460-4107/01 – Image Analysis II (AO2)

Gurantor department	Department of Computer Science	Credits	4
Subject guarantor	Ing. Radovan Fusek, Ph.D.	Subject version guarantor	Ing. Radovan Fusek, Ph.D.
Study level	undergraduate or graduate	Requirement	Optional
Year	2	Semester	winter
		Study language	Czech
Year of introduction	2015/2016	Year of cancellation
Intended for the faculties	FEI	Intended for study types	Follow-up Master

Instruction secured by
Login	Name	Tuitor	Teacher giving lectures
FUS032	Ing. Radovan Fusek, Ph.D.

Extent of instruction for forms of study
Form of study	Way of compl.	Extent
Full-time	Credit and Examination	2+2
Part-time	Credit and Examination	18+0

Subject aims expressed by acquired skills and competences

The aim of the course is to introduce students to modern methods of image analysis with a focus on their application to object detection and recognition. A central component of the course is to apply these these techniques in real-world contexts, such as facial analysis, pedestrian localization, and vehicle detection in images. In addition, students will learn to develop proficiency in the principles and applications of generative networks, including their use for dataset augmentation, the synthesis of realistic image samples, and the enhancement of recognition method robustness.

Teaching methods

Lectures
Tutorials
Teaching by an expert (lecture or tutorial)

Summary

The following topics are particularly discussed: modern methods for object detection and recognition in images, principles of deep learning combined with image analysis, current variants of convolutional neural networks and their practical applications for different types of objects. The subject will also include the theme of generative networks. Upon successful completion of the course, the student will be able to: - apply modern methods of image analysis for object detection and recognition in real-world environments, - evaluate and analyze the strengths and weaknesses of individual methods, - design and modify convolutional neural network models, - assess the robustness of the models, - apply these models to practical tasks, such as face recognition, pedestrian localization, or vehicle detection in images, - use generative networks to augment datasets, - generate image samples.

Compulsory literature:

1. Ayyadevara, V. Kishore; Reddy, Yeshwanth. Modern Computer Vision with PyTorch: Explore deep learning concepts and implement over 50 real-world image applications. Packt Publishing, 2020. ISBN 978-1839213472. 2. Lakshmanan, V.; Shlens, J.; Sukthankar, R. Practical Machine Learning for Computer Vision: End-to-End Machine Learning for Images. O’Reilly Media, 2021. ISBN 978-1098102364. 3. Zhang, A.; Lipton, Z. C.; Li, M.; Smola, A. J. Dive into Deep Learning. arXiv, 2021. Available at: https://doi.org/10.48550/arXiv.2106.11342.

Recommended literature:

1. Burger, W.; Burge, M. J. Principles of digital image processing: Fundamental techniques. Springer, 2011. ISBN 978-1848001909. 2. Chollet, F. Deep learning with Python. Manning, 2017. ISBN 978-1617294433. 3. Howse, Joseph; Minichino, Joe. Learning OpenCV 4 Computer Vision with Python 3. 3rd ed. Birmingham: Packt Publishing, 2020. ISBN 978-1789531619.

Additional study materials

Study supports in the EduDocs system

Way of continuous check of knowledge in the course of semester

Conditions for granting the credit: The tasks that form the program of exercises must be worked out. Exam - oral examination.

E-learning

Materials are available on the educator's website: https://mrl.cs.vsb.cz//people/fusek/ano2_course.html

Other requirements

No further requirements are imposed on student.

Prerequisities

Subject code	Abbreviation	Title	Requirement
460-4080	AO1	Image Analysis I	Recommended

Co-requisities

Subject has no co-requisities.

Subject syllabus:

Lectures: - Basic concepts of object detection in images; Haar-like features (AdaBoost, Viola-Jones); Local Binary Patterns (LBP); Histograms of Oriented Gradients (HOG). Methods for pedestrian detection in images; methods for face detection in images. Keypoint detectors and descriptors (e.g. SIFT, SURF). - Convolutional neural networks (basic principles, description of layers). Modern variants of convolutional neural networks (e.g. GoogLeNet, ResNet, EfficientNet). - Description of convolutional networks for object localization (e.g. R-CNN, Faster R-CNN, YOLO, SSD). - Description of generative networks (e.g. DCGAN, Diffusion-GAN). - Transformer networks (especially Vision Transformer - ViT) and their use in image analysis. - Convolutional neural networks for image segmentation (encoder-decoder networks, U-Net). - Human pose estimation using deep learning. - Optical systems in the area of self-driving vehicles, IR image processing, LiDAR data processing, depth image analysis, use of depth sensors (RealSense, Kinect). Computer Labs: - Development of the detector for the selected object of interest, implementation of the sliding window method, preparation of data for the training and testing phases of the detector. - Object analysis using Haar-like features, Local Binary Patterns (LBP), and Histograms of Oriented Gradients (HOG). - Experiments with convolutional neural networks, exploring the parameters of convolutional networks. - Application of different types of convolutional networks (e.g. GoogLeNet, ResNet, EfficientNet), comparison of detectors. - Practical use of localization methods based on convolutional neural networks (e.g. R-CNN, Faster R-CNN, YOLO). - Practical use of generative networks for data augmentation (DCGAN, Diffusion-GAN). - Experiments with image segmentation using encoder-decoder networks (U-Net). - Practical use of transformer networks for object analysis in images. - Analysis of objects in IR and depth images (RealSense, Kinect).

Conditions for subject completion

Part-time form (validity from: 2015/2016 Winter semester, validity until: 2021/2022 Winter semester)

Task name	Type of task	Max. number of points (act. for subtasks)	Min. number of points	Max. počet pokusů
Credit and Examination	Credit and Examination	100 (100)	51
Credit	Credit	45	20
Examination	Examination	55	6	3

Valid from	Valid until	Mandatory attendence participation
Jun 20, 2022 11:41:12 AM	Jun 20, 2022 5:10:49 PM	xxx

Mandatory attendence participation: The tasks that form the program of exercises must be completed.

Show history

Conditions for subject completion and attendance at the exercises within ISP:

Show history

Occurrence in study plans

Academic year	Programme	Branch/spec.	Zaměření	Form	Study language	Tut. centre	Year	Type of duty
2026/2027	(N0613A140034) Computer Science		DZO	K	Czech	Ostrava	2	Choice-compulsory type A	study plan
2026/2027	(N0613A140034) Computer Science		DZO	P	Czech	Ostrava	2	Choice-compulsory type A	study plan
2026/2027	(N0613A140034) Computer Science		PGV	P	Czech	Ostrava	2	Choice-compulsory type B	study plan
2026/2027	(N0613A140034) Computer Science		UI	P	Czech	Ostrava	2	Choice-compulsory type B	study plan
2026/2027	(N0541A170007) Computational and Applied Mathematics	(S02) Computational Methods and HPC		K	Czech	Ostrava	2	Optional	study plan
2026/2027	(N0541A170007) Computational and Applied Mathematics	(S01) Applied Mathematics		P	Czech	Ostrava	2	Optional	study plan
2026/2027	(N0541A170007) Computational and Applied Mathematics	(S01) Applied Mathematics		K	Czech	Ostrava	2	Optional	study plan
2026/2027	(N0541A170007) Computational and Applied Mathematics	(S02) Computational Methods and HPC		P	Czech	Ostrava	2	Optional	study plan
2025/2026	(N0688A140014) Industry 4.0			P	Czech	Ostrava	2	Choice-compulsory type B	study plan
2025/2026	(N0613A140034) Computer Science		DZO	P	Czech	Ostrava	2	Choice-compulsory type A	study plan
2025/2026	(N0613A140034) Computer Science		DZO	K	Czech	Ostrava	2	Choice-compulsory type A	study plan
2025/2026	(N0716A060001) Automotive Electronic Systems		SPA	P	Czech	Ostrava	2	Compulsory	study plan
2025/2026	(N0541A170007) Computational and Applied Mathematics	(S01) Applied Mathematics		P	Czech	Ostrava	2	Optional	study plan
2025/2026	(N0541A170007) Computational and Applied Mathematics	(S01) Applied Mathematics		K	Czech	Ostrava	2	Optional	study plan
2025/2026	(N0541A170007) Computational and Applied Mathematics	(S02) Computational Methods and HPC		P	Czech	Ostrava	2	Optional	study plan
2025/2026	(N0541A170007) Computational and Applied Mathematics	(S02) Computational Methods and HPC		K	Czech	Ostrava	2	Optional	study plan
2024/2025	(N0613A140034) Computer Science		DZO	P	Czech	Ostrava	2	Choice-compulsory type A	study plan
2024/2025	(N0613A140034) Computer Science		DZO	K	Czech	Ostrava	2	Choice-compulsory type A	study plan
2024/2025	(N0688A140014) Industry 4.0			P	Czech	Ostrava	2	Choice-compulsory type B	study plan
2024/2025	(N0716A060001) Automotive Electronic Systems		SPA	P	Czech	Ostrava	2	Compulsory	study plan
2024/2025	(N0541A170007) Computational and Applied Mathematics	(S01) Applied Mathematics		K	Czech	Ostrava	2	Optional	study plan
2024/2025	(N0541A170007) Computational and Applied Mathematics	(S01) Applied Mathematics		P	Czech	Ostrava	2	Optional	study plan
2024/2025	(N0541A170007) Computational and Applied Mathematics	(S02) Computational Methods and HPC		P	Czech	Ostrava	2	Optional	study plan
2024/2025	(N0541A170007) Computational and Applied Mathematics	(S02) Computational Methods and HPC		K	Czech	Ostrava	2	Optional	study plan
2023/2024	(N0688A140014) Industry 4.0			P	Czech	Ostrava	2	Choice-compulsory type B	study plan
2023/2024	(N0613A140034) Computer Science		DZO	K	Czech	Ostrava	2	Choice-compulsory type A	study plan
2023/2024	(N0613A140034) Computer Science		DZO	P	Czech	Ostrava	2	Choice-compulsory type A	study plan
2023/2024	(N0716A060001) Automotive Electronic Systems		SPA	P	Czech	Ostrava	2	Compulsory	study plan
2023/2024	(N0541A170007) Computational and Applied Mathematics	(S01) Applied Mathematics		P	Czech	Ostrava	2	Optional	study plan
2023/2024	(N0541A170007) Computational and Applied Mathematics	(S01) Applied Mathematics		K	Czech	Ostrava	2	Optional	study plan
2023/2024	(N0541A170007) Computational and Applied Mathematics	(S02) Computational Methods and HPC		P	Czech	Ostrava	2	Optional	study plan
2023/2024	(N0541A170007) Computational and Applied Mathematics	(S02) Computational Methods and HPC		K	Czech	Ostrava	2	Optional	study plan
2023/2024	(N2647) Information and Communication Technology	(2612T025) Computer Science and Technology		P	Czech	Ostrava	2	Choice-compulsory	study plan
2023/2024	(N2647) Information and Communication Technology	(2612T025) Computer Science and Technology		K	Czech	Ostrava	2	Choice-compulsory	study plan
2022/2023	(N0613A140034) Computer Science		DZO	K	Czech	Ostrava	2	Choice-compulsory type A	study plan
2022/2023	(N0613A140034) Computer Science		DZO	P	Czech	Ostrava	2	Choice-compulsory type A	study plan
2022/2023	(N0688A140014) Industry 4.0			P	Czech	Ostrava	2	Choice-compulsory type B	study plan
2022/2023	(N0541A170007) Computational and Applied Mathematics	(S01) Applied Mathematics		K	Czech	Ostrava	2	Optional	study plan
2022/2023	(N0541A170007) Computational and Applied Mathematics	(S01) Applied Mathematics		P	Czech	Ostrava	2	Optional	study plan
2022/2023	(N0541A170007) Computational and Applied Mathematics	(S02) Computational Methods and HPC		K	Czech	Ostrava	2	Optional	study plan
2022/2023	(N0541A170007) Computational and Applied Mathematics	(S02) Computational Methods and HPC		P	Czech	Ostrava	2	Optional	study plan
2022/2023	(N2647) Information and Communication Technology	(2612T025) Computer Science and Technology		P	Czech	Ostrava	2	Choice-compulsory	study plan
2022/2023	(N2647) Information and Communication Technology	(2612T025) Computer Science and Technology		K	Czech	Ostrava	2	Choice-compulsory	study plan
2021/2022	(N0688A140014) Industry 4.0			P	Czech	Ostrava	2	Choice-compulsory type B	study plan
2021/2022	(N0541A170007) Computational and Applied Mathematics	(S01) Applied Mathematics		P	Czech	Ostrava	2	Optional	study plan
2021/2022	(N0541A170007) Computational and Applied Mathematics	(S02) Computational Methods and HPC		K	Czech	Ostrava	2	Optional	study plan
2021/2022	(N0541A170007) Computational and Applied Mathematics	(S02) Computational Methods and HPC		P	Czech	Ostrava	2	Optional	study plan
2021/2022	(N0541A170007) Computational and Applied Mathematics	(S01) Applied Mathematics		K	Czech	Ostrava	2	Optional	study plan
2021/2022	(N2647) Information and Communication Technology	(2612T025) Computer Science and Technology		P	Czech	Ostrava	2	Choice-compulsory	study plan
2021/2022	(N2647) Information and Communication Technology	(2612T025) Computer Science and Technology		K	Czech	Ostrava	2	Choice-compulsory	study plan
2020/2021	(N0688A140014) Industry 4.0			P	Czech	Ostrava	2	Choice-compulsory type B	study plan
2020/2021	(N2647) Information and Communication Technology	(2612T025) Computer Science and Technology		P	Czech	Ostrava	2	Choice-compulsory	study plan
2020/2021	(N2647) Information and Communication Technology	(2612T025) Computer Science and Technology		K	Czech	Ostrava	2	Choice-compulsory	study plan
2020/2021	(N0541A170007) Computational and Applied Mathematics	(S01) Applied Mathematics		K	Czech	Ostrava	2	Optional	study plan
2020/2021	(N0541A170007) Computational and Applied Mathematics	(S02) Computational Methods and HPC		P	Czech	Ostrava	2	Optional	study plan
2020/2021	(N0541A170007) Computational and Applied Mathematics	(S01) Applied Mathematics		P	Czech	Ostrava	2	Optional	study plan
2020/2021	(N0541A170007) Computational and Applied Mathematics	(S02) Computational Methods and HPC		K	Czech	Ostrava	2	Optional	study plan
2019/2020	(N2647) Information and Communication Technology	(2612T025) Computer Science and Technology		P	Czech	Ostrava	2	Choice-compulsory	study plan
2019/2020	(N2647) Information and Communication Technology	(2612T025) Computer Science and Technology		K	Czech	Ostrava	2	Choice-compulsory	study plan
2019/2020	(N0541A170007) Computational and Applied Mathematics	(S01) Applied Mathematics		P	Czech	Ostrava	2	Optional	study plan
2019/2020	(N0541A170007) Computational and Applied Mathematics	(S02) Computational Methods and HPC		P	Czech	Ostrava	2	Optional	study plan
2019/2020	(N0541A170007) Computational and Applied Mathematics	(S01) Applied Mathematics		K	Czech	Ostrava	2	Optional	study plan
2019/2020	(N0541A170007) Computational and Applied Mathematics	(S02) Computational Methods and HPC		K	Czech	Ostrava	2	Optional	study plan
2019/2020	(N0688A140014) Industry 4.0			P	Czech	Ostrava	2	Choice-compulsory type B	study plan
2018/2019	(N2647) Information and Communication Technology	(2612T025) Computer Science and Technology		P	Czech	Ostrava	2	Choice-compulsory	study plan
2018/2019	(N2647) Information and Communication Technology	(2612T025) Computer Science and Technology		K	Czech	Ostrava	2	Choice-compulsory	study plan
2017/2018	(N2647) Information and Communication Technology	(2612T025) Computer Science and Technology		P	Czech	Ostrava	2	Choice-compulsory	study plan
2017/2018	(N2647) Information and Communication Technology	(2612T025) Computer Science and Technology		K	Czech	Ostrava	2	Choice-compulsory	study plan
2016/2017	(N2647) Information and Communication Technology	(2612T025) Computer Science and Technology		P	Czech	Ostrava	2	Choice-compulsory	study plan
2016/2017	(N2647) Information and Communication Technology	(2612T025) Computer Science and Technology		K	Czech	Ostrava	2	Choice-compulsory	study plan
2015/2016	(N2647) Information and Communication Technology	(2612T025) Computer Science and Technology		P	Czech	Ostrava	2	Choice-compulsory	study plan
2015/2016	(N2647) Information and Communication Technology	(2612T025) Computer Science and Technology		K	Czech	Ostrava	2	Choice-compulsory	study plan

Occurrence in special blocks

Block name	Academic year	Form of study	Study language	Year	W	S	Type of block	Block owner

Assessment of instruction