You will work on a project until the end of semester. You must either choose one of the following topics or propose another topic of your interest related to your thesis by April 16. Please email me my with the topic you have chosen and the team members (maximum two members per team). If you would like to do something different, send me an email and we can talk about it.
- Automated color correction
- Print a color checker and use it to automatically correct color images. The idea is to use machine learning techniques to estimate the transformation.
- Human pose estimation using IMU data
- Use the IMU data from your mobile phone and propose a processing pipeline for estimating your pose. You can start simple, by processing accelerometer data and classifying two or three poses.
- Detect a faulty sensor
- Considering a sensor network, you will simulate a faulty sensor within the network and propose a processing pipeline to identify it.
The general requirement is that you implement the code at least with a simulated object, but best if you acquire images or signals in a controlled environment. You may reuse code from other sources, but cite them properly. Your final report should be between 6 - 8 pages using the IEEE template.
The following is a suggested structure for the report:
- Title, Author(s)
- Abstract: It should not be more than 300 words
- Introduction: this section introduces your problem, and the overall plan for approaching your problem
- Background/Related Work: This section discusses relevant literature for your project
- Approach: This section details the framework of your project. Be specific, which means you might want to include equations, figures, plots, etc
- Experiment: This section begins with what kind of experiments you’re doing, what kind of dataset(s) you’re using, and what is the way you measure or evaluate your results. It then shows in details the results of your experiments. By details, we mean both quantitative evaluations (show numbers, figures, tables, etc) as well as qualitative results (show images, example results, etc).
- Conclusion: What have you learned? Suggest future ideas.
- References: This is absolutely necessary.
IEEE paper template at overleaf.