A collection of retro-style web games.
Developed a Unix-like kernel in C, designing core OS components like virtual memory, process scheduling, and a file system.
The Weenix Operating System is a modular, Unix-like kernel developed as part of USC's CSCI 420. Built process management, threading, virtual memory, and file system from scratch.
Visualizes cloud heights using ISRO's INSAT 3DR infrared satellite data and lapse rate models.
Calculates altitudes from brightness temperatures and presents them as a 3D point cloud.
Compares DCT (JPEG) and DWT (JPEG2000) for image compression and progressive decoding.
Detailed analysis of compression efficiency and PSNR across different algorithms.
DWT-based video compression with motion vector prediction for optimized playback.
Achieves high compression ratios using block-based segmentation between foreground and background.
Custom 2D Game Engine built with OpenGL and C++ from scratch.
A custom 2D game engine built from scratch using C++ and OpenGL. Features include core engine architecture, rendering system using OpenGL, GLSL shader management, and basic physics/collision detection.
Self-learning Flappy Bird agent using the NEAT algorithm for neural evolution.
This project implements an AI for the Flappy Bird game using the NEAT algorithm. Explores evolutionary algorithms in game AI and balancing between exploration and exploitation.
Mini framework for building and training neural networks from scratch using NumPy.
This project involves building a neural network from the ground up using Python. Key components include implementation of forward and backward propagation and customizable network architecture.
Hazel-based engine with real-time ML-powered upscaling.
The Tookivi game engine, based on the Hazel engine, features real-time super-resolution upscaling via a Python script optimizing real-time image processing.
Upsampling and downsampling using Bilinear and Bicubic interpolation.
This project focuses on implementing various image resampling techniques such as Nearest Neighbor, Bilinear, and Bicubic interpolations.
Segments image pixels based on hue thresholds in the HSV color space.
This project focuses on image segmentation using HSV color space. Key features include HSV color space conversion and thresholding.
Autonomous thrust vector control using machine learning in physics simulations.
Authors: R Amarthya, A Agrawal, Y Chawla, A Kumar
This paper explores the use of machine learning for autonomous thrust vector control in guidance systems. It compares reinforcement learning models in a simulated environment, demonstrating their effectiveness for closed-loop control while considering factors like position, angle, velocity, and fuel consumption.
A Look Into The Past, Present, and Future of Augmented Reality.
Authors: Amarthya, R., Kumar, R., Bhogal, P.S., Anand, A., & Agrawal, A.
Augmented Reality (AR) technology blends digital and physical worlds, evolving into a powerful mobile tool. This paper examines AR's history, applications, and its impact on user interaction through 3D interfaces and Mobile AR Systems.