Land classification in satellite images by injecting traditional features to CNN models

Autor: Aksoy, Mehmet Cagri, Sirmacek, Beril, Unsalan, Cem
Přispěvatelé: Aksoy M. Ç., Sirmacek B., ÜNSALAN C.
Rok vydání: 2023
Předmět:
FOS: Computer and information sciences
GEOSCIENCES
GEOCHEMISTRY & GEOPHYSICS
Computer Science - Artificial Intelligence
Computer Vision and Pattern Recognition (cs.CV)
Sinyal İşleme
Temel Bilimler (SCI)
Mühendislik
Computer Science - Computer Vision and Pattern Recognition
J.0
ENGINEERING
CNN models
Yerbilimleri
Information Systems
Communication and Control Engineering
Earth and Planetary Sciences (miscellaneous)
Electrical and Electronic Engineering
Engineering
Computing & Technology (ENG)
ENGINEERING
ELECTRICAL & ELECTRONIC
Elektrik ve Elektronik Mühendisliği
land classification
JEOKİMYA VE JEOFİZİK
Jeofizik Mühendisliği
Dünya ve Gezegen Bilimleri (çeşitli)
68Txx
Mühendislik
Bilişim ve Teknoloji (ENG)
Geophysical Engineering
Artificial Intelligence (cs.AI)
traditional features
Fizik Bilimleri
Signal Processing
Natural Sciences (SCI)
Physical Sciences
Engineering and Technology
MÜHENDİSLİK
ELEKTRİK VE ELEKTRONİK
Mühendislik ve Teknoloji
Bilgi Sistemleri
Haberleşme ve Kontrol Mühendisliği
satellite images
Zdroj: Remote Sensing Letters. 14:157-167
ISSN: 2150-7058
2150-704X
Popis: © 2023 Informa UK Limited, trading as Taylor & Francis Group.Deep learning methods have been successfully applied to remote-sensing problems for several years. Among these methods, CNN-based models have high accuracy in solving the land classification problem using satellite or aerial images. Although these models have high accuracy, this generally comes with large memory size requirements. However, it is desirable to have small-sized models for applications, such as the ones implemented on unmanned aerial vehicles, with low memory space. Unfortunately, small-sized CNN models do not provide as high accuracy as with their large-sized versions. In this study, we propose a novel method to improve the accuracy of CNN models, especially the ones with small size, by injecting traditional features into them. To test the effectiveness of the proposed method, we applied it to the CNN models SqueezeNet, MobileNetV2, ShuffleNetV2, VGG16 and ResNet50V2 having size 0.5 MB to 528 MB. We used the sample mean, grey-level co-occurrence matrix features, Hu moments, local binary patterns, histogram of oriented gradients and colour invariants as traditional features for injection. We tested the proposed method on the EuroSAT dataset to perform land classification. Our experimental results show that the proposed method significantly improves the land classification accuracy especially when applied to small-sized CNN models.
Databáze: OpenAIRE
Externí odkaz: