ES-YOLO: Multi-Scale Port Ship Detection Combined with Attention Mechanism in Complex Scenes
Lixiang Cao, Jia Xi, Zixuan Xie, Teng Feng, Xiaomin Tian · 2025
Read ES-YOLO: Multi-Scale Port Ship Detection Combined with Attention Mechanism in Complex Scenes by Lixiang Cao, Jia Xi, Zixuan Xie, Teng Feng, Xiaomin Tian (2025) 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/pmc-12736885.txt.
Description
Lixiang Cao, Jia Xi, Zixuan Xie, Teng Feng, and Xiaomin Tian present a model for spotting ships in port images in a 2025 paper. Remote sensing pictures of harbors are hard: clouds hide ships, waves blur edges, buildings crowd the shore, and ships bunch together. Most past detectors were tuned for simpler scenes, such as open sea or a fixed camera angle.
Their model, ES-YOLO, adds a channel that sharpens edge detail, a lighter step for shrinking the image, and a layered scale setup that balances small and large ships. The team also built a data set, TJShip, from high-grade satellite images, covering craft from small fishing boats to big cargo ships. Comparison tests on that set show the design's gains.
Catalog record
| CREATOR | Lixiang Cao, Jia Xi, Zixuan Xie, Teng Feng, Xiaomin Tian |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 53 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |