Details

Autor(en) / Beteiligte

• Han, Feng
• Zhu, Song-Chun

Titel

Bottom-Up/Top-Down Image Parsing with Attribute Grammar

Ist Teil von

• IEEE transactions on pattern analysis and machine intelligence, 2009-01, Vol.31 (1), p.59-73

Ort / Verlag

Los Alamitos, CA: IEEE

Erscheinungsjahr

2009

Quelle

IEEE Electronic Library (IEL)

Beschreibungen/Notizen

• This paper presents a simple attribute graph grammar as a generative representation for made-made scenes, such as buildings, hallways, kitchens, and living rooms, and studies an effective top-down/bottom-up inference algorithm for parsing images in the process of maximizing a Bayesian posterior probability or equivalently minimizing a description length (MDL). Given an input image, the inference algorithm computes (or constructs) a parse graph, which includes a parse tree for the hierarchical decomposition and a number of spatial constraints. In the inference algorithm, the bottom-up step detects an excessive number of rectangles as weighted candidates, which are sorted in certain order and activate top-down predictions of occluded or missing components through the grammar rules. In the experiment, we show that the grammar and top-down inference can largely improve the performance of bottom-up detection.