Pyramid ALKNet for Semantic Parsing of Building Facade Image

The semantic parsing of building facade images is a fundamental yet challenging task in urban scene understanding. Existing works sought to tackle this task by using facade grammars or convolutional neural networks (CNNs). The former can hardly generate parsing results coherent with real images whil...

Full description

Saved in:
Bibliographic Details
Published in:IEEE geoscience and remote sensing letters 2021-06, Vol.18 (6), p.1009-1013
Main Authors: Ma, Wenguang, Ma, Wei, Xu, Shibiao, Zha, Hongbin
Format: Article
Language:English
Subjects:
Artificial neural networks
Building components
Building facades
Buildings
Facade parsing
Facades
Feature maps
Grammars
Image processing
Image segmentation
Kernel
large kernel
man-made structure
Measurement
Neural networks
nonlocal context
Occlusion
Scene analysis
Semantic segmentation
Semantics
Shape
Task analysis
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:The semantic parsing of building facade images is a fundamental yet challenging task in urban scene understanding. Existing works sought to tackle this task by using facade grammars or convolutional neural networks (CNNs). The former can hardly generate parsing results coherent with real images while the latter often fails to capture relationships among facade elements. In this letter, we propose a pyramid atrous large kernel (ALK) network (ALKNet) for the semantic segmentation of facade images. The pyramid ALKNet captures long-range dependencies among building elements by using ALK modules in multiscale feature maps. It makes full use of the regular structures of facades to aggregate useful nonlocal context information and thereby is capable of dealing with challenging image regions caused by occlusions, ambiguities, and so on. Experiments on both rectified and unrectified facade data sets show that ALKNet has better performances than those of state-of-the-art methods.
ISSN:1545-598X
1558-0571
DOI:10.1109/LGRS.2020.2993451