Developing a Deep Learning Model to Automatically Detect Microscale Objects in Images and Videos

Project Overview


Our project will use an object detection algorithm designed for small objects to determine how many cysts are on the roots of soybean plants. We will also create a device to integrate image capturing with the machine learning algorithm. This will increase productivity on farms and production of soybeans by about 15-30%.

Our device will go to farmers to limit the number of unnecessary pesticides used on their plants. It will also go to geneticists and researchers to run tests and find if certain species of soybeans are resistant to the soybean cyst nematodes.

Team Members

Ethan Baranowski

Electrical Engineer, COM S

Ethan is an electrical engineer specializing in computer engineering and artificial intelligence. He hopes to be leader of an impactful team of engineers.


A fun fact is he is a member of the Theta Delta Chi fraternity.

Chris Cannon

Software Engineer

Chris is a senior in software engineering, interested in computer vision and application development.


In his free time, he enjoys playing trombone, reading, and playing video games.

Matthew Kim

Computer Engineer

Matthew is a senior in Computer Engineering major. Currently, he is interested in Deep Learning and wants to learn more about the applications of the AI.


He knows how to play tennis and oboe.

Katie Moretina

Electrical Engineer

Katie is a senior in Electrical Engineering with an interest in control system design.


In her free time, she enjoys cooking, reading, and watching movies.





Design Documents

Design (491) Document
Design (491) Final Presentation
Project (492) Final Report
Project (492) Final Presentation




Lightning Talks

Design Lightning Talk
Project Plan Lightning Talk
Requirements, Constraints, and Engineering Standards Lightning Talk
Testing Lightning Talk




Weekly Reports (491)

Report 1
Report 2
Report 3
Report 4
Report 5
Report 6
Report 7
Report 8
Report 9

Biweekly Reports (492)

Biweekly Report 1 (Fall)
Biweekly Report 2 (Fall)
Biweekly Report 3 (Fall)
Biweekly Report 4 (Fall)
Biweekly Report 5 (Fall)
Biweekly Report 6 (Fall)