Computer vision

Course goals

• understands the motivation and goal of computer vision, including its applications and general challenges.
• understands the mechanisms of image formation in terms of geometry and radiometry.
• understands and is able to construct 3D voxel data from images or videos based on silhouettes.
• understands and is able to cluster data points based on various distance measures.
• understands the concepts of image features and their importance in computer vision.
• understands the challenges of image image classification and object detection.
• understands and is able to express the performance of classification and detection algorithms.
• understands and is able to develop a training and evaluation experiment to train and test computational models.
• understands the components and the learning mechanism of convolutional neural networks (CNN).
• understands the training of CNNs, and is able to develop and evaluate CNNs for image and video classification tasks.
• understands the concepts and components of vision transformers.

Assessment

• final exam (40% of the final mark)
• programming assignments, in pairs (60%)

To qualify for a repair of the final result the mark needs to be at least a 4, or “AANV”. There is no re-take for the assignments.

Content

This course is about the algorithms and mechanisms to extract and classify information from images and video.
The course combines theory and practice, with two themes: multi-view reconstruction and CNN image/video classification.

Course form
Lectures, tutorials, practicals.