Course contents
The course consists of two main parts.
- The goal of the first part is to give a brief introduction of deep learning (DL) and then turning to introduce most popular DL architectures for main computer vision tasks: image classification, object localization, object detection, semantic segmentation and instance segmentation.
- The second part gives an overview of sensor fusion techniques and modern sensors such as camera, radar and Lidar in the field of computer vision. Introduction to main DL-based techniques for image fusion, multi-source fusion and depth image prediction. Application of multi-senor fusion in autonomous driving and target recognition will be discussed.
Learning outcomes
Attendees of this course will leave with a good sense of how deep learning can be used for a range of computer vision tasks and sensor fusion technology. In addition to the theoretical content, students get familiar with various functionalities of DL tools to design, train and debug neural networks in practice on real computer vision tasks and data.
Teaching methods
The course offers a completely free schedule as the recorded lectures can be accessed through the Moodle course page. There is an online session after each two lectures for questions and assignments.
Completion methods
The course evaluation is based on taking the exam and delivering projects.
As a prerequisite, basics of probability, statistics and Python programming are advised.
More information in the University of Turku study guide.
You can get a digital badge after completing this course.