Please use this identifier to cite or link to this item:
http://hdl.handle.net/10397/89010
DC Field | Value | Language |
---|---|---|
dc.contributor | Department of Building and Real Estate | - |
dc.contributor | Research Institute for Sustainable Urban Development | - |
dc.creator | Jiang, SL | - |
dc.creator | Li, G | - |
dc.creator | Yao, W | - |
dc.creator | Hong, ZH | - |
dc.creator | Kuc, TY | - |
dc.date.accessioned | 2021-01-15T07:14:47Z | - |
dc.date.available | 2021-01-15T07:14:47Z | - |
dc.identifier.issn | 1682-1750 | - |
dc.identifier.uri | http://hdl.handle.net/10397/89010 | - |
dc.description | 2020 24th ISPRS Congress - Technical Commission II, 31 August - 2 September 2020 | en_US |
dc.language.iso | en | en_US |
dc.publisher | Copernicus GmbH | en_US |
dc.rights | © Author(s) 2020. This work is distributed under the Creative Commons Attribution 4.0 License (https://creativecommons.org/licenses/by/4.0/). | en_US |
dc.rights | The following publication Jiang, S. L., Li, G., Yao, W., Hong, Z. H., and Kuc, T. Y.: DUAL PYRAMIDS ENCODER-DECODER NETWORK FOR SEMANTIC SEGMENTATION IN GROUND AND AERIAL VIEW IMAGES, Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B2-2020, 605–610, is available at https://doi.org/10.5194/isprs-archives-XLIII-B2-2020-605-2020, 2020 | en_US |
dc.subject | Aerial and ground view image | en_US |
dc.subject | Convolution neural network | en_US |
dc.subject | Encoder-Decoder network | en_US |
dc.subject | Semantic segmentation | en_US |
dc.title | Dual pyramids encoder-decoder network for semantic segmentation in ground and aerial view images | en_US |
dc.type | Conference Paper | en_US |
dc.identifier.spage | 605 | - |
dc.identifier.epage | 610 | - |
dc.identifier.volume | 43 | - |
dc.identifier.issue | B2 | - |
dc.identifier.doi | 10.5194/isprs-archives-XLIII-B2-2020-605-2020 | - |
dcterms.abstract | Semantic segmentation is a fundamental research task in computer vision, which intends to assign a certain category to every pixel. Currently, most existing methods only utilize the deepest feature map for decoding, while high-level features get inevitably lost during the procedure of down-sampling. In the decoder section, transposed convolution or bilinear interpolation was widely used to restore the size of the encoded feature map; however, few optimizations are applied during up-sampling process which is detrimental to the performance for grouping and classification. In this work, we proposed a dual pyramids encoder-decoder deep neural network (DPEDNet) to tackle the above issues. The first pyramid integrated and encoded multi-resolution features through sequentially stacked merging, and the second pyramid decoded the features through dense atrous convolution with chained up-sampling. Without post-processing and multi-scale testing, the proposed network has achieved state-of-the-art performances on two challenging benchmark image datasets for both ground and aerial view scenes. | - |
dcterms.accessRights | open access | en_US |
dcterms.bibliographicCitation | International archives of the photogrammetry, remote sensing and spatial information sciences, 2020, v. 43, no. B2, p. 605-610 | - |
dcterms.isPartOf | International archives of the photogrammetry, remote sensing and spatial information sciences | - |
dcterms.issued | 2020 | - |
dc.identifier.scopus | 2-s2.0-85091116429 | - |
dc.relation.conference | ISPRS Congress on Technical Commission | - |
dc.identifier.eissn | 2194-9034 | - |
dc.description.validate | 202101 bcrc | - |
dc.description.oa | Version of Record | en_US |
dc.identifier.FolderNumber | OA_Scopus/WOS | en_US |
dc.description.pubStatus | Published | en_US |
Appears in Collections: | Conference Paper |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Jiang_Dual_pyramids_encoder-decoder.pdf | 1.11 MB | Adobe PDF | View/Open |
Page views
103
Last Week
3
3
Last month
Citations as of May 5, 2024
Downloads
41
Citations as of May 5, 2024
SCOPUSTM
Citations
1
Citations as of Apr 26, 2024
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.