Action Recognition in Video using Deep Learning
A two-stream convolutional network that recognises human actions in video by combining appearance (RGB frames) with motion (optical flow).
Things I’ve built outside my day job — research, systems programming and coursework I’m proud of.
A two-stream convolutional network that recognises human actions in video by combining appearance (RGB frames) with motion (optical flow).
A Unix-style shell written from scratch in C, with built-in commands and separately compiled external commands.
A Django banking application for transactions and account management, built security-first with session middleware, 2FA and DoS prevention.
Solving the N-Puzzle with AI search algorithms accelerated on the GPU with CUDA.
A multi-agent AI system for planning effective pesticide use.
Compares classifiers (SVM, random forest, logistic regression, CNN) across feature-extraction techniques for hand-gesture recognition.
Operating-systems work on the Linux Completely Fair Scheduler, written in C.