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

MsRi-CCF: Multi-Scale and Rotation-Insensitive Convolutional Channel Features for Geospatial Object Detection

Wu, Xin and Hong, Danfeng and Ghamisi, Pedram and Li, Wei and Tao, Ran (2018) MsRi-CCF: Multi-Scale and Rotation-Insensitive Convolutional Channel Features for Geospatial Object Detection. Remote Sensing, 10, 1910/1-1910/20. Multidisciplinary Digital Publishing Institute (MDPI). DOI: 10.3390/rs10121990 ISSN 2072-4292

[img] PDF - Published version
6MB

Official URL: https://www.mdpi.com/2072-4292/10/12/1990

Abstract

Geospatial object detection is a fundamental but challenging problem in the remote sensing community. Although deep learning has shown its power in extracting discriminative features, there is still room for improvement in its detection performance, particularly for objects with large ranges of variations in scale and direction. To this end, a novel approach, entitled multi-scale and rotation-insensitive convolutional channel features (MsRi-CCF), is proposed for geospatial object detection by integrating robust low-level feature generation, classifier generation with outlier removal, and detection with a power law. The low-level feature generation step consists of rotation-insensitive and multi-scale convolutional channel features, which were obtained by learning a regularized convolutional neural network (CNN) and integrating multi-scaled convolutional feature maps, followed by the fine-tuning of high-level connections in the CNN, respectively. Then, these generated features were fed into AdaBoost (chosen due to its lower computation and storage costs) with outlier removal to construct an object detection framework that facilitates robust classifier training. In the test phase, we adopted a log-space sampling approach instead of fine-scale sampling by using the fast feature pyramid strategy based on a computable power law. Extensive experimental results demonstrate that compared with several state-of-the-art baselines, the proposed MsRi-CCF approach yields better detection results, with 90.19% precision with the satellite dataset and 81.44% average precision with the NWPU VHR-10 datasets. Importantly, MsRi-CCF incurs no additional computational cost, which is only 0.92 s and 0.7 s per test image on the two datasets. Furthermore, we determined that most previous methods fail to gain an acceptable detection performance, particularly when they face several obstacles, such as deformations in objects (e.g., rotation, illumination, and scaling). Yet, these factors are effectively addressed by MsRi-CCF, yielding a robust geospatial object detection method.

Item URL in elib:https://elib.dlr.de/128210/
Document Type:Article
Title:MsRi-CCF: Multi-Scale and Rotation-Insensitive Convolutional Channel Features for Geospatial Object Detection
Authors:
AuthorsInstitution or Email of AuthorsAuthors ORCID iD
Wu, Xinaixueshuqian (at) gmail.comUNSPECIFIED
Hong, DanfengDanfeng.Hong (at) dlr.deUNSPECIFIED
Ghamisi, Pedramp.ghamisi (at) gmail.comUNSPECIFIED
Li, WeiBeijing Institute of TechnologyUNSPECIFIED
Tao, RanBeijing Institute of TechnologyUNSPECIFIED
Date:December 2018
Journal or Publication Title:Remote Sensing
Refereed publication:Yes
Open Access:Yes
Gold Open Access:Yes
In SCOPUS:Yes
In ISI Web of Science:Yes
Volume:10
DOI :10.3390/rs10121990
Page Range:1910/1-1910/20
Publisher:Multidisciplinary Digital Publishing Institute (MDPI)
ISSN:2072-4292
Status:Published
Keywords:AdaBoost; deep learning; object detection; optical remote sensing imagery; outlier removal; multi-scale aggregation; rotation-insensitive
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Earth Observation
DLR - Research area:Raumfahrt
DLR - Program:R EO - Erdbeobachtung
DLR - Research theme (Project):R - Vorhaben hochauflösende Fernerkundungsverfahren
Location: Oberpfaffenhofen
Institutes and Institutions:Remote Sensing Technology Institute > EO Data Science
Deposited By: Hong, Danfeng
Deposited On:05 Jul 2019 10:13
Last Modified:14 Dec 2019 04:27

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.