Create Your First Project
Start adding your projects to your portfolio. Click on "Manage Projects" to get started
Video-based Productivity Detection using Human Activity Analysis
Project type
Artificial Intelligence (AI), Deep Learning, Computer Vision
Language
Python
🦄 This is my FYP. A system named PDHAA is developed by utilizing deep learning algorithms and computer vision to analyze video footage of human activities in coffee shops and then classify the human actions, with the goal of detecting human productivity levels based on action analysis. It achieved an 93% accuracy through a dataset of 7,320 samples.
🦄 This system helps employers gain an understanding of their employees’ productivity based on a data-driven productivity assessment (objective) rather than human feelings (subjective). It has the potential to revolutionize productivity assessment by replacing subjective human judgments—such as manual observations, surveys, or self-reports—with precise, data-driven insights.
Tech Stack:
- Python, OpenCV, Mediapipe, Tensorflow
- Data collection and preprocessing, Feature engineering and extraction, Model development
- Deep learning, Convolutional Neural Network (CNN), Long Short Term Memory (LSTM)
Credit to Dr. Mohamad Sabri bin Sinal @ Zainal as my FYP supervisor
