Scribd
Upload
145 views9 pages

OpenCV Object Detection Tutorial

This document discusses object detection methods using OpenCV. It describes Haar-like features which extract edges, color and texture from samples to distinguish objects. An AdaBoost learning algorithm is used to train a classifier with these features, assigning higher weights to more distinctive ones. The trained classifier can then be used to detect objects in an image by analyzing features and comparing to the statistical model.

Uploaded by

bssandilya
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
145 views9 pages

OpenCV Object Detection Tutorial

This document discusses object detection methods using OpenCV. It describes Haar-like features which extract edges, color and texture from samples to distinguish objects. An AdaBoost learning algorithm is used to train a classifier with these features, assigning higher weights to more distinctive ones. The trained classifier can then be used to detect objects in an image by analyzing features and comparing to the statistical model.

Uploaded by

bssandilya
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd

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

•Feature’s value is calculated as the difference between the


sum of the pixels within white and black rectangle regions.

 1 if f i  threshold
f i  Sum(ri, white )  Sum(ri, black ) hi ( x)  
 1 if f i  threshold
Adaboost Learning

F  sign( w1h1  w2 h2  ...  wn hn )


 1 if f i   i
where, hi ( x)  
 1 if f i   i

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 [Link]
3. Build a vec file out of positive samples using
[Link]
4. Run [Link] to build the classifier.
5. Run [Link] to evaluate the
classifier.
6. Run [Link] to convert classifier to .xml
file
Links
• Original paper:
[Link]
[Link]
• How-to build a cascade of boosted classifiers based on Haar-
like features:
[Link]
ObjectDetection_HowTo.pdf
• [Link] and [Link], *.dll:
[Link]

You might also like