Course Unit Code | 460-4107/01 |
---|
Number of ECTS Credits Allocated | 4 ECTS credits |
---|
Type of Course Unit * | Optional |
---|
Level of Course Unit * | Second Cycle |
---|
Year of Study * | Second Year |
---|
Semester when the Course Unit is delivered | Winter Semester |
---|
Mode of Delivery | Face-to-face |
---|
Language of Instruction | Czech |
---|
Prerequisites and Co-Requisites | |
---|
| Prerequisities | Course Unit Code | Course Unit Title |
---|
| 460-4080 | Image Analysis I |
Name of Lecturer(s) | Personal ID | Name |
---|
| FUS032 | Ing. Radovan Fusek, Ph.D. |
Summary |
---|
The following topics are covered: Modern methods of object detection and object recognition. Typically, the approaches are based on the image descriptors that are combined with the machine learning methods. The principles and aplications of deep learning and convolutional neural networks are also covered (detection of vehicles, pedestrians, faces).
|
Learning Outcomes of the Course Unit |
---|
The goal of the course is to get the student acquainted with modern methods of image analysis that can be used in the area of object detection and recognition. An integral part is also application of this methods in the real world (e.g. detection and recognition of faces, localization of pedestrians, detection of cars). |
Course Contents |
---|
Lectures:
1. Main ideas behind object detection in images, a sliding window method.
2. Face detection methods, Haar-like features.
3. Local binary patterns for object detection.
4. Pedestrian detection methods, histograms of oriented gradients.
5. Keypoint detectors and descriptors (SIFT).
6. Convolutional neural networks (basic principles, layers).
7. Modern types of convolutional neural networks (e.g. VGGNet, GoogLeNet, ResNet).
8. Object localization using convolutional neural networks (e.g. R-CNN, Faster R-CNN, YOLO).
9. Optical systems in autonomous vehicles.
10. Detecting the background by the Gaussian mixture method.
11. Processing the images in IR spectrum and multispectral images.
12. Depth image processing (RealSense, Kinect).
13. LIDAR image processing.
14. Summary of lecture themes.
Computer Labs:
1. Implementation of basic template for object detection in images.
2. Implementation of a sliding window method.
3. Preparing data for training and testing.
4. Object detection using Haar-like features.
5. Object detection using local binary patterns.
6. Keypoint detectors and descriptors (SIFT).
7. Application of convolutional neural networks.
8. Experiments with parameters of convolutional neural networks.
9. Experiments with different types of convolutional neural networks (e.g. VGGNet, GoogLeNet, ResNet).
10. Experiments with created detectors, comparison of the results.
11. Object recognition in IR images. Image enhancements and subsequent processing.
12. Depth image processing (RealSense, Kinect).
13. Reserve.
14. Credit. |
Recommended or Required Reading |
---|
Required Reading: |
---|
1. Chollet, F.: Deep Learning with Python. Manning, ISBN-13: 978-1617294433, 2017
2. Gonzalez, R. C., Woods, R. E.: Digital image processing, New York, NY: Pearson, ISBN-13: 978-0133356724, 2018
3. Zhang, A., Lipton, Z.C., Li, M., Smola, A.J.: Dive into Deep Learning, https://d2l.ai, 2020 |
1. Chollet, F.: Deep Learning with Python. Manning, ISBN-13: 978-1617294433, 2017
2. Gonzalez, R. C., Woods, R. E.: Digital image processing, New York, NY: Pearson, ISBN-13: 978-0133356724, 2018
3. Zhang, A., Lipton, Z.C., Li, M., Smola, A.J.: Dive into Deep Learning, https://d2l.ai, 2020 |
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. Gary Bradski, Adrian Kaehler: Learning OpenCV 3: Computer Vision in C++ with the OpenCV Library, O'Reilly Media, 2017 |
1. E. Sojka, J. Gaura, and M. Krumnikl, Matematické základy digitálního zpracování obrazu. Ostrava, Plzeň: VŠB-TU Ostrava (Fakulta elektrotechniky a informatiky), Západočeská univerzita v Plzni, 2. vydání ed., 2011.
2. Burger, W., Burge, M., J.: Principles of Digital Image Processing: Fundamental Techniques, Springer, ISBN-10: 1848001908, ISBN-13: 978-1848001909, 2011
3. Brahmbhatt, S.: Practical OpenCV (Technology in Action), Apress, ISBN-10: 1430260793, ISBN-13: 978-1430260790, 2013
4. Gary Bradski, Adrian Kaehler: Learning OpenCV 3: Computer Vision in C++ with the OpenCV Library, O'Reilly Media, 2017 |
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 | 40 | 20 |
Examination | Examination | 60 | 20 |