Download:
|
by Bernt Schiele, James L. Crowley
ftp://whitechapel.media.mit.edu/pub/tech-reports/TR-453.ps.Z
Add To MetaCart
Abstract:
The appearance of an object is composed of local structure. This local structure can be described and characterized by a vector of local features measured by local operators such as Gaussian derivatives or Gabor filters. This article presents a technique where appearances of objects are represented by the joint statistics of local neighborhood operators. As such, this represents a new class of appearance based techniques for computer vision. Based on joint statistics, the article develops techniques for the identification of multiple objects at arbitrary positions and orientations in a cluttered scene. Experiments show that this technique can identify over 100 objects in the presence of major occlusions. Most remarkably, the technique has low complexity and therefore runs in real-time.
Citations
|
925
|
Color indexing
– Swain, Ballard
- 1991
|
|
531
|
The design and use of steerable filters
– Freeman, Adelson
- 1991
|
|
439
|
Theory of communication
– Gabor
- 1946
|
|
296
|
Statistical and Structural Approaches to Texture
– Haralick
- 1979
|
|
181
|
Efficient color histogram indexing for quadratic form distance functions
– Hafner, Sawhney
- 1995
|
|
176
|
Color constant color indexing
– Funt, Finlayson
- 1995
|
|
173
|
Object Recognition using Multidimensional Receptive Field Histograms
– Schiele
- 1997
|
|
156
|
confidence visual recognition of persons by a test of statistical independence
– “High
- 1993
|
|
100
|
A computational framework for determining stereo correspondence from a set of linear spatial filters
– Jones, Malik
- 1992
|
|
99
|
Deformable Kernels for Early Vision
– Perona
- 1995
|
|
61
|
Space and time bounds on indexing 3d models from 2d images
– Clemens, Jacobs
- 1991
|
|
58
|
Object indexing using an iconic sparse distributed memory
– Rao, Ballard
- 1995
|
|
50
|
Recursively implementing the Gaussian and its derivatives
– Deriche
- 1992
|
|
37
|
View variation of point set and line segment features
– Burns, Weiss, et al.
- 1990
|
|
19
|
Statistical learning, localization and identification of objects
– Hornegger, Niemann
- 1995
|
|
14
|
Three–dimensional object recognition using an unsupervised bcm network: The usefulness of distinguishing features
– Intrator, Gold
- 1993
|
|
14
|
A computational model of texture segmentation
– Malik, Perona
- 1989
|
|
14
|
Simulation of human retinal function with the gaussian derivative model
– Young
- 1986
|
|
10
|
Cluster-based probability model applied to image restoration and compression
– Popat, Picard
- 1994
|
|
9
|
Preattentive Gaze Control for Robot Vision
– Westelius
- 1992
|
|
8
|
Recognizing 3D Objects using Photometric Invariant
– Nagao
- 1995
|
|
6
|
Learning appearance models for object recognition
– Pope, Lowe
- 1996
|
|
6
|
Combining grayvalue invariants with local constraints for object recognition
– Schmid, Mohr
- 1996
|
|
5
|
Information: entropies, divergences et moyennes
– Basseville
- 1996
|
|
4
|
Systematic design of indexing strategies for object recognition
– Califano, Mohan
- 1993
|
|
2
|
Invariants for Recognition. ESPRIT--Basic-Research-Workshop
– Burkhardt, Zisserman
- 1992
|
|
1
|
Reconnaissance d'Objets par leurs Statistiques de Couleurs
– Verdi`ere, V
- 1996
|
