460-4129/02 – Image Processing in Automobiles (ZODA)
| Gurantor department | Department of Computer Science | Credits | 4 |
| Subject guarantor | doc. Dr. Ing. Eduard Sojka | Subject version guarantor | doc. Dr. Ing. Eduard Sojka |
| Study level | undergraduate or graduate | Requirement | Compulsory |
| Year | 1 | Semester | winter |
| | Study language | English |
| Year of introduction | 2019/2020 | Year of cancellation | 2022/2023 |
| Intended for the faculties | FEI | Intended for study types | Follow-up Master |
Subject aims expressed by acquired skills and competences
The course acquaints the students with the methods of digital image processing and image analysis. These methods are applied in the algorithms for autonomous driving. After passing the course, the student will understand the principles of the operations with the images and will be able to implement them.
Teaching methods
Lectures
Tutorials
Summary
The following topics are covered: point and geometric operations, convolution, edge detection, feature extraction, classification methods, image segmentation, scene reconstruction, depth data analysis. The course includes the computer labs in which the computer programs are realized corresponding to the mentioned topics.
Compulsory literature:
1. Gonzalez, R., C., Woods, R., E.: Digital Image Processing, Prentice Hall, ISBN-10: 013168728X, ISBN-13: 978-0131687288, 2007
2. Burger, W., Burge, M., J.: Principles of Digital Image Processing: Fundamental Techniques, Springer, ISBN-10: 1848001908, ISBN-13: 978-1848001909, 2011
Recommended literature:
1. Petrou, M., Petrou, C.: Image Processing: The Fundamentals, Wiley, ISBN-10: 047074586X, ISBN-13: 978-0470745861, 2010
2. Brahmbhatt, S.: Practical OpenCV (Technology in Action), Apress, ISBN-10: 1430260793, ISBN-13: 978-1430260790, 2013
Way of continuous check of knowledge in the course of semester
Credit: 40 points (tasks assigned during the exercises)
Exam: 60 points (written and oral form)
E-learning
Other requirements
No further requirements are imposed on student.
Prerequisities
Subject has no prerequisities.
Co-requisities
Subject has no co-requisities.
Subject syllabus:
Lectures:
1. Digital image. Sensors, transformation to the digital form.
2. Transformations of brightness. Geometric transformations.
3. Convolution and image filtration.
4. Fourier transform and its application in images.
5. Image compression.
6. Edge detection, corner detection, morphological image processing.
7. Segmentation methods.
8. Advanced segmentation methods.
9. Selection and computation of features for pattern recognition.
10. Classification methods.
11. Analysis of time-varying images. Object tracking.
12. Scene reconstruction from pair of images. Camera calibration.
13. Depth data processing. Object registration.
14. Spare space.
Exercises:
1. Introduction to OpenCV.
2. Gamma correction, histogram equalization.
3. Convolution, convolution masks, image denoising.
4. Discrete Fourier Transform.
5. Morphological image processing. Erosion and dilatation operations.
6. Edge detection.
7. Image segmentation, thresholding, adaptive thresholding.
8. Distance-based image segmentation.
9. Classification methods. Computing moments.
10. Classification using an artificial neural network.
11. Tracking of objects in video sequences. Kalman filtering.
12. Object registration in depth data.
13. Spare space.
14. Credit.
Conditions for subject completion
Occurrence in study plans
Occurrence in special blocks
Assessment of instruction