Automatic detection and counting of wheat spike based on DMseg-Count
Hecang Zang, Yilong Peng, Meng Zhou, Guoqiang Li, Guoqing Zheng, Hualei Shen · 2024
Read Automatic detection and counting of wheat spike based on DMseg-Count by Hecang Zang, Yilong Peng, Meng Zhou, Guoqiang Li, Guoqing Zheng, Hualei Shen (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-11607314.txt.
Description
Hecang Zang and co-authors teach a computer to count wheat ears in field photographs, a number that forecasts the harvest, in a 2024 paper. Counting by eye is slow, and photographs fight back: harsh light, odd angles, and ears overlapping into a golden tangle. Earlier counting networks looked at the whole image and missed fine detail where ears crowd. The team's model adds a local branch that studies small patches closely.
The new branch produces a segmentation map of individual ears, whose detail is fused with the global view by element-wise multiplication. Training balances the counting error against the local map's accuracy. The authors report sharper counts under the messy conditions of real fields. Better ear counts feed yield prediction and variety trials, helping breeders judge which wheat lines deserve wider planting.
Catalog record
| CREATOR | Hecang Zang, Yilong Peng, Meng Zhou, Guoqiang Li, Guoqing Zheng, Hualei Shen |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 46 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |