Structural Descriptors for Category Level Object Detection

We propose a new class of descriptors which exhibits the ability to yield meaningful structural descriptions of objects. These descriptors are constructed from two types of image primitives: quadrangles and ellipses. The primitives are extracted from an image based on human cognitive psychology and...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on multimedia 2009-12, Vol.11 (8), p.1407-1421
Main Authors: Chia, A.Y.-S., Rahardja, S., Rajan, D., Leung, M.K.H.
Format: Article
Language:English
Subjects:
Animals
Applied sciences
Artificial intelligence
Bicycles
Brightness
Categories
Category modeling
Clutter
Cognitive psychology
Computer science
control theory
systems
Data mining
Descriptions
Exact sciences and technology
Human
Humans
Mathematical models
Mouth
Multimedia
Object detection
Pattern recognition. Digital image processing. Computational geometry
Psychology
Shape
structural representation
Testing
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We propose a new class of descriptors which exhibits the ability to yield meaningful structural descriptions of objects. These descriptors are constructed from two types of image primitives: quadrangles and ellipses. The primitives are extracted from an image based on human cognitive psychology and model local parts of objects. Experiments reveal that these primitives densely cover objects in images. In this regard, structural information of an object can be comprehensively described by these primitives. It is found that a combination of simple spatial relationships between primitives plus a small set of geometrical attributes provide rich and accurate local structural descriptions of objects. Category level object detection of four-legged animals, bicycles, and cars images is demonstrated under scaling, moderate viewpoint variations, and background clutter. Promising results are achieved.
ISSN:1520-9210
1941-0077
DOI:10.1109/TMM.2009.2032683