ST-CenterNet: Small Target Detection Algorithm with Adaptive Data Enhancement
General target detection with deep learning has made tremendous strides in the past few years. However, small target detection sometimes is associated with insufficient sample size and difficulty in extracting complete feature information. For safety during autonomous driving, remote signs and pedes...
Uloženo v:
| Vydáno v: | Entropy (Basel, Switzerland) Ročník 25; číslo 3; s. 509 |
|---|---|
| Hlavní autoři: | , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Switzerland
MDPI AG
16.03.2023
MDPI |
| Témata: | |
| ISSN: | 1099-4300, 1099-4300 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | General target detection with deep learning has made tremendous strides in the past few years. However, small target detection sometimes is associated with insufficient sample size and difficulty in extracting complete feature information. For safety during autonomous driving, remote signs and pedestrians need to be detected from driving scenes photographed by car cameras. In the early period of a medical lesion, because of the small area of the lesion, target detection is of great significance to detect masses and tumors for accurate diagnosis and treatment. To deal with these problems, we propose a novel deep learning model, named CenterNet for small targets (ST-CenterNet). First of all, due to the lack of visual information on small targets in the dataset, we extracted less discriminative features. To overcome this shortcoming, the proposed selective small target replication algorithm (SSTRA) was used to realize increasing numbers of small targets by selectively oversampling them. In addition, the difficulty of extracting shallow semantic information for small targets results in incomplete target feature information. Consequently, we developed a target adaptation feature extraction module (TAFEM), which was used to conduct bottom-up and top-down bidirectional feature extraction by combining ResNet with the adaptive feature pyramid network (AFPN). The improved new network model, AFPN, was added to solve the problem of the original feature extraction module, which can only extract the last layer of the feature information. The experimental results demonstrate that the proposed method can accurately detect the small-scale image of distributed targets and simultaneously, at the pixel level, classify whether a subject is wearing a safety helmet. Compared with the detection effect of the original algorithm on the safety helmet wearing dataset (SHWD), we achieved mean average precision (mAP) of 89.06% and frames per second (FPS) of 28.96, an improvement of 18.08% mAP over the previous method. |
|---|---|
| AbstractList | General target detection with deep learning has made tremendous strides in the past few years. However, small target detection sometimes is associated with insufficient sample size and difficulty in extracting complete feature information. For safety during autonomous driving, remote signs and pedestrians need to be detected from driving scenes photographed by car cameras. In the early period of a medical lesion, because of the small area of the lesion, target detection is of great significance to detect masses and tumors for accurate diagnosis and treatment. To deal with these problems, we propose a novel deep learning model, named CenterNet for small targets (ST-CenterNet). First of all, due to the lack of visual information on small targets in the dataset, we extracted less discriminative features. To overcome this shortcoming, the proposed selective small target replication algorithm (SSTRA) was used to realize increasing numbers of small targets by selectively oversampling them. In addition, the difficulty of extracting shallow semantic information for small targets results in incomplete target feature information. Consequently, we developed a target adaptation feature extraction module (TAFEM), which was used to conduct bottom-up and top-down bidirectional feature extraction by combining ResNet with the adaptive feature pyramid network (AFPN). The improved new network model, AFPN, was added to solve the problem of the original feature extraction module, which can only extract the last layer of the feature information. The experimental results demonstrate that the proposed method can accurately detect the small-scale image of distributed targets and simultaneously, at the pixel level, classify whether a subject is wearing a safety helmet. Compared with the detection effect of the original algorithm on the safety helmet wearing dataset (SHWD), we achieved mean average precision (mAP) of 89.06% and frames per second (FPS) of 28.96, an improvement of 18.08% mAP over the previous method. General target detection with deep learning has made tremendous strides in the past few years. However, small target detection sometimes is associated with insufficient sample size and difficulty in extracting complete feature information. For safety during autonomous driving, remote signs and pedestrians need to be detected from driving scenes photographed by car cameras. In the early period of a medical lesion, because of the small area of the lesion, target detection is of great significance to detect masses and tumors for accurate diagnosis and treatment. To deal with these problems, we propose a novel deep learning model, named CenterNet for small targets (ST-CenterNet). First of all, due to the lack of visual information on small targets in the dataset, we extracted less discriminative features. To overcome this shortcoming, the proposed selective small target replication algorithm (SSTRA) was used to realize increasing numbers of small targets by selectively oversampling them. In addition, the difficulty of extracting shallow semantic information for small targets results in incomplete target feature information. Consequently, we developed a target adaptation feature extraction module (TAFEM), which was used to conduct bottom-up and top-down bidirectional feature extraction by combining ResNet with the adaptive feature pyramid network (AFPN). The improved new network model, AFPN, was added to solve the problem of the original feature extraction module, which can only extract the last layer of the feature information. The experimental results demonstrate that the proposed method can accurately detect the small-scale image of distributed targets and simultaneously, at the pixel level, classify whether a subject is wearing a safety helmet. Compared with the detection effect of the original algorithm on the safety helmet wearing dataset (SHWD), we achieved mean average precision (mAP) of 89.06% and frames per second (FPS) of 28.96, an improvement of 18.08% mAP over the previous method.General target detection with deep learning has made tremendous strides in the past few years. However, small target detection sometimes is associated with insufficient sample size and difficulty in extracting complete feature information. For safety during autonomous driving, remote signs and pedestrians need to be detected from driving scenes photographed by car cameras. In the early period of a medical lesion, because of the small area of the lesion, target detection is of great significance to detect masses and tumors for accurate diagnosis and treatment. To deal with these problems, we propose a novel deep learning model, named CenterNet for small targets (ST-CenterNet). First of all, due to the lack of visual information on small targets in the dataset, we extracted less discriminative features. To overcome this shortcoming, the proposed selective small target replication algorithm (SSTRA) was used to realize increasing numbers of small targets by selectively oversampling them. In addition, the difficulty of extracting shallow semantic information for small targets results in incomplete target feature information. Consequently, we developed a target adaptation feature extraction module (TAFEM), which was used to conduct bottom-up and top-down bidirectional feature extraction by combining ResNet with the adaptive feature pyramid network (AFPN). The improved new network model, AFPN, was added to solve the problem of the original feature extraction module, which can only extract the last layer of the feature information. The experimental results demonstrate that the proposed method can accurately detect the small-scale image of distributed targets and simultaneously, at the pixel level, classify whether a subject is wearing a safety helmet. Compared with the detection effect of the original algorithm on the safety helmet wearing dataset (SHWD), we achieved mean average precision (mAP) of 89.06% and frames per second (FPS) of 28.96, an improvement of 18.08% mAP over the previous method. |
| Audience | Academic |
| Author | Guo, Yujie Lu, Xu |
| AuthorAffiliation | College of Computer Science, Guangdong Polytechnic Normal University, Guangzhou 510665, China; jennyguoyj@163.com |
| AuthorAffiliation_xml | – name: College of Computer Science, Guangdong Polytechnic Normal University, Guangzhou 510665, China; jennyguoyj@163.com |
| Author_xml | – sequence: 1 givenname: Yujie surname: Guo fullname: Guo, Yujie – sequence: 2 givenname: Xu orcidid: 0000-0002-6097-032X surname: Lu fullname: Lu, Xu |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/36981396$$D View this record in MEDLINE/PubMed |
| BookMark | eNptkk1v1DAQhi1URNuFA38AReICh7T-SJyYC1ptC1QqcOhytibOOOtVEi-Ot4h_X2-3rNoKWfJY42dez3jmlByNfkRC3jJ6JoSi58hLKmhJ1QtywqhSeSEoPXp0Pian07SmlAvO5CtyLKSqmVDyhHy_WeYLHCOGHxg_ZTcD9H22hNBhzC4woonOj9m873xwcTVkf9KezVvYRHeL2QVEyC7HFYwGh6Tymry00E_45sHOyK8vl8vFt_z659erxfw6NynJmLOmshygkcqKirWtLJmtq7ZhsmmENba0RglqWmAKyloyBNY2yBvZ8rIBRsWMXO11Ww9rvQlugPBXe3D63uFDpyFEZ3rUBTKKgnPLTV0oxYBWWIpCNbJCVBaT1ue91mbbDNiaVEaA_ono05vRrXTnbzWjtKgUY0nhw4NC8L-3OEU9uMlg38OIfjtpXqnUoLoqVELfP0PXfhvG9Fc7islCciESdbanOkgVuNH69LBJq8XBmdR765J_XhWikgVPZkbePa7hkPy_Pifg4x4wwU9TQHtAGNW7GdKHGUrs-TPWuAi7OUhZuP4_EXfSF8aj |
| CitedBy_id | crossref_primary_10_1016_j_dsp_2024_104611 crossref_primary_10_3390_s24216985 crossref_primary_10_1016_j_rineng_2025_105545 crossref_primary_10_1088_1361_6501_ad42c5 crossref_primary_10_3390_electronics14112274 crossref_primary_10_3390_s24144628 crossref_primary_10_1038_s41598_023_47716_2 |
| Cites_doi | 10.1109/ICIP.2018.8451686 10.1109/LSP.2021.3079850 10.1007/978-3-030-01252-6_24 10.1109/ACCESS.2019.2929760 10.1109/TPAMI.2016.2577031 10.1007/s11042-020-08725-9 10.1088/1742-6596/1983/1/012017 10.1016/j.neucom.2021.03.091 10.1109/CVPR.2017.106 10.1007/s13042-019-01006-4 10.1155/2019/4042624 10.1016/j.landurbplan.2020.103921 10.1109/CVPRW.2019.00103 10.1007/978-3-030-21344-2 10.1109/IWECAI55315.2022.00088 10.1109/DSAA.2019.00023 10.1109/DCABES52998.2021.00031 10.1109/JSTARS.2020.3025582 10.1109/CVPR46437.2021.01556 10.1117/1.JEI.28.4.043023 10.1109/CompComm.2018.8780907 10.1016/j.ijdrr.2018.09.015 10.1016/j.patcog.2019.107149 10.1109/ICCV.2019.00502 10.1145/2733373.2806349 10.1109/ACCESS.2020.3014910 10.1016/j.patcog.2021.108258 10.3390/app10010087 10.1109/ISCAS51556.2021.9401434 10.1109/WACV48630.2021.00360 10.1109/SIU49456.2020.9302500 10.1109/CVPR46437.2021.00281 10.1007/978-3-030-01264-9_45 10.3390/agriculture10090416 10.1007/978-3-319-46448-0_2 10.1016/j.patcog.2021.108290 10.1109/ISCID.2019.10112 10.1109/VCIP.2016.7805452 10.1007/978-1-4899-7687-1_79 10.1007/978-3-319-10602-1_48 10.1016/j.neucom.2022.11.062 10.1109/ICCV.2017.322 10.1609/aaai.v35i3.16336 10.1109/WSAI51899.2021.9486316 10.1109/CVPR42600.2020.00856 10.3390/rs13050847 10.1109/ICCV.2017.324 |
| ContentType | Journal Article |
| Copyright | COPYRIGHT 2023 MDPI AG 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. 2023 by the authors. 2023 |
| Copyright_xml | – notice: COPYRIGHT 2023 MDPI AG – notice: 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. – notice: 2023 by the authors. 2023 |
| DBID | AAYXX CITATION NPM 7TB 8FD 8FE 8FG ABJCF ABUWG AFKRA AZQEC BENPR BGLVJ CCPQU DWQXO FR3 HCIFZ KR7 L6V M7S PHGZM PHGZT PIMPY PKEHL PQEST PQGLB PQQKQ PQUKI PTHSS 7X8 5PM DOA |
| DOI | 10.3390/e25030509 |
| DatabaseName | CrossRef PubMed Mechanical & Transportation Engineering Abstracts Technology Research Database ProQuest SciTech Collection ProQuest Technology Collection Materials Science & Engineering Collection ProQuest Central (Alumni) ProQuest Central UK/Ireland ProQuest Central Essentials ProQuest Central ProQuest Technology Collection ProQuest One ProQuest Central Engineering Research Database SciTech Premium Collection Civil Engineering Abstracts ProQuest Engineering Collection Engineering Database ProQuest Central Premium ProQuest One Academic (New) Publicly Available Content Database ProQuest One Academic Middle East (New) ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Applied & Life Sciences ProQuest One Academic (retired) ProQuest One Academic UKI Edition Engineering collection MEDLINE - Academic PubMed Central (Full Participant titles) DOAJ Directory of Open Access Journals |
| DatabaseTitle | CrossRef PubMed Publicly Available Content Database Technology Collection Technology Research Database ProQuest One Academic Middle East (New) Mechanical & Transportation Engineering Abstracts ProQuest Central Essentials ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest Central ProQuest One Applied & Life Sciences ProQuest Engineering Collection ProQuest Central Korea ProQuest Central (New) Engineering Collection Civil Engineering Abstracts Engineering Database ProQuest One Academic Eastern Edition ProQuest Technology Collection ProQuest SciTech Collection ProQuest One Academic UKI Edition Materials Science & Engineering Collection Engineering Research Database ProQuest One Academic ProQuest One Academic (New) MEDLINE - Academic |
| DatabaseTitleList | CrossRef Publicly Available Content Database MEDLINE - Academic PubMed |
| Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 3 dbid: PIMPY name: ProQuest Publicly Available Content Database url: http://search.proquest.com/publiccontent sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| EISSN | 1099-4300 |
| ExternalDocumentID | oai_doaj_org_article_4e10e322f2c84991a07e5349b67ee9fe PMC10047911 A743764274 36981396 10_3390_e25030509 |
| Genre | Journal Article |
| GeographicLocations | China |
| GeographicLocations_xml | – name: China |
| GrantInformation_xml | – fundername: the National Natural Science Foundation of China grantid: 62176067 – fundername: Scientific and Technological Planning Project of Guangzhou grantid: 202103000040 – fundername: Key Project of Guangdong Province Basic Research Foundation grantid: 2020B1515120095 – fundername: Project Supported by Guangdong Province Universities and Colleges Pearl River Scholar Funded Scheme grantid: 2019 – fundername: Scientific and Technological Planning Project of Guangzhou grantid: 201903010041 – fundername: National Natural Science Foundation of China grantid: 62176067 – fundername: Scientific and Technological Planning Project of Guangzhou grantid: 201903010041; 202103000040 – fundername: Guangdong Province Universities and Colleges Pearl River Scholar Funded Scheme grantid: 2019 |
| GroupedDBID | 29G 2WC 5GY 5VS 8FE 8FG AADQD AAFWJ AAYXX ABDBF ABJCF ACIWK ACUHS ADBBV AEGXH AENEX AFFHD AFKRA AFPKN AFZYC ALMA_UNASSIGNED_HOLDINGS BCNDV BENPR BGLVJ CCPQU CITATION CS3 DU5 E3Z ESX F5P GROUPED_DOAJ GX1 HCIFZ HH5 IAO ITC J9A KQ8 L6V M7S MODMG M~E OK1 OVT PGMZT PHGZM PHGZT PIMPY PQGLB PROAC PTHSS RNS RPM TR2 TUS XSB ~8M NPM 7TB 8FD ABUWG AZQEC DWQXO FR3 KR7 PKEHL PQEST PQQKQ PQUKI 7X8 5PM |
| ID | FETCH-LOGICAL-c509t-1b7f2aab69f371dd651f87db16bb3fcf5fc930cda19a5861ea1dbe2b6d25ba103 |
| IEDL.DBID | DOA |
| ISICitedReferencesCount | 8 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000958782400001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1099-4300 |
| IngestDate | Fri Oct 03 12:43:21 EDT 2025 Tue Nov 04 02:07:31 EST 2025 Sun Nov 09 10:33:20 EST 2025 Fri Jul 25 12:10:59 EDT 2025 Tue Nov 04 18:16:41 EST 2025 Mon Jul 21 06:05:11 EDT 2025 Tue Nov 18 21:07:00 EST 2025 Sat Nov 29 07:10:31 EST 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 3 |
| Keywords | adaptive data enhancement deep learning selective oversampling small target detection |
| Language | English |
| License | Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c509t-1b7f2aab69f371dd651f87db16bb3fcf5fc930cda19a5861ea1dbe2b6d25ba103 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 |
| ORCID | 0000-0002-6097-032X |
| OpenAccessLink | https://doaj.org/article/4e10e322f2c84991a07e5349b67ee9fe |
| PMID | 36981396 |
| PQID | 2791646233 |
| PQPubID | 2032401 |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_4e10e322f2c84991a07e5349b67ee9fe pubmedcentral_primary_oai_pubmedcentral_nih_gov_10047911 proquest_miscellaneous_2792508749 proquest_journals_2791646233 gale_infotracacademiconefile_A743764274 pubmed_primary_36981396 crossref_primary_10_3390_e25030509 crossref_citationtrail_10_3390_e25030509 |
| PublicationCentury | 2000 |
| PublicationDate | 20230316 |
| PublicationDateYYYYMMDD | 2023-03-16 |
| PublicationDate_xml | – month: 3 year: 2023 text: 20230316 day: 16 |
| PublicationDecade | 2020 |
| PublicationPlace | Switzerland |
| PublicationPlace_xml | – name: Switzerland – name: Basel |
| PublicationTitle | Entropy (Basel, Switzerland) |
| PublicationTitleAlternate | Entropy (Basel) |
| PublicationYear | 2023 |
| Publisher | MDPI AG MDPI |
| Publisher_xml | – name: MDPI AG – name: MDPI |
| References | Hu (ref_14) 2018; 2018 Van (ref_47) 2023; 519 Wu (ref_65) 2021; 1983 Luo (ref_54) 2021; 28 ref_58 ref_13 ref_12 ref_56 ref_55 ref_10 Ren (ref_27) 2016; 39 ref_53 ref_51 Qiu (ref_11) 2019; 28 Kaku (ref_7) 2019; 33 ref_18 ref_15 ref_59 ref_61 ref_60 Liu (ref_19) 2020; 8 ref_25 ref_23 Wellmann (ref_9) 2020; 204 ref_22 ref_66 ref_21 Ma (ref_50) 2020; 100 ref_20 ref_64 ref_63 ref_62 ref_29 ref_28 ref_26 Han (ref_57) 2022; 60 Zhou (ref_45) 2022; 122 Niu (ref_52) 2021; 452 ref_36 ref_35 ref_34 Yin (ref_31) 2020; 13 ref_33 ref_32 ref_30 ref_39 ref_38 ref_37 Chen (ref_49) 2019; 13 Zhou (ref_17) 2019; 10 Miao (ref_24) 2022; 122 ref_46 ref_44 ref_42 ref_41 ref_40 ref_1 Zhang (ref_43) 2020; 79 ref_3 ref_2 ref_48 ref_8 ref_5 ref_4 ref_6 Zhao (ref_16) 2019; 7 |
| References_xml | – ident: ref_46 doi: 10.1109/ICIP.2018.8451686 – volume: 28 start-page: 1060 year: 2021 ident: ref_54 article-title: A deep feature fusion network based on multiple attention mechanisms for joint iris-periocular biometric recognition publication-title: IEEE Signal Process. Lett. doi: 10.1109/LSP.2021.3079850 – ident: ref_55 – ident: ref_56 doi: 10.1007/978-3-030-01252-6_24 – volume: 7 start-page: 101160 year: 2019 ident: ref_16 article-title: Detection, tracking, and geolocation of moving vehicle from uav using monocular camera publication-title: IEEE Access doi: 10.1109/ACCESS.2019.2929760 – volume: 39 start-page: 1137 year: 2016 ident: ref_27 article-title: Faster R-CNN: Towards real-time object detection with region proposal networks publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2016.2577031 – volume: 2018 start-page: 4546896 year: 2018 ident: ref_14 article-title: Small object detection with multiscale features publication-title: Int. J. Digit. Multimed. Broadcast. – volume: 79 start-page: 17445 year: 2020 ident: ref_43 article-title: A real-time recognition method of static gesture based on DSSD publication-title: Multimed. Tools Appl. doi: 10.1007/s11042-020-08725-9 – volume: 1983 start-page: 012017 year: 2021 ident: ref_65 article-title: An improved target detection algorithm based on EfficientNet publication-title: J. Phys. Conf. Ser. doi: 10.1088/1742-6596/1983/1/012017 – volume: 452 start-page: 48 year: 2021 ident: ref_52 article-title: A review on the attention mechanism of deep learning publication-title: Neurocomputing doi: 10.1016/j.neucom.2021.03.091 – ident: ref_48 doi: 10.1109/CVPR.2017.106 – ident: ref_23 – volume: 10 start-page: 3155 year: 2019 ident: ref_17 article-title: Enhance the recognition ability to occlusions and small objects with Robust Faster R-CNN publication-title: Int. J. Mach. Learn. Cybern. doi: 10.1007/s13042-019-01006-4 – ident: ref_15 doi: 10.1155/2019/4042624 – volume: 204 start-page: 103921 year: 2020 ident: ref_9 article-title: Remote sensing in urban planning: Contributions towards ecologically sound policies publication-title: Landsc. Urban Plan. doi: 10.1016/j.landurbplan.2020.103921 – ident: ref_26 doi: 10.1109/CVPRW.2019.00103 – ident: ref_10 doi: 10.1007/978-3-030-21344-2 – ident: ref_44 doi: 10.1109/IWECAI55315.2022.00088 – ident: ref_42 doi: 10.1109/DSAA.2019.00023 – ident: ref_66 – ident: ref_38 – ident: ref_34 doi: 10.1109/DCABES52998.2021.00031 – volume: 13 start-page: 5862 year: 2020 ident: ref_31 article-title: Hot region selection based on selective search and modified fuzzy C-Means in remote sensing Images publication-title: IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. doi: 10.1109/JSTARS.2020.3025582 – volume: 13 start-page: 1049 year: 2019 ident: ref_49 article-title: SSD object detection algorithm with multi-scale convolution feature fusion publication-title: J. Front. Comput. Sci. Technol. – ident: ref_20 – ident: ref_59 – ident: ref_58 doi: 10.1109/CVPR46437.2021.01556 – volume: 28 start-page: 043023 year: 2019 ident: ref_11 article-title: Automatic visual defects inspection of wind turbine blades via YOLO-based small object detection approach publication-title: J. Electron. Imaging doi: 10.1117/1.JEI.28.4.043023 – ident: ref_41 doi: 10.1109/CompComm.2018.8780907 – volume: 33 start-page: 417 year: 2019 ident: ref_7 article-title: Satellite remote sensing for disaster management support: A holistic and staged approach based on case studies in Sentinel Asia publication-title: Int. J. Disaster Risk Reduct. doi: 10.1016/j.ijdrr.2018.09.015 – volume: 100 start-page: 107149 year: 2020 ident: ref_50 article-title: MDFN: Multi-scale deep feature learning network for object detection publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2019.107149 – ident: ref_62 doi: 10.1109/ICCV.2019.00502 – ident: ref_18 doi: 10.1145/2733373.2806349 – volume: 60 start-page: 1 year: 2022 ident: ref_57 article-title: Align deep features for oriented object detection publication-title: IEEE Trans. Geosci. Remote Sens. – volume: 8 start-page: 145740 year: 2020 ident: ref_19 article-title: Small-object detection in UAV-captured images via multi-branch parallel feature pyramid networks publication-title: IEEE Access doi: 10.1109/ACCESS.2020.3014910 – volume: 122 start-page: 108258 year: 2022 ident: ref_24 article-title: Balanced single-shot object detection using cross-context attention-guided network publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2021.108258 – ident: ref_1 doi: 10.3390/app10010087 – ident: ref_61 doi: 10.1109/ISCAS51556.2021.9401434 – ident: ref_53 doi: 10.1109/WACV48630.2021.00360 – ident: ref_40 – ident: ref_63 – ident: ref_4 doi: 10.1109/SIU49456.2020.9302500 – ident: ref_21 – ident: ref_60 doi: 10.1109/CVPR46437.2021.00281 – ident: ref_6 – ident: ref_25 – ident: ref_37 doi: 10.1007/978-3-030-01264-9_45 – ident: ref_29 – ident: ref_8 doi: 10.3390/agriculture10090416 – ident: ref_33 doi: 10.1007/978-3-319-46448-0_2 – volume: 122 start-page: 0031 year: 2022 ident: ref_45 article-title: Contextual ensemble network for semantic segmentation publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2021.108290 – ident: ref_2 – ident: ref_5 doi: 10.1109/ISCID.2019.10112 – ident: ref_32 doi: 10.1109/VCIP.2016.7805452 – ident: ref_39 doi: 10.1007/978-1-4899-7687-1_79 – ident: ref_13 doi: 10.1007/978-3-319-10602-1_48 – volume: 519 start-page: 104 year: 2023 ident: ref_47 article-title: Feature pyramid network with multi-scale prediction fusion for real-time semantic segmentation publication-title: Neurocomputing doi: 10.1016/j.neucom.2022.11.062 – ident: ref_28 doi: 10.1109/ICCV.2017.322 – ident: ref_64 – ident: ref_30 doi: 10.1609/aaai.v35i3.16336 – ident: ref_35 doi: 10.1109/WSAI51899.2021.9486316 – ident: ref_36 – ident: ref_3 doi: 10.1109/CVPR42600.2020.00856 – ident: ref_51 doi: 10.3390/rs13050847 – ident: ref_22 – ident: ref_12 doi: 10.1109/ICCV.2017.324 |
| SSID | ssj0023216 |
| Score | 2.3639731 |
| Snippet | General target detection with deep learning has made tremendous strides in the past few years. However, small target detection sometimes is associated with... |
| SourceID | doaj pubmedcentral proquest gale pubmed crossref |
| SourceType | Open Website Open Access Repository Aggregation Database Index Database Enrichment Source |
| StartPage | 509 |
| SubjectTerms | Adaptive algorithms Adaptive control adaptive data enhancement Algorithms Alliances Datasets Deep learning Feature extraction Frames per second Machine learning Methods Modules Neural networks Pedestrians Safety helmets selective oversampling Semantics Sensors small target detection Target acquisition Target detection Visual discrimination |
| SummonAdditionalLinks | – databaseName: Engineering Database dbid: M7S link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Lb9QwELagcOACRTwaaCuDkOASdW0ndswFLbQVF1ZIu0i9RX52K22zy27K72fGmw2NQFx6ja1o7Hl4Zjz-hpB3HlwIV1qbF9pWeRFkzK3QLpfKe848vtorUrMJNZlUFxf6e5dw23RllTubmAy1XzrMkZ9wpREKiwvxafUzx65ReLvatdC4Tx4gSgJLpXvTPuASnMktmpCA0P4kwHEvEO9kcAYlqP6_DfKtE2lYLXnr-Dl_clfC98njzvGk462kPCX3QvOMfJvOcszvhvUktB_p9NosFnSWisPpaWhTmVZDx4tL-GE7v6aYtaVjb1ZoJOmpaQ09a-YoOJhkfE5-nJ_NvnzNuwYLuYNdaHNmVeTGWKmjUMx7WbJYKW-ZtFZEF8votBg5b5g2ZSVZMMzbwK30vLSGjcQLstcsm3BAKLfgF5ZgLDl3BSuUVeAJGVkKq6WupMjIh92W165DH8cmGIsaohDkTt1zJyNv-6mrLeTGvyZ9Rr71ExAlO31Yri_rTunqIrBRAIsVuasgsmNmpEIpQCqlCkHHkJH3yPUadRmIcaZ7kgBLQlSsegzulYIATRUZOdwxt-6UfFP_4WxG3vTDoJ5452KasLxJc4DkShVA8cutHPU0C9gZcMBlRqqBhA0WNRxpruYJApyl1gCMvfo_Xa_JIw5qgDVzTB6SvXZ9E47IQ_ervdqsj5Oy_AZ_wh57 priority: 102 providerName: ProQuest |
| Title | ST-CenterNet: Small Target Detection Algorithm with Adaptive Data Enhancement |
| URI | https://www.ncbi.nlm.nih.gov/pubmed/36981396 https://www.proquest.com/docview/2791646233 https://www.proquest.com/docview/2792508749 https://pubmed.ncbi.nlm.nih.gov/PMC10047911 https://doaj.org/article/4e10e322f2c84991a07e5349b67ee9fe |
| Volume | 25 |
| WOSCitedRecordID | wos000958782400001&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: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 1099-4300 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0023216 issn: 1099-4300 databaseCode: DOA dateStart: 20160101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 1099-4300 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0023216 issn: 1099-4300 databaseCode: M~E dateStart: 19990101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre – providerCode: PRVPQU databaseName: Engineering Database customDbUrl: eissn: 1099-4300 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0023216 issn: 1099-4300 databaseCode: M7S dateStart: 19990301 isFulltext: true titleUrlDefault: http://search.proquest.com providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: eissn: 1099-4300 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0023216 issn: 1099-4300 databaseCode: BENPR dateStart: 19990301 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Publicly Available Content Database customDbUrl: eissn: 1099-4300 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0023216 issn: 1099-4300 databaseCode: PIMPY dateStart: 19990301 isFulltext: true titleUrlDefault: http://search.proquest.com/publiccontent providerName: ProQuest |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Lb9QwELagcOBSFfEKLSuDkOASNbYTO-a2pVvBoasVu0jLKfIrbKVtttqmHPntnUmy0UYgceGSQzyKxvOwZ5zxN4S89xBCuMzaONU2j9Mgy9gK7WKpvOfM4629tGk2oabTfLnUs71WX1gT1sIDt4I7TQNLAlhdyV0O0TkziQqZgC9LFYIuA66-idK7ZKpLtQRnssUREpDUnwbY6AUinQx2nwak_8-leG8vGtZJ7m08F0fksIsY6bjl9Cl5EKpn5HK-iPFgNmynof5E59dmvaaLpqqbnoe6qa-q6Hj9cwPJ_-qa4nErHXtzg6sbPTe1oZNqhRrH08Hn5PvFZPH5S9x1RogdTKKOmVUlN8ZKXQrFvJcZK3PlLZPWitKVWem0SJw3TJsslywY5m3gVnqeWcMS8YIcVJsqvCKUWwjoMljlOHcpS5VVEMIYmQmrpc6liMjHncQK18GGY_eKdQHpAwq36IUbkXc96U2LlfE3ojMUe0-A8NbNC1B60Sm9-JfSI_IBlVagEwIzznR3CWBKCGdVjCEuUpBZqTQiJzu9Fp133hZcaYRV4wJm97YfBr_CnyWmCpu7hgZYzlUKHL9szaDnWYBkIHKWEckHBjKY1HCkulo12N2swfRn7PX_EMMxecLB1rEkjskTclBv78Ib8tj9qq9utyPyUC3zEXl0NpnOvo0a_xhhaescn78nMDL7ejn7cQ9MURaS |
| linkProvider | Directory of Open Access Journals |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lb9QwELZKQYILD_EKFDAIBJeosZ3YMRJCC9uqVdsV0i5Sb8GvdCtts8tuCuJP8RsZOw-6AnHrgWtsRTP2Ny97PIPQSwsuhMm0jlOp8zh1vIw1kybmwlpKrH-1l4ZmE2I0yo-P5acN9LN7C-PTKjudGBS1nRt_Rr5NhfSlsChj7xdfY981yt-udi00GlgcuB_fIWRbvdsfwv6-onR3Z_JxL267CsQGjGMdEy1KqpTmsmSCWMszUubCasK1ZqUps9JIlhiriFRZzolTxGpHNbc004okDP57BV0FN4LKkCo47gM8RglvqhcxJpNtB-4F8_VV1mxeaA3wpwG4YAHXszMvmLvdW__bQt1GN1vHGg8aSbiDNlx1Fx2NJ7E_v3bLkavf4vGZms3wJCS_46GrQxpahQezE2Cgnp5hfyqNB1YtvBHAQ1UrvFNNvWD4Q9R76POlcHAfbVbzyj1EmGrwezMwBpSalKRCC_D0FM-YllzmnEXoTbfFhWmrq_smH7MCoiyPhqJHQ4Re9FMXTUmRv0364HHST_BVwMOH-fKkaJVKkTqSONDIJTU5RK5EJcJlDKSOC-dk6SL02qOs8LoKiDGqfXIBLPmqX8UA3EcBAahII7TVgaloldiq-I2kCD3vh0H9-DslVbn5eZgDJOciBYofNLjtaWawMhBg8Ajla4heY2p9pDqdhhLnJLQ-IOTRv-l6hq7vTY4Oi8P90cFjdIOCCPr8QMK30Ga9PHdP0DXzrT5dLZ8GQcXoy2UD_hf-fX7P |
| linkToPdf | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V3db9MwED-NDiFeBoivjAEGgeAlam0ndoKEUKGrqMaqSivS9hT8lXVSl5Y2A_Gv8ddxTtOwCsTbHniNrejO_t2Xfb4DeGHRhTCx1mGU6iSMnMhDzVMTCmkto9a_2ouqZhNyOEyOj9PRFvxcv4XxaZVrnVgpajsz_oy8zWTqS2Exztt5nRYx6vXfzb-GvoOUv2ldt9NYQeTA_fiO4dvy7aCHe_2Ssf7--MPHsO4wEBo0lGVItcyZUlqkOZfUWhHTPJFWU6E1z00e5yblHWMVTVWcCOoUtdoxLSyLtaIdjv-9BtvokkesBdujweHopAn3OKNiVcuI87TTduhscF9tZcMCVo0C_jQHl-zhZq7mJePXv_U_L9tt2KldbtJdycgd2HLFXTg8Gof-ZNsthq58Q47O1XRKxlVaPOm5skpQK0h3eooMlJNz4s-rSdequTcPpKdKRfaLiRcZf7x6Dz5fCQf3oVXMCvcQCNPoEcdoJhgzEY2klugDKhFznYo0ETyA1-vtzkxdd923_5hmGH95ZGQNMgJ43kydr4qN_G3Se4-ZZoKvD159mC1Os1rdZJGjHYe6OmcmwZiWqo50MUd5FNK5NHcBvPKIy7wWQ2KMqh9jIEu-HljWRcdSYmgqowD21sDKavW2zH6jKoBnzTAqJn_bpAo3u6jmIMmJjJDiBysMNzRzXBkMPUQAyQa6N5jaHCnOJlXxc1o1RaB09990PYUbiPPs02B48AhuMpRGnzhIxR60ysWFewzXzbfybLl4UkstgS9Xjfhf4N2JBQ |
| 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=ST-CenterNet%3A+Small+Target+Detection+Algorithm+with+Adaptive+Data+Enhancement&rft.jtitle=Entropy+%28Basel%2C+Switzerland%29&rft.au=Yujie+Guo&rft.au=Xu+Lu&rft.date=2023-03-16&rft.pub=MDPI+AG&rft.eissn=1099-4300&rft.volume=25&rft.issue=3&rft.spage=509&rft_id=info:doi/10.3390%2Fe25030509&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_4e10e322f2c84991a07e5349b67ee9fe |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1099-4300&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1099-4300&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1099-4300&client=summon |