• Skip to primary navigation
  • Skip to main content
  • Skip to primary sidebar
  • Skip to footer

Center for Artificial Intelligence and Cybersecurity – AIRI

  • Home
  • About Us
    • Center Activities
    • Vision, Mission and Goals
    • Center Faculty
    • Steering Committee
    • Press
  • Research
    • Scientific Projects
    • Research Papers
  • Laboratories
    • Machine Learning
    • Natural Speech & Language Processing
    • Blockchain Technology
    • Information Processing & Pattern Recognition
    • AI in Medicine
    • Data Mining
    • Computer Vision
    • Complex Networks
    • Human-Computer Interaction
    • Maritime Cybersecurity
    • Autonomous Navigation
    • AI in Mechatronics
    • AI in Education
    • Hybrid Computational Methods
    • Drug Design
    • Legal Aspects of AI
    • Ethically Aligned AI
    • Cultural Complexity
    • Trustworthy and Explainable AI
  • Collaboration
    • Industry Collaboration
    • Industry Projects
    • International Collaboration
  • News
  • Contact
  • Login

Deep Learning for Feature Extraction in Remote Sensing: A Case-Study of Aerial Scene Classification

14.07.2020

Scene classification relying on images is essential in many systems and applications related to remote sensing. The scientific interest in scene classification from remotely collected images is increasing, and many datasets and algorithms are being developed. The introduction of convolutional neural networks (CNN) and other deep learning techniques contributed to vast improvements in the accuracy of image scene classification in such systems. To classify the scene from areal images, we used a two-stream deep architecture. We performed the first part of the classification, the feature extraction, using pre-trained CNN that extracts deep features of aerial images from different network layers: the average pooling layer or some of the previous convolutional layers. Next, we applied feature concatenation on extracted features from various neural networks, after dimensionality reduction was performed on enormous feature vectors. We experimented extensively with different CNN architectures, to get optimal results. Finally, we used the Support Vector Machine (SVM) for the classification of the concatenated features. The competitiveness of the examined technique was evaluated on two real-world datasets: UC Merced and WHU-RS. The obtained classification accuracies demonstrate that the considered method has competitive results compared to other cutting-edge techniques.

Authors:
Biserka Petrovska, Eftim Zdravevski, Petre Lameski, Roberto Corizzo, Ivan Štajduhar, Jonatan Lerga
Journal:
Sensors
Publishing date:
14.07.2020
View original article

Primary Sidebar

Latest Projects

Advanced Data Analysis Using Digital Signal Processing and Machine Learning Techniques

Compound Flooding in Coastal Rivers in Present and Future Climate

Data Processing on Graphs

North Adriatic Hydrogen Valley

Data Governance and Intellectual Property Governance in Common European Data Spaces – DGIP-CEDS

Latest Research Papers

Digital Twin-Driven Federated Learning and Reinforcement Learning-Based Offloading for Energy-Efficient Distributed Intelligence in IoT Networks

Forecasting the Trajectory of Personal Watercrafts Using Models Based on Recurrent Neural Networks

A System for Real-Time Detection of Abandoned Luggage

Enhancing Biophysical Muscle Fatigue Model in the Dynamic Context of Soccer

Pravna tehnologija (Legal Tech) i njezina (ne)prikladnost za zamjenu pravne struke

Latest News

Invited lecture: “About the first GPS receiver on the Moon, and the other NASA space PNT stories” by James J. Miller (NASA)

Agreement on collaboration between the Faculty of Engineering in Rijeka and the Shanghai Artificial Intelligence Research Institute

Arian Skoki defended his doctoral thesis “Data-Driven Assessment of Player Performance and Recovery in Soccer”

Anna Maria Mihel defended her PhD dissertation topic

Prof. dr. sc. Renato Filjar participated at the meeting of the 31st National Space-Based Positioning, Navigation and Timing US Advisory Board

We provide the expertise for solving real world problems using AI

If your company wants to implement artificial intelligence in your products or services, or increase your level of cybersecurity, our multidisciplinary team of scientists is your ideal partner.

Contact us

Footer

Center for Artificial Intelligence and Cybersecurity
  • jlerga@airi.uniri.hr
  • +385 51 406 500

University of Rijeka

University of Rijeka

About the Center

  • About Us
  • News
  • Privacy Policy
  • Contact

Center Activities

  • Laboratories
  • Scientific Projects
  • Industry Projects
  • Research Papers
  • Industry Collaboration
  • International Collaboration

Footer bottom left

© 2020 Center for Artificial Intelligence and Cybersecurity, all rights reserved.

Designed & developed by Nela Dunato Art & Design