At the end of this course, students will be able to:
- Understand formation of images, the types of camera models and the camera parameters.
- Apply different image processing and feature extraction techniques to images to extract low-level meaningful information.
- Understand different mid-level and high-level vision problems such as motion estimation, depth estimation, object recognition, scene understanding and apply them on real-world problems.
- Describe the different vision theories and the link between visual perception and computer vision.
- Gather hands-on experience on implementing contemporary deep learning based approaches for computer vision