Python

Project Overview A smart security framework designed to perform object detection at the edge and centralize analytics. This system minimizes storage overhead by alerting the user only when actionable items (such as persons) are detected. Key Implementation Details Edge Capture: Programmed ESP32-Cam microcontrollers in C++ to capture and stream low-latency MJPEG video streams over a local Wi-Fi connection. Machine Learning Inference: Developed a Python processing backend using a quantized YOLOv5 neural network to analyze incoming video feeds frame-by-frame. Instant Notifications: Integrated the system with the Telegram Bot API to dispatch instant photo captures and telemetry alerts directly to the user’s mobile device. 🔗 GitHub Repository

Project Overview Developed within a team of 6 students, OccuPI is a fully integrated IoT system that tracks room capacity and occupancy, designed for efficient facility management. Key Implementation Details Edge Detection: Programmed Raspberry Pi devices to analyze local camera feeds using YOLO computer vision networks, detecting person coordinates at the edge. Secure Networking: Configured secure MQTT (MQTTS) and HTTPS network protocols to transmit room count telemetry to a central Debian system. Central Storage & Analysis: Engineered a backend to receive inputs, saving them into a PostgreSQL database. Created a responsive web dashboard for administrators to monitor rooms and view historical data. 🔒 Note: This is a collaborative academic project, the source repository is kept private.

Project Overview Developed in collaboration with an academic team of 4 classmates, this project provides a full-stack dashboard built to collect, structure, and visualize live data streamed from remote IoT sensors. Key Implementation Details Scraping Daemon: Programmed a persistent Python worker background thread to monitor and parse incoming MQTT broker payloads. Data Indexing: Configured a Django backend mapped to a MariaDB database to structure, save, and retrieve telemetry data points. Interactive UI: Engineered a clean, interactive user dashboard using Chart.js to render real-time charts, featuring date filters and a raw CSV data exporter. 🔗 GitHub Repository