A Precise Segmentation Algorithm of Pumpkin Seedling Point Cloud Stem Based on CPHNet
Author:
Deng Qiaomei1, Zhao Junhong2, Li Rui1ORCID, Liu Genhua3, Hu Yaowen4, Ye Ziqing3, Zhou Guoxiong3ORCID
Affiliation:
1. College of Computer & Mathematics, Central South University of Forestry and Technology, Changsha 410004, China 2. Institute of Facility Agriculture, Guangdong Academy of Agricultural Sciences, Guangzhou 510640, China 3. College of Electronic Information & Physics, Central South University of Forestry and Technology, Changsha 410073, China 4. College of Computer, National University of Defense Technology, Changsha 410073, China
Abstract
Accurate segmentation of the stem of pumpkin seedlings has a great influence on the modernization of pumpkin cultivation, and can provide detailed data support for the growth of pumpkin plants. We collected and constructed a pumpkin seedling point cloud dataset for the first time. Potting soil and wall background in point cloud data often interfere with the accuracy of partial cutting of pumpkin seedling stems. The stem shape of pumpkin seedlings varies due to other environmental factors during the growing stage. The stem of the pumpkin seedling is closely connected with the potting soil and leaves, and the boundary of the stem is easily blurred. These problems bring challenges to the accurate segmentation of pumpkin seedling point cloud stems. In this paper, an accurate segmentation algorithm for pumpkin seedling point cloud stems based on CPHNet is proposed. First, a channel residual attention multilayer perceptron (CRA-MLP) module is proposed, which suppresses background interference such as soil. Second, a position-enhanced self-attention (PESA) mechanism is proposed, enabling the model to adapt to diverse morphologies of pumpkin seedling point cloud data stems. Finally, a hybrid loss function of cross entropy loss and dice loss (HCE-Dice Loss) is proposed to address the issue of fuzzy stem boundaries. The experimental results show that CPHNet achieves a 90.4% average cross-to-merge ratio (mIoU), 93.1% average accuracy (mP), 95.6% average recall rate (mR), 94.4% F1 score (mF1) and 0.03 plants/second (speed) on the self-built dataset. Compared with other popular segmentation models, this model is more accurate and stable for cutting the stem part of the pumpkin seedling point cloud.
Funder
Key-Area Research and Development Program of Guangdong Province Scientific and Technological Innovation Strategic Program of Guangdong Academy of Agricultural Sciences Guangzhou Science and Technology Plan Project Transfer Fund for Introduction of Scientific and Technological Talents of Guangdong Academy of Agricultural Sciences Research and development of key technologies and equipment for smart factory-scale fish and vegetable symbiosis Academic Team Construction Project of Guangdong Academy of Agricultural Sciences
Reference60 articles.
1. Analysis of concepts and categories of plant phenome and phenomics;Pan;Acta Agron. Sin.,2015 2. Zhan, J., Xie, Y., Guo, J., Hu, Y., Zhou, G., Cai, W., Wang, Y., Chen, A., Liu, X., and Li, M. (2023). DGPF-RENet: A Low Data Dependence Network with Low Training Iterations for Hyperspectral Image Classification. IEEE Trans. Geosci. Remote Sens. 3. UAV-based road crack object-detection algorithm;He;Autom. Constr.,2023 4. Plant phenomics and high-throughput phenotyping: Accelerating rice functional genomics using multidisciplinary technologies;Yang;Curr. Opin. Plant Biol.,2013 5. Deng, J., Huang, W., Zhou, G., Hu, Y., Li, L., and Wang, Y. (2023). Identification of Banana Leaf Disease Based on KVA and GR-ARNet. J. Integr. Agric.
|
|