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

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...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:ISPRS international journal of geo-information Jg. 11; H. 10; S. 527
Hauptverfasser: Yan, Xiongfeng, Yang, Min
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Basel MDPI AG 01.10.2022
Schlagworte:
Algorithms
Cartography
Coders
Cognition & reasoning
Cognitive ability
Comparative analysis
Comparative studies
Convolution
Deep learning
encoder–decoder
Fourier transforms
Inspection
Methods
Neural networks
Pattern recognition
Shape
shape encoding
shape retrieval
shape similarity
Teaching methods
Visual inspection
ISSN:2220-9964, 2220-9964
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung: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.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2220-9964
2220-9964
DOI:10.3390/ijgi11100527