Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Scribd
Upload
394 views

Object Detection Tutorial

This document provides an overview of object detection methods using OpenCV. It discusses using simple image features to detect simple objects and learning-based methods like Viola-Jones to detect complex objects. The Viola-Jones method uses Haar-like features and AdaBoost learning on positive and negative image samples to build a statistical model for object detection. It then describes the process for building an object detector using OpenCV's Haar training tools by collecting samples, training the classifier, and converting it to an XML file.

Uploaded by

Hidoi Jinko
Copyright
© Attribution Non-Commercial (BY-NC)
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
394 views

Object Detection Tutorial

This document provides an overview of object detection methods using OpenCV. It discusses using simple image features to detect simple objects and learning-based methods like Viola-Jones to detect complex objects. The Viola-Jones method uses Haar-like features and AdaBoost learning on positive and negative image samples to build a statistical model for object detection. It then describes the process for building an object detector using OpenCV's Haar training tools by collecting samples, training the classifier, and converting it to an XML file.

Uploaded by

Hidoi Jinko
Copyright
© Attribution Non-Commercial (BY-NC)
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
You are on page 1/ 9

A Tutorial on Object

Detection Using OpenCV


Introduction
The goal of object detection is to find an
object of a pre-defined class in a static
image or video frame.


Methods
Simple objects
Extracting certain image features, such as edges, color
regions, textures, contours, etc.
Complex objects
Learning-based method:
Viola and Jones, Rapid object detection using a boosted cascade of
simple features, CVPR 2001


Statistical model-based training
Take multiple positive samples, i.e., objects of
interest, and negative samples, i.e., images
that do not contain objects.
Different features are extracted from samples
and distinctive features are compressed into
the statistical model parameters.
It is easy to make an adjustment by adding new
positive or negative samples.
Haar-like Features
Example
Features value is calculated as the difference between the
sum of the pixels within white and black rectangle regions.
) Sum(r ) Sum(r
black i, white i,
=
i
f

<
>
=
threshold f if
threshold f if
x h
i
i
i
1
1
) (
Adaboost Learning
) ... (
2 2 1 1 n n
h w h w h w sign F + + + =

<
>
=
i i
i i
i
f if
f if
x h
u
u
1
1
) ( , where
The more distinctive the feature, the larger the weight.
Detector in Intel OpenCV
1. Collect a database of positive samples and a
database of negative samples.
2. Mark object by objectmarker.exe
3. Build a vec file out of positive samples using
createsamples.exe
4. Run haartraining.exe to build the classifier.
5. Run performance.exe to evaluate the
classifier.
6. Run haarconv.exe to convert classifier to .xml
file
Links
Original paper:
http://research.microsoft.com/~viola/Pubs/Detect/violaJones_C
VPR2001.pdf
How-to build a cascade of boosted classifiers based on Haar-
like features:
http://lab.cntl.kyutech.ac.jp/~kobalab/nishida/opencv/OpenCV_
ObjectDetection_HowTo.pdf
Objectmarker.exe and haarconv.exe, *.dll:
http://www.iem.pw.edu.pl/~domanskj/haarkit.rar

You might also like