Deep learning object detection to estimate the nectar sugar mass of flowering vegetation
Deep learning object detection to estimate the nectar sugar mass of flowering vegetation
复制标题
深度学习目标检测来估计开花植物的花蜜糖量
DOI：
10.1002/2688-8319.12099
复制
发表时间：
2021
影响因子：
2.9
通讯作者：
Hicks D
中科院分区：
文献类型：
--
作者：
Hicks D
花卉资源是传粉昆虫丰富度和多样性的关键驱动力，但在野外和实验室中对其进行量化是费力的，需要专业技能。使用25，000个具有野外工作真实质量的标记标签的数据集，卷积神经网络（Faster R-CNN）被训练来检测25个分类群的花蜜产生花单位，在50幅模型不可见的类似植被图像的测试集上进行花卉单元检测，准确率为90%，召回率为86%，F1得分（精确度和召回率的调和平均值）为88%。在这个栖息地的植物丰富度范围内，模型的性能是一致的。CNN和三位人类测量员对花蜜糖质量的估计进行了比较，得出了相似的平均值和标准差。超过一半的花蜜糖质量的估计模型属于人类测量员的绝对范围内。样方图像样本的最佳数量被确定为与人类测量员的平均数量相同。对于10-15个重复的标准样方采样协议，这种深度学习的应用可以将每一个植被的传粉植物调查时间从几小时缩短到几分钟。CNN仅限于样方的单个视图，没有手动检查或标本收集的范围，虽然与人类测量员相比，其目标检测是确定性的，其花卉单位定义是标准化的。从规定性到基于结果，这种方法提供了一个独立的草地管理晴雨表，土地所有者和计划管理者都可以使用。该模型可以适应其他生态资源，如冬季鸟类食物，花粉量，昆虫侵扰和树木开花/结果的视觉估计，并通过调整分类阈值可能会显示出可接受的分类分化的存在-不存在调查。
Floral resources are a key driver of pollinator abundance and diversity, yet their quantification in the field and laboratory is laborious and requires specialist skills.Using a dataset of 25,000 labelled tags of fieldwork‐realistic quality, a convolutional neural network (Faster R‐CNN) was trained to detect the nectar‐producing floral units of 25 taxa in surveyors’ quadrat images of native, weed‐rich grassland in the United Kingdom.Floral unit detection on a test set of 50 model‐unseen images of comparable vegetation returned a precision of 90%, recall of 86% and F1 score (the harmonic mean of precision and recall) of 88%. Model performance was consistent across the range of floral abundance in this habitat.Comparison of the nectar sugar mass estimates made by the CNN and three human surveyors returned similar means and standard deviations. Over half of the nectar sugar mass estimates made by the model fell within the absolute range of those of the human surveyors.The optimal number of quadrat image samples was determined to be the same for the CNN as for the average human surveyor. For a standard quadrat sampling protocol of 10–15 replicates, this application of deep learning could cut pollinator‐plant survey time per stand of vegetation from hours to minutes.The CNN is restricted to a single view of a quadrat, with no scope for manual examination or specimen collection, though in contrast to human surveyors its object detection is deterministic and its floral unit definition is standardized.As agri‐environment schemes move from prescriptive to results‐based, this approach provides an independent barometer of grassland management which is usable by both landowner and scheme administrator. The model can be adapted to visual estimations of other ecological resources such as winter bird food, floral pollen volume, insect infestation and tree flowering/fruiting, and by adjustment of classification threshold may show acceptable taxonomic differentiation for presence–absence surveys.
登录
查看更多内容
作者对“深度学习对象检测来估计开花植物的花蜜糖质量”的回复
DOI：
--
发表时间：
2021
期刊：
影响因子：
--
作者：
Damien Hicks;Mathilde Baude;Christoph Kratz;Pierre Ouvrard;Graham Stone
通讯作者：
Graham Stone
基于目标检测和CNN的昆虫交互分析
DOI：
--
发表时间：
2019
期刊：
IEEE International Workshop on Multimedia Signal Processing
影响因子：
--
作者：
Paul Tresson;P. Tixier;W. Puech;D. Carval
通讯作者：
D. Carval
使用深度学习进行水下鱼类检测用于水力发电应用
DOI：
--
发表时间：
2018
期刊：
2018 International Conference on Computational Science and Computational Intelligence (CSCI)
影响因子：
--
作者：
Wenwei Xu;S. Matzner
通讯作者：
S. Matzner
加强道路边缘以帮助传粉媒介保护：回顾
影响因子：
5.9
作者：
Benjamin B. Phillips;C. Wallace;Bethany R. Roberts;A. T. Whitehouse;K. Gaston;J. Bullock;L. Dicks;J. Osborne
通讯作者：
J. Osborne
影响因子：
3.7
作者：
Ditria, Ellen M.;Lopez-Marcano, Sebastian;Connolly, Rod M.
通讯作者：
Connolly, Rod M.