4.6 Article

Improved weed segmentation in UAV imagery of sorghum fields with a combined deblurring segmentation model

期刊

PLANT METHODS
卷 19, 期 1, 页码 -

出版社

BMC
DOI: 10.1186/s13007-023-01060-8

关键词

Weed detection; Segmentation; Machine learning; Computer vision; Deblurring; UAV

向作者/读者索取更多资源

In this study, a combined deblurring and segmentation model called DeBlurWeedSeg is proposed for weed and crop segmentation in motion blurred images. The model outperforms a standard segmentation model without deblurring, showing a relative improvement of 13.4% in terms of the Sorensen-Dice coefficient.
Background Efficient and site-specific weed management is a critical step in many agricultural tasks. Image captures from drones and modern machine learning based computer vision methods can be used to assess weed infestation in agricultural fields more efficiently. However, the image quality of the captures can be affected by several factors, including motion blur. Image captures can be blurred because the drone moves during the image capturing process, e.g. due to wind pressure or camera settings. These influences complicate the annotation of training and test samples and can also lead to reduced predictive power in segmentation and classification tasks. Results In this study, we propose DeBlurWeedSeg, a combined deblurring and segmentation model for weed and crop segmentation in motion blurred images. For this purpose, we first collected a new dataset of matching sharp and naturally blurred image pairs of real sorghum and weed plants from drone images of the same agricultural field. The data was used to train and evaluate the performance of DeBlurWeedSeg on both sharp and blurred images of a hold-out test-set. We show that DeBlurWeedSeg outperforms a standard segmentation model that does not include an integrated deblurring step, with a relative improvement of 13.4% in terms of the Sorensen-Dice coefficient. Conclusion Our combined deblurring and segmentation model DeBlurWeedSeg is able to accurately segment weeds from sorghum and background, in both sharp as well as motion blurred drone captures. This has high practical implications, as lower error rates in weed and crop segmentation could lead to better weed control, e.g. when using robots for mechanical weed removal.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.6
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据