Region-Level Motion- Based Background Modeling and Subtraction Using MRFs Shih-Shinh Huang Li-Chen...

26
Region-Level Motion-Ba Region-Level Motion-Ba sed Background sed Background Modeling and Subtracti Modeling and Subtracti on Using MRFs on Using MRFs Shih-Shinh Huang Shih-Shinh Huang Li-Chen Fu Li-Chen Fu Pei-Yung Hsiao Pei-Yung Hsiao 2007 IEEE 2007 IEEE
  • date post

    15-Jan-2016
  • Category

    Documents

  • view

    214
  • download

    0

Transcript of Region-Level Motion- Based Background Modeling and Subtraction Using MRFs Shih-Shinh Huang Li-Chen...

Page 1: Region-Level Motion- Based Background Modeling and Subtraction Using MRFs Shih-Shinh Huang Li-Chen Fu Pei-Yung Hsiao 2007 IEEE.

Region-Level Motion-Based Region-Level Motion-Based BackgroundBackground

Modeling and Subtraction Modeling and Subtraction Using MRFsUsing MRFsShih-Shinh HuangShih-Shinh Huang

Li-Chen FuLi-Chen FuPei-Yung HsiaoPei-Yung Hsiao

2007 IEEE2007 IEEE

Page 2: Region-Level Motion- Based Background Modeling and Subtraction Using MRFs Shih-Shinh Huang Li-Chen Fu Pei-Yung Hsiao 2007 IEEE.

AbstractAbstract

This paper presents a new approach to aThis paper presents a new approach to automatic segmentation of foreground outomatic segmentation of foreground objects from an image sequence by integrbjects from an image sequence by integrating techniques of background subtracating techniques of background subtraction and motion-based foreground segmtion and motion-based foreground segmentation.entation.

Page 3: Region-Level Motion- Based Background Modeling and Subtraction Using MRFs Shih-Shinh Huang Li-Chen Fu Pei-Yung Hsiao 2007 IEEE.

OutlineOutline

INTRODUCTIONINTRODUCTION REGION-BASED MOTION REGION-BASED MOTION

SEGMENTATIONSEGMENTATION BACKGROUND MODELINGBACKGROUND MODELING MRFS-BASED CLASSIFICATIONMRFS-BASED CLASSIFICATION RESULTSRESULTS CONCLUSIONCONCLUSION

Page 4: Region-Level Motion- Based Background Modeling and Subtraction Using MRFs Shih-Shinh Huang Li-Chen Fu Pei-Yung Hsiao 2007 IEEE.

INTRODUCTIONINTRODUCTION

In many applications, success of detecting foreground regions from a static background scene is an important step before high-level processing.

In real-world situations, there exist several kinds of environment variations that will make the foreground detection more difficult.

Page 5: Region-Level Motion- Based Background Modeling and Subtraction Using MRFs Shih-Shinh Huang Li-Chen Fu Pei-Yung Hsiao 2007 IEEE.

Several kinds of environment variations

Illumination VariationGradual illumination variationSudden illumination variationShadow

Motion VariationGlobal motionLocal motion

Page 6: Region-Level Motion- Based Background Modeling and Subtraction Using MRFs Shih-Shinh Huang Li-Chen Fu Pei-Yung Hsiao 2007 IEEE.

System Overview

Page 7: Region-Level Motion- Based Background Modeling and Subtraction Using MRFs Shih-Shinh Huang Li-Chen Fu Pei-Yung Hsiao 2007 IEEE.

REGION-BASED MOTION REGION-BASED MOTION SEGMENTATIONSEGMENTATION

motion vector

Page 8: Region-Level Motion- Based Background Modeling and Subtraction Using MRFs Shih-Shinh Huang Li-Chen Fu Pei-Yung Hsiao 2007 IEEE.

Region Projection

Projecting regions in the previous frame to the current one, is to facilitate the segmentation.

Page 9: Region-Level Motion- Based Background Modeling and Subtraction Using MRFs Shih-Shinh Huang Li-Chen Fu Pei-Yung Hsiao 2007 IEEE.

Motion Marker Extraction

The output of this step is a set of motion-coherent regions, all pixels within a region comply with a motion model.

Page 10: Region-Level Motion- Based Background Modeling and Subtraction Using MRFs Shih-Shinh Huang Li-Chen Fu Pei-Yung Hsiao 2007 IEEE.
Page 11: Region-Level Motion- Based Background Modeling and Subtraction Using MRFs Shih-Shinh Huang Li-Chen Fu Pei-Yung Hsiao 2007 IEEE.

Boundary Determination

Merge uncertain pixels to one of the markers.

Page 12: Region-Level Motion- Based Background Modeling and Subtraction Using MRFs Shih-Shinh Huang Li-Chen Fu Pei-Yung Hsiao 2007 IEEE.
Page 13: Region-Level Motion- Based Background Modeling and Subtraction Using MRFs Shih-Shinh Huang Li-Chen Fu Pei-Yung Hsiao 2007 IEEE.

BACKGROUND MODELINGBACKGROUND MODELING

A brief description of Stauffer and Grimson’s work is first given and then we introduce the Bhattacharyya distance as the difference measure between the region from the region-based motion segmentation and the one represented by the background model.

Page 14: Region-Level Motion- Based Background Modeling and Subtraction Using MRFs Shih-Shinh Huang Li-Chen Fu Pei-Yung Hsiao 2007 IEEE.

Adaptive Gaussian Mixture Models

Page 15: Region-Level Motion- Based Background Modeling and Subtraction Using MRFs Shih-Shinh Huang Li-Chen Fu Pei-Yung Hsiao 2007 IEEE.

Bhattacharyya Distance

Page 16: Region-Level Motion- Based Background Modeling and Subtraction Using MRFs Shih-Shinh Huang Li-Chen Fu Pei-Yung Hsiao 2007 IEEE.

Shadow effectShadow effect

However, the region similarity defined in this way will lead to misclassification of the background region where direct light is blocked by the foreground object.

Page 17: Region-Level Motion- Based Background Modeling and Subtraction Using MRFs Shih-Shinh Huang Li-Chen Fu Pei-Yung Hsiao 2007 IEEE.

An example of shadow An example of shadow effecteffect

Page 18: Region-Level Motion- Based Background Modeling and Subtraction Using MRFs Shih-Shinh Huang Li-Chen Fu Pei-Yung Hsiao 2007 IEEE.

MRFS-BASED MRFS-BASED CLASSIFICATIONCLASSIFICATION

Incorporate the background model to classify every region in the segmentation map SM into either a foreground object or a background one by MRFs.

Page 19: Region-Level Motion- Based Background Modeling and Subtraction Using MRFs Shih-Shinh Huang Li-Chen Fu Pei-Yung Hsiao 2007 IEEE.

MRFs Framework

Page 20: Region-Level Motion- Based Background Modeling and Subtraction Using MRFs Shih-Shinh Huang Li-Chen Fu Pei-Yung Hsiao 2007 IEEE.

Region Classification

Page 21: Region-Level Motion- Based Background Modeling and Subtraction Using MRFs Shih-Shinh Huang Li-Chen Fu Pei-Yung Hsiao 2007 IEEE.
Page 22: Region-Level Motion- Based Background Modeling and Subtraction Using MRFs Shih-Shinh Huang Li-Chen Fu Pei-Yung Hsiao 2007 IEEE.

RESULTSRESULTS

Page 23: Region-Level Motion- Based Background Modeling and Subtraction Using MRFs Shih-Shinh Huang Li-Chen Fu Pei-Yung Hsiao 2007 IEEE.
Page 24: Region-Level Motion- Based Background Modeling and Subtraction Using MRFs Shih-Shinh Huang Li-Chen Fu Pei-Yung Hsiao 2007 IEEE.
Page 25: Region-Level Motion- Based Background Modeling and Subtraction Using MRFs Shih-Shinh Huang Li-Chen Fu Pei-Yung Hsiao 2007 IEEE.
Page 26: Region-Level Motion- Based Background Modeling and Subtraction Using MRFs Shih-Shinh Huang Li-Chen Fu Pei-Yung Hsiao 2007 IEEE.

CONCLUSIONCONCLUSION

Experimental results demonstrate that our proposed method can successfully extract the foreground objects even under situations with illumination variation, shadow, and local motion.

Our on-going research is to develop a tracking algorithm which can be used track the detected object.