Homework answers / question archive / Linear LeastSquares Table of Contents: Due Date Introduction What you need to do Problem Statement Submission Guidelines Collaboration Policy Due Date 11:59PM, Thursday, September 8, 2022 Introduction This home work is designed to test your understanding of mathematics tutorial discussed in this link, specifically RANSAC

Linear LeastSquares Table of Contents: Due Date Introduction What you need to do Problem Statement Submission Guidelines Collaboration Policy Due Date 11:59PM, Thursday, September 8, 2022 Introduction This home work is designed to test your understanding of mathematics tutorial discussed in this link, specifically RANSAC

Computer Science

Share With

---

Linear LeastSquares

Table of Contents:

Due Date

Introduction

What you need to do

Problem Statement

Submission Guidelines

Collaboration Policy

Due Date

11:59PM, Thursday, September 8, 2022

Introduction

This home work is designed to test your understanding of mathematics tutorial discussed in this

link, specifically RANSAC. We highly recommend you to read the entire math tutorial, not just

the RANSAC section. The task is to fit the best possible line to two dimensional data points

using different linear least square techniques discussed in the tutorials such that the line defines

the best possible set of data points:

Line fitting using Linear Least Squares

Outliers rejection using Regularization

Outliers rejection using RANSAC

What you need to do

The 2D points data is provided in the form of .mat file (click here to download). The visualization

of data with different noise level is shown in the following figure.

CMSC426 Computer Vision

9/4/22, 8:15 PM Linear Least Squares

https://cmsc426.github.io/2020/hw/hw1/ 2/3

Problem Statement

Write matlab code to visualize geometric interpretation of eigenvalues/covariance matrix

as shown in Fig. 10 of this link [40 points]

Decide the best outlier rejection technique for each of these datasets and write matlab

code to fit the line. Also, discuss why your choice of technique is optimal [60 points]

Submission Guidelines

If your submission does not comply with the following guidelines, you’ll be given ZERO

credit

File tree and naming

Your submission on Canvas must be a zip file, following the naming convention

YourDirectoryID_hw1.zip. For example, xyz123_hw1.zip. The file must have the following

directory structure, based on the starter files

YourDirectoryID_hw1.zip.

data/.

plot_eigen.m.

least_square.m.

report.pdf

Report

9/4/22, 8:15 PM Linear Least Squares

https://cmsc426.github.io/2020/hw/hw1/ 3/3

For each section of the homework, explain briefly what you did, and describe any interesting

problems you encountered and/or solutions you implemented. You must include the following

details in your writeup:

Your understanding of eigenvectors and eigenvalues

Your choice of outlier rejection technique for each dataset

Limitation of each outliers rejection technique

Your report must be full English sentences,NOT** commented code. There is a word limit of

750 words and no minimum length requirement**