当前位置: X-MOL 学术Comput. Electron. Agric. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
A high-precision detection method of hydroponic lettuce seedlings status based on improved Faster RCNN
Computers and Electronics in Agriculture ( IF 7.7 ) Pub Date : 2021-02-23 , DOI: 10.1016/j.compag.2021.106054
Zhenbo Li , Ye Li , Yongbo Yang , Ruohao Guo , Jinqi Yang , Jun Yue , Yizhe Wang

In order to improve the efficiency and reduce high cost for seedlings sorting in the raising process of hydroponic lettuce seedlings, we propose an automatic detection method for hydroponic lettuce seedlings based on improved Faster RCNN framework, taking the dead and double-planting status of seedlings growing in a single hole as our research objects. Since the characteristics of hydroponic lettuce seedlings are dense and small in the images, our model uses High Resolution Network (HRNet) as the backbone network for image feature extraction so as to obtain reliable and high- resolution feature expressions. Besides, we adopt focal loss as the classification loss in the Region Proposal Network (RPN) stage to address the imbalance between difficult and easy samples in seedlings classification. We also employ the Region of Interest (RoI) Align instead of the RoI Pooling layer to improve the detection accuracy of seedlings in the different status. The results show that the mean average precision of our method for the hydroponic lettuce seedlings is 86.2%, which is higher than RetinaNet, SSD, Cascade RCNN, FCOS and other detectors. Compared with different feature extraction networks, the detection accuracy of adopting HRNet performs nicely. Therefore, our method presented for the detection of hydroponic lettuce seedlings status can achieve high accuracy and identify seedlings in a problematic status well, which will provide technical support for automatic seedlings detection of hydroponic lettuce.



中文翻译:

基于改进的Faster RCNN的水培生菜幼苗状态的高精度检测方法

为了提高水培生菜育苗过程中分选的效率并降低高成本,我们提出了一种基于改进的Faster RCNN框架的水培生菜幼苗自动检测方法,该方法考虑了幼苗生长的死苗和复种状况成为我们研究的对象。由于水培莴苣幼苗的特征在图像中密集且较小,因此我们的模型使用高分辨率网络(HRNet)作为骨干网络进行图像特征提取,从而获得可靠且高分辨率的特征表达。此外,在区域建议网(RPN)阶段,我们将焦点损失作为分类损失,以解决幼苗分类中难点和易点样本之间的不平衡问题。我们还采用了感兴趣区域(RoI)对齐而不是RoI合并层,以提高不同状态下的幼苗检测精度。结果表明,该方法对水培生菜幼苗的平均平均精度为86.2%,高于RetinaNet,SSD,Cascade RCNN,FCOS等检测器。与不同的特征提取网络相比,采用HRNet的检测精度较好。因此,我们提出的水培生菜幼苗状态检测方法可以达到较高的准确度,并能很好地识别出有问题的幼苗,为水培生菜幼苗的自动检测提供技术支持。结果表明,该方法对水培生菜幼苗的平均平均精度为86.2%,高于RetinaNet,SSD,Cascade RCNN,FCOS等检测器。与不同的特征提取网络相比,采用HRNet的检测精度较好。因此,我们提出的水培生菜幼苗状态检测方法可以达到较高的准确度,并能很好地识别出有问题的幼苗,为水培生菜幼苗的自动检测提供技术支持。结果表明,该方法对水培生菜幼苗的平均平均精度为86.2%,高于RetinaNet,SSD,Cascade RCNN,FCOS等检测器。与不同的特征提取网络相比,采用HRNet的检测精度较好。因此,我们提出的水培生菜幼苗状态检测方法可以达到较高的准确度,并能很好地识别出有问题的幼苗,为水培生菜幼苗的自动检测提供技术支持。

更新日期:2021-02-23
down
wechat
bug