ARTÍCULO
TITULO

A Comparative Study of Various Deep Learning Approaches to Shape Encoding of Planar Geospatial Objects

Xiongfeng Yan and Min Yang    

Resumen

The shape encoding of geospatial objects is a key problem in the fields of cartography and geoscience. Although traditional geometric-based methods have made great progress, deep learning techniques offer a development opportunity for this classical problem. In this study, a shape encoding framework based on a deep encoder?decoder architecture was proposed, and three different methods for encoding planar geospatial shapes, namely GraphNet, SeqNet, and PixelNet methods, were constructed based on raster-based, graph-based, and sequence-based modeling for shape. The three methods were compared with the existing deep learning-based shape encoding method and two traditional geometric methods. Quantitative evaluation and visual inspection led to the following conclusions: (1) The deep encoder?decoder methods can effectively compute shape features and obtain meaningful shape coding to support the shape measure and retrieval task. (2) Compared with the traditional Fourier transform and turning function methods, the deep encoder?decoder methods showed certain advantages. (3) Compared with the SeqNet and PixelNet methods, GraphNet performed better due to the use of a graph to model the topological relations between nodes and efficient graph convolution and pooling operations to process the node features.

 Artículos similares

       
 
Muhammad Tayyab, Rana Ammar Aslam, Umar Farooq, Sikandar Ali, Shahbaz Nasir Khan, Mazhar Iqbal, Muhammad Imran Khan and Naeem Saddique    
Groundwater Arsenic (As) data are often sparse and location-specific, making them insufficient to represent the heterogeneity in groundwater quality status at unsampled locations. Interpolation techniques have been used to map groundwater As data at unsa... ver más
Revista: Water

 
Cen-Ying Liao, Lin Zhang, Si-Yu Hu, Shuai-Jie Xia and D. M. Li    
Empowering materials with self-healing capabilities is an attractive approach for sustainable development. This strategy involves using different methods to automatically heal microcracks and damages that occur during the service life of materials or str... ver más
Revista: Buildings

 
Xiaoyun Song, Heping Zheng, Lei Xu, Tingting Xu and Qiuyu Li    
An investigation was carried out to study the influence of two types of anti-washout admixtures (AWAs) on the performance of underwater concrete, specifically, workability and washout resistance. The tested AWAs were hydroxypropyl methylcellulose (HPMC) ... ver más
Revista: Buildings

 
Svetlana Pushkar    
Over the past five years, Leadership in Energy and Environmental Design Commercial Interior version 4 (LEED-CI v4)-certified office projects have been intensively studied in the USA and China, but they have not yet been studied in the Mediterranean regio... ver más
Revista: Buildings

 
Ángel Benigno González-Avilés, Carlos Pérez-Carramiñana, Antonio Galiano-Garrigós and María Isabel Pérez-Millán    
Over the last decade there has been a proliferation of glamping architecture. This study analyses the energy performance of geodesic domes for use in tourist glamping compared to more conventional prismatic architectural solutions. The energy analysis of... ver más
Revista: Buildings