{[ promptMessage ]}

Bookmark it

{[ promptMessage ]}

cs221-vision-slides

cs221-vision-slides - CS221 Artificial Intelligence...

Info icon This preview shows pages 1–9. Sign up to view the full content.

View Full Document Right Arrow Icon
CS221 Artificial Intelligence: Principles & Techniques Challenge Problem 2 Object Recognition and Tracking Ian Goodfellow Olga Russakovsky Stephen Gould [email protected] October, 2009
Image of page 1

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

View Full Document Right Arrow Icon
Overview ! Challenge problem ! Problem statement ! Starter code overview ! Milestone requirements ! Milestone techniques ! Object recognition tips and tricks ! OpenCV tutorial ! Introduction and installation ! Code samples
Image of page 2
Challenge Problem
Image of page 3

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

View Full Document Right Arrow Icon
Starter Code Overview Scores detections generated via test.cpp. Do not modify this file. evaluate.cpp Contains training starter code. You are free to modify everything in this file, or even replace it with multi- stage training. train.cpp Contains useful utility functions. utils.cpp Contains code that performs template matching for you. template.cpp Contains main() code for testing classifiers on videos. Do not modify this file. test.cpp Contains the data structures for annotated objects. Do not modify this file. objects.cpp Contains code for replaying object labels (such as ground truth labels). Do not modify these files. CXMLParser.cpp, replay.cpp Defines the Classifier class. You are free to modify this file, but do not modify the interface to the loadState() and run() methods. classifier.cpp
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 Classifier::saveState() ! -h provides help ! -v gives verbose output ! test [<options>] <video directory> ! <video directory> is the name of the video you want to test on (e.g. “vision/data/easy”) ! -c <filename> configures the classifier with parameters from a file using Classifier::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)
Image of page 5

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

View Full Document Right Arrow Icon
Classifier Class class Classifier { protected : CvRNG rng; CvMat *parameters; // TO DO: ADD YOUR MEMBER VARIABLES HERE public : // constructors and destructors Classifier(); virtual ~Classifier(); // load and save classifier configuration virtual bool loadState( const char *); virtual bool saveState( const char *); // run the classifier over a single frame virtual bool run( const IplImage *, CObjectList *); // train the classifier using given set of files virtual bool train(TTrainingFileList&); protected : // TO DO: ADD YOUR MEMBER FUNCTIONS HERE };
Image of page 6
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/
Image of page 7

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

View Full Document Right Arrow Icon
CObject Class class CObject { public : CvRect rect; // object's bounding box (x,y,width,height) std::string label; // object's class public : // constructors
Image of page 8
Image of page 9
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

What students are saying

  • Left Quote Icon

    As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

    Student Picture

    Kiran Temple University Fox School of Business ‘17, Course Hero Intern

  • Left Quote Icon

    I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

    Student Picture

    Dana University of Pennsylvania ‘17, Course Hero Intern

  • Left Quote Icon

    The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

    Student Picture

    Jill Tulane University ‘16, Course Hero Intern