SubjectsSubjects(version: 875)
Course, academic year 2020/2021
3D Computer Vision - NPGR001
Title: 3D počítačové vidění
Guaranteed by: Department of Software and Computer Science Education (32-KSVI)
Faculty: Faculty of Mathematics and Physics
Actual: from 2019
Semester: winter
E-Credits: 5
Hours per week, examination: winter s.:2/2 Ex [hours/week]
Capacity: unlimited
Min. number of students: unlimited
State of the course: taught
Language: Czech, English
Teaching methods: full-time
Additional information:
Guarantor: prof. Ing. Václav Hlaváč, CSc.
Class: Informatika Bc.
Informatika Mgr. - volitelný
Classification: Informatics > Computer Graphics and Geometry
Annotation -
Last update: doc. RNDr. Pavel Töpfer, CSc. (23.01.2019)
The subject introduces methods of 3D computer vision. First, in three lectures, we summarize the necessary concepts of digital image processing / analysis. We follow with the description of one (intensity, RGB) camera and related geometry. We will learn how to use two or more cameras to determine the depth in the scene and for 3D reconstruction. We will add further depth sensory modalities, namely lidars, radars, sonars. We will explain how to combine information from a variety of sensors. We will practically illustrate the methods in the tasks associated with self-driving cars.
Course completion requirements -
Last update: prof. Ing. Václav Hlaváč, CSc. (24.05.2019)

Credit from exercises. Oral exam. Preparation time as needed. Programming is not a part of the exam.

Literature -
Last update: doc. RNDr. Pavel Töpfer, CSc. (21.01.2019)

Šonka M., Hlaváč V., Boyle R.: Image Processing, Analysis and Machine vision, 4th edition, Cengage Learning, Inc , 2015. Asi deset kopií je k dispozici v knihovně Centra strojového vnímání, katedry kybernetiky FEL.

Szeliski R.: Computer Vision: Algorithms and Application, Springer, Berlin, 2010. 812 p. The book draft is freely available for download

Hartley R., Zisserman A: Multiple View Geometry in Computer Vision, Second edition, Cambridge University Press, March 2004. The downloadable draft.

Syllabus -
Last update: doc. RNDr. Pavel Töpfer, CSc. (23.01.2019)

1. Overview of digital image processing (digital image properties, intensity and geometry transformations, pre-processing, edge detection and interest points / areas).

2. Objects in the image, necessity of interpretation, segmentation of objects.

3. 3D computer vision, goals and applications, overview of the subject. Practical optics. Radial distortion.

4. Camera, projection matrix and its decomposition.

5. Geometry for describing a solid body in 3D. Projective transformation.

6. Geometry of one perspective camera. One camera calibration.

7. Geometry of two cameras, epipolar restriction, fundamental matrix. Geometry of multiple cameras.

8. Essential matrix and its decomposition. 7-point algorithm for estimating the fundamental matrix, 5-point algorithm for estimating the essential matrix.

9. The correspondence problem and its solution.

10. Reconstruction of 3D scene from several views. Shape from motion.

11. Other algorithms for 3D reconstruction, Random Sampling Optimization (RANSAC), Bundle Adjustment.

12. Depth sensors (lidar, radar, sonar, structured light cameras)

13. Merging information from different depth sensors.

14. Practical application in a self-driving car.

Charles University | Information system of Charles University |