====== TTK37 Visual Analytics and Automation ======

===== Computer Vision and AI for Multi-Disciplinary Applications in Aquaculture and Industry =====

\\
**Study points:** 3.75\\

**Instructor:** NN

===== Motivation =====
The integration of computer vision and artificial intelligence (AI) is changing the industry by enabling automated, data-driven decision-making. In aquaculture, these technologies allow monitoring of fish health, behavior, and environmental conditions, helping farms become more sustainable and efficient. This course provides a practical exploration along with theoretical aspects of visual analytics and automation, focusing on aquaculture but with large transferable knowledge relevant to a broader industry. Students will acquire both theoretical knowledge and hands-on experience, preparing them to address real-world challenges using state-of-the-art technologies.

===== Learning Outcomes =====
By the end of this course, students will:

  * Understand selected practical and theoretical foundations of computer vision, AI, and machine learning, along with their potential for task automation in aquaculture and other industries.

  * Have hands-on experience from computer vision projects specifically aimed at analyzing underwater video footage.

===== Lectures (and Hands-on Activities) =====

Feature Extraction, Object Detection, and Tracking
Fundamental concepts and methods of extracting relevant visual information.

 * Underwater Imaging and Video Analytics \\ -> Imaging challenges underwater and AI approaches to cope with them.

 * Stereo Vision and 3D Reconstruction \\ -> Principles of stereo imaging, depth perception, and practical methods for reconstruction.

 * AI for Underwater Video Analysis \\ -> Applying AI and machine learning techniques to automate analysis of underwater footage.

 * Monitoring Fish Health and Behavior \\ -> Techniques and case studies for assessing fish conditions and welfare using visual analytics.

 * Practical Labs and Projects \\ ->
Hands-on experience using open-source tools and real underwater footage.

(**Note:** Lecture-topics topics may undergo changes as the course content is currently under development.)

===== Prerequisites =====

A background in signal processing or related fields is recommended. Familiarity with programming languages such as C++, Python, or MATLAB is advantageous for engaging with the practical components of the course.