Storage tank detection in remote sensing images based on circular bounding boxes and large selective kernel

Yu Liu, Yong Wan, Weimin Huang, Zihao Zhan · 2025

Read Storage tank detection in remote sensing images based on circular bounding boxes and large selective kernel by Yu Liu, Yong Wan, Weimin Huang, Zihao Zhan (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-12714706.txt.

Description

Yu Liu, Yong Wan, Weimin Huang, and Zihao Zhan present a 2025 paper on spotting storage tanks in satellite and aerial images. Tanks at oil and gas sites matter for tracking methane leaks, a strong greenhouse gas. Older feature-based methods raise many false alarms, and standard deep learning detectors miss small tanks or confuse them with the background.

Their method draws circular boxes, matching the round top view of most tanks, and adds a large selective kernel that adjusts how wide the model looks. Round boxes keep the overlap score steady for small objects. The authors report fewer missed tanks and fewer false hits than the common detectors they compare against.

Catalog record

CREATORYu Liu, Yong Wan, Weimin Huang, Zihao Zhan
YEAR2025
COLLECTIONPAPERS
FORMATTXT
FILE SIZE57 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC12714706

Browse the full library · About the Tower of Babel