Computer Vision (in English)

• 26 hrs lectures
• 26 hrs projects

• 51 pts final exam (26 pts written part, 25 pts test part)
• 9 pts mid-term test (3 pts written part, 6 pts test part)
• 40 pts projects

Students will gain a comprehensive overview of the principles and methods of computer vision, ranging from geometric approaches to current methods based on neural networks. They will understand the process of scene capture, camera calibration and the reconstruction of 3D information, and will apply this knowledge in practice in an individual homework assignment. They will become familiar with representations of image data and with modern approaches to object detection and recognition. In a practical assignment, they will build their own dataset and train their own object detector. They will further apply the acquired knowledge in a team project on a selected topic. At the same time, they will improve their skills in working with image processing and machine learning tools in Python, in data preparation and annotation, and in the evaluation of experimental results.

• Szeliski, R.: Computer Vision: Algorithms and Applications, 2nd edition, Springer, 2022, ISBN 978-3-030-34371-2

• Torralba, A., Isola, P., Freeman, W.T.: Foundations of Computer Vision, The MIT Press, 2024, ISBN 978-0-262-04897-2 

• Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision, 2nd edition, Cambridge University Press, 2004, ISBN 978-0-521-54051-3

• Prince, S.J.D.: Understanding Deep Learning, The MIT Press, 2023, ISBN 978-0-262-04864-4

1. Introduction, motivation and applications/Úvod, základy, motivace a aplikace (Zermčík 15.9.)
2. Scanning object detection, boosted classifiers, acceleration/Detekce objektů oknem, boostované klasifikátory, akcelerace (Zemčík 22.9.)
3. Statistical Pattern Recognition, Bayesian Clasifier and GMM/Statistické rozpoznávání, Bayesovský klasifikátor a GMM (Španěl 29.9.)
4. Clustering and Image Segmentation / Shlukování a segmentace obrazu (Španěl 6.10. slajdy1, slajdy2, slajdy3)
5. Object Detection - Trees, Random Forests, Yolo/Detekce objektů - Stromy, "Random Forests",Yolo (Juránek, 13.10. slajdy-en)
6. Convolutional Neural Networks and Automatic Image Tagging/Konvoluční neuronové sítě a tagování obrazu (Hradiš, 20.10. slajdy)
7. Hough Transform, RHT, RANSAC, Sequence Processing/Houghova transformace, RHT, RANSAC, zpracování sekvencí (Hradiš, 27.10. slajdy1, slajdy2, slajdy2-en)
8. 3D Computer Vision/3D počítačové vidění (3.11. Šolony)
9. Test, Stereovision, SLAM/Stereoviděni, SLAM (10.11. Šolony)
10. Analysis and Feature Extraction from Images/Analýza a extrakce příznaků z textur (Čadík 24.11. slajdy)
11. Image Registration/Registrace obrazu (Čadík, 1.12. slajdy)
12. Invariant Image Regions/Invariantní oblasti obrazu, conclusions (Beran, 8.12. slajdy, Zemčík)

NOTE: The topics and dates are just FYI, not guaranteed, and will be continuously updated.

The project work in the course consists of two parts:

1. (10 pts) Two individual homework assignments. In the first half of the semester, students calibrate a camera and project a 3D animation into real video (augmented reality). In the second half of the semester, they create their own dataset and train their own object detector.
2. (30 pts) A team project for 2–3 students on selected topics. After consultation, students may propose a topic of their own. The results will be presented during a poster session at the end of the semester. Projects from past years can be seen here: https://www.fit.vut.cz/person/ikostelnik/public/knn-pova-projects/.

Two home assignments, mid-term test and individual project.