vision_slides

vision_slides - CS221ArtificialIntelligence:...

Info iconThis preview shows pages 1–8. Sign up to view the full content.

View Full Document Right Arrow Icon
    CS221 Artificial Intelligence:  Challenge Problem 2 Object Recognition and Tracking Stephen Gould <sgould@stanford.edu> Ian Goodfellow <ia3n@stanford.edu> October, 2007
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
    Overview Challenge problem Problem statement Source code overview Haar features Milestone requirements OpenCV tutorial Introduction and installation Code samples Object recognition tips and tricks
Background image of page 2
    Challenge Problem
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
    Source Code Overview classifier.cpp Defines the CClassifier class. You are free to modify  this file, but do not modify the interface to the  loadState() and run() methods. CXMLParser.cpp Class for parsing XML files. Used for replaying ground  truth object labels. objects.cpp Contains the data structures for annotated objects.  Do  not modify this file. replay.cpp Contains code for replaying object labels (such as  ground truth labels).  Do not modify this file. test.cpp Contains main() code for testing classifiers on videos.  Do not modify this file. train.cpp Contains training starter code. You are free to modify  everything in this file. utils.cpp Contains useful utility functions.
Background image of page 4
    Command-line Options train [<options>] <directory> <directory>  is the root directory containing (subdirectories of) all the  training images -c <filename>  writes learned parameters to a file after training using  CClassifier::saveState() -h  provides help -v  gives verbose output test [<options>] <AVI filename> <AVI filename>  is the name of the video you want to test on (e.g.  “easy.avi”) -c <filename>  configures the classifier with parameters from a file  using  CClassifier::loadState() -g <filename>  displays ground truth labels from an XML file -h  provides help -o <filename>  saves classifications to an XML file (same format as  –g ) -v  gives verbose output -x  disables display of the video (if you don’t have X-windows)
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
    Training File Lists typedef struct _TTrainingFile { std::string filename; // full path to image file std::string label; // subdirectory name } TTrainingFile; typedef struct _TTrainingFileList { std::vector<TTrainingFile> files; // list of files std::vector<std::string> classes; // list of classes (subdirectories) } TTrainingFileList; data/ mug/ other/ code/
Background image of page 6
    CObject Class class CObject { public : CvRect rect; // object's bounding box (x,y,width,height) std::string label; // object's class public : // constructors CObject(); CObject( const CObject&); CObject( const CvRect&, const std::string&); // destructor virtual ~CObject();
Background image of page 7

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 8
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 11/30/2009 for the course CS 221 taught by Professor Koller,ng during the Winter '09 term at Stanford.

Page1 / 27

vision_slides - CS221ArtificialIntelligence:...

This preview shows document pages 1 - 8. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online