Machine perception and image analysis

Course guarantor:

Václav Hlaváč

Lecturer:

Matouš Cejnek, Václav Hlaváč, Cyril Oswald

Tutor:

Matouš Cejnek, Václav Hlaváč, Kateřina Kobrlová, Cyril Oswald

Supervisor:

Department of Instrumentation and Control Engineering

Synopsis:

We will introduce students to machine perception, a necessary prerequisite for building autonomous robots or machines. The subject prepares students for practically applying methods in the Industry 4.0 direction.

Requirements:

Syllabus of lectures:

Machine perception, observations, percepts, and their interpretation. Role of the context and semantics.

Digital image. Image acquisition, physical viewpoint. Inverse task and unusability.

Image processing. Detection of edge elements.

Image segmentation.

Statistical pattern recognition. Role of learning.

Image object description and their classification using statistical pattern recognition methods.

3D vision, the geometry of one and more cameras. 3D reconstruction.

Image acquisition hardware, depth maps, smart cameras.

Computer vision applied in industry. Examples.

Autonomous robots. World representation, its creation, updates based on perception.

Planning in autonomous robotics.

Tactile feedback in robotics.

Use of tactile and visual feedback in manipulation tasks.

Cooperation of humans and robots in industry.

Syllabus of tutorials:

Study Objective:

The aim of the course is to introduce students to methods of image processing, analysis and perception for robots. The course will teach students how images are processed and analyzed by a computer. We will explain methods of digital image processing when we do not have semantic knowledge of the image content. We will also study image analysis procedures, when we can segment objects from the background, describe their features and recognize them according to semantics. We will build on the student's knowledge of mathematical analysis, linear algebra and signal theory.

Study materials:

M. Sonka, V. Hlavac, R. Boyle, Image processing, analysis, and machine vision, Fourth edition. Stamford, CT, USA: Cengage Learning, 2015.

R. Szeliski, Computer vision: algorithms and applications. London; New York: Springer, 2011.

Fahimi, F.: Autonomous Robots: Modeling, Path Planning, and Control, Springer 2009

Note:

Further information:

http://people.ciirc.cvut.cz/~hlavac/teaching/FS-StrojVnimAO/

Time-table for winter semester 2025/2026:

	06:00–08:0008:00–10:0010:00–12:0012:00–14:0014:00–16:0016:00–18:0018:00–20:0020:00–22:0022:00–24:00
Mon	roomT4:A1-405a Cejnek M. Kobrlová K. 09:00–10:30 (parallel nr.1) Dejvice roomJP:B-633 Hlaváč V. Cejnek M. 12:30–14:00 (lecture parallel1) Jugoslávských partyzánů 3
Tue
Wed
Thu
Fri

Time-table for summer semester 2025/2026:

Time-table is not available yet

The course is a part of the following study plans: