Projects

A robotics project that integrates a robotic arm mounted on a mobile platform to autonomously detect, navigate towards, and manipulate(lift) objects based on natural language commands using 6D pose estimation of the object. The project will utilize ROS, Gazebo, ArUco Markers, 6D pose estimator and LLMs.

View Project

The project is designed to enhance road safety and traffic management by accurately detecting and tracking objects on roads and highways. Uses YOLOv7 and DeepSORT for object detection on BDD100K dataset.

View Project View Demo

The Final Year Design Project aims to improve object grasping and manipulation in warehouses. It features an autonomous robotic arm that efficiently retrieves items from any defined place using dual monocular cameras for 6D object pose estimation and techniques involving robotics and machine learning for grasping strategies that includes kinematic modeling and inverse kinematic modeling of the robotic arm.

View Presentation View Project View Demonstration View Research Paper

This project demonstrates the use of YOLOv8 for detecting American Sign Language (ASL) gestures.

View Project View Demo

The SmartScan Billing Assistant is a computer vision-based project designed to automate the process of calculating the total bill by detecting products and adding their prices using a camera, similar to a cashier. This project uses the YOLOv8 model for object detection and tracking. This is the MVP of the main project I did for a supermarket where I implemented the SmartScan billing system on more than 20 products.

View Project

Facial Emotion Detection using YOLOv8 is a Flask web application designed to detect facial emotions in real time. Leveraging the power of the YOLOv8 model, this project offers a robust solution for identifying a range of emotions directly from images or webcam feeds.

View Project View Demo

Flask application designed to perform forecasting using classical models. The application allows users to select from a variety of forecasting models to predict future values based on a dataset collected from a real workshop.

View Project View Demo

Human Sense Ads is a project designed to detect humans, extract their features, and generate personalized messages using a language model (LLM) to grab their attention towards advertisements displayed on a screen.

View Project View Demo

This project consists of a React-based frontend that listens to user queries, sends them to a Flask backend, and receives responses generated by a locally set up Llama3 language model.

View Project