Object Recognition, Convolutional Neural Networks, SLAM, Image Based Rendering, Computational Photography, Autonomous Driving, Event Based Camera

Competencies that will be developed

Specialist skills Intercultural skills Communication skills Critical thinking skills Practical and/or problem-solving skills

Class flow

Lectures and programming exercises.

Course schedule/Required learning

  Course schedule Required learning
Class 1 Image Retrieval To understand Bag-of-Words and approximate nearest neighbor search
Class 2 Generic Object Recognition To understand generic object recognition using local descriptors
Class 3 Programming: Object Recognition Implementation of a basic object recognition method
Class 4 Object Tracking To understand object tracking using time series filters
Class 5 Programming: Object Tracking Implementation of Object Tracking using a time series filter
Class 6 Convolutional Neural Networks To understand weight sharing, pooling, and error backpropagation
Class 7 Programming: Neural Networks Implementation of neural network
Class 8 Visual SLAM (Simultaneous Localization And Mapping) To understand optimization of location and 3D shapes
Class 9 Image-based Rendering To understand reflection models, BRDF, and light field.
Class 10 Computational Photography To understand super resolution and deblurring
Class 11 Machine Learning for Vision To understand types of machine learning (e.g. supervised learning, unsupervised learning, reinforcement learning)
Class 12 Visual Recognition for Autonomous Driving To understand recognition tasks needed for autonomous driving
Class 13 Event-based Camera To understand the basics and applications of event-based camera
Class 14 Discussion: Frontiers of Computer Vision To discuss current issues in computer vision

Out-of-Class Study Time (Preparation and Review)

Students are encouraged to review the materials taught in each class for about 60 minutes.

Textbook(s)

None required.

Reference books, course materials, etc.

Lecture slides are used during the class.
Richard Szeliski, Computer Vision: Algorithms and Applications, 2nd ed., Springer, 2011.
Richard Hartley and Andrew Zisserman, Multiple View Geometry in Computer Vision, 2nd ed., Cambridge University Press, 2004.

Assessment criteria and methods

Final Report (40%) and 3 short reports (60%)

Related courses

  • ART.T467 : Fundamentals of Computer Vision
  • ART.T551 : Image and Video Recognition
  • CSC.T439 : Augmented Reality
  • ART.T463 : Computer Graphics
  • XCO.T489 : Fundamentals of artificial intelligence
  • ART.T465 : Sparse Signal Processing and Optimization
  • ART.T547 : Multimedia Information Processing

Prerequisites (i.e., required knowledge, skills, courses, etc.)

Students are required to have knowledges on fundamentals of computer vision, linear algebra, calculus, probability, and statistics.

Contact information (e-mail and phone)    Notice : Please replace from "[at]" to "@"(half-width character).

isato[at]c.titech.ac.jp; reikawa[at]c.titech.ac.jp

Office hours

11:30-12:00 on Wednesdays

Other

Students are required to set up environment to use MATLAB and Python.

Page Top