https://www.mdu.se/

mdu.sePublikationer
Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Improved Detection Method for Micro-Targets in Remote Sensing Images
Department of Computer Engineering, Taiyuan Institute of Technology, Taiyuan 030008, China.
Mälardalens universitet, Akademin för innovation, design och teknik, Inbyggda system.ORCID-id: 0000-0001-9857-4317
chool of Computer Science and Technology, Taiyuan Normal University, Jinzhong 030619, China.
School of Computer and Information Technology, Beijing Jiaotong University, Beijing 100044, China.
2024 (Engelska)Ingår i: Information, E-ISSN 2078-2489, Vol. 15, nr 2, artikel-id 108Artikel i tidskrift (Refereegranskat) Published
Abstract [en]

With the exponential growth of remote sensing images in recent years, there has been a significant increase in demand for micro-target detection. Recently, effective detection methods for small targets have emerged; however, for micro-targets (even fewer pixels than small targets), most existing methods are not fully competent in feature extraction, target positioning, and rapid classification. This study proposes an enhanced detection method, especially for micro-targets, in which a combined loss function (consisting of NWD and CIOU) is used instead of a singular CIOU loss function. In addition, the lightweight Content-Aware Reassembly of Features (CARAFE) replaces the original bilinear interpolation upsampling algorithm, and a spatial pyramid structure is added into the network model’s small target layer. The proposed algorithm undergoes training and validation utilizing the benchmark dataset known as AI-TOD. Compared to speed-oriented YOLOv7-tiny, the mAP0.5 and mAP0.5:0.95 of our improved algorithm increased from 42.0% and 16.8% to 48.7% and 18.9%, representing improvements of 6.7% and 2.1%, respectively, while the detection speed was almost equal to that of YOLOv7-tiny. Furthermore, our method was also tested on a dataset of multi-scale targets, which contains small targets, medium targets, and large targets. The results demonstrated that mAP0.5:0.95 increased from “9.8%, 54.8%, and 68.2%” to “12.6%, 55.6%, and 70.1%” for detection across different scales, indicating improvements of 2.8%, 0.8%, and 1.9%, respectively. In summary, the presented method improves detection metrics for micro-targets in various scenarios while satisfying the requirements of detection speed in a real-time system.

Ort, förlag, år, upplaga, sidor
Multidisciplinary Digital Publishing Institute (MDPI) , 2024. Vol. 15, nr 2, artikel-id 108
Nyckelord [en]
CARAFE, micro-targets, NWD, remote sensing images, spatial pyramid, Feature extraction, Interactive computer systems, Large datasets, Real time systems, Remote sensing, Content-aware, Content-aware reassembly of feature, Detection methods, Loss functions, Micro-target, Reassembly, Small targets, Spatial pyramids, Image enhancement
Nationell ämneskategori
Data- och informationsvetenskap
Identifikatorer
URN: urn:nbn:se:mdh:diva-66179DOI: 10.3390/info15020108ISI: 001172402600001Scopus ID: 2-s2.0-85185707305OAI: oai:DiVA.org:mdh-66179DiVA, id: diva2:1842870
Anmärkning

Article; Export Date: 06 March 2024; Cited By: 0; Correspondence Address: P. Wu; School of Computer and Information Technology, Beijing Jiaotong University, Beijing, 100044, China; email: 14112078@bjtu.edu.cn

Tillgänglig från: 2024-03-06 Skapad: 2024-03-06 Senast uppdaterad: 2024-03-13Bibliografiskt granskad

Open Access i DiVA

Fulltext saknas i DiVA

Övriga länkar

Förlagets fulltextScopus

Person

Xiong, Ning

Sök vidare i DiVA

Av författaren/redaktören
Xiong, Ning
Av organisationen
Inbyggda system
I samma tidskrift
Information
Data- och informationsvetenskap

Sök vidare utanför DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetricpoäng

doi
urn-nbn
Totalt: 21 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf