Show simple item record

dc.contributor.authorWang, Chen
dc.contributor.authorBai, Xiao
dc.contributor.authorWang, Shuai
dc.contributor.authorZhou, Jun
dc.contributor.authorRen, Peng
dc.date.accessioned2019-07-04T12:33:40Z
dc.date.available2019-07-04T12:33:40Z
dc.date.issued2019
dc.identifier.issn1545-598X
dc.identifier.doi10.1109/LGRS.2018.2872355
dc.identifier.urihttp://hdl.handle.net/10072/382838
dc.description.abstractObject detection plays an active role in remote sensing applications. Recently, deep convolutional neural network models have been applied to automatically extract features, generate region proposals, and predict corresponding object class. However, these models face new challenges in VHR remote sensing images due to the orientation and scale variations and the cluttered background. In this letter, we propose an end-to-end multiscale visual attention networks (MS-VANs) method. We use skip-connected encoder-decoder model to extract multiscale features from a full-size image. For feature maps in each scale, we learn a visual attention network, which is followed by a classification branch and a regression branch, so as to highlight the features from object region and suppress the cluttered background. We train the MS-VANs model by a hybrid loss function which is a weighted sum of attention loss, classification loss, and regression loss. Experiments on a combined data set consisting of Dataset for Object Detection in Aerial Images and NWPU VHR-10 show that the proposed method outperforms several state-of-the-art approaches.
dc.description.peerreviewedYes
dc.languageEnglish
dc.publisherIEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
dc.relation.ispartofpagefrom310
dc.relation.ispartofpageto314
dc.relation.ispartofissue2
dc.relation.ispartofjournalIEEE GEOSCIENCE AND REMOTE SENSING LETTERS
dc.relation.ispartofvolume16
dc.subject.fieldofresearchArtificial Intelligence and Image Processing
dc.subject.fieldofresearchElectrical and Electronic Engineering
dc.subject.fieldofresearchGeomatic Engineering
dc.subject.fieldofresearchcode0801
dc.subject.fieldofresearchcode0906
dc.subject.fieldofresearchcode0909
dc.titleMultiscale Visual Attention Networks for Object Detection in VHR Remote Sensing Images
dc.typeJournal article
dc.type.descriptionC1 - Articles
dc.type.codeC - Journal Articles
gro.hasfulltextNo Full Text
gro.griffith.authorZhou, Jun
gro.griffith.authorWang, Chen


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

  • Journal articles
    Contains articles published by Griffith authors in scholarly journals.

Show simple item record