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.
- 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.
✔ Applicable | How instructors' work experience benefits the course |
---|---|
The instructors have been using methods of image recognition in the automotive industry. |
Image Retrieval, Generic Object Recognition, Convolutional Neural Networks, SLAM, Image Based Rendering, Computational Photography, Autonomous Driving, Event Based Camera
✔ Specialist skills | Intercultural skills | Communication skills | Critical thinking skills | Practical and/or problem-solving skills |
Lectures and programming exercises.
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 |
Students are encouraged to review the materials taught in each class for about 60 minutes.
None required.
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.
Final Report (40%) and 3 short reports (60%)
Students are required to have knowledges on fundamentals of computer vision, linear algebra, calculus, probability, and statistics.
isato[at]c.titech.ac.jp; reikawa[at]c.titech.ac.jp
11:30-12:00 on Wednesdays
Students are required to set up environment to use MATLAB and Python.