computer vision presentation ppt

Acknowledgements

The lecture slides build upon many preceding efforts by other instructors, including Derek Hoiem (UIUC), James Hays (Georgia Tech), Steve Seitz (UW), Kristen Grauman (UT Austin), and Devi Parikh (Georgia Tech). Feel free to use and modify any of the slides for academic and research purposes. Please do credit the original sources where appropriate

First Principles of Computer Vision

This lecture series on computer vision is presented by Shree Nayar , T. C. Chang Professor of Computer Science at Columbia Engineering. It has been designed for students, practitioners and enthusiasts who have no prior knowledge of computer vision.

• What is Computer Vision?
• What is Vision Used For?
• How Do Humans Do it?
• Topics Covered
• About the Lecture Series
• References and Credits
• Pinhole & Perspective Projection
• Image Formation using Lenses
• Depth of Field
• Lens Related Issues
• Wide Angle Cameras
• Animal Eyes
• A Brief History of Imaging
• Types of Image Sensors
• Resolution, Noise, Dynamic Range
• Sensing Color
• Camera Response & HDR Imaging
• Nature’s Image Sensors
• Geometric Properties
• Segmenting Binary Images
• Iterative Modification
• Pixel Processing
• LSIS and Convolution
• Linear Image Filters
• Non-Linear Image Filters
• Template Matching
• Fourier Transform
• Convolution Theorem
• Filtering in Frequency Domain
• Deconvolution
• Sampling Theory and Aliasing
• What is an Edge?
• Edge Detection Using Gradients
• Edge Detection Using Laplacian
• Canny Edge Detector
• Corner Detection
• Fitting Lines and Curves
• Active Contours
• Hough Transform
• Generalized Hough Transform
• What is an Interest Point?
• Detecting Blobs
• SIFT Detector
• SIFT Descriptor
• 2x2 Image Transformations
• 3x3 Image Transformations
• Computing Homography
• Dealing with Outliers: RANSAC
• Warping and Blending Images
• Uses of Face Detection
• Haar Features for Face Detection
• Integral Image
• Nearest Neighbor Classifier
• Support Vector Machine
• Radiometric Concepts
• Scn. Radiance & Img. Irradiance
• Reflectance Models
• Reflection from Rough Surfaces
• Dichromatic Model
• Gradient Space & Reflectance Map
• Photometric Stereo
• Lambertian Case
• Calibration Based Photo. Stereo
• Shape from Normals
• Interreflections
• Human Perception of Shading
• Stereographic Projection
• Shape from Shading Algorithm
• Shading Illusions
• Point Spread Function
• Depth from Focus
• Depth from Defocus
• Photometric Stereo Systems
• Structured Light Range Finding
• Phase Shifting Method
• Structured Light Systems
• Time of Flight Method
• Linear Camera Model
• Camera Calibration
• Intrinsic and Extrinsic Matrices
• Simple Stereo
• Problem of Uncalibrated Stereo
• Epipolar Geometry
• Estimating Fundamental Matrix
• Finding Correspondences
• Computing Depth
• Stereo Vision in Nature
• Motion Field & Optical Flow
• Optical Flow Constraint Equation
• Lucas-Kanade Method
• Coarse-to-Fine Flow Estimation
• Application of Optical Flow
• Structure from Motion Problem
• Observation Matrix
• Rank of Observation Matrix
• Tomasi-Kanade Factorization
• Change Detection
• Gaussian Mixture Model
• Object Tracking using Template Matching
• Tracking by Feature Detection
• Segmentation by humans
• Segmentation as Clustering
• k-Means Segmentation
• Mean-Shift Segmentation
• Graph Based Segmentation
• Shape vs. Appearance
• Learning Appearance
• Principal Component Analysis
• Finding Principal Components
• PCA and SVD
• Parametric Appearance Representation
• Appearance Matching
• Perceptron Network
• Activation Function
• Neural Network
• Gradient Descent
• Backpropagation Algorithm
• Example Applications
• When to Use Machine Learning?

Computer Vision

Dec 20, 2019

1.39k likes | 1.79k Views

Computer Vision. Chapter 1 Introduction. The goal of computer vision is to make useful decisions about real physical objects and scenes based on sensed images. Applications areas. Industrial inspection Medical imaging Image database and query Satellite and surveillance imagery

Share Presentation

Presentation Transcript

Computer Vision Chapter 1 Introduction

The goal of computer vision is to make useful decisions about real physical objects and scenes based on sensed images.

Applications areas • Industrial inspection • Medical imaging • Image database and query • Satellite and surveillance imagery • Entertainment • Handwriting and printed character recognition

Image dimensionality • 1D • audio (sound) • 2D • digital camera picture, chest x-ray, ultrasound • 3D • video sequence of 2D images • multispectral 2D images • volumetric medical imagery (CT, MRI) • 4D • PET-CT • MRI

Image types • Binary • Grayscale • Color • Multispectral

Operations on images • Neighborhood (local) operations • Enhancing the entire image • Combining multiple images • Ex. differences, noise reduction, blending • Feature extraction • Ex. area, centroid (center of mass), orientation, lines • invariants

Extracting features

Example features

General hardware discussion • General purpose vs. special purpose (DSP, GPU) • Uniprocessors vs. parallel processors (COWs, multiprocessors) • Sensors (discussed later)

General software discussion • Android SDK • Java-based • freely available from http://developer.android.com/sdk/index.html • Albie start app • doxygen for source code documentation • freely available from doxygen.org • code format • http://www.oracle.com/technetwork/java/codeconv-138413.html

General software discussion C# use Visual C# (Express Edition is freely available from Microsoft) CSImageViewer starter app main course web page has links doxygen for source code documentation code format

Introduction to doxygen

What’s in a program file? • Comments • Code

What’s a compiler? • A program • Input • Processing • Output

What’s a compiler? • A program • Input: • Text file (your program) • Processing: • Convert HLL statements into machine code (or similar) • Ignore comments • Output: • A binary file of machine code (or similar)

Traditional documentation • Code files are separate from design documents. • Wouldn’t it be great if we could bring code and documentation together into the same file(s)?

Tools like doxygen and javadoc • A program • Input: • Text file (your program) • Processing: • Convert (specially formatted) comments into documentation • Ignore HLL statements • Output: • Documentation (typically in HTML)

Getting started with doxygen • Download from doxygen.org. • Do this only once in directory (folder) containing your source code: (already done for you) doxygen –g • This creates a doxygen configuration file called Doxyfile which you may edit to change default options. • Edit Doxyfile and make sure all EXTRACTs are YES • Then whenever you change your code and wish to update the documentation: doxygen • which updates all documentation in html subdirectory • Demonstrate.

Usingdoxygen: document every (source code) file /** * \file ImageData.java * \brief contains ImageData class definition (note that this * class is abstract) * * <more verbose description here> * \author George J. Grevera, Ph.D. */ . . .

Using doxygen: document every class //---------------------------------------------------------------------- /** \brief CSImageViewer class. * * Longer description goes here. */ public class CSImageViewer : Form { . . .

Using doxygen: document every function //---------------------------------------------------------------- /** \brief Given a pixel's row and column location, this * function returns the gray pixel value. * \param row image row * \param col image column * \returns the gray pixel value at that position */ public int getGray ( int row, int col ) { int offset = row * mW + col; return mOriginalData[ offset ]; }

Using doxygen: document every function (parameters) //---------------------------------------------------------------- /** \brief Given a pixel's row and column location, this * function returns the gray pixel value. * \param row image row * \param col image column * \returns the gray pixel value at that position */ public int getGray ( int row, int col ) { int offset = row * mW + col; return mOriginalData[ offset ]; }

Using doxygen: document every function (return value) //---------------------------------------------------------------- /** \brief Given a pixel's row and column location, this * function returns the gray pixel value. * \param row image row * \param col image column * \returns the gray pixel value at that position */ public int getGray ( int row, int col ) { int offset = row * mW + col; return mOriginalData[ offset ]; }

Using doxygen: document all class members (and global and static variables in C/C++) protected bool mIsColor; ///< true if color (rgb); false if gray protected bool mImageModified; ///< true if image has been modified protected int mW; ///< image width protected int mH; ///< image height protected int mMin; ///< overall min image pixel value protected int mMax; ///< overall max image pixel value protected String mFname; ///< (optional) file name

doxygen(lengthier example including html) /** \brief Actual original (unmodified) unpacked (1 component per * array entry) image data. * * If the image data are gray, each entry in this array represents a * gray pixel value. So mImageData[0] is the first pixel's gray * value, mImageData[1] is the second pixel's gray value, and so * on. Each value may be 8 bits or 16 bits. 16 bits allows for * values in the range [0..65535]. * <br> <br> * If the image data are color, triples of entries (i.e., 3) represent * each color rgb value. So each value is in [0..255] for 24-bit * color where each component is 8 bits. So mImageData[0] is the * first pixel's red value, mImageData[1] is the first pixel's green * value, mImageData[2] is the first pixel's blue value, mImageData[3] * is the second pixel's red value, and so on. */ protected int[] mOriginalData;

Required documentation rules • Each file, class, method, and member variable must be documented w/ doxygen. • Exception is when we follow the one-class-per-file rule. In that case only the class or file needs to be documented. • The contents of the body of each method should contain comments, but none of these comments should be in the doxygen format. (Not every comment is a doxygen comment.)

Not every comment should be a doxygen comment. Required: • every file/class • every function/method • every class member (data) • (in C/C++, every static and/or global variable) Use regular, plain comments in the body of a function/method. (One exception is the \todo.)

int mColorImageData[][][]; ///< should be mColorImageData[mH][mW][3] //---------------------------------------------------------------------- /** \brief Given a buffered image, this ctor reads the image data, stores * the raw pixel data in an array, and creates a displayable version of * the image. Note that this ctor is protected. The user should only * use ImageData.load( fileName ) to instantiate an object of this type. * \param bi buffered image used to construct this class instance * \param w width of image * \param h height of image * \returns nothing (constructor) */ protected ColorImageData ( final BufferedImage bi, final int w, final int h ) { mW = w; mH = h; mOriginalImage = bi; mIsColor = true; //format TYPE_INT_ARGB will be saved to mDisplayData mDisplayData = mOriginalImage.getRGB(0, 0, mW, mH, null, 0, mW); mImageData = new int[ mW * mH * 3 ]; mMin = mMax = mDisplayData[0] & 0xff; for (int i=0,j=0; i<mDisplayData.length; i++) { mDisplayData[i] &= 0xffffff; //just to insure that we only have 24-bit rgb final int r = (mDisplayData[i] & 0xff0000) >> 16; final int g = (mDisplayData[i] & 0xff00) >> 8; final int b = mDisplayData[i] & 0xff; if (r<mMin) mMin = r; if (g<mMin) mMin = g; …

Summary of most useful tags \file \author \brief \param \returns \todo (not used in assignments) And many, many others.

Back to images and imaging… The good, the bad, and the ugly

The good, the bad, and the ugly. • Success is usually hard won! • Problems: • Matching models to reality • Lighting variation • Sensor noise • Occlusion & rotation/translation/scale • Limited resolution • An image is a discrete model of an underlying continuous function • Spatial discretization • Sensed values quantization • Levels Of Detail (LOD)

So let’s try to recognize chairs. Task that is trivial for us.

The good, the bad, and the ugly. • Problem: Matching models to reality

The good, the bad, and the ugly. • Problem: Matching models to reality • Maybe CAD/CAM models can help! • http://www.3dcadbrowser.com/browse.aspx?category=59

The good, the bad, and the ugly. • Problems: Lighting variation

The good, the bad, and the ugly. • Problem: Sensor noise

The good, the bad, and the ugly. • Problem: Occlusion

The good, the bad, and the ugly. • Problem: Rotation, reflection, translation, & scale

The good, the bad, and the ugly. • Problem: • Limited resolution • An image is a discrete model of an underlying continuous function • Spatial discretization (above and below) • Sensed values quantization (next slide) • Too much of a good thing can be a problem too!

• More by User

Computer Vision. Spring 2006 15-385,-685 Instructor: S. Narasimhan Wean 5403 T-R 3:00pm – 4:20pm. Boundary Detection: Hough Transform Lecture #9 Reading: Computer Vision (Ballard and Brown): Chapter 4

814 views • 43 slides

Computer Vision. Spring 2006 15-385,-685 Instructor: S. Narasimhan Wean 5403 T-R 3:00pm – 4:20pm. Aliasing - Really bad in video. Text Aliasing. Edge Detection Lecture #7. Edge Detection. Convert a 2D image into a set of curves Extracts salient features of the scene

798 views • 39 slides

Computer Vision. Spring 2006 15-385,-685 Instructor: S. Narasimhan Wean 5403 T-R 3:00pm – 4:20pm Lecture #17. Structured Light + Range Imaging Lecture #17. (Thanks to Slides from Levoy, Rusinkiewicz, Bouguet, Perona). 3D Scanning. Structured Light Reconstruction.

680 views • 34 slides

Computer Vision . Geometric Camera Models and Camera Calibration. Coordinate Systems. Let O be the origin of a 3D coordinate system spanned by the unit vectors i, j, and k orthogonal to each other. i. P. O. k. j. Coordinate vector. Homogeneous Coordinates. n. H. P. O.

633 views • 29 slides

458 views • 17 slides

Computer Vision. Spring 2006 15-385,-685 Instructor: S. Narasimhan Wean 5403 T-R 3:00pm – 4:20pm Lecture #13. Announcements. Homework 4 will be out today. Due 4/4/06. Please start early. Midterm stats: A range  40+, B range  30+ 40+  13 students 30+  9 students

481 views • 26 slides

Computer Vision. Spring 2006 15-385,-685 Instructor: S. Narasimhan Wean 5403 T-R 3:00pm – 4:20pm Lecture #18. Polyhedral Objects and Line Drawing Lecture #18. Line Drawings. We often communicate using Line Drawings. Engineering Drawings. Topics.

405 views • 26 slides

Computer Vision. Spring 2010 15-385,-685 Instructor: S. Narasimhan WH 5409 T-R 10:30am – 11:50am Lecture #18. Principal Components Analysis Lecture #18. Example: 53 Blood and urine measurements (wet chemistry) from 65 people (33 alcoholics, 32 non-alcoholics). Matrix Format.

643 views • 52 slides

Vision Computer

DS,JX. Vision Computer. DS, JX. Cameras. DS, JX. Everything Else. NF, VG. Router. System Block Diagram for Vehicle Lab (7/8/04). NF, VG. Control Computers. Arbiter. Other Team. Help!. Needs Work. Working. System Block Diagram -Rooftop Vision System- 7/8/04. RFID Reader

271 views • 2 slides

Computer Vision. Filename: eie426-computer-vision-0809.ppt. Contents. Perception generally Image formation Color vision Edge detection Image segmentation Visual attention 2D  3D Object recognition. Perception generally. Stimulus (percept) S, World W S = g(W)

700 views • 42 slides

Computer Vision. Ronald Frazier CIS 479 April 20, 1999. Introduction. Important area of study Ease of use for new users Managing large quantities of images. Combines a Variety of Disciplines. Standard Programming Techniques Artificial Intelligence Techniques Neural Networks Fuzzy Logic

331 views • 19 slides

Computer Vision. Spring 2010 15-385,-685 Instructor: S. Narasimhan PH A18B T-R 10:30am – 11:50am Lecture #13. Mechanisms of Reflection. source. incident direction. surface reflection. body reflection. surface. Surface Reflection: Specular Reflection Glossy Appearance

586 views • 40 slides

Computer Vision. CMSC 25000 Artificial Intelligence March 11, 2008. Roadmap. Motivation Computer vision applications Is a Picture worth a thousand words? Low level features Feature extraction: intensity, color High level features Top-down constraint: shape from stereo, motion,..

712 views • 43 slides

Lecture 10 Roger S. Gaborski. Computer Vision. Algorithm Development: Edges. We would like to develop algorithms that detect important edges in images The ‘quality’ of edges will depend on the image characteristics Noise can result in false edges. Profiles of an Ideal Edge.

576 views • 48 slides

Computer Vision. Stereo Vision. Pinhole Camera. Perspective Projection. Stereo Vision. Two cameras. Known camera positions. Recover depth. scene point. p. p’. image plane. optical center. Correspondences. p. p’. Matrix form of cross product. a =a x i +a y j +a z k.

447 views • 23 slides

Computer Vision. Spring 2010 15-385,-685 Instructor: S. Narasimhan WH 5409 T-R 10:30am – 11:50am Lecture #19. Principal Components Analysis on Images Lecture #19. The Space of Faces. An image is a point in a high dimensional space An N x M image is a point in R NM

416 views • 39 slides

Computer Vision. The 2D projective plane and it’s applications HZ Ch 2. In particular: Ch 2.1-4, 2.7, Szelisky: Ch 2.1.1, 2.1.2 Estimation:HZ: Ch 4.1-4.2.5, 4.4.4-4.8 cursorly. Richard Hartley and Andrew Zisserman, Multiple View Geometry , Cambridge University Publishers, 2 nd ed. 2004.

692 views • 66 slides

Computer Vision. http://www.cvl.iis.u-tokyo.ac.jp/ class2018/2018w/class2018w.html. Contents. Papers on Patch-based Object Recognition Using Images This week and next week This week Basic techniques on recent object recognition Comparison with 20Q. What is “ Object Recognition ” ?.

795 views • 69 slides

Got any suggestions?

We want to hear from you! Send us a message and help improve Slidesgo

Top searches

Trending searches

49 templates

44 templates

61 templates

american history

85 templates

el salvador

34 templates

63 templates

Computer Vision Research Poster

It seems that you like this template, computer vision research poster presentation, free google slides theme, powerpoint template, and canva presentation template.

Soon, computers will rule over the whole world. Until that day comes, we're free to design new templates, like this one for research posters (one of our newest structures). We've decided that the theme will be "computer vision", you know, that field in computer science that refers to how machines understand images from the real world. Customize this techie design and then print it if necessary. Our computer overlords will allow it... for now!

Features of this template

• 100% editable and easy to modify
• 8 different slides to impress your audience
• Contains easy-to-edit graphics such as graphs, maps, tables, timelines and mockups
• Includes 500+ icons and Flaticon’s extension for customizing your slides
• Designed to be used in Google Slides, Canva, and Microsoft PowerPoint
• 4:3 standard format for screens
• Includes information about fonts, colors, and credits of the resources used

How can I use the template?

Am I free to use the templates?

How to attribute?

Attribution required If you are a free user, you must attribute Slidesgo by keeping the slide where the credits appear. How to attribute?

Register for free and start downloading now

Related posts on our blog.

How to Add, Duplicate, Move, Delete or Hide Slides in Google Slides

How to Change Layouts in PowerPoint

How to Change the Slide Size in Google Slides

Related presentations.

Premium template

Unlock this template and gain unlimited access

CS 231A Course Project

Course Project Overview

Important Dates

Oct 21 (11:59pm) , Finalizing team members : Maximum team size: 2 . Send us an email with your team name and team members.

Oct 21 (11:59pm) , Proposal submission : Submit a 0.5 page course project proposal in our provided template. Send a PDF file to [email protected]

Nov 18 (11:59pm) , Project milestone : Submit a 2-3 page course project milestone report.

Dec 13 (11:59pm) , Final report and code submission : No late days allowed.

Dec 14 (14:00pm) , Project presentation submission : No late days allowed.

Dec 15 (10am - 12pm) , Course project presentation. Location: Room 200-305 (Room 305 of Building 200)

Grading Policy

presentation: 5% write-up: 10%  •  clarity, structure, language, references: 3%  •  background literature survey, good understanding of the problem: 3%  •  good insights and discussions of methodology, analysis, results, etc.: 4% technical: 15%  •  correctness: 5%  •  depth: 5%  •  innovation: 5% evaluation and results: 10%  •  sound evaluation metric: 3%  •  thoroughness in analysis and experimentation: 3%  •  results and performance: 4%

Project Submission Details

You must use our provided templates . Email your project proposal, milestone report, final report and zipped code to: [email protected] , with the following format: Subject Line: Course Project Proposal/Milestone/Report Body: Full names of all group members, SUNet ID's and Project title Attachments: Write-up as LastName_LastName_Paper.pdf, Code as LastName_LastName_Code.zip, where the titles have all the last names of the group members.

You must use our provided presentation template . Email your Powerpoint slides (.ppt file) to [email protected] , with the following format: Subject Line: Course Project Presentation Body: Full names of all group members, SUNet ID's and Project title Attachments: Powerpoint slides as LastName_LastName_Presentation.ppt, where the titles have all the last names of the group members.

Final Report Write-up Guidelines

Your final write-up should be between 8 - 10 pages using the template provided. After the class, we will post all the final reports online (restricted to CS231a students only) so that you can read about each others’ work. If you do not want your writeup to be posted online, then please let us know at least a week in advance of the final writeup submission deadline. The following is a suggested structure for your report:

• Title, Author(s)

• Abstract: It should not be more than 300 words;

• Introduction: this section introduces your problem, and the overall plan for approaching your problem

• Background/Related Work: This section discusses relevant literature for your project

• Approach: This section details the framework of your project. Be specific, which means you might want to include equations, figures, plots, etc

• Experiment: This section begins with what kind of experiments you're doing, what kind of dataset(s) you're using, and what is the way you measure or evaluate your results. It then shows in details the results of your experiments. By details, I mean both quantitative evaluations (show numbers, figures, tables, etc) as well as qualitative results (show images, example results, etc).

• Conclusion: What have you learned? Suggest future ideas.

• References: This is absolutely necessary. Reports without references will not receive a score higher than 20 points (total is 40 points).

• Supplementary materials: This is NOT counted toward your 8-10 page limit. Please submit your codes as supplementary materials.

Project Presentation Guidelines

Each team should give a two minutes project presentation. After your presentation, there will be one minute for audiences to ask questions. You must use the template provided by us ( Download it here ) and make sure that your presentation contains exactly two slides. We will compile the presentation slides from all teams into a single big .ppt file and show it using our laptop, so you do not need to worry about bringing computers on the presentation day.

Project Proposal

We have provided the template for your final write-up. Your proposal should follow the same template , and should be no more than 1 page. Your proposal should describe as clearly as possible the following:

• What is the computer vision problem that you will be investigating? Why is it interesting?

• What image or video data will you use? If you are collecting new datasets, how do you plan to collect them?

• What method or algorithm are you proposing? If there are existing implementations, will you use them and how? How do you plan to improve or modify such implementations?

• Which reading will you examine to provide context and background?

• How will you evaluate your results? Qualitatively, what kind of results do you expect (e.g. plots or figures)? Quantitatively, what kind of analysis will you use to evaluate and/or compare your results (e.g. what performance metrics or statistical tests)?

Project Milestone

Your project milestone report should be between 2 - 3 pages using the template provided. The following is a suggested structure for your report:

• Problem statement: Describe your problem precisely specifying the dataset to be used, expected results and evaluation

• Technical Approach: Describe the methods you intend to apply to solve the given problem

• Intermediate/Preliminary Results: State and evaluate your results upto the milestone

You may consult any papers, books, online references, or publicly available implementations (such as SIFT) for ideas and code that you may want to incorporate into your strategy or algorithm, so long as you clearly cite your sources in your code and your writeup. However, under no circumstances may you look at another group’s code or incorporate their code into your project.

Project Reports of Previous Years

Winter, 2010-2011

3D Model Segmentation and Labeling

Generic Object/Scene recognition for the Smart Album Project

Text Detection and Character Recognition in Scene Images with Unsupervised Feature Learning

Learning Slow Features for Object Recognition

RoboGrader: Scoring Multiple Choice Tests with a Smartphone

Joint Subclassing and Classification

Heuristics for Decision Tree Selection and Weight Assignment in Random Forest for Fine-Grained Image Classification

Hole Filling Method Using Edge Based Interpolated Depth for View Synthesis

RGB-Z Segmentation of Objects in a Cluttered Scene Using a Kinect Sensor

Simultaneous Segmentation and Tracking in Point Cloud Data using the Iterative Closest Point Algorithm

KFace3D: Facial Recognition using RGBD Data

Comparison of Aircraft Tracking Using Top-Down and Bottom-Up Approaches

Geometric Understanding of Indoor Scenes

Object Pose Estimation using Optical Flow and POSIT

Real Time Subcutaneous Vein Recognition of Forearm Veins

Face Detection and Tracking for BabyCam

Image Retrieval, Semantic & Geographic Annotation using visual/multimedia representations and textual information

Smart Album: Face Recognition and Landmark Recognition in Album

Computer-assisted Detection of Defects during the Fabrication of PDMS chips

Unsupervised Learning of Invariances with Temporal Coherence

Image-based Web Page Classification

Winter, 2009-2010

Using a Functionality Model for Chair Detection

Fusing Multi-Channel Cues for Image Organization

Generalizing ImageNet to SmartPhones

Motion-sensitive Low-noise Imaging

Unsupervised Image Segmentation using Deep Belief Nets

The Retinal Algorithm to Detect, Segment and Track Moving Objects with Observer Motion

Unsupervised Feature Learning of Bi-modal Features

Efficient Classification and Segmentation of Specular Objects

Feature Descriptors for Tiny Image Categorization

A feature tracking approach to painted aperture

Baseline Scene Classifications

Camera Tracking with Fixed Point Math for Mobile Devices

Modeling Mutual Context of Object and Human Pose in Human-Object Interaction Activities

Sub-meter Indoor Localization in Unmodified Environments with Inexpensive Sensors

Segmentation of seismic images

Object Detecting in Images using Time Series Ensemble Methods

Learning Visual Invariance in a 2-Layer Neural Network

The "Find Mii" Challenge

Find Mii on Wii

"Find Mii" is a game on Nintendo Wii Play. It basically involves identifying certian avatars (Miis) from a bunch of them, standing still or moving around in various styles. If you are not yet proficient in this game, let Elvis show you how to play it in the videos below.

As we know computers are designed to work in certain areas of human endeavor that are not terribly challenging to human intelligence but sometimes beyond human patience. In this course project you will be programming the computer to play the game as good as Elvis did.

You don't have to worry about any "interface" issue (as some of you asked in class). Actually you will only be dealing with images instead of programming the Wii game controller.

Project Mission

In the course project, you will be focusing on 4 tasks in "Find Mii" as described below.

Task 1 : Find this Mii! ... You will be given a reference picture of one Mii. Identify that one in a crowd.

Task 2 : Find 2 look-alikes! ... Pay attention to the faces (and hair styles?) as they might be wearing different sweaters.

Task 3 : Find n odd Miis out! ... Some Miis are odd in their styles of shaking heads or footsteps. Find them out.

Task 4 : Find the fastest Mii! ... Someone is running (or swimming) fast. Catch that one.

For each task you have 3 levels: easy, medium, and hard.

For each task & level we will give you a video file from gamplay (that would be 12 in total), and you need to identify a given number of Miis.

Minimum requirement: 3 different tasks, 1 level for each.

You will be handling different tasks & levels separately (of course you can have functionalities shared among them, just follow the comments in the infrastructure code). You don't have to do all the 12 task & levels, the minimum requirement is that you complete at least three different tasks, one level for each. However you are strongly encouraged to do all 4 tasks on higher levels to earn more points for the final challenge!