CS231A Midterm Review - Stanford University
CS231A Midterm ReviewMay 19, 2017
Midterm Logistics In-class midterm at Skilling Auditorium at 3:00-4:20 PM on May 22, 2017SCPD students not taking exam at Stanford should coordinate with SCPD.Open book and open notes. Not open computer.Lectures 1 - 12 (through Image Classification & 2D Object Detection)10 T/F, 10 MC, 3 longer questions (similar to last year’s)
Topics you should know for the Exam General knowledge of linear algebra (matrix multiplication, SVD, etc)Camera Models and TransformationsNon-perspective CamerasCamera CalibrationSingle View MetrologyEpipolar GeometryStructure from MotionActive Stereo and Volumetric StereoFitting and MatchingRANSACHough TransformDetectors and DescriptorsImage Classification2D Object Detection
Homogeneous Coordinates Homogenous coordinates allow us to apply a larger variety oftransformations with matrix multiplication For example, we use homogeneous coordinates to handle the 3D - 2D projectionAny point (x, y) becomes represented as (x, y, 1)More generally (a1, a2, , an, w) represents the point (a1/w, a2/w, , an/w)
Types of transformations Isometric transformations preserve distances Similarity transformations preserve shape Rotation, translation, scalingAffine transformations preserve parallelism Rotation, translation, reflectionRotation, translation, scaling, shearing, etc.T(v) Av t, A is invertibleProjective transformations map lines to lines Pretty much everything else
Camera Parameters Extrinsic parameters Rotation and translation from the world frameIntrinsic parameters Focal length in x and y direction, camera center offset, skew, distortionMost people assume only 5 parameters (for the sake of this class)
Camera Calibration
Camera CalibrationSolve by SVD!
Single View Metrology Vanishing points and vanishing lines (horizon) This leads to being able to find angles between lines and planes (recall PS1)You can also calibrate the camera from a single image!
Epipolar Geometry Understanding the geometry of the scene and the camerasShould have knowledge of this entire scene and basic triangulation Epipoles, epipolar lines, reprojection error, etc.
Unique Cases of Epipolar Geometry Parallel cameras make the epipoles at infinityForward translation make the epipoles in the same location
The Fundamental Matrix Relates corresponding points with a single constraint7 degrees of freedomCan be found using Eight Point Algorithm and Normalized Eight-PointalgorithmSolve by SVD!
Structure from Motion Estimating both the camera positions and the 3D structure simultaneouslyfrom point correspondencesYou’ve implemented a few algorithms: Factorization methodAn iterative triangulation method
Active Stereo and Volumetric Stereo Active Stereo Replaces one camera with a projectorVolumetric Stereo Space carvingShadow carvingVoxel coloring
RANSAC Select random sample of minimum sizeCompute a model from thisCompute the inliers within the modelRepeat steps for a fixed amount and return the model with the most inliers
Hough Transform Find some parameter space that defines the line, plane, etc. that we’re tryingto estimateFor each observation, plot in this parameter space Could be points, lines, hyperplanes, etc.Grid up the parameter space and find cells with many observationsIf there is a problem, will be similar to the example found in lecture
Detectors and Descriptors Corner detectors Edge detectors Similar to edge detection, but in 2DSIFT Find areas of high gradients, but should smooth before doing so to remove noiseShould know about Laplacian of Gaussian and Difference of GaussianBlob detection Harris corner detectorA local descriptor around keypoints based on gradients in the imageScale and in-plane rotation invariantHOG Implemented in PS3 - you should know about it!
Image Classification and 2D Object Detection This questions on the midterm will be purely conceptual - nothing toodifficultBag of words Histogram representation of “words” (features)Part of PS4 (don’t need to implement, but skimming the ideas in preparationfor the midterm is a good idea) Sliding window detectorsNon-maximal suppression
Exam Advice When studying, make a cheat sheet to quickly reference at exam time. You will not need to know the complex math derivations involved in thecourse. Since you have 80 minutes, you do not want to sift through pages of notes.There are some linear algebra problems, though!You will need to know how generally things work and explain them (cameramatrices, SFM, RANSAC, Hough transforms, etc.).This review session is not comprehensive of all material on the exam!
CS231A Midterm Review May 19, 2017. Midterm Logistics In-class midterm at Skilling Auditorium at 3:00-4:20 PM on May 22, 2017 . Unique Cases of Epipolar Geometry . This review session is not comprehensive of all material on the exam! .
SEISMIC: A Self-Exciting Point Process Model for Predicting Tweet Popularity Qingyuan Zhao Stanford University qyzhao@stanford.edu Murat A. Erdogdu Stanford University erdogdu@stanford.edu Hera Y. He Stanford University yhe1@stanford.edu Anand Rajaraman Stanford University anand@cs.stanford.edu Jure Leskovec Stanford University jure@cs.stanford .
Algebra 2 - Midterm Exam Review The Algebra 2 Midterm Exam must be taken by ALL Algebra 2 students. An exemption pass may be used to exempt the score for the Algebra 2 Midterm Exam. It should be presented to your teacher prior to taking the exam. The Algebra 2 Midterm Exam will consist of 30 multiple choice questions.
Computer Science Stanford University ymaniyar@stanford.edu Madhu Karra Computer Science Stanford University mkarra@stanford.edu Arvind Subramanian Computer Science Stanford University arvindvs@stanford.edu 1 Problem Description Most existing COVID-19 tests use nasal swabs and a polymerase chain reaction to detect the virus in a sample. We aim to
Domain Adversarial Training for QA Systems Stanford CS224N Default Project Mentor: Gita Krishna Danny Schwartz Brynne Hurst Grace Wang Stanford University Stanford University Stanford University deschwa2@stanford.edu brynnemh@stanford.edu gracenol@stanford.edu Abstract In this project, we exa
Stanford University Stanford, CA 94305 bowang@stanford.edu Min Liu Department of Statistics Stanford University Stanford, CA 94305 liumin@stanford.edu Abstract Sentiment analysis is an important task in natural language understanding and has a wide range of real-world applications. The typical sentiment analysis focus on
Geometry Midterm Review Packet 7 Geometry: Midterm Short Answer Practice 1. Find the coordinates of point P along the directed line segment AB so that AP to PB is the given ratio. A) A(1, 3), B(8, 4); 4 to 1 B) A(-2, 1), B(4, 5); 3 to 7 2. Determine if the following lines are parallel, perpendicular, or neither. Explain your reasoning. A) 1
On each exam, you will be given a MIPS Green Sheet attached to the exam. Midterm 1: Covers up to and including the 07/02 lecture on CALL. Midterm 1: One 8.5"x11", double-sided cheat sheet. The clobber policy allows you to override your Midterm 1 and Midterm 2 scores with the score of the corresponding section on the final exam if you
Awards Q and A This document provides answers to some of the frequently asked questions about the National Apprenticeship Awards. If you would like more information or help with your entry, you can email us at entries@appawards.co.uk or call the helpline on 0800 954 88 96.
