Improving the Detection of Small Oriented Objects in Aerial Images
Small oriented objects that represent tiny pixel-area in large-scale aerial images are difficult to detect due to their size and orientation. Existing oriented aerial detectors have shown promising results but are mainly focused on orientation modeling with less regard to the size of the objects. In...
Gespeichert in:
Veröffentlicht in: | arXiv.org 2024-01 |
---|---|
Hauptverfasser: | , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | |
container_start_page | |
container_title | arXiv.org |
container_volume | |
creator | Chandler Timm C Doloriel Cajote, Rhandley D |
description | Small oriented objects that represent tiny pixel-area in large-scale aerial images are difficult to detect due to their size and orientation. Existing oriented aerial detectors have shown promising results but are mainly focused on orientation modeling with less regard to the size of the objects. In this work, we proposed a method to accurately detect small oriented objects in aerial images by enhancing the classification and regression tasks of the oriented object detection model. We designed the Attention-Points Network consisting of two losses: Guided-Attention Loss (GALoss) and Box-Points Loss (BPLoss). GALoss uses an instance segmentation mask as ground-truth to learn the attention features needed to improve the detection of small objects. These attention features are then used to predict box points for BPLoss, which determines the points' position relative to the target oriented bounding box. Experimental results show the effectiveness of our Attention-Points Network on a standard oriented aerial dataset with small object instances (DOTA-v1.5) and on a maritime-related dataset (HRSC2016). The code is publicly available. |
doi_str_mv | 10.48550/arxiv.2401.06503 |
format | Article |
fullrecord | <record><control><sourceid>proquest_arxiv</sourceid><recordid>TN_cdi_arxiv_primary_2401_06503</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2914966194</sourcerecordid><originalsourceid>FETCH-LOGICAL-a524-b021052e0c14aba3769710b4052220c2b0b70db06a3d3ae07098518a20acd7a53</originalsourceid><addsrcrecordid>eNotj8tqwzAUREWh0JDmA7qqoGu7V1eSZS_T9GUIeNHszZWtpAp-pLIT2r-vm3Q1MDMMcxi7ExCrVGt4pPDtTzEqEDEkGuQVm6GUIkoV4g1bDMMeADAxqLWcsae8PYT-5LsdHz8df3ajq0bfd7zf8o-WmoYXwbtudDUv7H7KBu47vnTBU8PzlnZuuGXXW2oGt_jXOdu8vmxW79G6eMtXy3VEGlVkAQVodFAJRZakSTIjwKrJQ4QKLVgDtYWEZC3JgYEs1SIlBKpqQ1rO2f1l9gxYHoJvKfyUf6DlGXRqPFwaE9HX0Q1jue-PoZs-lZgJlSWJyJT8BbiiU8s</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2914966194</pqid></control><display><type>article</type><title>Improving the Detection of Small Oriented Objects in Aerial Images</title><source>arXiv.org</source><source>Free E- Journals</source><creator>Chandler Timm C Doloriel ; Cajote, Rhandley D</creator><creatorcontrib>Chandler Timm C Doloriel ; Cajote, Rhandley D</creatorcontrib><description>Small oriented objects that represent tiny pixel-area in large-scale aerial images are difficult to detect due to their size and orientation. Existing oriented aerial detectors have shown promising results but are mainly focused on orientation modeling with less regard to the size of the objects. In this work, we proposed a method to accurately detect small oriented objects in aerial images by enhancing the classification and regression tasks of the oriented object detection model. We designed the Attention-Points Network consisting of two losses: Guided-Attention Loss (GALoss) and Box-Points Loss (BPLoss). GALoss uses an instance segmentation mask as ground-truth to learn the attention features needed to improve the detection of small objects. These attention features are then used to predict box points for BPLoss, which determines the points' position relative to the target oriented bounding box. Experimental results show the effectiveness of our Attention-Points Network on a standard oriented aerial dataset with small object instances (DOTA-v1.5) and on a maritime-related dataset (HRSC2016). The code is publicly available.</description><identifier>EISSN: 2331-8422</identifier><identifier>DOI: 10.48550/arxiv.2401.06503</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Computer Science - Artificial Intelligence ; Computer Science - Computer Vision and Pattern Recognition ; Datasets ; Image enhancement ; Object recognition</subject><ispartof>arXiv.org, 2024-01</ispartof><rights>2024. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,784,885,27925</link.rule.ids><backlink>$$Uhttps://doi.org/10.1109/WACVW58289.2023.00023$$DView published paper (Access to full text may be restricted)$$Hfree_for_read</backlink><backlink>$$Uhttps://doi.org/10.48550/arXiv.2401.06503$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Chandler Timm C Doloriel</creatorcontrib><creatorcontrib>Cajote, Rhandley D</creatorcontrib><title>Improving the Detection of Small Oriented Objects in Aerial Images</title><title>arXiv.org</title><description>Small oriented objects that represent tiny pixel-area in large-scale aerial images are difficult to detect due to their size and orientation. Existing oriented aerial detectors have shown promising results but are mainly focused on orientation modeling with less regard to the size of the objects. In this work, we proposed a method to accurately detect small oriented objects in aerial images by enhancing the classification and regression tasks of the oriented object detection model. We designed the Attention-Points Network consisting of two losses: Guided-Attention Loss (GALoss) and Box-Points Loss (BPLoss). GALoss uses an instance segmentation mask as ground-truth to learn the attention features needed to improve the detection of small objects. These attention features are then used to predict box points for BPLoss, which determines the points' position relative to the target oriented bounding box. Experimental results show the effectiveness of our Attention-Points Network on a standard oriented aerial dataset with small object instances (DOTA-v1.5) and on a maritime-related dataset (HRSC2016). The code is publicly available.</description><subject>Computer Science - Artificial Intelligence</subject><subject>Computer Science - Computer Vision and Pattern Recognition</subject><subject>Datasets</subject><subject>Image enhancement</subject><subject>Object recognition</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>GOX</sourceid><recordid>eNotj8tqwzAUREWh0JDmA7qqoGu7V1eSZS_T9GUIeNHszZWtpAp-pLIT2r-vm3Q1MDMMcxi7ExCrVGt4pPDtTzEqEDEkGuQVm6GUIkoV4g1bDMMeADAxqLWcsae8PYT-5LsdHz8df3ajq0bfd7zf8o-WmoYXwbtudDUv7H7KBu47vnTBU8PzlnZuuGXXW2oGt_jXOdu8vmxW79G6eMtXy3VEGlVkAQVodFAJRZakSTIjwKrJQ4QKLVgDtYWEZC3JgYEs1SIlBKpqQ1rO2f1l9gxYHoJvKfyUf6DlGXRqPFwaE9HX0Q1jue-PoZs-lZgJlSWJyJT8BbiiU8s</recordid><startdate>20240112</startdate><enddate>20240112</enddate><creator>Chandler Timm C Doloriel</creator><creator>Cajote, Rhandley D</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20240112</creationdate><title>Improving the Detection of Small Oriented Objects in Aerial Images</title><author>Chandler Timm C Doloriel ; Cajote, Rhandley D</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a524-b021052e0c14aba3769710b4052220c2b0b70db06a3d3ae07098518a20acd7a53</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Computer Science - Artificial Intelligence</topic><topic>Computer Science - Computer Vision and Pattern Recognition</topic><topic>Datasets</topic><topic>Image enhancement</topic><topic>Object recognition</topic><toplevel>online_resources</toplevel><creatorcontrib>Chandler Timm C Doloriel</creatorcontrib><creatorcontrib>Cajote, Rhandley D</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Access via ProQuest (Open Access)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection><collection>arXiv Computer Science</collection><collection>arXiv.org</collection><jtitle>arXiv.org</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Chandler Timm C Doloriel</au><au>Cajote, Rhandley D</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Improving the Detection of Small Oriented Objects in Aerial Images</atitle><jtitle>arXiv.org</jtitle><date>2024-01-12</date><risdate>2024</risdate><eissn>2331-8422</eissn><abstract>Small oriented objects that represent tiny pixel-area in large-scale aerial images are difficult to detect due to their size and orientation. Existing oriented aerial detectors have shown promising results but are mainly focused on orientation modeling with less regard to the size of the objects. In this work, we proposed a method to accurately detect small oriented objects in aerial images by enhancing the classification and regression tasks of the oriented object detection model. We designed the Attention-Points Network consisting of two losses: Guided-Attention Loss (GALoss) and Box-Points Loss (BPLoss). GALoss uses an instance segmentation mask as ground-truth to learn the attention features needed to improve the detection of small objects. These attention features are then used to predict box points for BPLoss, which determines the points' position relative to the target oriented bounding box. Experimental results show the effectiveness of our Attention-Points Network on a standard oriented aerial dataset with small object instances (DOTA-v1.5) and on a maritime-related dataset (HRSC2016). The code is publicly available.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><doi>10.48550/arxiv.2401.06503</doi><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | EISSN: 2331-8422 |
ispartof | arXiv.org, 2024-01 |
issn | 2331-8422 |
language | eng |
recordid | cdi_arxiv_primary_2401_06503 |
source | arXiv.org; Free E- Journals |
subjects | Computer Science - Artificial Intelligence Computer Science - Computer Vision and Pattern Recognition Datasets Image enhancement Object recognition |
title | Improving the Detection of Small Oriented Objects in Aerial Images |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-23T06%3A45%3A08IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_arxiv&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Improving%20the%20Detection%20of%20Small%20Oriented%20Objects%20in%20Aerial%20Images&rft.jtitle=arXiv.org&rft.au=Chandler%20Timm%20C%20Doloriel&rft.date=2024-01-12&rft.eissn=2331-8422&rft_id=info:doi/10.48550/arxiv.2401.06503&rft_dat=%3Cproquest_arxiv%3E2914966194%3C/proquest_arxiv%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2914966194&rft_id=info:pmid/&rfr_iscdi=true |