Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges

In he past decade, object detection has achieved significant progress in natural images but not in aerial images, due to the massive variations in the scale and orientation of objects caused by the bird's-eye view of aerial images. More importantly, the lack of large-scale benchmarks has become...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence Jg. 44; H. 11; S. 7778 - 7796
Hauptverfasser: Ding, Jian, Xue, Nan, Xia, Gui-Song, Bai, Xiang, Yang, Wen, Yang, Michael Ying, Belongie, Serge, Luo, Jiebo, Datcu, Mihai, Pelillo, Marcello, Zhang, Liangpei
Format: Journal Article
Sprache:Englisch
Veröffentlicht: New York IEEE 01.11.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
ISSN:0162-8828, 1939-3539, 2160-9292, 1939-3539
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract In he past decade, object detection has achieved significant progress in natural images but not in aerial images, due to the massive variations in the scale and orientation of objects caused by the bird's-eye view of aerial images. More importantly, the lack of large-scale benchmarks has become a major obstacle to the development of object detection in aerial images (ODAI). In this paper, we present a large-scale Dataset of Object deTection in Aerial images (DOTA) and comprehensive baselines for ODAI. The proposed DOTA dataset contains 1,793,658 object instances of 18 categories of oriented-bounding-box annotations collected from 11,268 aerial images. Based on this large-scale and well-annotated dataset, we build baselines covering 10 state-of-the-art algorithms with over 70 configurations, where the speed and accuracy performances of each model have been evaluated. Furthermore, we provide a code library for ODAI and build a website for evaluating different algorithms. Previous challenges run on DOTA have attracted more than 1300 teams worldwide. We believe that the expanded large-scale DOTA dataset, the extensive baselines, the code library and the challenges can facilitate the designs of robust algorithms and reproducible research on the problem of object detection in aerial images.
AbstractList In he past decade, object detection has achieved significant progress in natural images but not in aerial images, due to the massive variations in the scale and orientation of objects caused by the bird's-eye view of aerial images. More importantly, the lack of large-scale benchmarks has become a major obstacle to the development of object detection in aerial images (ODAI). In this paper, we present a large-scale Dataset of Object deTection in Aerial images (DOTA) and comprehensive baselines for ODAI. The proposed DOTA dataset contains 1,793,658 object instances of 18 categories of oriented-bounding-box annotations collected from 11,268 aerial images. Based on this large-scale and well-annotated dataset, we build baselines covering 10 state-of-the-art algorithms with over 70 configurations, where the speed and accuracy performances of each model have been evaluated. Furthermore, we provide a code library for ODAI and build a website for evaluating different algorithms. Previous challenges run on DOTA have attracted more than 1300 teams worldwide. We believe that the expanded large-scale DOTA dataset, the extensive baselines, the code library and the challenges can facilitate the designs of robust algorithms and reproducible research on the problem of object detection in aerial images.In he past decade, object detection has achieved significant progress in natural images but not in aerial images, due to the massive variations in the scale and orientation of objects caused by the bird's-eye view of aerial images. More importantly, the lack of large-scale benchmarks has become a major obstacle to the development of object detection in aerial images (ODAI). In this paper, we present a large-scale Dataset of Object deTection in Aerial images (DOTA) and comprehensive baselines for ODAI. The proposed DOTA dataset contains 1,793,658 object instances of 18 categories of oriented-bounding-box annotations collected from 11,268 aerial images. Based on this large-scale and well-annotated dataset, we build baselines covering 10 state-of-the-art algorithms with over 70 configurations, where the speed and accuracy performances of each model have been evaluated. Furthermore, we provide a code library for ODAI and build a website for evaluating different algorithms. Previous challenges run on DOTA have attracted more than 1300 teams worldwide. We believe that the expanded large-scale DOTA dataset, the extensive baselines, the code library and the challenges can facilitate the designs of robust algorithms and reproducible research on the problem of object detection in aerial images.
In he past decade, object detection has achieved significant progress in natural images but not in aerial images, due to the massive variations in the scale and orientation of objects caused by the bird’s-eye view of aerial images. More importantly, the lack of large-scale benchmarks has become a major obstacle to the development of object detection in aerial images (ODAI). In this paper, we present a large-scale Dataset of Object deTection in Aerial images (DOTA) and comprehensive baselines for ODAI. The proposed DOTA dataset contains 1,793,658 object instances of 18 categories of oriented-bounding-box annotations collected from 11,268 aerial images. Based on this large-scale and well-annotated dataset, we build baselines covering 10 state-of-the-art algorithms with over 70 configurations, where the speed and accuracy performances of each model have been evaluated. Furthermore, we provide a code library for ODAI and build a website for evaluating different algorithms. Previous challenges run on DOTA have attracted more than 1300 teams worldwide. We believe that the expanded large-scale DOTA dataset, the extensive baselines, the code library and the challenges can facilitate the designs of robust algorithms and reproducible research on the problem of object detection in aerial images.
Author Luo, Jiebo
Yang, Wen
Zhang, Liangpei
Bai, Xiang
Belongie, Serge
Xue, Nan
Pelillo, Marcello
Ding, Jian
Xia, Gui-Song
Datcu, Mihai
Yang, Michael Ying
Author_xml – sequence: 1
  givenname: Jian
  orcidid: 0000-0002-7188-5884
  surname: Ding
  fullname: Ding, Jian
  email: jian.ding@whu.edu.cn
  organization: State Key Laboratory LIESMARS, Wuhan University, Wuhan, Hubei, China
– sequence: 2
  givenname: Nan
  orcidid: 0000-0002-5449-8073
  surname: Xue
  fullname: Xue, Nan
  email: xuenan@whu.edu.cn
  organization: National Engineering Research Center for Multimedia Software, School of Computer Science and Institute of Artificial Intelligence, Wuhan University, Wuhan, Hubei, China
– sequence: 3
  givenname: Gui-Song
  orcidid: 0000-0001-7660-6090
  surname: Xia
  fullname: Xia, Gui-Song
  email: guisong.xia@whu.edu.cn
  organization: National Engineering Research Center for Multimedia Software, School of Computer Science, Institute of Artificial Intelligence, China
– sequence: 4
  givenname: Xiang
  orcidid: 0000-0002-3449-5940
  surname: Bai
  fullname: Bai, Xiang
  email: xbai@hust.edu.cn
  organization: School of Electronic Information, Huazhong University of Science and Technology, Wuhan, Hubei, China
– sequence: 5
  givenname: Wen
  orcidid: 0000-0002-3263-8768
  surname: Yang
  fullname: Yang, Wen
  email: yangwen@whu.edu.cn
  organization: School of Electronic Information, China
– sequence: 6
  givenname: Michael Ying
  orcidid: 0000-0002-0649-9987
  surname: Yang
  fullname: Yang, Michael Ying
  email: michael.yang@utwente.nl
  organization: Faculty of Geo-Information Science and Earth Observation (ITC), University of Twente, Enschede, NB, The Netherlands
– sequence: 7
  givenname: Serge
  orcidid: 0000-0002-0388-5217
  surname: Belongie
  fullname: Belongie, Serge
  email: sjb344@cornell.edu
  organization: Department of Computer Science, Cornell University and Cornell Tech, Ithaca, NY, USA
– sequence: 8
  givenname: Jiebo
  orcidid: 0000-0002-4516-9729
  surname: Luo
  fullname: Luo, Jiebo
  email: jluo@cs.rochester.edu
  organization: Department of Computer Science, University of Rochester, Rochester, NY, USA
– sequence: 9
  givenname: Mihai
  orcidid: 0000-0002-3477-9687
  surname: Datcu
  fullname: Datcu, Mihai
  email: mihai.datcu@dlr.de
  organization: Remote Sensing Technology Institute, German Aerospace Center (DLR), Cologne, NRW, Germany
– sequence: 10
  givenname: Marcello
  orcidid: 0000-0001-8992-9243
  surname: Pelillo
  fullname: Pelillo, Marcello
  email: pelillo@unive.it
  organization: DAIS, Ca'Foscari University of Venice, Venezia, Italy
– sequence: 11
  givenname: Liangpei
  orcidid: 0000-0001-6890-3650
  surname: Zhang
  fullname: Zhang, Liangpei
  email: zlp62@whu.edu.cn
  organization: State Key Laboratory LIESMARS, Wuhan University, Wuhan, Hubei, China
BookMark eNp9kLtOwzAUQC1URB_wA7BYYmFJ8SNxHLZSXpWKikSZLce5aVNSp9jpwN_j0oqhA9Ndzrm-Pn3UsY0FhC4pGVJKstv52-h1MmSE0SGnNM0kP0E9RgWJMpaxDuoRKlgkJZNd1Pd-RQiNE8LPUJfHgvKMkh6azPIVmBY_QBtG1VhcWTwCV-kaT9Z6Af4Oj_BUuwVE70bXgO_BmuVau0-sbYHHS13XYAN3jk5LXXu4OMwB-nh6nI9founseTIeTSPDU9ZGzLCUiYKUIueUlyLJU5PkAmKWcQGaMxPTWKeJLItEFJDTGJjUJCNFrEHnKR-gm_3ejWu-tuBbta68gbrWFpqtVyyR4aNCih16fYSumq2z4ToVjqDhyQAFSu4p4xrvHZTKVK3etWidrmpFidrlVr-51S63OuQOKjtSN64Kbb7_l672UgUAf0KWCEJCkR9aDYka
CODEN ITPIDJ
CitedBy_id crossref_primary_10_1109_TGRS_2024_3523505
crossref_primary_10_1109_TGRS_2024_3374880
crossref_primary_10_1007_s00138_023_01477_0
crossref_primary_10_1016_j_procs_2024_12_001
crossref_primary_10_1109_LGRS_2024_3431223
crossref_primary_10_1109_TPAMI_2023_3290594
crossref_primary_10_1109_TPAMI_2025_3583006
crossref_primary_10_1109_TCSVT_2025_3547436
crossref_primary_10_3390_s22020464
crossref_primary_10_1016_j_conbuildmat_2025_142718
crossref_primary_10_1109_JSTARS_2024_3456854
crossref_primary_10_1109_TGRS_2025_3578632
crossref_primary_10_1109_TMM_2023_3305120
crossref_primary_10_3390_app13127080
crossref_primary_10_1016_j_iswa_2025_200561
crossref_primary_10_1016_j_jag_2024_103918
crossref_primary_10_3390_aerospace11050392
crossref_primary_10_3390_drones8050189
crossref_primary_10_3390_rs14215460
crossref_primary_10_1109_TGRS_2023_3289307
crossref_primary_10_3390_drones9010029
crossref_primary_10_1109_JSTARS_2022_3206085
crossref_primary_10_1109_LGRS_2024_3381429
crossref_primary_10_1016_j_isprsjprs_2025_06_003
crossref_primary_10_1109_TGRS_2025_3559798
crossref_primary_10_3390_rs17081348
crossref_primary_10_1109_JSTARS_2025_3568853
crossref_primary_10_1016_j_isprsjprs_2024_01_005
crossref_primary_10_1109_TMC_2025_3544516
crossref_primary_10_1016_j_autcon_2023_105258
crossref_primary_10_1109_TGRS_2025_3546489
crossref_primary_10_1117_1_JEI_33_5_053003
crossref_primary_10_1109_TIP_2024_3422881
crossref_primary_10_1088_1361_6501_add612
crossref_primary_10_1109_LGRS_2022_3167530
crossref_primary_10_1007_s10489_023_05227_7
crossref_primary_10_1109_JSTARS_2023_3284309
crossref_primary_10_3390_s23063061
crossref_primary_10_1109_JSTARS_2025_3571814
crossref_primary_10_1088_1361_6501_ad90ff
crossref_primary_10_1016_j_displa_2024_102834
crossref_primary_10_1016_j_jag_2022_102804
crossref_primary_10_3390_ijgi11030189
crossref_primary_10_1007_s11227_025_07561_8
crossref_primary_10_1016_j_engappai_2025_111854
crossref_primary_10_1109_TPAMI_2024_3508072
crossref_primary_10_1038_s41597_023_02576_3
crossref_primary_10_5909_JBE_2025_30_4_620
crossref_primary_10_1109_JSEN_2025_3568844
crossref_primary_10_1109_MGRS_2023_3293459
crossref_primary_10_1109_JSTARS_2023_3241969
crossref_primary_10_1109_TGRS_2024_3375069
crossref_primary_10_3390_jimaging8070182
crossref_primary_10_1109_TCE_2025_3527678
crossref_primary_10_1109_TGRS_2023_3310026
crossref_primary_10_1109_JSTARS_2023_3326957
crossref_primary_10_1109_TIM_2025_3569353
crossref_primary_10_3390_rs13204151
crossref_primary_10_1016_j_neucom_2025_129844
crossref_primary_10_1109_TII_2024_3378841
crossref_primary_10_1007_s11432_022_3718_5
crossref_primary_10_3390_app12178707
crossref_primary_10_1109_LRA_2025_3566604
crossref_primary_10_1007_s11263_024_01989_w
crossref_primary_10_1016_j_buildenv_2025_113300
crossref_primary_10_1080_2150704X_2024_2305177
crossref_primary_10_1016_j_patcog_2024_110976
crossref_primary_10_1109_TCSVT_2023_3335157
crossref_primary_10_1109_TIP_2023_3331908
crossref_primary_10_3390_rs14122756
crossref_primary_10_3390_electronics13224402
crossref_primary_10_1109_LGRS_2022_3211325
crossref_primary_10_1007_s12145_024_01447_8
crossref_primary_10_1109_TGRS_2023_3315053
crossref_primary_10_1109_TGRS_2024_3452010
crossref_primary_10_1109_TGRS_2024_3402271
crossref_primary_10_3390_drones9080557
crossref_primary_10_3390_rs17173029
crossref_primary_10_1038_s41598_025_99634_0
crossref_primary_10_1109_TCSVT_2024_3509872
crossref_primary_10_1109_TGRS_2025_3553128
crossref_primary_10_1109_TGRS_2023_3281331
crossref_primary_10_1080_01431161_2022_2048319
crossref_primary_10_1016_j_knosys_2024_112534
crossref_primary_10_1016_j_isprsjprs_2025_02_025
crossref_primary_10_1109_JSTARS_2024_3460730
crossref_primary_10_1109_TIP_2025_3556344
crossref_primary_10_1016_j_rsase_2025_101641
crossref_primary_10_1371_journal_pone_0315267
crossref_primary_10_3390_rs14112605
crossref_primary_10_1109_TCSVT_2025_3532243
crossref_primary_10_1007_s11042_023_15860_6
crossref_primary_10_3390_rs17081454
crossref_primary_10_3390_rs14071694
crossref_primary_10_1109_TGRS_2024_3375398
crossref_primary_10_1109_TGRS_2024_3475482
crossref_primary_10_1109_JIOT_2023_3303346
crossref_primary_10_3390_drones7070434
crossref_primary_10_1016_j_engappai_2025_111140
crossref_primary_10_1016_j_isprsjprs_2022_12_004
crossref_primary_10_1109_TGRS_2023_3344195
crossref_primary_10_1109_JSTARS_2024_3525177
crossref_primary_10_1109_JSTARS_2023_3265700
crossref_primary_10_1016_j_cag_2024_104014
crossref_primary_10_1007_s10462_025_11256_0
crossref_primary_10_1007_s10462_025_11150_9
crossref_primary_10_1007_s43538_025_00474_3
crossref_primary_10_1080_01431161_2023_2275322
crossref_primary_10_1016_j_dib_2025_111482
crossref_primary_10_1109_JSTARS_2024_3488034
crossref_primary_10_3390_s24186054
crossref_primary_10_1007_s10278_025_01460_3
crossref_primary_10_1016_j_jag_2024_104208
crossref_primary_10_1109_TGRS_2024_3368630
crossref_primary_10_1109_JSTARS_2025_3601564
crossref_primary_10_1016_j_apenergy_2024_124055
crossref_primary_10_1109_TNNLS_2023_3319363
crossref_primary_10_1109_TMM_2024_3521793
crossref_primary_10_1109_TITS_2025_3530678
crossref_primary_10_1016_j_isprsjprs_2022_06_002
crossref_primary_10_1109_TGRS_2024_3385985
crossref_primary_10_1109_TGRS_2024_3391621
crossref_primary_10_1109_TGRS_2023_3278075
crossref_primary_10_1109_LGRS_2025_3557816
crossref_primary_10_1109_TGRS_2025_3601164
crossref_primary_10_1109_TGRS_2024_3363614
crossref_primary_10_1016_j_engappai_2025_110852
crossref_primary_10_1117_1_JEI_33_5_053061
crossref_primary_10_3390_rs15092347
crossref_primary_10_1080_10095020_2024_2404719
crossref_primary_10_1007_s00521_024_09917_2
crossref_primary_10_1109_LGRS_2024_3510093
crossref_primary_10_1109_TGRS_2023_3278933
crossref_primary_10_3390_rs17091556
crossref_primary_10_3390_rs16244806
crossref_primary_10_1155_2022_8515510
crossref_primary_10_1016_j_isprsjprs_2023_08_001
crossref_primary_10_1109_ACCESS_2024_3495523
crossref_primary_10_1109_LGRS_2023_3234267
crossref_primary_10_1038_s41598_025_00239_4
crossref_primary_10_4018_IJCINI_335496
crossref_primary_10_1038_s41598_024_55570_z
crossref_primary_10_1109_TGRS_2024_3514741
crossref_primary_10_1109_JSTARS_2023_3315544
crossref_primary_10_1038_s41598_024_80035_8
crossref_primary_10_3390_rs15112827
crossref_primary_10_1109_ACCESS_2023_3299235
crossref_primary_10_3390_app15158727
crossref_primary_10_1109_JSTARS_2023_3335294
crossref_primary_10_1109_TCSVT_2024_3444795
crossref_primary_10_3390_electronics12183737
crossref_primary_10_3390_electronics14030408
crossref_primary_10_1080_10095020_2022_2162980
crossref_primary_10_3390_agronomy15082014
crossref_primary_10_1007_s42979_023_01748_7
crossref_primary_10_1007_s10489_023_05246_4
crossref_primary_10_1038_s41597_025_04567_y
crossref_primary_10_1016_j_eswa_2024_126034
crossref_primary_10_1080_2150704X_2025_2492903
crossref_primary_10_1109_TCYB_2024_3392474
crossref_primary_10_1109_JSTARS_2024_3422215
crossref_primary_10_3390_rs15092343
crossref_primary_10_1016_j_engappai_2025_111206
crossref_primary_10_3390_app142411988
crossref_primary_10_3390_rs17121997
crossref_primary_10_3390_drones8030074
crossref_primary_10_3390_drones9080549
crossref_primary_10_3390_s24165342
crossref_primary_10_1016_j_isprsjprs_2025_05_006
crossref_primary_10_3390_rs16122077
crossref_primary_10_1109_LRA_2023_3245421
crossref_primary_10_1016_j_isprsjprs_2021_12_004
crossref_primary_10_1016_j_dsp_2025_105158
crossref_primary_10_1109_OJSP_2025_3578273
crossref_primary_10_3389_fpls_2022_876069
crossref_primary_10_1109_JSTARS_2025_3540304
crossref_primary_10_1109_TGRS_2021_3133956
crossref_primary_10_1109_JSTARS_2024_3408154
crossref_primary_10_1145_3664598
crossref_primary_10_1007_s10489_023_05082_6
crossref_primary_10_1109_ACCESS_2025_3526180
crossref_primary_10_1109_ACCESS_2021_3091810
crossref_primary_10_1109_TGRS_2025_3582173
crossref_primary_10_1109_TVT_2023_3262129
crossref_primary_10_1109_TPAMI_2024_3393024
crossref_primary_10_1109_TCDS_2024_3523018
crossref_primary_10_1109_JSTARS_2025_3600396
crossref_primary_10_1109_TPAMI_2025_3544621
crossref_primary_10_1016_j_trc_2025_105205
crossref_primary_10_1016_j_displa_2023_102486
crossref_primary_10_1016_j_jestch_2025_102076
crossref_primary_10_3390_s23156887
crossref_primary_10_1007_s10489_022_03393_8
crossref_primary_10_1155_2022_3001939
crossref_primary_10_3390_rs16193697
crossref_primary_10_3390_rs14071534
crossref_primary_10_3390_rs15174201
crossref_primary_10_1109_MGRS_2023_3272825
crossref_primary_10_1109_TIP_2024_3523802
crossref_primary_10_1108_IDD_05_2022_0048
crossref_primary_10_1109_TGRS_2025_3601549
crossref_primary_10_3390_rs16234522
crossref_primary_10_1371_journal_pone_0330929
crossref_primary_10_1109_JSTARS_2024_3429395
crossref_primary_10_3390_rs15061479
crossref_primary_10_3390_app15158370
crossref_primary_10_1016_j_neucom_2025_129432
crossref_primary_10_1109_TGRS_2022_3180068
crossref_primary_10_3390_rs17162876
crossref_primary_10_1109_TGRS_2023_3311093
crossref_primary_10_1109_TGRS_2024_3485590
crossref_primary_10_1109_JSTARS_2023_3347235
crossref_primary_10_1038_s41598_025_85488_z
crossref_primary_10_1109_TGRS_2024_3409624
crossref_primary_10_1109_TPAMI_2022_3162583
crossref_primary_10_1109_TITS_2024_3489888
crossref_primary_10_1109_JSTARS_2023_3247455
crossref_primary_10_1109_TGRS_2023_3292418
crossref_primary_10_1016_j_aei_2024_102727
crossref_primary_10_1109_TIV_2024_3442924
crossref_primary_10_1080_01431161_2024_2343137
crossref_primary_10_1016_j_dsp_2025_105465
crossref_primary_10_1007_s10489_023_04935_4
crossref_primary_10_1109_ACCESS_2025_3527881
crossref_primary_10_1007_s11042_023_17625_7
crossref_primary_10_1109_JSTARS_2024_3349541
crossref_primary_10_1109_JSTARS_2024_3424954
crossref_primary_10_1109_TGRS_2025_3562395
crossref_primary_10_3390_rs14184435
crossref_primary_10_1109_TNNLS_2024_3510391
crossref_primary_10_1109_TGRS_2024_3456240
crossref_primary_10_3390_electronics13153029
crossref_primary_10_1016_j_isprsjprs_2025_01_037
crossref_primary_10_1109_TGRS_2023_3276853
crossref_primary_10_1109_TCSVT_2025_3544741
crossref_primary_10_1016_j_jag_2024_103740
crossref_primary_10_1016_j_rsase_2025_101692
crossref_primary_10_3390_rs17132213
crossref_primary_10_3390_rs14184581
crossref_primary_10_3390_s25133952
crossref_primary_10_3390_aerospace11110888
crossref_primary_10_1038_s41598_023_49448_9
crossref_primary_10_1016_j_patcog_2025_112254
crossref_primary_10_1109_TGRS_2023_3285443
crossref_primary_10_1109_ACCESS_2025_3604288
crossref_primary_10_3390_rs13214386
crossref_primary_10_1109_TGRS_2023_3305578
crossref_primary_10_1109_TGRS_2025_3600107
crossref_primary_10_1109_TGRS_2024_3397678
crossref_primary_10_3390_rs15225372
crossref_primary_10_1109_JSTARS_2024_3417615
crossref_primary_10_3390_rs14061385
crossref_primary_10_1109_LGRS_2025_3560388
crossref_primary_10_1080_17538947_2024_2390427
crossref_primary_10_3390_rs14133230
crossref_primary_10_1007_s00530_025_01864_9
crossref_primary_10_3390_electronics14142815
crossref_primary_10_3390_drones9070495
Cites_doi 10.1109/CVPR.2017.351
10.1109/CVPR.2019.00746
10.1007/978-3-540-88682-2_4
10.1007/s11263-020-01316-z
10.1109/CVPR.2014.81
10.1109/ICDAR.2015.7333942
10.1109/CVPR.2019.00511
10.1109/ICCV.2017.324
10.1109/LGRS.2016.2565705
10.1109/TGRS.2016.2645610
10.1109/CVPR.2010.5539970
10.1109/ICCV.2019.00108
10.1109/TIP.2021.3073319
10.1109/CVPR.2018.00418
10.1016/j.jvcir.2015.11.002
10.1109/LGRS.2015.2439517
10.1109/ICIP.2018.8451454
10.14358/PERS.85.4.297
10.1109/ICCV.2017.89
10.1109/TPAMI.2007.1011
10.1007/978-3-540-74198-5_14
10.1109/TIP.2018.2867198
10.1109/ICIP.2015.7351502
10.1109/ICCV.2019.00840
10.1109/TMM.2018.2818020
10.1007/s11263-009-0275-4
10.1016/j.isprsjprs.2019.11.023
10.1109/CVPR.2018.00377
10.1007/978-3-319-46487-9_48
10.1109/TPAMI.2016.2577031
10.1109/TGRS.2019.2900302
10.1109/CVPR.2011.5995347
10.1007/978-3-030-58598-3_40
10.1109/CVPR.2017.690
10.1109/TGRS.2020.3010051
10.1109/CVPR42600.2020.01122
10.1109/JSTARS.2017.2697003
10.1109/TGRS.2016.2601622
10.1109/TPAMI.2020.2974745
10.1109/ICIP.2017.8296411
10.1016/j.isprsjprs.2014.10.002
10.1007/978-3-642-15558-1_14
10.1109/CVPR.2018.00421
10.1109/TPAMI.2011.94
10.1109/TGRS.2013.2296351
10.1109/TGRS.2020.2981203
10.1007/s11263-009-0306-1
10.1109/TGRS.2017.2685945
10.1109/TIP.2018.2825107
10.1016/j.compind.2018.03.014
10.1609/aaai.v30i1.9987
10.1109/CVPR.2017.106
10.1007/s11263-016-0981-7
10.1109/TGRS.2019.2899955
10.1109/TIP.2017.2773199
10.1109/CVPR.2018.00244
10.1109/CVPR.2019.00296
10.1109/CVPR.2016.596
10.1109/ICASSP40776.2020.9053738
10.1109/ICCV.2017.528
10.1109/CVPR.2017.527
10.1109/ICCV.2015.169
10.1109/WACV45572.2020.9093447
10.1109/CVPR.2009.5206848
10.3390/rs11242930
10.1109/CVPR.2019.00300
10.1109/CVPR.2018.00150
10.3390/rs11202417
10.1109/ICCV.2019.00832
10.1109/ICCV.2017.322
10.1109/CVPR.2018.00619
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
DBID 97E
RIA
RIE
AAYXX
CITATION
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
7X8
DOI 10.1109/TPAMI.2021.3117983
DatabaseName IEEE Xplore (IEEE)
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
Computer and Information Systems Abstracts
Electronics & Communications Abstracts
Technology Research Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
MEDLINE - Academic
DatabaseTitle CrossRef
Technology Research Database
Computer and Information Systems Abstracts – Academic
Electronics & Communications Abstracts
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts Professional
MEDLINE - Academic
DatabaseTitleList MEDLINE - Academic
Technology Research Database

Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
– sequence: 2
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Computer Science
EISSN 2160-9292
1939-3539
EndPage 7796
ExternalDocumentID 10_1109_TPAMI_2021_3117983
9560031
Genre orig-research
GrantInformation_xml – fundername: CNCS-UEFISCDI
  grantid: PN-III-P4-ID-PCE-2020-2120
– fundername: National Post-Doctoral Program for Innovative Talents
  grantid: BX20200248
– fundername: National Natural Science Foundation of China; NSFC
  grantid: 61922065; 61771350; 41820104006
  funderid: 10.13039/501100001809
GroupedDBID ---
-DZ
-~X
.DC
0R~
29I
4.4
53G
5GY
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACGFO
ACGFS
ACIWK
ACNCT
AENEX
AGQYO
AHBIQ
AKJIK
AKQYR
ALMA_UNASSIGNED_HOLDINGS
ASUFR
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
DU5
E.L
EBS
EJD
F5P
HZ~
IEDLZ
IFIPE
IPLJI
JAVBF
LAI
M43
MS~
O9-
OCL
P2P
PQQKQ
RIA
RIE
RNS
RXW
TAE
TN5
UHB
~02
AAYXX
CITATION
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
7X8
ID FETCH-LOGICAL-c372t-2c2726d0f6b313f65b7c5b6e42936ea32c414a758fd56deb14e28a090d4aeab73
IEDL.DBID RIE
ISICitedReferencesCount 376
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000864325900038&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0162-8828
1939-3539
IngestDate Wed Oct 01 14:45:43 EDT 2025
Sun Jun 29 16:47:27 EDT 2025
Tue Nov 18 22:36:05 EST 2025
Sat Nov 29 02:58:18 EST 2025
Wed Aug 27 02:15:40 EDT 2025
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 11
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c372t-2c2726d0f6b313f65b7c5b6e42936ea32c414a758fd56deb14e28a090d4aeab73
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ORCID 0000-0002-3449-5940
0000-0002-0388-5217
0000-0002-5449-8073
0000-0001-6890-3650
0000-0002-4516-9729
0000-0001-8992-9243
0000-0002-3263-8768
0000-0001-7660-6090
0000-0002-0649-9987
0000-0002-3477-9687
0000-0002-7188-5884
OpenAccessLink https://research.utwente.nl/en/publications/f794557d-8bbd-439e-98d2-6b3791c23d70
PMID 34613910
PQID 2721429673
PQPubID 85458
PageCount 19
ParticipantIDs proquest_miscellaneous_2580016867
ieee_primary_9560031
crossref_citationtrail_10_1109_TPAMI_2021_3117983
crossref_primary_10_1109_TPAMI_2021_3117983
proquest_journals_2721429673
PublicationCentury 2000
PublicationDate 2022-11-01
PublicationDateYYYYMMDD 2022-11-01
PublicationDate_xml – month: 11
  year: 2022
  text: 2022-11-01
  day: 01
PublicationDecade 2020
PublicationPlace New York
PublicationPlace_xml – name: New York
PublicationTitle IEEE transactions on pattern analysis and machine intelligence
PublicationTitleAbbrev TPAMI
PublicationYear 2022
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References ref56
ref12
ref59
ref15
ref58
ref14
ref53
ref52
ref55
ref11
ref54
ref10
ref17
zamir (ref46) 2019
ref18
chen (ref71) 2019; 20
li (ref25) 2019
ref92
ref51
azimi (ref19) 2018
zhou (ref32) 2014
han (ref57) 2021
ref90
shermeyer (ref41) 2020
ref89
ref45
li (ref87) 2017
ref47
ref86
ref42
ref85
ref88
ref44
ref43
ref49
ref7
(ref82) 0
ref9
ref4
ref3
ref6
ref5
ref81
ref84
ref83
girshick (ref29) 2018
ref80
ref79
ref35
ref78
ref34
ref37
ref36
zhu (ref48) 2018
ref75
ref31
ref74
ref30
yang (ref91) 2020
ref33
ref76
ref2
ref1
ref39
ref38
chen (ref40) 2020
ref73
massa (ref69) 2018
ref72
ref68
ref24
ref67
ref23
lin (ref13) 2014
lam (ref27) 2018
ref26
ref64
ref20
hsieh (ref8) 2017
ref63
ref66
ref22
ref65
ref21
liu (ref16) 2015; 12
chen (ref28) 2019
wu (ref70) 2019
wu (ref77) 2019
ref60
ref62
ref61
liu (ref50) 2016
References_xml – year: 0
  ident: ref82
  publication-title: Wikipedia the Free Encyclopedia Wikipedia the Free Encyclopedia
– year: 2019
  ident: ref77
  article-title: Soft sampling for robust object detection
  publication-title: Proc British Mach Vis Conf
– ident: ref68
  doi: 10.1109/CVPR.2017.351
– ident: ref30
  doi: 10.1109/CVPR.2019.00746
– ident: ref26
  doi: 10.1007/978-3-540-88682-2_4
– ident: ref35
  doi: 10.1007/s11263-020-01316-z
– ident: ref52
  doi: 10.1109/CVPR.2014.81
– start-page: 4165
  year: 2017
  ident: ref8
  article-title: Drone-based object counting by spatially regularized regional proposal network
  publication-title: Proc IEEE Int Conf Comput Vis
– ident: ref83
  doi: 10.1109/ICDAR.2015.7333942
– year: 2018
  ident: ref27
  article-title: xView: Objects in context in overhead imagery
– ident: ref88
  doi: 10.1109/CVPR.2019.00511
– start-page: 487
  year: 2014
  ident: ref32
  article-title: Learning deep features for scene recognition using places database
  publication-title: Proc 27th Int Conf Neural Inf Process Syst
– ident: ref85
  doi: 10.1109/ICCV.2017.324
– year: 2018
  ident: ref48
  article-title: Vision meets drones: A challenge
– start-page: 207
  year: 2020
  ident: ref41
  article-title: RarePlanes: Synthetic data takes flight
  publication-title: Proc IEEE/ CVF Winter Conf Appl Comput Vis
– year: 2019
  ident: ref70
  article-title: Detectron2
– ident: ref4
  doi: 10.1109/LGRS.2016.2565705
– ident: ref43
  doi: 10.1109/TGRS.2016.2645610
– volume: 20
  start-page: 1
  year: 2019
  ident: ref71
  article-title: SimpleDet: A simple and versatile distributed framework for object detection and instance recognition
  publication-title: J Mach Learn Res
– ident: ref74
  doi: 10.1109/CVPR.2010.5539970
– ident: ref36
  doi: 10.1109/ICCV.2019.00108
– ident: ref80
  doi: 10.1109/TIP.2021.3073319
– year: 2021
  ident: ref57
  article-title: Align deep features for oriented object detection
  publication-title: IEEE Trans Geosci Remote Sens
– ident: ref14
  doi: 10.1109/CVPR.2018.00418
– ident: ref15
  doi: 10.1016/j.jvcir.2015.11.002
– volume: 12
  start-page: 1938
  year: 2015
  ident: ref16
  article-title: Fast multiclass vehicle detection on aerial images
  publication-title: IEEE Geosci Remote Sens Lett
  doi: 10.1109/LGRS.2015.2439517
– year: 2017
  ident: ref87
  article-title: Light-head R-CNN: In defense of two-stage object detector
– ident: ref38
  doi: 10.1109/ICIP.2018.8451454
– ident: ref39
  doi: 10.14358/PERS.85.4.297
– ident: ref55
  doi: 10.1109/ICCV.2017.89
– ident: ref60
  doi: 10.1109/TPAMI.2007.1011
– ident: ref31
  doi: 10.1007/978-3-540-74198-5_14
– ident: ref6
  doi: 10.1109/TIP.2018.2867198
– ident: ref17
  doi: 10.1109/ICIP.2015.7351502
– ident: ref22
  doi: 10.1109/ICCV.2019.00840
– ident: ref89
  doi: 10.1109/TMM.2018.2818020
– start-page: 150
  year: 2018
  ident: ref19
  article-title: Towards multi-class object detection in unconstrained remote sensing imagery
  publication-title: Proc Asian Conf Comput Vis
– ident: ref11
  doi: 10.1007/s11263-009-0275-4
– ident: ref47
  doi: 10.1016/j.isprsjprs.2019.11.023
– ident: ref81
  doi: 10.1109/CVPR.2018.00377
– ident: ref37
  doi: 10.1007/978-3-319-46487-9_48
– ident: ref54
  doi: 10.1109/TPAMI.2016.2577031
– ident: ref45
  doi: 10.1109/TGRS.2019.2900302
– ident: ref49
  doi: 10.1109/CVPR.2011.5995347
– ident: ref64
  doi: 10.1007/978-3-030-58598-3_40
– ident: ref51
  doi: 10.1109/CVPR.2017.690
– ident: ref66
  doi: 10.1109/TGRS.2020.3010051
– ident: ref90
  doi: 10.1109/CVPR42600.2020.01122
– start-page: 28
  year: 2019
  ident: ref46
  article-title: iSAID: A large-scale dataset for instance segmentation in aerial images
  publication-title: Proc IEEE Conf Comp Vis Pattern Recognit
– ident: ref72
  doi: 10.1109/JSTARS.2017.2697003
– ident: ref9
  doi: 10.1109/TGRS.2016.2601622
– ident: ref63
  doi: 10.1109/TPAMI.2020.2974745
– ident: ref56
  doi: 10.1109/ICIP.2017.8296411
– ident: ref42
  doi: 10.1016/j.isprsjprs.2014.10.002
– start-page: 21
  year: 2016
  ident: ref50
  article-title: SSD: Single shot multibox detector
  publication-title: Proc Eur Conf Comput Vis
– ident: ref2
  doi: 10.1007/978-3-642-15558-1_14
– ident: ref21
  doi: 10.1109/CVPR.2018.00421
– start-page: 740
  year: 2014
  ident: ref13
  article-title: Microsoft COCO: Common objects in context
  publication-title: Proc Eur Conf Comput Vis
– ident: ref7
  doi: 10.1109/TPAMI.2011.94
– year: 2018
  ident: ref69
  article-title: MaskRCNN-benchmark: Fast, modular reference implementation of instance segmentation and object detection algorithms in PyTorch
– ident: ref5
  doi: 10.1109/TGRS.2013.2296351
– year: 2020
  ident: ref40
  article-title: FGSD: A dataset for fine-grained ship detection in high resolution satellite images
– ident: ref92
  doi: 10.1109/TGRS.2020.2981203
– ident: ref3
  doi: 10.1007/s11263-009-0306-1
– ident: ref34
  doi: 10.1109/TGRS.2017.2685945
– ident: ref62
  doi: 10.1109/TIP.2018.2825107
– ident: ref1
  doi: 10.1016/j.compind.2018.03.014
– ident: ref33
  doi: 10.1609/aaai.v30i1.9987
– ident: ref58
  doi: 10.1109/CVPR.2017.106
– ident: ref75
  doi: 10.1007/s11263-016-0981-7
– ident: ref20
  doi: 10.1109/TGRS.2019.2899955
– ident: ref44
  doi: 10.1109/TIP.2017.2773199
– ident: ref61
  doi: 10.1109/CVPR.2018.00244
– ident: ref18
  doi: 10.1109/CVPR.2019.00296
– ident: ref84
  doi: 10.1109/CVPR.2016.596
– ident: ref78
  doi: 10.1109/ICASSP40776.2020.9053738
– year: 2018
  ident: ref29
  article-title: Detectron
– ident: ref76
  doi: 10.1109/ICCV.2017.528
– year: 2019
  ident: ref28
  article-title: MMDetection: Open MMLab detection toolbox and benchmark
– ident: ref10
  doi: 10.1109/CVPR.2017.527
– start-page: 20
  year: 2019
  ident: ref25
  article-title: Learning object-wise semantic representation for detection in remote sensing imagery
  publication-title: Proc IEEE Conf Comp Vis Pattern Recognit
– ident: ref53
  doi: 10.1109/ICCV.2015.169
– ident: ref67
  doi: 10.1109/WACV45572.2020.9093447
– ident: ref12
  doi: 10.1109/CVPR.2009.5206848
– ident: ref65
  doi: 10.3390/rs11242930
– ident: ref79
  doi: 10.1109/CVPR.2019.00300
– ident: ref59
  doi: 10.1109/CVPR.2018.00150
– start-page: 677
  year: 2020
  ident: ref91
  article-title: Arbitrary-oriented object detection with circular smooth label
  publication-title: Proc Eur Conf Comput Vis
– ident: ref73
  doi: 10.3390/rs11202417
– ident: ref24
  doi: 10.1109/ICCV.2019.00832
– ident: ref86
  doi: 10.1109/ICCV.2017.322
– ident: ref23
  doi: 10.1109/CVPR.2018.00619
SSID ssj0014503
Score 2.7426703
Snippet In he past decade, object detection has achieved significant progress in natural images but not in aerial images, due to the massive variations in the scale...
SourceID proquest
crossref
ieee
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 7778
SubjectTerms aerial images
Aerial patrol
Algorithms
Annotations
benchmark dataset
Benchmarks
Codes
Datasets
Earth
Libraries
Object detection
Object recognition
oriented object detection
remote sensing
Software
Software algorithms
Task analysis
Websites
Title Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges
URI https://ieeexplore.ieee.org/document/9560031
https://www.proquest.com/docview/2721429673
https://www.proquest.com/docview/2580016867
Volume 44
WOSCitedRecordID wos000864325900038&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVIEE
  databaseName: IEEE Electronic Library (IEL)
  customDbUrl:
  eissn: 2160-9292
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0014503
  issn: 0162-8828
  databaseCode: RIE
  dateStart: 19790101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1bS-UwEB5UfNAH7-LZVYng21pt0zRp9-2sFzzgDdaF81baZIqya4-cy_7-nclpi7Ai-FZoEtp8M5mZJDMfwHHoyoysLAba8daNUzpInbWBTC0jziXmlCebMHd36XCYPSzASZcLg4j-8hme8qM_y3cjO-OtsjP25UNOml40Rs9ztboTA5V4FmTyYEjDKYxoE2TC7OzxoX87oFBQRhShcoEuJs-JFRmyjBNn39gjT7Dy36rsTc3V-uc-cgPWGpdS9OcysAkLWG_BekvXIBrt3YLVN7UHt2FwX_IWjLjAqb-NVYvnWvS9PIrBC60yk--iL274onjwk4BE8YOGeXopxr9FUTtx3rKwTHbg19Xl4_l10PAqBDY2chpIK43ULqx0GUdxpZPS2KTUSKYp1ljE0qpIFRRIVC7RjhZzhTItwix0qsCiNPEuLNWjGvdAkHdQRsZmFXUmoKsMS2Mwqaq0MuRZqR5E7ezmtik6ztwXf3IffIRZ7sHJGZy8AacH37o-r_OSGx-23mYMupbN9PdgvwUxb7RyktNvR_ST2lCvo-416RMfkhQ1jmbUJknZDU61-fL-yF9hRXIKhM9H3Iel6XiGB7Bs_06fJ-NDEs1heuhF8x_t3NrY
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT9wwEB4hilR6KOWlbkuLK_UGgcRx7KS3LQ-x6rIgsUjcosSeqKglW-2jv78z3iRCAlXiFskPxf48nhnbMx_A19CVGWlZDLTjoxundJA6awOZWkacU8wpTzZhRqP07i67XoHDLhYGEf3jMzziT3-X7yZ2wUdlx2zLhxw0_SpRSobLaK3uzkAlngeZbBiScXIk2hCZMDseX_cvB-QMyoh8VE7RxfQ5sSJVlnHo7CON5ClWnuzLXtmcb7zsN9_B28aoFP3lKtiEFay3YKMlbBCN_G7Bm0fZB7dhcFXyIYw4xbl_j1WL-1r0_YoUgwfaZ2bfRF8M-al4cENQovhO3fx8KKa_RFE7cdLysMx24Pb8bHxyETTMCoGNjZwH0kojtQsrXcZRXOmkNDYpNZJyijUWsbQqUgW5EpVLtKPtXKFMizALnSqwKE28C6v1pMb3IMg-KCNjs4oaE9RVhqUxmFRVWhmyrVQPonZ2c9ukHWf2i9-5dz_CLPfg5AxO3oDTg4OuzZ9l0o3_1t5mDLqazfT3YK8FMW_kcpbTsCMapDbU6ktXTBLF1yRFjZMF1UlSNoRTbT483_M-vL4YXw7z4WD04yOsSw6I8NGJe7A6ny7wE6zZv_P72fSzX6D_AFGl3Tc
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Object+Detection+in+Aerial+Images%3A+A+Large-Scale+Benchmark+and+Challenges&rft.jtitle=IEEE+transactions+on+pattern+analysis+and+machine+intelligence&rft.au=Ding%2C+Jian&rft.au=Xue%2C+Nan&rft.au=Xia%2C+Gui-Song&rft.au=Bai%2C+Xiang&rft.date=2022-11-01&rft.pub=IEEE&rft.issn=0162-8828&rft.volume=44&rft.issue=11&rft.spage=7778&rft.epage=7796&rft_id=info:doi/10.1109%2FTPAMI.2021.3117983&rft_id=info%3Apmid%2F34613910&rft.externalDocID=9560031
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0162-8828&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0162-8828&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0162-8828&client=summon