Small Ship Detection on Optical Satellite Imagery with YOLO and YOLT

Wilder Nina, William Condori, Vicente Machaca, Juan Villegas, Eveling Castro

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

5 Scopus citations


Actually, the use of deep learning in object detection gives good results, but this performance decreases when there are small objects in the image. In this work, is presented a comparison between the last version of You Only Look Once (YOLO) and You Only Look Twice (YOLT) on the problem of detecting small objects (ships) on optical satellite imagery. Two datasets were used: High-Resolution Ship Collection (HRSC) and Mini Ship Data Set (MSDS), the last one was built by us. The mean object’s width for HRSC and MSDS are 150 and 50 pixels, respectively. The results showed that YOLT is good only for small objects with 76,06% of Average Precision (AP), meanwhile, YOLO reached 69,80% in the MSDS dataset. Moreover, in the case of the HRSC dataset where have objects of different sizes, YOLT obtained a 40% of AP against 75% of YOLO.

Original languageEnglish
Title of host publicationAdvances in Information and Communication - Proceedings of the 2020 Future of Information and Communication Conference FICC
EditorsKohei Arai, Supriya Kapoor, Rahul Bhatia
Number of pages14
ISBN (Print)9783030394417
StatePublished - 2020
EventFuture of Information and Communication Conference, FICC 2020 - San Francisco, United States
Duration: 5 Mar 20206 Mar 2020

Publication series

NameAdvances in Intelligent Systems and Computing
Volume1130 AISC
ISSN (Print)2194-5357
ISSN (Electronic)2194-5365


ConferenceFuture of Information and Communication Conference, FICC 2020
Country/TerritoryUnited States
CitySan Francisco

Bibliographical note

Publisher Copyright:
© 2020, Springer Nature Switzerland AG.


  • Object detection
  • Satellite Imagery
  • Ship detection
  • Small objects
  • YOLO
  • YOLT


Dive into the research topics of 'Small Ship Detection on Optical Satellite Imagery with YOLO and YOLT'. Together they form a unique fingerprint.

Cite this