IWRA Proceedings

< Return to abstract list

Poster P-2-3-16: Irrigated well room recognition based on high resolution remote sensing image and deep learning algorithm

XVIII IWRA World Water Congress Beijing China 2023
Sub-theme 2: Promoting Water Efficiency, Productivity and Services
Author(s): Xuli Zan, Suchuang Di, Xuemin Li, HangZhang , YueWang
Xuli Zan , Suchuang Di, Xuemin Li, HangZhang , YueWang
Beijing Water Science and Technology Institute, Beijing, 100048, PR China.

Poster: PDF

Abstract

Study conclusions

Faster RCNN model is better than YOLO v 7 in terms of identifying agricultural irrigated wells

Compared with modern facility agriculture and orchard forest land type, the irrigated well room recognition effect is better under the environment of traditional cultivated land type

Relying on existing remote sensing image resolution 0 8 m) and detection sample datasets, it is not possible to accurately locate integrated irrigated well room with extremely small areas using recognition algorithms

IWRA Proceedings office@iwra.org - https://www.iwra.org/member/index.php