arXivDaily arXiv每日学术速递 周一至周五更新
看起来今天可以划水了
arXiv 2501.00527cs.CVcs.LG
收藏

利用边界损失进行植物与叶片的分层全景分割

Exploiting Boundary Loss for the Hierarchical Panoptic Segmentation of Plants and Leaves

Lincoln Centre for Autonomous Systems(林肯自主系统中心);University of Lincoln(林肯大学);Lincoln Institute of Agri-Food Technology(林肯农食品技术学院)

Madeleine Darbyshire, Elizabeth Sklar, Simon Parsons

AI总结:

本文提出一种结合 focal loss 和 boundary loss 的分层全景分割方法,同时实现叶片计数与杂草定位,在标准训练集上达到 81.89 的 PQ+,并提升了叶片计数精度。

摘要:

精准农业利用数据和机器学习,使农民能够监测作物并精准实施干预。这使得除草剂可以仅精准施用于杂草,或肥料仅精准施用于营养不足的作物,而非整个田地。该方法有望在最大化产量的同时,最小化资源使用和对周围环境的危害。为此,我们提出了一种分层全景分割方法,能够同时确定叶片数量(作为植物生长的标识符)并定位图像中的杂草。特别是,我们的方法旨在通过引入 focal loss 和 boundary loss 来改善较小实例(如叶片和杂草)的分割效果。这不仅带来了具有竞争力的性能,在标准训练集上达到了 81.89 的 PQ+,而且我们还证明了我们的方法能够提高叶片计数的准确性。代码可在 https://github.com/madeleinedarbyshire/HierarchicalMask2Former 获取。

英文摘要:

Precision agriculture leverages data and machine learning so that farmers can monitor their crops and target interventions precisely. This enables the precision application of herbicide only to weeds, or the precision application of fertilizer only to undernourished crops, rather than to the entire field. The approach promises to maximize yields while minimizing resource use and harm to the surrounding environment. To this end, we propose a hierarchical panoptic segmentation method that simultaneously determines leaf count (as an identifier of plant growth)and locates weeds within an image. In particular, our approach aims to improve the segmentation of smaller instances like the leaves and weeds by incorporating focal loss and boundary loss. Not only does this result in competitive performance, achieving a PQ+ of 81.89 on the standard training set, but we also demonstrate we can improve leaf-counting accuracy with our method. The code is available at https://github.com/madeleinedarbyshire/HierarchicalMask2Former.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑