期刊
ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION
卷 11, 期 10, 页码 -出版社
MDPI
DOI: 10.3390/ijgi11100527
关键词
shape encoding; encoder-decoder; deep learning; shape similarity; shape retrieval
资金
- National Natural Science Foundation of China [42001415, 42071450]
- Open Research Fund Program of Key Laboratory of Digital Mapping and Land Information Application Engineering, Ministry of Natural Resources [ZRZYBWD202101]
- State Key Laboratory of Geo-Information Engineering [SKLGIE2020-Z-4-1]
This study presents a deep learning-based shape encoding framework for geospatial objects. Three different methods, namely GraphNet, SeqNet, and PixelNet, were proposed to encode planar geospatial shapes using different modeling approaches. Comparison with existing methods and traditional geometric methods shows that the deep encoder-decoder methods have advantages in computing shape features and coding, with potential applications in shape measurement and retrieval tasks.
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据