Redirigiendo al acceso original de articulo en 16 segundos...
ARTÍCULO
TITULO

DeepWindows: Windows Instance Segmentation through an Improved Mask R-CNN Using Spatial Attention and Relation Modules

Yanwei Sun    
Shirin Malihi    
Hao Li and Mehdi Maboudi    

Resumen

Windows, as key components of building facades, have received increasing attention in facade parsing. Convolutional neural networks have shown promising results in window extraction. Most existing methods segment a facade into semantic categories and subsequently employ regularization based on the structure of manmade architectures. These methods merely concern the optimization of individual windows, without considering the spatial areas or relationships of windows. This paper presents a novel windows instance segmentation method based on Mask R-CNN architecture. The method features a spatial attention region proposal network and a relation module-enhanced head network. First, an attention module is introduced in the region proposal network to generate a spatial attention map, then the attention map is multiplied with the objectness scores of the classification branch. Second, for the head network, relation modules are added to model the spatial relationships between proposals. Appearance and geometric features are combined for instance recognition. Furthermore, we constructed a new window instance segmentation dataset with 1200 annotated images. With our dataset, the average precisions of our method on detection and segmentation increased from 53.1% and 53.7% to 56.4% and 56.7% compared with Mask R-CNN. A comparison with state-of-the-art methods also proves the predominance of our proposed method.

 Artículos similares

       
 
Kate Carlson, Barbara P. Buttenfield and Yi Qiang    
Quantification of all types of uncertainty helps to establish reliability in any analysis. This research focuses on uncertainty in two attribute levels of wetland classification and creates visualization tools to guide analysis of spatial uncertainty pat... ver más

 
Andrea Emma Pravitasari, Galuh Syahbana Indraprahasta, Ernan Rustiadi, Vely Brian Rosandi, Yuri Ardhya Stanny, Siti Wulandari, Rista Ardy Priatama and Alfin Murtadho    
This paper is situated within the discussion of mega-urbanization, a particular urbanization process that entails a large-scale agglomeration. In this paper, our focus is on urbanization in Java, Indonesia?s most dynamic region. We add to the literature ... ver más

 
Yansong Li, Yaning Chen, Yapeng Chen, Weili Duan, Jiayou Wang and Xu Wang    
Global changes in drought and wetness and their future trends in arid regions have recently become a major focus of research attention. The Tarim River Basin (TRB) in Xinjiang, China, is among the most climate-sensitive regions in the world. This study u... ver más
Revista: Water

 
Yuhao He, Qianlong Zhao, Shanqi Sun, Wenjing Li and Waishan Qiu    
The COVID-19 outbreak followed by the strict citywide lockdown in Shanghai has sparked negative emotion surges on social media platforms in 2022. This research aims to investigate the spatial?temporal heterogeneity of a unique emotion (helplessness) and ... ver más

 
Feng Zhang, Pei Zhang, Miao Wu, Tiantian Wang, Liyue Gao and Yonghui Cheng    
Cultural space (CS) holds significant importance for inheriting regional culture, serving people?s lives, and boosting sustainable community development. In this study, based on the research case of the Hanzhong section of the Hanjiang River Basin (HSHRB... ver más
Revista: Buildings