Research Article
A Machine Learning Framework for Large-Scale Behavioral Monitoring to Assess Thermotolerance in Dairy Cows
Volume 14 · Pages 326–342
PublishedOpen paper
Daniel Ogbuigwe
I love learning
Featured computer vision buildSAM3 basketball tracking
Featured Work
The projects I'd show you first — with the footage to prove they exist.
Basketball Shot Counting with YOLOv12 and SAM3
2026 · Personal computer vision experiment
A two-stage video analysis pipeline that uses a compact YOLOv12 detector to prompt SAM3, then converts stable segmentation masks into made- and missed-shot counts. The project demonstrates the practical accuracy and compute tradeoff between lightweight detection and GPU-assisted foundation-model tracking.
View project →
Assessing Dairy Cow Thermotolerance Through Behavioral Monitoring
2025 · Prairie View A&M University
A machine learning and computer vision framework for evaluating thermotolerance-related behavior in a commercial dairy herd by quantifying how frequently individual cows used water troughs and mechanical brushes during the summer study period. Published in IEEE Access.
View project →
Knowing Every Hen: Multi-Camera Poultry Monitoring
2025–present · Prairie View A&M University
NSF-funded research at PVAMU: two synchronized cameras, homography fusion and color re-identification track individual laying hens through their day — feeding, drinking, laying — to catch problems like bumblefoot before a human would.
View project →
Building an FDM 3D Printer
2021 · B.Eng thesis, Baze University
My mechanical engineering thesis at Baze University: design and construction of a working fused-deposition-modelling 3D printer — assembled, calibrated and commissioned by hand, then put to work printing a miniature engine block.
View project →
Waste Wiz
Hackathon build
A hackathon sprint with four teammates that ended with medals around our necks — Waste Wiz, our take on smarter waste handling, built in one caffeinated weekend.
View project →Selected research
Publications
Open the paper directly from its publication preview.
A little history
About
I’m a graduate researcher in Computer Science at Prairie View A&M University. My work centers on using AI to understand real agricultural environments.
Research
In the lab, I have worked on applications of computer vision and IoT in agriculture, including systems that turn farm video and sensor data into useful behavioral and operational information. My next research direction will be hyperspectral imaging in agriculture. I have not selected a specific topic yet; I’m currently exploring the problems and possibilities in that space.
Engineering
Alongside my research, I work on systems, machine learning, and algorithms. I’m actively learning parallel computing with CUDA, developing my C++ software-engineering skills, and doing embedded-systems work. I also work with data science and data-mining methods when a problem calls for them.
Personal projects
Outside formal research, I enjoy game development. I’m working through the four projects in a Packt C++ game-programming book, building a rendering engine in C and C++, and experimenting with reinforcement learning and Monte Carlo Tree Search through tic-tac-toe and chess. I also model sports highlights through video data mining with YOLO-style models and computer-vision pipelines, and analyze football, basketball, and American-football datasets for my own analytics interests and goals.
Let's Connect
Research collaborations, interesting datasets, engineering roles — or just to talk football and ML. My inbox is open.