Ви переглядаєте архівну версію офіційного сайту НУЛП (2005-2020р.р.). Актуальна версія: https://lpnu.ua

Methods of Computer Vision in Intelligent Robotic Systems

Major: Software engineering
Code of Subject: 8.121.00.M.23
Credits: 4
Department: Publishing Information Technologies
Lecturer: Professor, Dr.Sc. Melnyk Roman Andriyovych
Semester: 3 семестр
Mode of Study: денна
Learning outcomes:
Knowledge:
- ability to demonstrate scientific methods of artificial intelligence that allows computers to analyze and understand an image;
- ability to demonstrate knowledge of a class of algorithms called the Convolution Neural Network.
- ability to create Computer Vision Applications: Automatic inspection (image-based automated inspection), e.g., in manufacturing applications, Assisting humans in identification tasks (to identify object/species using their properties), e.g., a species identification system, Controlling processes (in a way of monitoring robots), Detecting events, e.g., for visual surveillance or people counting, Modelling objects or environments, medical image analysis or topographical modelling, Navigation or mobile robot
- ability to demonstrate knowledge of Image Classification and Segmentation : semantic segmentation., instance segmentation
- to apply the mathematical theory of computer vision methods to determine the reliability of software systems based on experimental data;
- to analyze and investigate the Computer Vision Models, Learning, and Inference;
- to analyze the image, which may be an object, a text description, a three-dimensional model, and so on
Required prior and related subjects:
- Prerequisites: Artificial intelligence systems
- co-requisites: Intelligent data mining
Summary of the subject:
Optical character recognition (OCR). Machine inspection. Retail (e.g. automated checkouts).3D model building (photogrammetry). Medical imaging. Automotive safety. Match move (e.g. merging CGI with live actors in movies). Motion capture. Surveillance. Fingerprint recognition and biometrics. Object Classification: Object Identification: Object Verification: Object Detection: Object Landmark Detection: Object Segmentation: Object Recognition: Classic approaches and machine learning approaches. Deep neural networks. Network architectures Local and global networks. Feature size. Preparing data. Training parameters. Troubleshooting.
Recommended Books:
• Computer Vision: Algorithms and Applications (Texts in Computer Science) , 2011, by Richard Szeliski
Computer Vision: Models, Learning, and Inference Simon J. D. Prince
• Computer Vision: A Modern Approach , 2nd Edition,
by David A. Forsyth , Jean Ponce
• Д.Д. Пелешко та інші. Аналіз та обробка потоків даних засобами обчислювального інтелекту. “ЛП”.
• Р.О. Ткаченко та інші. Нейромережеві засоби штучного інтелекту “ЛП”.
• Roman Melnyk, Arsenii Zawyalow, Image Retrieval by Statistical Features and Artificial Neural Networks TCSET-2017.
Assessment methods and criteria:
- Current control (40%): written reports on laboratory work, completion of individual research assignment, oral examination
- Final control (60%, exam): testing (60%)