智慧农业（中英文）2024，Vol.6Issue(2)：128-139,12.DOI:10.12133/j.smartag.SA202310002
用于小麦多生长阶段倒伏边界精准检测的分层交互特征金字塔网络
HI-FPN:A Hierarchical Interactive Feature Pyramid Network for Accurate Wheat Lodging Localization Across Multiple Growth Periods
摘要
Abstract
[Objective]Wheat lodging is one of the key isuess threatening stable and high yields.Lodging detection technology based on deep learning generally limited to identifying lodging at a single growth stage of wheat,while lodging may occur at var-ious stages of the growth cycle.Moreover,the morphological characteristics of lodging vary significantly as the growth pe-riod progresses,posing a challenge to the feature capturing ability of deep learning models.The aim is exploring a deep learning-based method for detecting wheat lodging boundaries across multiple growth stages to achieve automatic and ac-curate monitoring of wheat lodging.[Methods]A model called Lodging2Former was proposed,which integrates the inno-vative hierarchical interactive feature pyramid network(HI-FPN)on top of the advanced segmentation model Mask2For-mer.The key focus of this network design lies in enhancing the fusion and interaction between feature maps at adjacent hi-erarchical levels,enabling the model to effectively integrate feature information at different scales.Building upon this,even in complex field backgrounds,the Lodging2Former model significantly enhances the recognition and capturing capa-bilities of wheat lodging features at multiple growth stages.[Results and Discussions]The Lodging2Former model dem-onstrated superiority in mean average precision(mAP)compared to several mainstream algorithms such as mask region-based convolutional neural network(Mask R-CNN),segmenting objects by locations(SOLOv2),and Mask2Former.When applied to the scenario of detecting lodging in mixed growth stage wheat,the model achieved mAP values of 79.5%,40.2%,and 43.4%at thresholds of 0.5,0.75,and 0.5 to 0.95,respectively.Compared to Mask2Former,the performance of the improved model was enhanced by 1.3%to 4.3%.Compared to SOLOv2,a growth of 9.9%to 30.7%in mAP was achieved;and compared to the classic Mask R-CNN,a significant improvement of 24.2%to 26.4%was obtained.Further-more,regardless of the IoU threshold standard,the Lodging2Former exhibited the best detection performance,demonstrat-ing good robustness and adaptability in the face of potential influencing factors such as field environment changes.[Con-clusions]The experimental results indicated that the proposed HI-FPN network could effectively utilize contextual seman-tics and detailed information in images.By extracting rich multi-scale features,it enabled the Lodging2Former model to more accurately detect lodging areas of wheat across different growth stages,confirming the potential and value of HI-FPN in detecting lodging in multi-growth-stage wheat.关键词
无人机/深度学习/小麦倒伏检测/特征金字塔网络/Mask2FormerKey words
drone/deep learning/wheat lodging detection/feature pyramid network/Mask2Former分类
信息技术与安全科学引用本文复制引用
庞春晖,陈鹏,夏懿,章军,王兵,邹岩,陈天娇,康辰瑞,梁栋..用于小麦多生长阶段倒伏边界精准检测的分层交互特征金字塔网络[J].智慧农业（中英文）,2024,6(2):128-139,12.基金项目
National Natural Science Foundation of China Projects(62072002,62273001) （62072002,62273001）
Anhui Provincial Major Science and Technology Special Project(202003a06020016) （202003a06020016）
Supported by the Special Fund for Anhui Agriculture Research System(2021-2025) （2021-2025）
Excellent Scientific Re-search Innovation Team of Anhui Province Universities(2022AH010005) 国家自然科学基金项目(62072002 （2022AH010005）
62273001) （）
安徽省科技重大专项(202003a06020016) （202003a06020016）
安徽省现代农业产业技术体系建设专项资金(2021-2025) （2021-2025）
安徽省高校优秀科研创新团队(2022AH010005) （2022AH010005）
