This project contains the program scripts for the classic game “Snake” and an artificial intelligence agent that can play the game automatically. The intelligent agent is trained using deep reinforcement learning and includes two versions: an agent based on a Multi-Layer Perceptron (MLP) and an agent based on a Convolution Neural Network (CNN), with the latter having a higher average game score.
CMSC426_Final_Project
This final project is about Visual Odometry.
CMSC426_Project06
This assignment used PyTorch to train neural networks for the tasks of image classification and image segmentation.
CMSC426_Project05
This assignment implemented the Affine Structure from Motion algorithm which continues the interest point detection and tracking problem from HW2.
CMSC426_Project04
This assignment aims to implement an algorithm for automatically estimating homography with RANSAC; Also the normalized 8-point algorithm; and the Image Stitching Algorithm.
CMSC426_Project03
This assignment aims to get familiar with shape alignment using the iterative closest point (ICP) algorithm; And object instance recognition using SIFT features and the nearest neighbor distance ratio test.
CMSC320_Final_Project
This is the final project for class CMSC320. The title of this project is “Analysis of Crime Data in Washington, D.C.”
CMSC320_Project03
The purpose of this assignment is to practice and experiment with linear regression using data from gapminder.org.
CMSC426_Project02
This assignment implemented a corner detector and feature tracker that track features from the image sequence hotel.
CMSC426_Project01
This assignment aims to explore image processing techniques, specifically hybrid images and pyramids.