LHR-YOLO: A SAR small-target ship detection method based on improved YOLO11

Miao Zhou, Dezhi Han, Xiang Shen, Yangshuyi Xu, Chongqing Chen · 2026

Read LHR-YOLO: A SAR small-target ship detection method based on improved YOLO11 by Miao Zhou, Dezhi Han, Xiang Shen, Yangshuyi Xu, Chongqing Chen (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0359334.txt.

Description

Miao Zhou and four co-authors present an improved ship spotting algorithm for radar images, in a 2026 PLOS ONE article. Synthetic aperture radar can watch the seas through cloud and darkness, but small ships blur into speckle noise and busy coastal backgrounds. Their system, LHR-YOLO, rebuilds parts of a popular detection network to sharpen exactly those faint, tiny targets.

Edge enhancing filters at the input stage make small outlines easier to see, while a redesigned backbone mixes features across scales. A high resolution detection head then pins down each vessel's position. On two public radar datasets the system beat the base network it grew from, lifting small ship accuracy by several points. Better automated watch over shipping lanes and coastal waters is the practical aim behind the work.

Catalog record

CREATORMiao Zhou, Dezhi Han, Xiang Shen, Yangshuyi Xu, Chongqing Chen
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE63302
LICENSECC_BY
RIGHTSCC BY
SOURCEPLOS

Source: https://doi.org/10.1371/journal.pone.0359334

Browse the full library · About the Tower of Babel