Carter S
- Research Program Mentor

PhD candidate at University of Wisconsin - Madison

Expertise

Computer Vision, Robotics, Machine Learning

Bio

I am a Computer Science PhD student at the University of Wisconsin - Madison. I am interested in computer vision and robot sensing; my current research focuses on attaching novel vision-based sensors to robots, and interpreting data from those sensors to respond to the environment. I regularly mentor undergraduate students at UW-Madison on robotics and computer vision projects. Outside of research, I am interested in photography and digital art. I love using computer graphics techniques to generate cool images, and manipulating photographs with code. I also love playing disc golf, as a break from staring at images on a computer screen all day!

Project ideas

Project ideas are meant to help inspire student thinking about their own project. Students are in the driver seat of their research and are free to use any or none of the ideas shared by their mentors.

Super-Resolution Images with a Mobile Phone

Images from a mobile phone look nice at a distance, but if you zoom in, you'll see that they lack the high resolution detail present in images from a dedicated camera. Is it possible to combine the information from multiple mobile phone images of the same object to create one super high resolution image, comparable to one from a dedicated camera? In this computer vision / image processing project, a student could compare multiple approaches for performing such super-resolution, including algorithmically founded approaches from image processing, and approaches based on generative AI models like Stable Diffusion and DALL-E. The results of this project can be written up as a research paper and/or blog post.

Predicting Crop Yields from Weather Data

Given data about an area's temperature, humidity, sunshine, and rainfall, how well can you predict how well a given crop will grow? In this machine learning project, you will leverage freely available datasets to create a machine learning model to predict crop yield from weather data. Such a machine learning model could be used to predict crop shortages, and increase food security in the wake of climate change. The results of this research can be written up as a research paper and/or blog post.