Computer vision is a field of research that uses computers to extract information of interest from data acquired by visual sensor. This course introduces the fundamentals of computer vision, including image processing, image features extraction, 3D structure reconstruction, segmentation, and camera calibration. This course aims to develop bases to study advanced computer vision topics such as image recognition and image generation.
- To be able to explain and implement basic image processing, filtering, feature extraction, and 3D reconstruction methods.
- To be able to explain about image segmentation and camera calibration.
✔ Applicable | How instructors' work experience benefits the course |
---|---|
The instructors have been using methods such as feature extraction, 3D reconstruction, and calibration in the automotive industry. |
Image Processing, Image Filtering, Image Features, Optical Flow, Epipolar Geometry, Stereo Matching, Image Segmentation, Camera Calibration
✔ 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 | Introduction | To understand areas of computer vision |
Class 2 | Basics of Image Processing | To understand basics of digital image processing |
Class 3 | Programming: Image Processing | Implementation of basic image processing |
Class 4 | Filtering | To understand 2D filters (e.g. smoothing, edge extraction) |
Class 5 | Programming: Filtering | Implementation of basic image filtering |
Class 6 | Image Features | To understand key point detectors and local descriptors |
Class 7 | Programming: Image Features | Implementation of a representative key point detector or local descriptor. |
Class 8 | Optical Flow | To understand basics of optical flow (e.g. Lukas-Kanade method) |
Class 9 | Epipolar Geometry | To understand epipolar geometry, essential matrix, and motion parameter estimation |
Class 10 | Stereo Matching | To understand 3D reconstruction from stereo camera |
Class 11 | Programming: 3D Reconstruction | Implementation of 3D reconstruction method from multiple images |
Class 12 | Segmentation | To understand segmentation method (e.g. Level Set, Graph Cut) |
Class 13 | Camera Calibration | To understand extrinsic and intrinsic parameters |
Class 14 | Discussion: Related Work | To discuss related computer vision papers |
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 undergraduate-level knowledges on computer science, 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 an environment to use MATLAB and Python.