elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Unconstrained Aerial Scene Recognition with Deep Neural Networks and a New Dataset

Hua, Yuansheng and Mou, LiChao and Jin, Pu and Zhu, Xiao Xiang (2021) Unconstrained Aerial Scene Recognition with Deep Neural Networks and a New Dataset. In: International Geoscience and Remote Sensing Symposium (IGARSS), pp. 1-4. IGARSS 2021, 11.-16. July 2021, Brussels, Belgium.

[img] PDF
492kB

Abstract

Aerial scene recognition is a fundamental research problem in interpreting high-resolution aerial imagery. Over the past few years, most studies focus on classifying an image into one scene category, while in real-world scenarios, it is more often that a single image contains multiple scenes. Therefore, in this paper, we investigate a more practical yet underexplored task---multi-scene recognition in single images. To this end, we create a large-scale dataset, called MultiScene dataset, composed of 100,000 unconstrained images each with multiple labels from 36 different scenes. Among these images, 14,000 of them are manually interpreted and assigned ground-truth labels, while the remaining images are provided with crowdsourced labels, which are generated from low-cost but noisy OpenStreetMap (OSM) data. By doing so, our dataset allows two branches of studies: 1) developing novel CNNs for multi-scene recognition and 2) learning with noisy labels. We experiment with extensive baseline models on our dataset to offer a benchmark for multi-scene recognition in single images. Aiming to expedite further researches, we will make our dataset and pre-trained models available

Item URL in elib:https://elib.dlr.de/142811/
Document Type:Conference or Workshop Item (Speech)
Title:Unconstrained Aerial Scene Recognition with Deep Neural Networks and a New Dataset
Authors:
AuthorsInstitution or Email of AuthorsAuthor's ORCID iD
Hua, YuanshengYuansheng.Hua (at) dlr.deUNSPECIFIED
Mou, LiChaoLiChao.Mou (at) dlr.deUNSPECIFIED
Jin, Pupu.jin (at) tum.deUNSPECIFIED
Zhu, Xiao Xiangxiaoxiang.zhu (at) dlr.dehttps://orcid.org/0000-0001-5530-3613
Date:July 2021
Journal or Publication Title:International Geoscience and Remote Sensing Symposium (IGARSS)
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In SCOPUS:Yes
In ISI Web of Science:No
Page Range:pp. 1-4
Status:Published
Keywords:Convolutional neural network (CNN), multi-scene recognition in single images, crowdsourced annotations, large-scale aerial image dataset
Event Title:IGARSS 2021
Event Location:Brussels, Belgium
Event Type:international Conference
Event Dates:11.-16. July 2021
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Earth Observation
DLR - Research area:Raumfahrt
DLR - Program:R EO - Earth Observation
DLR - Research theme (Project):R - Artificial Intelligence
Location: Oberpfaffenhofen
Institutes and Institutions:Remote Sensing Technology Institute > EO Data Science
Deposited By: Hua, Yuansheng
Deposited On:24 Jun 2021 12:33
Last Modified:09 Aug 2021 13:26

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
electronic library is running on EPrints 3.3.12
Copyright © 2008-2017 German Aerospace Center (DLR). All rights reserved.