DSCA-PSPNet: Dynamic spatial-channel attention pyramid scene parsing network for sugarcane field segmentation in satellite imagery

Yujian Yuan, Lina Yang, Kan Chang, Youju Huang, Haoyan Yang, Jiale Wang · 2024

Read DSCA-PSPNet: Dynamic spatial-channel attention pyramid scene parsing network for sugarcane field segmentation in satellite imagery by Yujian Yuan, Lina Yang, Kan Chang, Youju Huang, Haoyan Yang, Jiale Wang (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-10829042.txt.

Description

Yujian Yuan and co-authors present a 2023 paper on mapping sugarcane fields from satellite images. Pinpointing cane fields guides yield forecasts and farm planning. The task is hard: light varies, field sizes vary, and cane can look like other growth. The team built a segmentation network with a tuned backbone and new attention blocks that weigh place and channel cues.

A fresh high-detail image set from a Guangxi county anchors the tests. The model beat top rivals, with overlap near 88 percent and accuracy above 92. It also ran in under five milliseconds per image on a gaming-grade card. Removing the new attention blocks hurt scores most in ablation tests. Code and data will be posted publicly, the team says.

Catalog record

CREATORYujian Yuan, Lina Yang, Kan Chang, Youju Huang, Haoyan Yang, Jiale Wang
YEAR2024
COLLECTIONPAPERS
FORMATTXT
FILE SIZE58 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC10829042

Browse the full library · About the Tower of Babel