The objective of the learning modules is to explore some concept relative to computer vision that will not be covered in class. The area of computer vision is huge, and there is no way to cover it all in one semester. Given that these topics may not be fully covered in class, though individual aspects of some of them might be, it is important to pick a topic that you are interested in. The bulk of the learning will be done by you through the exploration of the topic, the generation of code, and its execution on standard data sets (or typical deployments) within computer vision.

The different learning modules are:

1. Image-Based Classification
2. Object Recognition
3. Object Detection
4. Surveillance w/Static Camera
5. Object/Target Tracking
6. Point Cloud Processing
7. HCI / Gesture Control
8. Autonomous Navigation/Vehicles
9. Action Recognition
10. Augmented Reality/Virtual Reality
11. Simultaneous Localization and Mapping

Because this is a less controlled set of activities, please make sure to submit visually communicative results and otherwise make an effort to effectively communicate the activities performed and their outcomes. The ones with strikeout are not available.

Main