Difference between revisions of "Object Recognition"

From Robot Intelligence
Jump to: navigation, search
Line 4: Line 4:
  
 
* Affine Category Shape Model
 
* Affine Category Shape Model
** Shape-based SPCF (Sampled Points from Contour Fragments) Features
+
** Contour fragment-based SPCF (Sampled Points from Contour Fragments) features
 
** Rotation-invariant shape contexts with geometric blur
 
** Rotation-invariant shape contexts with geometric blur
 
::[[File:cate_pairwise.png|500px]]
 
::[[File:cate_pairwise.png|500px]]
Line 18: Line 18:
  
 
= Object Identification =
 
= Object Identification =
 +
 
== Concept ==
 
== Concept ==
* C
+
 
* D
+
* Shape-Based Feature Point Extraction
 +
** Contour Fragment-based SPCF (Sampled Points from Contour Fragments) feaetures
 +
 
 +
* Descriptor Computation in Bisected Local Regions
 +
** Rotation-invariant shape contexts with geometric blur
 +
** Color histogram in the  opponent color space

Revision as of 18:10, 17 June 2016

Object Categorization

Concept

  • Affine Category Shape Model
    • Contour fragment-based SPCF (Sampled Points from Contour Fragments) features
    • Rotation-invariant shape contexts with geometric blur
Cate pairwise.png
  • Spectral Matching
    • Pairwise geometric descriptors between features
  • Object Localization
    • RANSAC-based outlier removal
Cate overview.png


Object Identification

Concept

  • Shape-Based Feature Point Extraction
    • Contour Fragment-based SPCF (Sampled Points from Contour Fragments) feaetures
  • Descriptor Computation in Bisected Local Regions
    • Rotation-invariant shape contexts with geometric blur
    • Color histogram in the opponent color space