SylabUZ
Course name | Computer vision systems |
Course ID | 11.9-WE-AutP-CVS-Er |
Faculty | Faculty of Computer Science, Electrical Engineering and Automatics |
Field of study | WIEiA - oferta ERASMUS / Automatic Control and Robotics |
Education profile | - |
Level of studies | First-cycle Erasmus programme |
Beginning semester | winter term 2018/2019 |
Semester | 6 |
ECTS credits to win | 3 |
Course type | optional |
Teaching language | english |
Author of syllabus |
|
The class form | Hours per semester (full-time) | Hours per week (full-time) | Hours per semester (part-time) | Hours per week (part-time) | Form of assignment |
Lecture | 15 | 1 | - | - | Credit with grade |
Laboratory | 30 | 2 | - | - | Credit with grade |
· Familiarize students with the successive stages of the vision system (from the acquisition process to the result of the classification algorithm)
· Develop the ability to use the vision system, configure its basic parameters and use information from the system in the robot control.
Basics of Robotics, Digital Signal Processing, Decision Supporting Systems
Characteristics and architecture of the video system. Camera Configurations: "Eye in the hand" and "Eye off the hand". Basic parameters of the vision system. Potential applications. Challenges and problems. Integration of the vision system with executive devices (robots). Standard tasks (pick and place, quality control, etc).
Optics: lens construction, lens parameters: focal length, brightness, abberations, distortion, vignetting. Focusing methods. Depth of field.
Acquisition of images. Range of visible light, infrared and ultraviolet bands. Photosensitivity. Parameters of sensors (resolution, dimensions
and proportions). CMOS, CCD and others sensors. RGGB filters (Beyer mesh). ISO sensitivity. Exposition.
Backlighting systems: "backlight", "light-field", "diffuse-light" (axial diffuse-light). Operating modes: continuous and triggered.
Image transmition standards and protocols.
Digital representation of the image. Image file formats: RAW, TIF and JPEG. Lossy and lossless representation. Color models: RGB, CMYK, HSV, xyz and others. Conversions between color models.
Image processing. Histogram operations (normalization, alignment, stretching). Noncontext operations: arithmetic, non-linear (gamma correction). Contextual operations (filtration): lowpass filters (averaging, smoothing), high pass (sharpening, directional, detecting edges), median filter.
Morphological operations. Erosion and dilation. Closing and opening. Hit Or Miss, Top-Hat, Bottom-Hat operations. Edge extraction. Skeletonization. Morphological operations for images in shades of gray.
Methods of object segmentation. Recall. Otsu algorithm.
Basics of extraction and selection of features of objects. Basic pattern recognition methods. Template matching method.
Calibration of the camera. Location and orientation of the camera in the robot base layout.
Control of the industrial manipulator using information from the video system.
Lecture: conventional lecture, discussion
Laboratory: laboratory exercises
Outcome description | Outcome symbols | Methods of verification | The class form |
Lecture - obtaining a positive grade in written tests.
Laboratory - the main condition to get a pass is sufficient marks for all laboratory exercises conducted during the semester.
Calculation of the final grade: = lecture 50% + laboratory 50%
1. P. I. Corke, Robotics, Vision and Control Fundamental Algorithms in MATLAB, Springer, 2019, www.petercorke.com (available online)
2. P. I. Corke, VISUAL CONTROL OF ROBOTS: High-Performance Visual Servoing,
3. B. K. P. Horn, Robot Vision, MIT Press, McGraw–Hill, 1986
4. R. C. Gonzales, P. Wintz, Digital Image Processing, Addison–Wesley, London, 1977.
1. E.R. Davies, Machine Vision, Elsevier, 2005
2. D. H. Ballard, C. M. Brown, Computer Vision, Prentice–Hall, New York, 1982.
Modified by dr hab. inż. Wojciech Paszke, prof. UZ (last modification: 02-05-2020 14:50)