moving object detection with background model based on spatio -temporal texture
DESCRIPTION
Moving Object Detection with Background Model based on spatio -Temporal Texture. Ryo Yumiba , Masanori Miyoshi,Hirononbu Fujiyoshi WACV 2011. Outline. Introduction ST-patch features Background subtraction Generation of background model Moving object detection Update background model - PowerPoint PPT PresentationTRANSCRIPT
Moving Object Detection with Background Model based on spatio-Temporal Texture
Ryo Yumiba, Masanori Miyoshi,Hirononbu FujiyoshiWACV 2011
Outline
• Introduction• ST-patch features• Background subtraction– Generation of background model– Moving object detection– Update background model
• Experimental result
Introduction
• Background subtraction is a common method for detecting moving object.– Advantage: not requiring previous knowledge of moving object– Problem: cannot discriminate moving objects from background when these
background change significantly
• Two approaches to generating BG model covering changes:– Pixel-wise background model– Patch-wise background model
• Proposed method cover global changes by using appearance information and it cover local changes by using motion information
ST-Patch Features
• SP-patch have been used for several applications.• Calculated as statistical values of pixel grayscale
gradients within a small patch.• Let be a spatio-temporal gadients
appearance information
motion information[7]
ST-Patch Features• Patch size: 15*15*5(frame)
– Appearance components differ between tree and road without regard to motion
– Motion components increase according to temporal change– Motion components differ from transitions of sunlight and
waving of tree
Generation of Background Model• Use Gaussian mixture distribution of ST-patch to generate
background model.
• Parameters are calculated previously from examples of background video using EM algorithm
• Background changes generally differ according to location calculate Parameters at each block
Detection of moving
object
• Step1: Extract ST-patch at each block of each frame• Step2: Compare with background model• Step3: moving object• Step4: number of detected block > moving object candidate flag is set ON• Step5: flag in step4 stays ON more than
active alarm against moving object
Update of Background Model• It is difficult to generate a background model that wholly
covers changes in background in advance update background model during moving object detection
Number of normalized distribution < add new one
Means of distributions are close Weight is less than
Experimental Results
• Compare with the method use only appearance features within a patch in image.
• Parameter setting– Input : 320×240, 30fps– Patch size : 15*15*5
Experimental Result-- Outdoor Scene
• Waving tree, sunlight• Use 1179 frames without pedestrians to generate
background model
• Regard 1359 frames as frames with moving objects
Experimental Results
-- Outdoor Scene
289 frames# FN ↓ ( background updating)∴
Experimental Results
-- ceiling light scene
Experimental Results
Outdoor Scene
Experimental Results