Please use this identifier to cite or link to this item: http://dx.doi.org/10.14279/depositonce-8974
Main Title: Capsule Networks for Object Detection in UAV Imagery
Author(s): Mekhalfi, Mohamed Lamine
Bejiga, Mesay Belete
Soresina, Davide
Melgani, Farid
Demir, Begüm
Type: Article
Language Code: en
Abstract: Recent advances in Convolutional Neural Networks (CNNs) have attracted great attention in remote sensing due to their high capability to model high-level semantic content of Remote Sensing (RS) images. However, CNNs do not explicitly retain the relative position of objects in an image and, thus, the effectiveness of the obtained features is limited in the framework of the complex object detection problems. To address this problem, in this paper we introduce Capsule Networks (CapsNets) for object detection in Unmanned Aerial Vehicle-acquired images. Unlike CNNs, CapsNets extract and exploit the information content about objects’ relative position across several layers, which enables parsing crowded scenes with overlapping objects. Experimental results obtained on two datasets for car and solar panel detection problems show that CapsNets provide similar object detection accuracies when compared to state-of-the-art deep models with significantly reduced computational time. This is due to the fact that CapsNets emphasize dynamic routine instead of the depth.
URI: https://depositonce.tu-berlin.de/handle/11303/9983
http://dx.doi.org/10.14279/depositonce-8974
Issue Date: 17-Jul-2019
Date Available: 10-Sep-2019
DDC Class: 006 Spezielle Computerverfahren
620 Ingenieurwissenschaften und zugeordnete Tätigkeiten
Subject(s): unmanned aerial vehicles
object detection
convolutional neural networks
capsule networks
dynamic routing
Sponsor/Funder: EC/H2020/759764/EU/Accurate and Scalable Processing of Big Data in Earth Observation Fact Sheet/BigEarth
License: https://creativecommons.org/licenses/by/4.0/
Journal Title: Remote Sensing
Publisher: MDPI
Publisher Place: Basel
Volume: 11
Issue: 14
Article Number: 1694
Publisher DOI: 10.3390/rs11141694
EISSN: 2072-4292
Appears in Collections:FG Remote Sensing Image Analysis Group » Publications

Files in This Item:
File Description SizeFormat 
remotesensing-11-01694.pdf982.92 kBAdobe PDFView/Open


This item is licensed under a Creative Commons License Creative Commons