| Course Unit Code | 460-4080/01 |
|---|
| Number of ECTS Credits Allocated | 4 ECTS credits |
|---|
| Type of Course Unit * | Choice-compulsory |
|---|
| Level of Course Unit * | Second Cycle |
|---|
| Year of Study * | First Year |
|---|
| Semester when the Course Unit is delivered | Summer Semester |
|---|
| Mode of Delivery | Face-to-face |
|---|
| Language of Instruction | Czech |
|---|
| Prerequisites and Co-Requisites | Course succeeds to compulsory courses of previous semester |
|---|
| Name of Lecturer(s) | Personal ID | Name |
|---|
| SOJ10 | doc. Dr. Ing. Eduard Sojka |
| Summary |
|---|
| The following topics are discussed: Image segmentation, detecting edges, regions, and feature points. Measuring objects for recognition based on features. Classification using discriminant functions, classification based on clustering, classification using neural networks. Using deep neural networks for image analysis. Reconstructing 3D scenes. Analysing 3D point clouds. Processing images varying in time. Object tracking. Recognising actions from video frames. The course includes the computer labs in which the computer programs are realised corresponding to the mentioned topics. |
| Learning Outcomes of the Course Unit |
|---|
| The course provides the students with the foundations of image analysis. After passing the course, the student will understand the principles of the selected method of image segmentation and image analysis and will be able to implement them. |
| Course Contents |
|---|
Lectures:
1. Detecting edges in images, gradient methods, zero-crossing method, parametric edge models.
2. Image segmentation by region growing/splitting, thresholding, optimal threshold selection, adaptive thresholding.
3. Canny edge detector, Hough transform.
4. Detecting the feature points in images.
5. Measuring the objects for recognition, selecting and computing the descriptors.
6. Evaluating the efficiency of descriptors, introduction to universal descriptors (HoG).
7. Classification using discriminant functions, clustering, and SVM.
8. Classification using classical shallow neural networks.
9. Introduction to the deep neural networks, network architectures for recognising objects in images.
10. Creating 3D models from images, camera calibration, 3D sensors.
11. The problem of finding the correspondence between the images, and some methods for its solution.
12. Analysis of 3D point clouds, detecting the feature points, computing the descriptors, geometric consistency.
13. Analysis of images changing in time, optical flow, object tracking, Kalman filtering.
14. Introduction to action recognition from video frames.
Computer labs:
1. Edge detection, gradient and zero-crossing methods.
2. Canny edge detector, parametric edge models.
3. Thresholding, optimal threshold selection.
4. Hough transform.
5. Selecting the features/descriptors for classification.
6. Optimizing the set of descriptors, universal descriptors (HoG).
7. Classification using etalons and discriminant functions.
8. Classification using k-means clustering, classification using SVM.
9. Classification using shallow neural networks.
10. Classification using deep neural networks.
11. Classification using deep neural networks – continuation.
12. Optical flow.
13. Tracking the objects in video frames.
14. Obtaining the credit. |
| Recommended or Required Reading |
|---|
| Required Reading: |
|---|
Mandatory:
Gonzalez, R., C., Woods, R., E.: Digital Image Processing, 4th Edition, Pearson, ISBN-13: 9780134734804, 9780133356724, 2018.
Aggarwal, CC: Neural Networks and Deep Learning, Springer, ISBN: 978-3-319-94463-0, 978-3-319-94462-3, 2018.
|
1. Sojka, E., Gaura, J., Krumnikl, M.: Matematické základy digitálního zpracování obrazu, VŠB-TU Ostrava, 2011.
2. E. Sojka, Digitální zpracování a analýza obrazů, učební texty, VŠB-TU Ostrava, 2000 (ISBN 80-7078-746-5).
3. Gonzalez, R., C., Woods, R., E.: Digital Image Processing, 4th Edition, Pearson, ISBN-13: 9780134734804, 9780133356724, 2018.
4. Aggarwal, CC: Neural Networks and Deep Learning, Springer, ISBN: 978-3-319-94463-0, 978-3-319-94462-3, 2018.
|
| Recommended Reading: |
|---|
1. Burger, W., Burge, M., J.: Principles of Digital Image Processing: Fundamental Techniques, Springer, ISBN-10: 1848001908, ISBN-13: 978-1848001909, 2011
2. Brahmbhatt, S.: Practical OpenCV (Technology in Action), Apress, ISBN-10: 1430260793, ISBN-13: 978-1430260790, 2013
3. Petrou, M., Petrou, C.: Image Processing: The Fundamentals, Wiley, ISBN-10: 047074586X, ISBN-13: 978-0470745861, 2010 |
1. Burger, W., Burge, M., J.: Principles of Digital Image Processing: Fundamental Techniques, Springer, ISBN-10: 1848001908, ISBN-13: 978-1848001909, 2011
2. Brahmbhatt, S.: Practical OpenCV (Technology in Action), Apress, ISBN-10: 1430260793, ISBN-13: 978-1430260790, 2013
3. Petrou, M., Petrou, C.: Image Processing: The Fundamentals, Wiley, ISBN-10: 047074586X, ISBN-13: 978-0470745861, 2010 |
| Planned learning activities and teaching methods |
|---|
| Lectures, Tutorials |
| Assesment methods and criteria |
|---|
| Task Title | Task Type | Maximum Number of Points
(Act. for Subtasks) | Minimum Number of Points for Task Passing |
|---|
| Credit and Examination | Credit and Examination | 100 (100) | 51 |
| Credit | Credit | 25 | 12 |
| Examination | Examination | 75 | 30 |