# Lecture-10 - Alper Yilmaz Motivation Change Detection Skin...

This preview shows pages 1–4. Sign up to view the full content.

Alper Yilmaz UCF Computer Vision Lab. 1 Change Detection, Skin Detection Lecture-10 UCF Computer Vision Lab. 2 Motivation ! Detection of interesting objects in videos is the first step in the process of automated surveillance. Focus of attention method greatly reduces the processing time required for tracking and activity recognition. UCF Computer Vision Lab. 3 Introduction ! Objectives: ! Given a sequence of images from a stationary camera identify pixels comprising ‘interesting’ objects. General Solution –Model properties of the scene (e.g. color, texture e.t.c) at each pixel. All independently moving objects are interesting! –Significant change in the properties indicates an interesting change. UCF Computer Vision Lab. 4 Introduction ! Problems in Realistic situations: ! Moving but uninteresting objects ! e.g. trees, flags or grass. Long term illumination changes •e.g. time of day. Quick illumination changes •e.g. cloudy weather Shadows Other Physical changes in the background •Dropping or picking up of objects Initialization UCF Computer Vision Lab. 5 Segmenting Background UCF Computer Vision Lab. 6 Difference Pictures ! Jain, R. and Nagel, H. 1979. ``On the analysis of accumulative difference pictures from image sequences of real world scenes”. IEEE Trans. on Pattern Analysis and Machine Intelligence 1, 2, pp 206-214.

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

View Full Document
Alper Yilmaz UCF Computer Vision Lab. 2 UCF Computer Vision Lab. 7 Background Subtraction - = ! Problem: Choosing a threshold ! Pixel is foreground if I 1 ( x , y )- I 2 ( x , y ) ! ! otherwise background? ! What is the correct value of ! ? UCF Computer Vision Lab. 8 Setting a Threshold ! = 10 ! = 20 ! = 50 ! = 100 ! = 200 ! = 300 UCF Computer Vision Lab. 9 MODELING PIXEL INTENSITIES WITH A NORMAL DISTRIBUTION Each pixel intensity can be modeled by a Normal Distribution, defined in terms of a mean " and variance # 2 , as as N ( " , # 2 ). ). " and and # are called parameters. are called parameters. Useful when you wish to establish membership of a pixel to one of several models. N ( " , # 2 ) is a probability distribution ) is a probability distribution function defined by: ) 2 ( ) ( 2 2 2 2 2 1 ) , | ( # " \$# # " % % & x e f x UCF Computer Vision Lab. 10 Bi-variate Normal Distribution ! If we were interested in r-g , or g-b , or r- b ! The mean can be updated over time simply as UCF Computer Vision Lab. 11 Covariance ( ) * * + , & - # # 0 0 ( ) * * + , & - 2 1 0 0 # # ( ) * * + , & - 22 21 12 11 # # # # UCF Computer Vision Lab. 12 Tri-variate Normal
Alper Yilmaz UCF Computer Vision Lab. 3 UCF Computer Vision Lab. 13 Method I: P finder !

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

View Full Document
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

### What students are saying

• 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.

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

• 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.

Dana University of Pennsylvania ‘17, Course Hero Intern

• 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.

Jill Tulane University ‘16, Course Hero Intern