文献类型：期刊文献

英文题名：MTSC-Net: A Semi-Supervised Counting Network for Estimating the Number of Slash pine New Shoots

作者：Zhang, Zhaoxu[1] Li, Yanjie[2] Cao, Yue[3] Wang, Yu[1] Guo, Xuchao[1] Hao, Xia[1]

第一作者：Zhang, Zhaoxu

通信作者：Guo, XC[1];Hao, X[1]

机构：[1]Shandong Agr Univ, Coll Informat Sci & Engn, Tai An 271018, Shandong, Peoples R China;[2]Chinese Acad Forestry, Res Inst Subtrop Forestry, Hangzhou 311400, Zhejiang, Peoples R China;[3]Taishan Coll Sci & Technol, Sch Big Data, Tai An 271034, Shandong, Peoples R China

年份：2024

卷号：6

外文期刊名：PLANT PHENOMICS

收录：;EI(收录号：20243817042709);Scopus(收录号：2-s2.0-85203622756);WOS:【SCI-EXPANDED(收录号:WOS:001310493700001)】；

基金：This research was supported by the Shandong Province Natural Science Foundation Youth Branch under grant ZR20-23QF016, the Biological Breeding-Major projects (Grant no. 2023ZD040580105) and the Fundamental Research Funds of CAF (CAFYBB2022QA001).

语种：英文

外文关键词：Mean square error

摘要：The new shoot density of slash pine serves as a vital indicator for assessing its growth and photosynthetic capacity, while the number of new shoots offers an intuitive reflection of this density. With deep learning methods becoming increasingly popular, automated counting of new shoots has greatly improved in recent years but is still limited by tedious and expensive data collection and labeling. To resolve these issues, this paper proposes a semi-supervised counting network (MTSC-Net) for estimating the number of slash pine new shoots. First, based on the mean-teacher framework, we introduce the improved VGG19 to extract multiscale new shoot features. Second, to connect local new shoot feature information with global channel features, attention feature fusion module is introduced to achieve effective feature fusion. Finally, the new shoot density map and density probability distribution are processed in a fine-grained manner through multiscale dilated convolution of the regression head and classification head. In addition, a masked image modeling strategy is introduced to encourage the contextual understanding of global new shoot features and improve the counting performance. The experimental results show that MTSC-Net outperforms other semi-supervised counting models with labeled percentages ranging from 5% to 50%. When the labeled percentage is 5%, the mean absolute error and root mean square error are 17.71 and 25.49, respectively. These findings demonstrate that our work can be used as an efficient semi-supervised counting method to provide automated support for tree breeding and genetic utilization.