Print

2022　3D 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)
Kanezaki Asako 
Class Format
Lecture    (HyFlex)
Media-enhanced courses
Day/Period(Room No.)
Tue3-4(W833)  Fri3-4(S223)  
Group
-
Course number
ART.T466
Credits
2
Academic year
2022
Offered quarter
4Q
Syllabus updated
2022/10/3
Lecture notes updated
-
Language used
English
Access Index

Course description and aims

This course teaches how to process images and 3D data so as to extract higher-level information from the data. It covers the basics of data processing, geometric transformations, and linear algebra for machine learning, as well as recent cutting-edge research on deep neural networks, with hands-on exercises using programming languages such as Python.

Student learning outcomes

At the end of this course, students should be able to
1) acquire the basics of image and 3D data processing, and
2) implement their own desired processing including deep learning with e.g., Python.

Keywords

Image Processing, 3D Data Processing, Geometric Transformations, Deep Learning, Neural Networks

Competencies that will be developed

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

Class flow

This course will be taught with slides and programming exercises.

Course schedule/Required learning

  Course schedule Required learning
Class 1 Input/Output of image and 3D data Understand 3D sensors and how to input, output, and visualize data.
Class 2 Image and 3D data pre-processing Learn about data filtering and geometric transformations.
Class 3 Image and 3D features Learn about image features such as SIFT and 3D keypoints/local features.
Class 4 Image and 3D data correspondence search Learn about k-d tree data structure and nearest neighbor search
Class 5 3D data registration Understand RANSAC and graph matching, and the ICP algorithm
Class 6 Linear algebra as a basis for machine learning Learn about linear algebra, the foundation of machine learning
Class 7 Data classification using machine learning Learn data classification techniques by support vector machines, etc.
Class 8 Foundation of deep learning Understand layers and the back propagation technique of deep learning
Class 9 Image processing with deep learning (1) Learn methods of image classification using deep learning
Class 10 Image processing with deep learning (2) Learn techniques such as image segmentation using deep learning
Class 11 3D data processing with deep learning (1) Learn methods of 3D data classification using deep learning
Class 12 3D data processing with deep learning (2) Learn techniques such as 3D data segmentation using deep learning
Class 13 3D data processing with deep learning (3) Learn about 3D representations using implicit functions, machine learning using geometric information, etc.
Class 14 Summary and Discussion Summary and discussion of the lecture

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

To enhance effective learning, students are encouraged to spend approximately 100 minutes preparing for class and another 100 minutes reviewing class content afterwards (including assignments) for each class.
They should do so by referring to textbooks and other course material.

Textbook(s)

None

Reference books, course materials, etc.

Materials translated into English from the above-mentioned Japanese reference book will be distributed.

Assessment criteria and methods

Comprehension of lecture content will be evaluated. Grades will be based on exercises and reports.

Related courses

  • ART.T467 ： Fundamentals of Computer Vision
  • ART.T552 ： Advanced Topics in Computer Vision
  • ART.T551 ： Image and Video Recognition

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

There are no prerequisites for this course.

Page Top