Bridging the Gap Between Computational Efficiency and Segmentation Fidelity in Object-Based Image Analysis
Fernanda Pereira Leite Aguiar, Irenilza de Alencar Nääs, Marcelo Tsuguio Okano · 2024
Read Bridging the Gap Between Computational Efficiency and Segmentation Fidelity in Object-Based Image Analysis by Fernanda Pereira Leite Aguiar, Irenilza de Alencar Nääs, Marcelo Tsuguio Okano (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-11672607.txt.
Description
Watching animals in video calls for software that outlines each animal fast and faithfully, and those two goals fight. Fernanda Pereira Leite Aguiar and co-authors present a preprocessing algorithm that balances them in this 2024 paper. Object-based image analysis groups pixels into objects before a learning model reads them. Pixel-level and unsupervised methods often blur edges or cost too much on complex scenes.
Their pipeline mixes convolution steps, value compression, and polynomial reshaping of the image. The goal is cleaner object outlines plus structured data about each object. Tests showed lower computing demand with better outline accuracy, above all on busy backgrounds. Reliable outlines feed robust tracking of behavior. Farm and lab cameras could both use such a front end.
Catalog record
| CREATOR | Fernanda Pereira Leite Aguiar, Irenilza de Alencar Nääs, Marcelo Tsuguio Okano |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 55 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |