A lightweight model for echo trace detection in echograms based on improved YOLOv8
Jungang Ma, Jianfeng Tong, Minghua Xue, Junfan Yao · 2024
Read A lightweight model for echo trace detection in echograms based on improved YOLOv8 by Jungang Ma, Jianfeng Tong, Minghua Xue, Junfan Yao (2024) 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-11621696.txt.
Description
Jungang Ma and three co-authors build a leaner AI model to find fish in sonar images, in this twenty twenty-four paper. Robot boats and divers now carry echo sounders to study water life. The standard detection models are too heavy to fit in those devices and stumble on noisy, crowded images.
Their trimmed model cuts computing cost and stored size while spotting the faint traces fish leave on echograms. New parts sharpen feature picking, blend detail across scales, and help find small targets. Tested on real echograms, the lean model scored well for its size, a step toward smart sounders that can work on the water.
Catalog record
| CREATOR | Jungang Ma, Jianfeng Tong, Minghua Xue, Junfan Yao |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 49 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |