Perceptual Organization of Curvilinear Structures - PowerPoint PPT Presentation

About This Presentation
Title:

Perceptual Organization of Curvilinear Structures

Description:

Laboratoire de G nie Informatique et d 'Ing nierie de Production, N mes ... Scale, sensitiveness. Fusion of primary hypotheses. Similarity - elimination of duplicates. ... – PowerPoint PPT presentation

Number of Views:44
Avg rating:3.0/5.0
Slides: 53
Provided by: alqu1
Learn more at: http://www.alquier.org
Category:

less

Transcript and Presenter's Notes

Title: Perceptual Organization of Curvilinear Structures


1
Perceptual Organization of Curvilinear Structures
Laurent Alquier Research Director Chabane
Oussalah Professor Thesis Advisor Philippe
Montesinos Assistant Professor
- UNIVERSITE MONTPELLIER II - - Laboratoire de
Génie Informatique et d 'Ingénierie de
Production, Nîmes - - September, 30th 1998 -
2
Image Analysis
Construction of a symbolic representation
Detection of visual cues
3
Visual Perception
  • Theories of Visual Perception
  • Continuous flow of visual information
  • Necessity to guide perception

4
Perceptual Organization
  • Principles
  • Pre-attentive phenomenon of grouping
  • Global visual properties Saliency
  • Imposed to perception before interpretation
  • Elementary groups
  • Principle of "good shape"
  • Simplicity, closure, familiarity Stability
  • Useful properties
  • Generic, robust - Qualitative organization

References
  • Gestalt Theory Wertheimer, Koffka - 1923

5
Overview
  • Introduction.
  • Context and Objectives.
  • Organization using Saliency Networks.
  • High Levels of Organization.
  • Contributions and Perspectives.

6
Objectives
  • Complete system of image analysis
  • Segmentation - hypotheses - interpretation
  • Application of psycho-vision principles
  • Analysis of complex scenes
  • Restriction to shapes from contours
  • Validation with artificial scenes
  • Application to images of real scenes
  • Goal
  • Extract a set of elements of representation
  • Remain open to possible needs from future
    applications

7
Overview of the system
  • Edge detection
  • Three levels of organization
  • Selection of salient structures
  • Extraction of elementary hypotheses
  • Organization into complex hypotheses
  • Hierarchic relationship between hypotheses
  • Application
  • Detection of junctions
  • Structural matching

8
Overview
  • Introduction.
  • Context and Objectives.
  • Organization using Saliency Networks.
  • High Levels of Organization.
  • Contributions and Perspectives.

9
Detection of Curvilinear Structures
  • Goal
  • Select the most regular contours
  • Complete discontinuities
  • Extract stable structures ( noise, scale )

10
Grouping by Saliency
  • Principles
  • Estimate the visual quality of a structure
  • optimise this quality function
  • Direct Approach
  • Extension Fields (Guy and Medioni, 1996)
  • Stochastic Completion Fields (Williams and
    Jacobs, 1994)
  • Approaches by optimisation
  • Neural Networks (F. Mangin, 1994)
  • Mean Field Annealing (L. Hérault, 1991)
  • Saliency Network (Shashua et Ullman, 1989)

11
Saliency Network
12
Saliency Network (2)
  • Selection of a Primitive
  • Definition of visual properties.
  • Definition of Local Neighborhood
  • Network of locally connected elements.
  • Quality function for a group
  • Estimate compatibility between elements of a
    group.
  • "Extensible" functions.
  • Definition of Saliency
  • Quality of the best possible group for a given
    primitive

13
Local Neighborhood
  • Relationships between primitives.
  • Primitives linked using Elements of Connection.
  • Properties of Proximity and Compatibility.
  • Method suited for curved groups.
  • Importance of neighborhood.
  • Initialize optimisation of the network.
  • Sets complexity of optimisation.
  • Influence visual quality of groups.

14
Quality Function
  • Properties of Continuity
  • Proximity, smoothness, similarity.
  • Formalism
  • Linear combination of opposed constraints.
  • "Internal" relationships.
  • Visual properties of groups expected.
  • "External" relationships.
  • Imposed by contours from image.

Ã¥
Ã¥


G
a
a
)
F(
R
R
j
j
k
k
ÃŽ
ÃŽ
external


internal


j
k
15
Structural Saliency
  • Recursive expression
  • F is supposed to be an "extensible function"
  • Formal definition.
  • Best sum of contributions around a primitive
    according to two directions.

16
Structural Saliency (2)
  • Example of recursive expression
  • Local term.
  • Contribution of neighbors.
  • Iterative optimisation.
  • Research of best neighbors.
  • Update of contributions

17
Structural Saliency (3)
  • Properties
  • Local measurements - Global optimisation.
  • Completion of discontinuities.
  • Saliency Map.
  • Grouping possible by following connections.
  • Only one optimal group for each primitive.

18
Structural Saliency (4)
  • Application
  • Organization of Pixels.
  • Static neighborhood.
  • Heavy computation.
  • Slow optimisation.
  • Organization of Chains.
  • Dynamic Neighborhood.
  • Reduced complexity.
  • Fast optimisation.

19
Consequence of grouping
Organization of chains
Normal edge linking
20
Detection of Salient Groups
21
Elementary Groups
  • Classes of groups
  • Starting points along a global structure.
  • "Attraction" phenomenon.
  • Evaluation of groups
  • Local saliency.
  • Global saliency ( sum of saliency of primitives )
  • Accumulation of votes
  • Selection
  • Threshold from evaluations.

22
Elementary Groups (2)
23
Overview
  • Introduction.
  • Context and Objectives.
  • Organization using Saliency Networks.
  • High Levels of Organization.
  • Primary Hypotheses.
  • Complex groups and applications.
  • Contributions and perspectives.

24
Primary Hypotheses
  • Structural Hypotheses
  • Straight parts Segments.
  • Curved parts Arcs.
  • Special points Junctions, inflection points,
    corners.
  • Principles of extraction
  • Detection from each elementary group
  • Scale, sensitiveness.
  • Fusion of primary hypotheses.
  • Similarity - elimination of duplicates.

25
Primary Hypotheses (2)
  • Elements of symbolic representation
  • Set of Hypotheses
  • Role of ambiguities and errors.
  • Certain amount of duplicates tolerated.
  • Problems to solve
  • Discretization
  • Structures with different scales within the same
    scene.
  • Output
  • Similar groups superimposed
  • Exceptions to properties of continuity
    (occlusions and junctions)

26
Hypotheses - Segments
Salient Groups
Recursive division (tolerance Es)
Elementary segments
Fusion of similar segments (length,orientation)
Points of interest
Grouped segments
27
Segments ( before organization )
28
Segments ( after organization )
29
Hypotheses - Arcs
Salient Groups
Division according to Extremes of Curvature
(Scale Ea)
Classes of Elementary Arcs
Fusion of similar arcs (classe,superposition)
Points of Interest
Grouped Arcs
30
Arcs ( after organization )
31
Points of Interest
32
Overview
  • Introduction.
  • Context and Objectives.
  • Organization using Saliency Networks.
  • High Levels of Organization.
  • Primary Hypotheses.
  • Complex groups and applications.
  • Contributions and perspectives.

33
Complex groups
  • Example of application
  • Extraction of multiple junctions
  • Structural matching of junctions
  • Motivations
  • Rich structural information
  • Location of center, orientation of branches
  • Robust matching possible
  • Precise location possible after matching
  • Structures difficult to extract
  • Alterations from contour detection
  • Few publications in that area

34
Organization of junctions
Segments
Points
Intersections
Confirmation of center
Detection of Double Junctions
Fusion of Similar Junctions (proximity of
centers, similar branches)
Multiple Junctions
35
Detection of double junctions
36
Fusion into multiple junctions
37
Structural Matching
  • Principle
  • Consistent labeling of two sets of junctions
  • Requires
  • Direct comparison of junctions
  • Evaluate motion (transformation)
  • Between two images
  • Within a single image
  • Conditional comparison

38
Structural Matching (2)
  • Method in two stages
  • Temporal Matching
  • Elimination of improbable matches
  • Spatial Matching
  • Elimination of improbable groups
  • Properties
  • Matching as perceptual grouping
  • Tolerate important differences between images
  • Mutual reinforcement of two type of organization

39
Structural Matching (3)
40
Structural Matching (4)
41
Overview
  • Introduction.
  • Context and Objectives.
  • Organization using Saliency Networks.
  • High Levels of Organization.
  • Contributions and perspectives.

42
Contributions
  • Saliency Networks
  • Generic Formalism
  • Generalized to Organization of Chains
  • Configurable Quality Function
  • More stable optimisation
  • Choice of the most important connections
  • Extraction of final groups
  • Selection of the most salient structures

References
Shashua and Ullman, 1991 - Alter and Basri, 1997
43
Contributions (2)
  • Organization of Geometric Hypotheses
  • Segments
  • Arcs
  • Points of Interest
  • Modular approach
  • Global strategy of organization
  • Specialized modules
  • Hypotheses defined for only one scale
  • Application to numerous types of scenes

References
Mohan and Nevatia, 1992 - Sarkar and Boyer, 1993
- Gao and Wong, 1993
44
Contributions (3)
  • Perceptual Organization of Junctions
  • Detection of Elementary Junctions
  • Organization into Multiple Junctions
  • Structural Matching
  • Cooperation between Spatial Perceptual
    Organization and Temporal Matching.

References
Matas and Kittler, 1993 - Chang and Aggarwal, 1997
45
Results
  • Stable results
  • Generic parameters for classes of scenes
  • Robust in case of perturbations
  • Reasonable computation time on low-end systems
  • Example
  • PC - Pentium 100 - 65 Mo RAM
  • Image 800x600 pixels
  • 500 chains in a scene
  • Grouping with Saliency Network 30s
  • Global computation time 5 min

46
Application Outdoor Scenes
47
Application Satellite Imaging
48
Junction Matching
49
Junction Matching (2)
50
Short term extensions
  • Organization of Generic Objects
  • Quantitative evaluation of results
  • Qualitative results only for now
  • Numerous parameters
  • Empirical definition for now
  • Automatic validation of hypotheses
  • Multi-scale detection
  • Hierarchical Structural Matching
  • Top-down approach

51
Perspectives
  • Integration with other visual cues
  • Visual attention - tracking

References
Laurent Iti, 1997 Caltech - Roch and Ullman, 1985
52
Perspectives (2)
  • Automatic Indexation of Models
  • Aspect graphs

References
Pope and Lowe, 1996
Write a Comment
User Comments (0)
About PowerShow.com