We describe a hierarchical probabilistic model for the detection and recognition of objects in cluttered, natural scenes. The model is based on a set of parts which describe the expected appearance and position, in an object centered coordinate frame, of features detected by a low-level interest operator. Each object category then has its own distribution over these parts, which are shared between objects. We learn the parameters of this model via a Gibbs sampler which uses the graphical model's structure to analytically average over many parameters. Applied to a database of images of isolated objects, the sharing of parts among objects improves detection accuracy when few training examples are available. We also extend this hierarchical framework to scenes containing multiple objects.
Learning hierarchical models of scenes, objects, and parts
Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 ; 2 ; 1331-1338 Vol. 2
2005-01-01
1954268 byte
Conference paper
Electronic Resource
English
Learning Hierarchical Models of Scenes, Objects, and Parts
British Library Conference Proceedings | 2005
|Describing Visual Scenes Using Transformed Objects and Parts
British Library Online Contents | 2008
|Guest Editorial: Scenes, Images and Objects
British Library Online Contents | 2012
|Objects layout graph for 3D complex scenes
IEEE | 2005
|Objects Layout Graph for 3d Complex Scenes
British Library Conference Proceedings | 2005
|