In this paper, we present an attribute graph grammar for image parsing on scenes with man-made objects, such as buildings, hallways, kitchens, and living moms. We choose one class of primitives - 3D planar rectangles projected on images and six graph grammar production rules. Each production rule not only expands a node into its components, but also includes a number of equations that constrain the attributes of a parent node and those of its children. Thus our graph grammar is context sensitive. The grammar rules are used recursively to produce a large number of objects and patterns in images and thus the whole graph grammar is a type of generative model. The inference algorithm integrates bottom-up rectangle detection which activates top-down prediction using the grammar rules. The final results are validated in a Bayesian framework. The output of the inference is a hierarchical parsing graph with objects, surfaces, rectangles, and their spatial relations. In the inference, the acceptance of a grammar rule means recognition of an object, and actions are taken to pass the attributes between a node and its parent through the constraint equations associated with this production rule. When an attribute is passed from a child node to a parent node, it is called bottom-up, and the opposite is called top-down.
Bottom-up/top-down image parsing by attribute graph grammar
Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 ; 2 ; 1778-1785 Vol. 2
2005-01-01
793795 byte
Conference paper
Electronic Resource
English
Bottom-up/Top-Down Image Parsing by Attribute Graph Grammar
British Library Conference Proceedings | 2005
|Geometric Reasoning Based on Graph Grammar Parsing
Online Contents | 1994
|Conversions of Feature-Based Design Representations Using Graph Grammar Parsing
Online Contents | 1994
|Grammar-Constrained Neural Semantic Parsing with LR Parsers
German Aerospace Center (DLR) | 2021
|