cvpr iccv 09 paper reading
Download
Skip this Video
Download Presentation
CVPR/ICCV 09 Paper Reading

Loading in 2 Seconds...

play fullscreen
1 / 58

CVPR/ICCV 09 Paper Reading - PowerPoint PPT Presentation


  • 275 Views
  • Uploaded on

CVPR/ICCV 09 Paper Reading. Dan Wang Nov. 6, 2009. Papers. CVPR: Learning Color and Locality Cues for Moving Object Detection and Segmentation  ICCV: Texel-based Texture Segmentation. Learning Color and Locality Cues for Moving Object Detection and Segmentation.

loader
I am the owner, or an agent authorized to act on behalf of the owner, of the copyrighted work described.
capcha
Download Presentation

PowerPoint Slideshow about 'CVPR/ICCV 09 Paper Reading' - kalinda


An Image/Link below is provided (as is) to download presentation

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.


- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -
Presentation Transcript
cvpr iccv 09 paper reading

CVPR/ICCV 09 Paper Reading

Dan Wang

Nov. 6, 2009

papers
Papers
  • CVPR:
    • Learning Color and Locality Cues for Moving Object Detection and Segmentation
  •  ICCV:
    • Texel-based Texture Segmentation
learning color and locality cues for moving object detection and segmentation

Learning Color and Locality Cues for Moving Object Detection and Segmentation

Feng Liu and Michael Gleicher

slide4
Authors
  • What does the paper do?
  • Problem of previous methods?
  • How to do?
slide5
Authors
  • What does the paper do?
  • Problem of previous methods?
  • How to do?
author 1 feng liu
Author 1 Feng Liu
  • Computer Sciences Department at the University of Wisconsin, Madison
  • Graduate student
  • Publications
    • Feng Liu, Michael Gleicher, Hailin Jin and Aseem Agarwala. Content-Preserving Warps for 3D Video Stabilization. ACM SIGGRAPH 2009
    • Feng Liu, Yu-hen Hu and Michael Gleicher. Discovering Panoramas in Web Videos. ACM Multimedia 2008
    • Feng Liu and Michael Gleicher. Texture-Consistent Shadow Removal. ECCV 2008
    • Feng Liu and Michael Gleicher. Video Retargeting: Automating Pan and Scan.  ACM Multimedia 2006
author 2 michael gleicher
Author 2 Michael Gleicher
  • Computer Sciences Department at the University of Wisconsin, Madison
  • Professor
  • Positions
    • 2009 – present – Professor
    • 2004 – 2009 – Associate Professor
    • 1998 - 2004 – Assistant Professor
  • http://pages.cs.wisc.edu/~gleicher/CV.pdf
slide8
Authors
  • What does the paper do?
  • Problem of previous methods?
  • How to do?
problem of previous methods
Problem of Previous Methods
  • Most previous automatic methods rely on object or camera motion to detect the moving object.
  • Small motion of object or camera do not provide sufficient information for these methods.
abstract
Abstract
  • The paper presents an algorithm for automatically detecting and segmenting a moving object from a monocular video.
  • Existing method: Rely on motion to detect moving object. When motion is sparse and insufficient, it fails…
  • What does this paper do ?
    • Unsupervised algorithm to learn object color and locality cues from the sparse motion information.
  • How to do?
    • Detect key frames, sub-objects
    • Learning from the sub-objects: color and locality cues
    • Combining cues in MRF framework
slide12
What is “Moving Object”?
    • Some compact regions with different apparent motion from background.
  • How to detect moving object
    • Estimate the global motion in a video
    • Calculate the discrepancy at each between the object motion and global motion
detect moving object
Detect Moving Object

projective transformationDetails in [19]

  • Model:
    • Use Homographyto model the global motion between two consecutive frames.
  • Feature:
    • Use a SIFT feature-based method to estimate the homography
detect moving object14
Detect Moving Object
  • With the homography, we calculate the motion cue(mc) at pixel (x,y) as :
key frame extraction
Key Frame Extraction
  • Definition
    • The frame where a moving object or its part can be reliably inferred from motion cues.
    • Motion cues are likely reliable when they are strong and compact.
segment moving sub objects from key frames
Segment Moving Sub-objects from Key Frames
  • Problem
    • Not all pixels of the moving object have significant motion cues. Motion cues are Sparse!
segment moving sub objects from key frames19
Segment Moving Sub-objects from Key Frames
  • Solution
    • Neighboring pixels are likely to have the same label.
    • Neighboring pixels with similar colors are more likely to have the same label.
  • Solved by Graph cut algorithm
segment moving sub objects from key frames20
Segment Moving Sub-objects from Key Frames

Number of pixels

Neighbor of pixel i

  • MRF priors on labels to model the interaction

Pixel label

segment moving sub objects from key frames21
Segment Moving Sub-objects from Key Frames
  • The likelihood of image I given a labeling can be modeled as follows:
learning color and locality cues
Learning Color and Locality Cues
  • Assumption
    • The moving sub-objects from all the key frames form a complete sampling of the moving objects.
  • Procedure
    • Lab color space
    • Build GMM
learning color and locality cues24
Learning Color and Locality Cues
  • The spatial affinity of pixel I to the moving object:
  • Location likelihood:

position

parameter

F: sub-object

experiments
Experiments
  • Insignificant camera and object motion
discussion
Discussion
  • Extracting moving object from a video with less object and camera motion is not easier than more objects and camera motion
  • Contribution
    • Unsupervised?
  • Currently
    • Off-line
    • Motion estimation is time consuming
  • Future
    • Parameters
    • Background modeling
texel based texture segmentation

Texel-based Texture Segmentation

Sinisa Todorovic, Narendra Ahuja

Reporter: Wang Dan

authors
Authors
  • Sinisa Todorovic
    • Assistant Professor
    • School of EECS, Oregon State University
    • Publication: CVPR 2009, ICCV 2009, TPAMI 2008...
  • Narendra Ahuja
    • Donald Biggar Willet Professor
    • Beckman Institute, UIUC
    • Publication: ICCV 2009, IJCV 2008, TPAMI…
problem
Problem
  • Given an arbitrary image, segment all texture subimages
    • Texture = Spatial repetition of texture elements, i.e.,texels
    • Texels are not identical, but only statistically similar to one another.
    • Texel placement along the texture surface is not periodic, but only statistically uniform.
    • Texels in the image are not homogeneous, but regions that may contain subregions.
rational
Rational
  • Texels occupy image regions
    • If the image contains texture, many regions will have similar properties
      • color, shape, layout of subregions
      • orientation, relative displacements
    • The pdf of region properties will have modes

Texture detection and segmentation

Detection of modes of pdf of region properties

contributions
Contributions
  • No assumptions about the pdf of texel properties
  • Both appearance and placement of the texels are allowed to be stochastic and correlated
  • New hierarchical, adaptive-bandwidth kernel to capture texel structural properties
method description
Method Description
  • Define a feature space of region properties
  • Descriptor of each region = Data point in the feature space
  • Partition the feature space into bins by Voronoi tessellation
  • Run the meanshift with the new, hierarchical kernel
  • Regions under a pdf mode comprise the texture subimage
the feature space of region properties
The feature space of region properties
  • Image hierarchical structure
  • Use multiscale segmentation algorithm[1], [4]
the feature space of region properties40
The feature space of region properties
  • A descriptor vector of prperties xi of image region i
    • Average contrast across i’s boundary
    • Area
    • Standard deviation of i’s children area
    • Displacement vector between the centroids of i and its parent region
    • Perimeter
    • Aspect ratio of intercepts of i’s principal axes with the i’s boundary
    • Orientation: the angle between principal axes and x-axis
    • Centroid of I
  • PCA 95%
  • Not scale and rotation invariance
voronoi diagram43
Voronoi Diagram
  • Definition:
    • Let P = {p1,p2, ... , pn} be a set of points in the plane (or in any dimensional space), which we call sites.
    • Define V(pi), the Voronoi cell for pi, to be the set of points q in the plane that are closer to pi than to any other site. That is, the Voronoi cell for pi is defined to be:
  • V(pi ) = {q | dist(pi,q) < dist(pj, q), for j != i}:
  • Anyway, it can partition the feature space…
  • http://www.dma.fi.upm.es/mabellanas/tfcs/fvd/voronoi.html
voronoi based binned meanshift
Voronoi-based Binned Meanshift
  • New variable-bandwidth matrix
slide46
Motivation
    • Texels, in general, are not homogenous-intensity regions, but may contain hierarchically embedded subregions.
    • Since region descriptors represent image regions, we can define hierarchical relationships between the descriptors based on the embedding of corresponding smaller regions within larger regions in the image.

Gaussian kernel

Hierarchical kernel

slide47
Voronoi partitioning of the feature space
    • Suppose x belongs to Bi, and x’ belongs to Bj

x

x’

  • Arbitrary points

xi

xj

  • Region descriptors
slide48
x belongs to Bi. Compute by finding the maximum subtree isomorphism between two trees rooted at at xi and xj as:
experimental evaluation
Experimental Evaluation
  • Qualitative Evaluation
  • Quantitative evaluation
    • G: the area of true texture
    • D: the area of a subimage that our approach segments
    • Segmentation error per texture:
slide50
(1) 100 collages of randomly mosaicked, 111 distinct Brodatz textures, where each texture occupies at least 1/6 of the collage
slide51
(2) 180 collages of randomly mosaicked, 140 distinct Prague textures from 10 thematic classes (e.g., flowers, plants, rocks, textile, wood, etc.), where each texture occupies at least 1/6 of the collage .
slide52
(3) 100 Aerial-Produce images, where 50 aerial images show housing developments, agricultural fields, and landscapes, and 50 images show produce aisles in supermarkets .
quantitative evaluation brodaz
Quantitative evaluation(Brodaz)
  • Quantitative evaluation
    • G: the area of true texture
    • D: the area of a subimage that our approach segments
    • Segmentation error per texture:

93.3%+3.7

structural properties vs ignoring them

77.9%+4.1 Simple Gaussian kernel, Variable bandwidth

Variable bandwidth in this paper

62.3%+7.8 Simple Gaussian kernel, Variable bandwidth [7]

quantitative evaluation prague
Quantitative evaluation(Prague)
  • G: the area of true texture
  • D: the area of a subimage that our approach segments
  • CS: Correct segmentation
  • OS: Over segmentation means G that is split into smaller regions D
  • US: DG
  • ME counts every G that does not belong to CS
  • NE counts every D that does not belong to US

“The state-of-the-art unsrpervised texture segmentation”

conclusion
Conclusion
  • We have presented a texel-based approach to segmenting image parts occupied by distinct textures. This is done by capturing intrinsic and placement properties of distinct groups of texels.
  • Experimental evaluation on texture mosaics and real-world images suggests that capturing structural properties of texels is very important for texture segmentation.
  • To account for texel substructure, we have derived and used a hierarchical, variable bandwidth kernel in the meanshift.

Slices are partly from SinisaTodorovic