Adaptive spatial-channel feature fusion and self-calibrated convolution for early maize seedlings counting in UAV images
Zhenyuan Sun, Zhi Yang, Yimin Ding, Boyan Sun, Saiju Li, Zhen Guo, Lei Zhu · 2025
Read Adaptive spatial-channel feature fusion and self-calibrated convolution for early maize seedlings counting in UAV images by Zhenyuan Sun, Zhi Yang, Yimin Ding, Boyan Sun, Saiju Li, Zhen Guo, Lei Zhu (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-11841422.txt.
Description
Zhenyuan Sun and six co-authors build a drone image system that counts young maize plants in a paper whose head reports 2024. Hand counts are slow and error-prone, and drone photos blur at varied heights, which hurts counts of small seedlings. Their model, RC-Dino, adapts a known detection network with two new parts.
One part recalibrates spatial features so seedlings stand out from bare soil. The other fuses feature maps from several layers to sharpen young plants. On a data set of more than eighty thousand labeled seedlings, the model beat five rival detectors by clear margins in precision and recall. Its parts also lifted other detectors when added.
Catalog record
| CREATOR | Zhenyuan Sun, Zhi Yang, Yimin Ding, Boyan Sun, Saiju Li, Zhen Guo, Lei Zhu |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 48 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |