Online study resources available anywhere, at any time
High-quality Study Documents, expert Tutors and Flashcards
Everything you need to learn more effectively and succeed
We are not endorsed by this school |
- Course Hero has verified this tag with the official school catalog
We are sorry, there are no listings for the current search parameters.
We don't have any study resources available yet.
We don't have any study resources available yet.
We don't have any study resources available yet.
We don't have any study resources available yet.
We don't have any study resources available yet.
We don't have any study resources available yet.
We don't have any study resources available yet.
We don't have any study resources available yet.
We don't have any study resources available yet.
We don't have any study resources available yet.
We don't have any study resources available yet.
We don't have any study resources available yet.
School: Penn State
Hash Table How can we retrieve a value (by key) from an associative container in O(1) time? Yes we can, with the help of a Hash Table! Hash table typically implements an internal array for storing data and provides a function for index (i.e. hash code) ca
School: Penn State
Course: INTRO COMP ARCH
CSE 431 Computer Architecture Fall 2005 Lecture 01: Introduction Mary Jane Irwin ( www.cse.psu.edu/~mji ) www.cse.psu.edu/~cg431 [Adapted from Computer Organization and Design, Patterson & Hennessy, 2005, UCB] CSE431 L01 Introduction.1 Irwin, PSU, 2005 Co
School: Penn State
Course: Topics In Computer Vision
EM Motivation want to do MLE of mixture of Gaussian parameters But this is hard, because of the summation in the mixture of Gaussian equation (cant take the log of a sum). If we knew which point contribute to which Gaussian component, the problem would
School: Penn State
Course: Multicasting
Robert Collins CSE598C, PSU Mean-shift, continued R.Collins, CSE, PSU CSE598C Fall 2012 Robert Collins CSE598C, PSU Background: Kernel Density Estimation Given a set of data samples xi; i=1.n Convolve with a kernel function H to generate a smooth function
School: Penn State
Course: Multicasting
Robert Collins CSE598C, PSU Introduction to Mean-Shift Tracking Robert Collins CSE598C, PSU Appearance-Based Tracking current frame + previous location likelihood over object location appearance model (e.g. image template, or Mode-Seeking (e.g. mean-shift
School: Penn State
Course: Multicasting
Robert Collins CSE598C Sampling Methods, Particle Filtering, and Markov-Chain Monte Carlo CSE598C Vision-Based Tracking Fall 2012, CSE Dept, Penn State Univ Robert Collins CSE598C References Robert Collins CSE598C Recall: Bayesian Filtering Rigorous gener
School: Penn State
Course: Multicasting
6.559479; CO\M6 7 gélT-lolzavg~ (v MK ML 00 (5ZWLM Mara/var. F-v'lk rm: 672$ X; n. X4 ML okMa-"nan? Y1 o. 7v. AL A (Sana-7 fray 774.43?" km A7 90mm, vw Ya): PCVDPCYIIM)Plek>PCyzln>PClx,> u , 6" Mv _ onml .1 Cur/war 671%. M o/tb on (aha) 47th [My cu rrm'l'
School: Penn State
Course: Topics In Computer Vision
This corresponds t o t he point in t he mixt ure of Gaussian powerpoint slides where I say I'll derive E_z[logP(X,Z| t het a)] on t he board
School: Penn State
Course: Topics In Computer Vision
Note: this derivation for the covariance matrix may not be correct (although it gets the right answer). The reason why is that we havent done anything to constrain the sigma matrix to be symmetric. For a symmetric matrix, all the elements are not independ
School: Penn State
Course: Topics In Computer Vision
M Cal/m ceééf? @ Comémi a: OUV (Lao/raw! 6AM girl A Down Low, W9; wlfTZ, 4.9 4; Moétl, X u, an 4" 7" Am Lioc. WWWB \ 9c ORNW4 vaA. C6773?) A" @ I r I Yr. 74 @ Nov-(K r9(Y«:Yz."~Y~l *3 = Pent?) F6721») "3611, Y, akLgp ft gun. liafaq PCX) Y1 \/-I )5: o "
School: Penn State
Course: Topics In Computer Vision
CSE586/EE554: Computer Vision II Spring 2012 Course Overview Instructor: Dr. Robert Collins, email: rcollins@cse.psu.edu Office: IST 354H Office Hours: TBA Course Description: Introduction of mathematical methods commonly used in computer vision along wit
School: Penn State
Course: Multicasting
Robert Collins Penn State Crowd Scene Analysis Using computer vision tools to look at people in public places Real-time monitoring situation awareness notifications/alarms After-action review traffic analysis VLPR 2012 Robert Collins Penn State Crow
School: Penn State
Course: Computer VIsion I
Robert Collins CSE486 Lecture 11: LoG and DoG Filters Robert Collins CSE486 Todays Topics Laplacian of Gaussian (LoG) Filter - useful for finding edges - also useful for finding blobs! approximation using Difference of Gaussian (DoG) Robert Collins CSE486
School: Penn State
Course: Computer VIsion I
Robert Collins CSE486, Penn State Lecture 3: Linear Operators Robert Collins CSE486, Penn State Administrivia I have put some Matlab image tutorials on Angel. Please take a look if you are unfamiliar with Matlab or the image toolbox. I have posted Homewor
School: Penn State
Course: Computer VIsion I
Robert Collins CSE486, Penn State Lecture 13: Camera Projection II Reading: T&V Section 2.4 Robert Collins CSE486, Penn State Recall: Imaging Geometry W Object of Interest in World Coordinate System (U,V,W) U V Robert Collins CSE486, Penn State Imaging Ge
School: Penn State
Course: Computer VIsion I
Robert Collins CSE486, Penn State Lecture 12: Camera Projection Reading: T&V Section 2.4 Robert Collins CSE486, Penn State Imaging Geometry W Object of Interest in World Coordinate System (U,V,W) U V Robert Collins CSE486, Penn State Imaging Geometry Came
School: Penn State
Course: Computer VIsion I
Robert Collins CSE486, Penn State Lecture 4: Smoothing Related text is T&V Section 2.3.3 and Chapter 3 Robert Collins CSE486, Penn State Summary about Convolution Computing a linear operator in neighborhoods centered at each pixel. Can be thought of as sl
School: Penn State
Course: FUND COMP ARCH
CSE 530 Final Project Presentation q <Survey on reducing power consumption for non volatile memories> <Tianqi Xu and Xiaobo Yu> CSE530 Final Project Presentation.1 <Tianqi Xu and Xiaobo Yu> Fall 2013 PSU Introduction q STT-RAM (spin-transfer torque RAM) q
School: Penn State
Course: FUND COMP ARCH
CSE 530 Final Project Presentation q <New Opportunities and Challenges for Non-volatile Memory Technologies> <Tianqi Xu and Xiaobo Yu> CSE530 Final Project Presentation.1 <YOURNAMES> Fall 2013 PSU The problem/opportunity (what is it, broadly?) q Provide g
School: Penn State
Course: Discrete Mathematics
CSE 260.2 Spring 2003 Quiz I 20 points Name _ 1. Use a truth table to prove p q ~p q. The truth table has been started for you. (You may not necessarily use all columns.) [8 pts] p q T T T F F T F F 2. Given the premises "If Zeus is human, then Zeus is mo
School: Penn State
Course: Discrete Mathematics
CSE 260.2 Spring 2003 Quiz I 20 points Name _ 1. Use a truth table to prove p q ~p q. The truth table has been started for you. (You may not necessarily use all columns.) [8 pts] p q ~p ~p q pq T T F T T T F F F F F T T T T F F T T T These two columns are
School: Penn State
Course: Discrete Mathematics
CSE 260 Exam Quiz Name _ Use the valid argument forms (and only the valid argument forms) we discussed in class to deduce the conclusion from the given premises. Number and label each step or deduction clearly. PREMISES: 1. ~p q 2. r 3. ~p r 4. ~s 5. ~q (
School: Penn State
Course: Multicasting
Homework 1. CSE 598C Vision-based Tracking, Fall 2012. Due Wed Fri 7, 2012 in Angel. This homework will actually be pretty easy, I think, if you followed the example on Gaussian Point Observations that we went over in class. You can view that example as o
School: Penn State
Course: Topics In Computer Vision
CSE586 Assignment 3, due March 17 Thurs 1) Prove that the set of all 2x2 matrices of the form [cos(theta) -sin (theta); sin(theta) cos(theta)] form a group under matrix multiplication. 2) Prove that the set of all complex numbers of the form e^cfw_i theta
School: Penn State
Course: Topics In Computer Vision
Homework 1 (due Monday Jan 24 by end of the day) 1. Consider the x=1 y=0: 10 y=1: 10 y=2: 0 (unnormalized) 2D bivariate distribution f(x,y) x=2 x=3 x=4 10 10 10 20 20 0 10 0 0 For each of the following, give your answer to 1) a) What is the marginal distr
School: Penn State
Course: VLSI
HOMEWORK 4 CMPEN 411 Due: 2/12/2013 11:30pm Learning Objective Use the VLSI CAD tools to design and implement an 8-bit Program Counter (PC) circuit in bit-slice style and analyze it. Instruction Implement the program counter circuit shown below in schemat
School: Penn State
Course: NUM LINEAR ALGEBRA
Hidden page Hidden page Hidden page Hidden page Hidden page Hidden page Hidden page Hidden page Hidden page Hidden page Hidden page Hidden page Hidden page Hidden page Hidden page Hidden page Hidden page Hidden page Hidden page Hidden page Hidden page Hid
School: Penn State
Course: Compiler Construction
Homework 2 (Due March 20th, 2012) 1. [25points] Identify the dependences in the following loop nest and indicate whether (a) they are loopindependent or loop-carried, and (b) whether they are flow, anti or output dependences? for i = 3, 100 U[i] = V[i] +
School: Penn State
Course: Multicasting
CSE598C: Vision-Based Tracking Fall 2012 Syllabus Instructor: Robert Collins, Associate Professor, CSE 354H IST Building Phone: 3-1944; email: rtc12@psu.edu Office Hours: Tues 2-4, Wed 9-9:50 Class Schedule: MWF 10:10AM 11:00PM; 370 Willard Textbook: No T
School: Penn State
Course: Comm Networks
CSE/EE 458: Communication Networks Instructor: Guohong Cao Ofce, Phone, Email: 310 pond lab, 863-1241, gcao@cse.psu.edu Ofce Hours: MW 9:30-10:50 TA: Namhyong Kim Ofce, Phone, Email: 125 Hammond, 865-9191, nakim@cse.psu.edu Ofce Hours: MF 10:30 - 12:
School: Penn State
Course: Cmptr Networks
CSE 514: Computer Networks Instructor: Guohong Cao Ofce, Phone, Email: 354G IST, 863-1241, gcao@cse.psu.edu Ofce Hours: TR 2:00 - 3:15 TA: Ofce, Phone, Email: Ofce Hours: Textbook: Computer Networks: A Top-Down Approach Featuring the Internet, Fourth
School: Penn State
Course: Distributed System
CSE 513: Distributed Systems Instructor: Guohong Cao Ofce, Phone, Email: 354G IST building, 863-1241, gcao@cse.psu.edu Ofce Hours: TR: 1PM - 2PM. TA: Wenhui Hu Ofce, Phone, Email: 338E IST, 865-0191, wxh180@cse.psu.edu Ofce Hours: Wed, 1- 2pm; Fri, 9
School: Penn State
Course: PROGRAMMING FOR ENGINEERS
COMPUTER SCIENCE & ENGINEERING 121 Spring 2007 Professor: Dr. Susan L. Quick Office: 111J IST Phone: 865-9507 E-mail: quick@cse.psu.edu or through ANGEL (Do not use any other e-mail address!) Office Hours: M 1:30 2:30, W: 3:30 5:30 or by appointmen
School: Penn State
Hash Table How can we retrieve a value (by key) from an associative container in O(1) time? Yes we can, with the help of a Hash Table! Hash table typically implements an internal array for storing data and provides a function for index (i.e. hash code) ca
School: Penn State
Course: INTRO COMP ARCH
CSE 431 Computer Architecture Fall 2005 Lecture 01: Introduction Mary Jane Irwin ( www.cse.psu.edu/~mji ) www.cse.psu.edu/~cg431 [Adapted from Computer Organization and Design, Patterson & Hennessy, 2005, UCB] CSE431 L01 Introduction.1 Irwin, PSU, 2005 Co
School: Penn State
Course: Topics In Computer Vision
EM Motivation want to do MLE of mixture of Gaussian parameters But this is hard, because of the summation in the mixture of Gaussian equation (cant take the log of a sum). If we knew which point contribute to which Gaussian component, the problem would
School: Penn State
Course: Multicasting
Robert Collins CSE598C, PSU Mean-shift, continued R.Collins, CSE, PSU CSE598C Fall 2012 Robert Collins CSE598C, PSU Background: Kernel Density Estimation Given a set of data samples xi; i=1.n Convolve with a kernel function H to generate a smooth function
School: Penn State
Course: Multicasting
Robert Collins CSE598C, PSU Introduction to Mean-Shift Tracking Robert Collins CSE598C, PSU Appearance-Based Tracking current frame + previous location likelihood over object location appearance model (e.g. image template, or Mode-Seeking (e.g. mean-shift
School: Penn State
Course: Multicasting
Robert Collins CSE598C Sampling Methods, Particle Filtering, and Markov-Chain Monte Carlo CSE598C Vision-Based Tracking Fall 2012, CSE Dept, Penn State Univ Robert Collins CSE598C References Robert Collins CSE598C Recall: Bayesian Filtering Rigorous gener
School: Penn State
Course: Multicasting
Robert Collins CSE598C Back to Lucas-Kanade Robert Collins CSE598C Step-by-Step Derivation The key to the derivation is Taylor series approximation: W [ I (W ([ x, y ]; P P) ~ [ I (W ([ x, y ]; P) I P ~ P We will derive this step-by-step. First, we need t
School: Penn State
Course: Multicasting
Robert Collins CSE598C Intro to Template Matching and the Lucas-Kanade Method Robert Collins CSE598C Appearance-Based Tracking current frame + previous location likelihood over object location appearance model (e.g. image template, or Mode-Seeking (e.g. m
School: Penn State
Course: Multicasting
Robert Collins CSE598C Particle Filter Failures References King and Forsyth, How Does CONDENSATION Behave with a Finite Number of Samples? ECCV 2000, 695-709. Karlin and Taylor, A First Course in Stochastic Processes, 2nd edition, Academic Press, 1975. Ro
School: Penn State
Course: Multicasting
6.559479; CO\M6 7 gélT-lolzavg~ (v MK ML 00 (5ZWLM Mara/var. F-v'lk rm: 672$ X; n. X4 ML okMa-"nan? Y1 o. 7v. AL A (Sana-7 fray 774.43?" km A7 90mm, vw Ya): PCVDPCYIIM)Plek>PCyzln>PClx,> u , 6" Mv _ onml .1 Cur/war 671%. M o/tb on (aha) 47th [My cu rrm'l'
School: Penn State
Course: Multicasting
CSE598C: Vision-Based Tracking Fall 2012 Syllabus Instructor: Robert Collins, Associate Professor, CSE 354H IST Building Phone: 3-1944; email: rtc12@psu.edu Office Hours: Tues 2-4, Wed 9-9:50 Class Schedule: MWF 10:10AM 11:00PM; 370 Willard Textbook: No T
School: Penn State
Course: Multicasting
Robert Collins Penn State Towards Crowd Scene Analysis Robert Collins CSE598C Robert Collins Penn State Example: Crowd Analysis Automated video analysis of crowds in public spaces using computer vision tools Real-time monitoring situation awareness not
School: Penn State
Course: Multicasting
Robert Collins CSE598C Outline of this Talk Data Association associate common detections across frames matching up who is who Two frames: linear assignment problem Generalize to three or more frames Greedy Method Polynomial time Mincost Network Flo
School: Penn State
Course: Multicasting
Robert Collins Penn State Crowd Scene Analysis Using computer vision tools to look at people in public places Real-time monitoring situation awareness notifications/alarms After-action review traffic analysis VLPR 2012 Robert Collins Penn State Crow
School: Penn State
Course: Multicasting
CSE 598C Vision-based Tracking Seminar Times: MW 10:10-11:00AM Willard 370 Instructor: Robert Collins Ofce Hours: Tues 2-4PM, Wed 9-9:50AM What is Tracking? typical idea: tracking a single target in isolation. Appearance-Based Tracking current frame + pre
School: Penn State
Course: Multicasting
Robert Collins Penn State Tracking in Dense Crowds Goal: Track targets in high-density crowd scenes. Challenges: lots of occlusion; small object sizes; appearances are similar Idea: Model typical crowd behavior to provide better motion priors. VLPR 2012 R
School: Penn State
Course: Multicasting
Robert Collins Penn State Appearance-Based Tracking current frame + previous location Response map (confidence map; likelihood image) current location appearance model (e.g. image template, or Mode-Seeking (e.g. mean-shift; Lucas-Kanade; particle filterin
School: Penn State
Course: Multicasting
Homework 1. CSE 598C Vision-based Tracking, Fall 2012. Due Wed Fri 7, 2012 in Angel. This homework will actually be pretty easy, I think, if you followed the example on Gaussian Point Observations that we went over in class. You can view that example as o
School: Penn State
Course: Multicasting
Robert Collins CSE598C Outline Data Association Scenarios Track Filtering and Gating Global Nearest Neighbor (GNN) Review: Linear Assignment Problem Murthys k-best Assignments Algorithm Probabilistic Data Association (PDAF) Joint Probabilistic Data Assoc
School: Penn State
Course: Topics In Computer Vision
CSE586 Assignment 3, due March 17 Thurs 1) Prove that the set of all 2x2 matrices of the form [cos(theta) -sin (theta); sin(theta) cos(theta)] form a group under matrix multiplication. 2) Prove that the set of all complex numbers of the form e^cfw_i theta
School: Penn State
Course: Topics In Computer Vision
CSE586/EE554 Computer Vision II EM incremental assignments Spring 2011 1. Given a d-dimensional mean vector v and dxd covariance matrix C (symmetric, pos def), generate N random sample points distributed according to a Gaussian with mean v and covariance
School: Penn State
Course: Topics In Computer Vision
This corresponds t o t he point in t he mixt ure of Gaussian powerpoint slides where I say I'll derive E_z[logP(X,Z| t het a)] on t he board
School: Penn State
Course: Topics In Computer Vision
Robert Collins CSE586 CSE 586/EE554 Topics in Computer Vision Course Introduction Spring 2012 Robert Collins CSE586 Course Goals Gain practical knowledge in Computer Vision focusing on solution methods understanding the underlying math knowing when/how
School: Penn State
Course: Topics In Computer Vision
Homework 1 (due Monday Jan 24 by end of the day) 1. Consider the x=1 y=0: 10 y=1: 10 y=2: 0 (unnormalized) 2D bivariate distribution f(x,y) x=2 x=3 x=4 10 10 10 20 20 0 10 0 0 For each of the following, give your answer to 1) a) What is the marginal distr
School: Penn State
Course: Topics In Computer Vision
Note: this derivation for the covariance matrix may not be correct (although it gets the right answer). The reason why is that we havent done anything to constrain the sigma matrix to be symmetric. For a symmetric matrix, all the elements are not independ
School: Penn State
Course: Topics In Computer Vision
Robert Collins CSE586 Introduction to Graphical Models Readings in Prince textbook: Chapters 10 and 11 but mainly only on directed graphs at this time Credits: Several slides are from: Review: Probability Theory Sum rule (marginal distributions) Product
School: Penn State
Course: Topics In Computer Vision
Robert Collins CSE586 CSE 586, Spring 2011 Advanced Computer Vision Procrustes Shape Analysis Robert Collins CSE586 Credits lots of slides are due to Lecture material from Tim Cootes University of Manchester. For more info, see http:/www.isbe.man.ac.uk/~b
School: Penn State
Course: Topics In Computer Vision
M Cal/m ceééf? @ Comémi a: OUV (Lao/raw! 6AM girl A Down Low, W9; wlfTZ, 4.9 4; Moétl, X u, an 4" 7" Am Lioc. WWWB \ 9c ORNW4 vaA. C6773?) A" @ I r I Yr. 74 @ Nov-(K r9(Y«:Yz."~Y~l *3 = Pent?) F6721») "3611, Y, akLgp ft gun. liafaq PCX) Y1 \/-I )5: o "
School: Penn State
Course: Multicasting
6.559479; CO\M6 7 gélT-lolzavg~ (v MK ML 00 (5ZWLM Mara/var. F-v'lk rm: 672$ X; n. X4 ML okMa-"nan? Y1 o. 7v. AL A (Sana-7 fray 774.43?" km A7 90mm, vw Ya): PCVDPCYIIM)Plek>PCyzln>PClx,> u , 6" Mv _ onml .1 Cur/war 671%. M o/tb on (aha) 47th [My cu rrm'l'
School: Penn State
Course: Topics In Computer Vision
This corresponds t o t he point in t he mixt ure of Gaussian powerpoint slides where I say I'll derive E_z[logP(X,Z| t het a)] on t he board
School: Penn State
Course: Topics In Computer Vision
Note: this derivation for the covariance matrix may not be correct (although it gets the right answer). The reason why is that we havent done anything to constrain the sigma matrix to be symmetric. For a symmetric matrix, all the elements are not independ
School: Penn State
Course: Topics In Computer Vision
M Cal/m ceééf? @ Comémi a: OUV (Lao/raw! 6AM girl A Down Low, W9; wlfTZ, 4.9 4; Moétl, X u, an 4" 7" Am Lioc. WWWB \ 9c ORNW4 vaA. C6773?) A" @ I r I Yr. 74 @ Nov-(K r9(Y«:Yz."~Y~l *3 = Pent?) F6721») "3611, Y, akLgp ft gun. liafaq PCX) Y1 \/-I )5: o "
School: Penn State
Course: Topics In Computer Vision
CSE586/EE554: Computer Vision II Spring 2012 Course Overview Instructor: Dr. Robert Collins, email: rcollins@cse.psu.edu Office: IST 354H Office Hours: TBA Course Description: Introduction of mathematical methods commonly used in computer vision along wit
School: Penn State
Course: Topics In Computer Vision
Probability Review Topics 1D distributions discrete (pmf) vs continuous (pdf) normalized vs unnormalized examples [1 2 1] ; uniform(0,1); 1-x^2 | -1 <= x <= 1; 2D (bivariate) distributions joint distribution (with examples of discrete and continuous) exam
School: Penn State
Course: FUND COMP ARCH
Computer Science and Engineering 530 Fundamentals of Computer Architecture Fall 2013 Tuesdays, Thursdays, 9:45-11:00am, 124 Walker (Preliminary) Course Outline (v1.0) L# Date Topic Reading 1 2 Aug 27 Aug 29 Introduction and class overview Technology trend
School: Penn State
4 CASE STUDY OUTLINE T his o utline lists t he i ndividual t opics to b e c overed i n t he case study. Chapters 5 t hrough 9 e xplain t he o utline a nd e laborate i t w ith e xamples. After the r eader becomes f amiliar w ith t his m anual, h e is l ike
School: Penn State
Course: Multicasting
Robert Collins Penn State Crowd Scene Analysis Using computer vision tools to look at people in public places Real-time monitoring situation awareness notifications/alarms After-action review traffic analysis VLPR 2012 Robert Collins Penn State Crow
School: Penn State
Course: Computer VIsion I
Robert Collins CSE486 Lecture 11: LoG and DoG Filters Robert Collins CSE486 Todays Topics Laplacian of Gaussian (LoG) Filter - useful for finding edges - also useful for finding blobs! approximation using Difference of Gaussian (DoG) Robert Collins CSE486
School: Penn State
Course: Computer VIsion I
Robert Collins CSE486, Penn State Lecture 3: Linear Operators Robert Collins CSE486, Penn State Administrivia I have put some Matlab image tutorials on Angel. Please take a look if you are unfamiliar with Matlab or the image toolbox. I have posted Homewor
School: Penn State
Course: Computer VIsion I
Robert Collins CSE486, Penn State Lecture 13: Camera Projection II Reading: T&V Section 2.4 Robert Collins CSE486, Penn State Recall: Imaging Geometry W Object of Interest in World Coordinate System (U,V,W) U V Robert Collins CSE486, Penn State Imaging Ge
School: Penn State
Course: Computer VIsion I
Robert Collins CSE486, Penn State Lecture 12: Camera Projection Reading: T&V Section 2.4 Robert Collins CSE486, Penn State Imaging Geometry W Object of Interest in World Coordinate System (U,V,W) U V Robert Collins CSE486, Penn State Imaging Geometry Came
School: Penn State
Course: Computer VIsion I
Robert Collins CSE486, Penn State Lecture 4: Smoothing Related text is T&V Section 2.3.3 and Chapter 3 Robert Collins CSE486, Penn State Summary about Convolution Computing a linear operator in neighborhoods centered at each pixel. Can be thought of as sl
School: Penn State
Course: Computer VIsion I
Robert Collins CSE486, Penn State Lecture 2: Intensity Surfaces and Gradients Robert Collins CSE486, Penn State Visualizing Images Recall two ways of visualizing an image Intensity pattern We see it at this level 2d array of numbers Computer works at this
School: Penn State
Course: Computer VIsion I
Robert Collins CSE486, Penn State Robert Collins CSE486, Penn State Lecture 18: Generalized Stereo Key idea: Any two images showing an overlapping view of the world can be treated as a stereo pair. Generalized Stereo: Epipolar Geometry . we just have to f
School: Penn State
Course: Computer VIsion I
Robert Collins CSE486, Penn State Lecture 17: Mosaicing and Stabilization Robert Collins CSE486, Penn State Recall: Planar Projection Internal params Perspective projection u Pixel coords v y Homography x Rotation + Translation Point on plane Robert Colli
School: Penn State
Course: Computer VIsion I
Robert Collins CSE486, Penn State Lecture 5: Gradients and Edge Detection Reading: T&V Section 4.1 and 4.2 Robert Collins CSE486, Penn State What Are Edges? Simple answer: discontinuities in intensity. Robert Collins CSE486, Penn State Boundaries of objec
School: Penn State
Course: Computer VIsion I
Robert Collins CSE486 Lecture 10: Pyramids and Scale Space Robert Collins CSE486 Recall Repeated convolution by a smaller Gaussian to simulate effects of a larger one. Cascaded Gaussians G*(G*f) = (G*G)*f [associativity] Robert Collins CSE486 Example: C
School: Penn State
Course: Computer VIsion I
Robert Collins CSE486, Penn State Lecture 08: Introduction to Stereo Reading: T&V Section 7.1 Robert Collins CSE486, Penn State Stereo Vision Inferring depth from images taken at the same time by two or more cameras. Robert Collins CSE486, Penn State Basi
School: Penn State
Course: Computer VIsion I
Robert Collins CSE486, Penn State Lecture 06: Harris Corner Detector Reading: T&V Section 4.3 Robert Collins CSE486, Penn State Motivation: Matchng Problem Vision tasks such as stereo and motion estimation require finding corresponding features across two
School: Penn State
Course: Computer VIsion I
Robert Collins CSE486, Penn State Lecture 14 Parameter Estimation Readings T&V Sec 5.1 - 5.3 Robert Collins CSE486, Penn State Summary: Transformations Euclidean similarity affine projective Robert Collins CSE486, Penn State Parameter Estimation We will t
School: Penn State
Course: Computer VIsion I
Robert Collins CSE486, Penn State Lecture 16: Planar Homographies Robert Collins CSE486, Penn State Motivation: Points on Planar Surface y x Robert Collins CSE486, Penn State Review : Forward Projection World Coords Camera Coords Film Coords U V W X Y Z x
School: Penn State
Course: Computer VIsion I
Robert Collins CSE486, Penn State Lecture 09: Stereo Algorithms Robert Collins CSE486, Penn State Recall: Simple Stereo System Z Y left y camera located at (0,0,0) z ( , x Image coords of point (X,Y,Z) Left Camera: Camps, PSU z ) Tx Right Camera: (X,Y,Z)
School: Penn State
Course: Computer VIsion I
Robert Collins CSE486, Penn State Lecture 7: Correspondence Matching Reading: T&V Section 7.2 Robert Collins CSE486, Penn State Recall: Derivative of Gaussian Filter Ix=dI(x,y)/dx Gx I(x,y) convolve Gy Iy=dI(x,y)/dy convolve Robert Collins CSE486, Penn St
School: Penn State
Course: Computer VIsion I
Robert Collins CSE486, Penn State Lecture 15 Robust Estimation : RANSAC Robert Collins CSE486, Penn State RECALL: Parameter Estimation: Lets say we have found point matches between two images, and we think they are related by some parametric transformatio
School: Penn State
Course: FUND COMP ARCH
CSE 530 Final Project Presentation q <New Opportunities and Challenges for Non-volatile Memory Technologies> <Tianqi Xu and Xiaobo Yu> CSE530 Final Project Presentation.1 <YOURNAMES> Fall 2013 PSU Introduction q STT-RAM (spin-transfer torque RAM) q q STT-
School: Penn State
Course: Introduction To Computer And Network Security
Wireless Security CSE497b - Spring 2007 Introduction Computer and Network Security Professor Jaeger www.cse.psu.edu/~tjaeger/cse497b-s07/ CSE497b Introduction to Computer and Network Security - Spring 2007 - Professor Jaeger At the mall . CSE497b Introduc
School: Penn State
Course: Introduction To Computer And Network Security
Realworldexample:StuxnetWorm Stuxnet:Overview June2010:Awormtarge<ngSiemensWinCC industrialcontrolsystem. Targetshighspeedvariablefrequency programmablelogicmotorcontrollersfromjust twovendors:Vacon(Finland)andFararoPaya (Iran) Onlywhenthecontrollersarer
School: Penn State
Course: Introduction To Computer And Network Security
Intrusion Detection Systems CMPSC 443 - Spring 2012 Introduction Computer and Network Security Professor Jaeger www.cse.psu.edu/~tjaeger/cse443-s12/ CMPSC 443 Introduction to Computer and Network Security - Spring 2012 - Professor Jaeger Intrusion Detecti
School: Penn State
Course: Introduction To Computer And Network Security
Lecture 19 & 20 - Web Security CMPSC 443 - Spring 2012 Introduction Computer and Network Security Professor Jaeger www.cse.psu.edu/~tjaeger/cse443-s12/ CMPSC 443 Introduction to Computer and Network Security - Spring 2012 - Professor Jaeger Network vs. We
School: Penn State
Course: Introduction To Computer And Network Security
Lecture 17 - Network Security CMPSC 443 - Spring 2012 Introduction Computer and Network Security Professor Jaeger www.cse.psu.edu/~tjaeger/cse443-s12/ CMPSC 443 Introduction to Computer and Network Security - Spring 2012 - Professor Jaeger Idea Why dont
School: Penn State
Course: Introduction To Computer And Network Security
Lecture 16 - Network Security CMPSC 443 - Spring 2012 Introduction Computer and Network Security Professor Jaeger www.cse.psu.edu/~tjaeger/cse443-s12/ CMPSC 443 Introduction to Computer and Network Security - Spring 2012 - Professor Jaeger The network . (
School: Penn State
Course: Introduction To Computer And Network Security
Mandatory Access Control CMPSC 443 - Spring 2012 Introduction Computer and Network Security Professor Jaeger www.cse.psu.edu/~tjaeger/cse443-s12/ CMPSC 443 Introduction to Computer and Network Security - Spring 2012 - Professor Jaeger Mandatory Protection
School: Penn State
Course: Introduction To Computer And Network Security
Access Control CMPSC 443 - Spring 2012 Introduction Computer and Network Security Professor Jaeger www.cse.psu.edu/~tjaeger/cse443-s12/ CMPSC 443 Introduction to Computer and Network Security - Spring 2012 - Professor Jaeger Access Control = Security? Do
School: Penn State
Course: Introduction To Computer And Network Security
Access Control CMPSC 443 - Spring 2012 Introduction Computer and Network Security Professor Jaeger www.cse.psu.edu/~tjaeger/cse443-s12/ CMPSC 443 Introduction to Computer and Network Security - Spring 2012 - Professor Jaeger Access Control Describe the p
School: Penn State
Course: Introduction To Computer And Network Security
Program Security CMPSC 443 - Spring 2012 Introduction Computer and Network Security Professor Jaeger www.cse.psu.edu/~tjaeger/cse443-s12/ CMPSC 443 Introduction to Computer and Network Security - Spring 2012 - Professor Jaeger System Resources Programs o
School: Penn State
Course: Introduction To Computer And Network Security
Program Security CMPSC 443 - Spring 2012 Introduction Computer and Network Security Professor Jaeger www.cse.psu.edu/~tjaeger/cse443-s12/ CMPSC 443 Introduction to Computer and Network Security - Spring 2012 - Professor Jaeger Programming Why do we write
School: Penn State
Course: FUND COMP ARCH
CSE 530 Final Project Presentation q <Survey on reducing power consumption for non volatile memories> <Tianqi Xu and Xiaobo Yu> CSE530 Final Project Presentation.1 <Tianqi Xu and Xiaobo Yu> Fall 2013 PSU Introduction q STT-RAM (spin-transfer torque RAM) q
School: Penn State
Course: FUND COMP ARCH
CSE 530 Final Project Presentation q <New Opportunities and Challenges for Non-volatile Memory Technologies> <Tianqi Xu and Xiaobo Yu> CSE530 Final Project Presentation.1 <YOURNAMES> Fall 2013 PSU The problem/opportunity (what is it, broadly?) q Provide g
School: Penn State
Course: Discrete Mathematics
CSE 260.2 Spring 2003 Quiz I 20 points Name _ 1. Use a truth table to prove p q ~p q. The truth table has been started for you. (You may not necessarily use all columns.) [8 pts] p q T T T F F T F F 2. Given the premises "If Zeus is human, then Zeus is mo
School: Penn State
Course: Discrete Mathematics
CSE 260.2 Spring 2003 Quiz I 20 points Name _ 1. Use a truth table to prove p q ~p q. The truth table has been started for you. (You may not necessarily use all columns.) [8 pts] p q ~p ~p q pq T T F T T T F F F F F T T T T F F T T T These two columns are
School: Penn State
Course: Discrete Mathematics
CSE 260 Exam Quiz Name _ Use the valid argument forms (and only the valid argument forms) we discussed in class to deduce the conclusion from the given premises. Number and label each step or deduction clearly. PREMISES: 1. ~p q 2. r 3. ~p r 4. ~s 5. ~q (
School: Penn State
Course: Discrete Mathematics
CSE 260 Discrete Mathematics for Computer Science Spring 2003, Section 2 Exam III: Combinatorics, Functions, Recurrences, Relations Form A - Solution April 11, 2003 Name _ Last 4 digits of ID _ _ _ _ Write your ID on every page of this exam. No notes, boo
School: Penn State
Course: Discrete Mathematics
CSE 260 Discrete Mathematics for Computer Science Spring 2003, Section 2 Exam II: Proof Techniques and Set Theory Form A - Key March 5, 2003 Name _ Last 4 digits of ID _ _ _ _ Write your name on every page of this exam. No notes, books, or calculators are
School: Penn State
Course: Discrete Mathematics
CSE 260 Discrete Mathematics for Computer Science Spring 2003, Section 2 Exam I: Logic Form A February 3, 2003 Name _ Last 4 digits of ID _ _ _ _ Write your name on every page of this exam. No notes, books, or calculators are permitted. Present each probl
School: Penn State
Course: Digital Logic
Student Name_ Section 1(9. 50A) or 2 (10.10A) Take home part of the Final CSE271. Answer both questions ( Ten points each question). Complete and submit at the end of 12/15/06 class or at the Exam hall before taking your exam. Attach additional paper as n
School: Penn State
Course: Digital Logic
Student name: _Section 4(9.05) or 3(12.20) Midterm Exam - I for CSE 271 Sections (3) and (4) Fall 2005 10/6/2005 - 8:15-10:15 p.m. - 112 Kern Dr Kabekode V. Bhat, Associate Professor of Computer Science & Engineering, The Pennsylvania State University,346
School: Penn State
Course: Digital Logic
Student name: _Section 3 or 4 Final Exam for CSE 271 Sections (3) and (4) Fall 2005 12- 12-2005, 12:20P-2:10P, 100 LIFE SCI, 009 LIFE SCI Dr Kabekode V. Bhat, Associate Professor of Computer Science & Engineering, The Pennsylvania State University111D, In
School: Penn State
Course: Digital Logic
Student name: _Section 4(9.05) or 3(12.20) Midterm Exam - II for CSE 271 Sections (3) and (4) Fall 2005 11/9/2005 - 8:15-10:15 p.m. - 112 Kern Dr Kabekode V. Bhat, Associate Professor of Computer Science & Engineering, The Pennsylvania State University 11
School: Penn State
Course: NUM LINEAR ALGEBRA
Computer Science/Mathematics 550 Numerical Linear Algebra Final Exam Due 27 April 2012, 5pm No late exams, please! 1. Exercise 3.4, p.49, Hansen book. Choose n = 16, 32, 64. 2. Distance from Orthogonality. Let X, U Rmn and let C, V Rnn . Suppose that C is
School: Penn State
Course: Compiler Construction
Simple Dependence Testing Main Theme Determining whether dependencies exist between two subscripted references to the same array in a loop nest Several tests to detect these dependencies Basics: Indices and Subscripts Index: Index variable for some loop s
School: Penn State
Course: INTRO COMP ARCH
CSE 431 Computer Architecture Fall 2005 Lecture 15: Midterm Exam Review Mary Jane Irwin ( www.cse.psu.edu/~mji ) www.cse.psu.edu/~cg431 [Adapted from Computer Organization and Design, Patterson & Hennessy, 2005 and Superscalar Microprocessor Design, Johns
School: Penn State
Course: LOG DESIGN DIG SYS
Exam I Name: CSE 471, Fall 2004 Section: _ Student ID number (last 4 digits): This is an OPEN BOOK and CLOSED NOTE exam. * Please write your name on every page and show all your work. * Write your solutions clearly. You may use backside of each page for s
School: Penn State
Course: LOG DESIGN DIG SYS
Final Exam Name: CSE 471, Fall 2004 Section: _ Student ID number (last four digits): This is an OPEN BOOK and CLOSED NOTE exam. * Write your solutions clearly. You may use backside of each page for scratch but the solutions must be shown on the designated
School: Penn State
Course: COMP ORG & DESIGN
Student Name_ Section 1& 2 Take home part of CSE331 Spring exam 2. Answer all questions (Total 10 points). Complete and submit at the beginning of Exam-2 (before taking your closed book part of exam 2). Attach additional paper as needed. Use notati
School: Penn State
Course: INTERMED PROGRMG
/ IOtest.cpp : Defines the entry point for the console application. / #include "stdafx.h" #include <fstream> #include <iostream> using namespace std; #define BEGIN { #define END } int _tmain(int argc, _TCHAR* argv[]) BEGIN ofstream testout; char infi
School: Penn State
Course: DATA STRUCTURES
CSE 260 SOLUTIONS TO YELLOW QUIZ 9 Spring 2007 1. [7 points] Let cn be the number of ways you can climb a staircase of n stairs if you can climb two or three stairs with each step that you take. Thus, for example, c1 = 0 and c2 = 1. Write a recurr
School: Penn State
CSE 260 SOLUTIONS TO YELLOW QUIZ 7 Spring 2007 INSTRUCTIONS: When your answer includes a product of integers, multiply them out. 1. [4 points] Suppose that we take a 52-card deck of cards and throw away all of the cards except aces, kings, queens,
School: Penn State
Course: Multicasting
Homework 1. CSE 598C Vision-based Tracking, Fall 2012. Due Wed Fri 7, 2012 in Angel. This homework will actually be pretty easy, I think, if you followed the example on Gaussian Point Observations that we went over in class. You can view that example as o
School: Penn State
Course: Topics In Computer Vision
CSE586 Assignment 3, due March 17 Thurs 1) Prove that the set of all 2x2 matrices of the form [cos(theta) -sin (theta); sin(theta) cos(theta)] form a group under matrix multiplication. 2) Prove that the set of all complex numbers of the form e^cfw_i theta
School: Penn State
Course: Topics In Computer Vision
Homework 1 (due Monday Jan 24 by end of the day) 1. Consider the x=1 y=0: 10 y=1: 10 y=2: 0 (unnormalized) 2D bivariate distribution f(x,y) x=2 x=3 x=4 10 10 10 20 20 0 10 0 0 For each of the following, give your answer to 1) a) What is the marginal distr
School: Penn State
Course: VLSI
HOMEWORK 4 CMPEN 411 Due: 2/12/2013 11:30pm Learning Objective Use the VLSI CAD tools to design and implement an 8-bit Program Counter (PC) circuit in bit-slice style and analyze it. Instruction Implement the program counter circuit shown below in schemat
School: Penn State
Course: NUM LINEAR ALGEBRA
Hidden page Hidden page Hidden page Hidden page Hidden page Hidden page Hidden page Hidden page Hidden page Hidden page Hidden page Hidden page Hidden page Hidden page Hidden page Hidden page Hidden page Hidden page Hidden page Hidden page Hidden page Hid
School: Penn State
Course: Compiler Construction
Homework 2 (Due March 20th, 2012) 1. [25points] Identify the dependences in the following loop nest and indicate whether (a) they are loopindependent or loop-carried, and (b) whether they are flow, anti or output dependences? for i = 3, 100 U[i] = V[i] +
School: Penn State
Course: Multicasting
CSE598C: Vision-Based Tracking Fall 2012 Syllabus Instructor: Robert Collins, Associate Professor, CSE 354H IST Building Phone: 3-1944; email: rtc12@psu.edu Office Hours: Tues 2-4, Wed 9-9:50 Class Schedule: MWF 10:10AM 11:00PM; 370 Willard Textbook: No T
School: Penn State
Course: Comm Networks
CSE/EE 458: Communication Networks Instructor: Guohong Cao Ofce, Phone, Email: 310 pond lab, 863-1241, gcao@cse.psu.edu Ofce Hours: MW 9:30-10:50 TA: Namhyong Kim Ofce, Phone, Email: 125 Hammond, 865-9191, nakim@cse.psu.edu Ofce Hours: MF 10:30 - 12:
School: Penn State
Course: Cmptr Networks
CSE 514: Computer Networks Instructor: Guohong Cao Ofce, Phone, Email: 354G IST, 863-1241, gcao@cse.psu.edu Ofce Hours: TR 2:00 - 3:15 TA: Ofce, Phone, Email: Ofce Hours: Textbook: Computer Networks: A Top-Down Approach Featuring the Internet, Fourth
School: Penn State
Course: Distributed System
CSE 513: Distributed Systems Instructor: Guohong Cao Ofce, Phone, Email: 354G IST building, 863-1241, gcao@cse.psu.edu Ofce Hours: TR: 1PM - 2PM. TA: Wenhui Hu Ofce, Phone, Email: 338E IST, 865-0191, wxh180@cse.psu.edu Ofce Hours: Wed, 1- 2pm; Fri, 9
School: Penn State
Course: PROGRAMMING FOR ENGINEERS
COMPUTER SCIENCE & ENGINEERING 121 Spring 2007 Professor: Dr. Susan L. Quick Office: 111J IST Phone: 865-9507 E-mail: quick@cse.psu.edu or through ANGEL (Do not use any other e-mail address!) Office Hours: M 1:30 2:30, W: 3:30 5:30 or by appointmen