The improved stratified transformer for organ segmentation of Arabidopsis
-
Published:2024
Issue:3
Volume:21
Page:4669-4697
-
ISSN:1551-0018
-
Container-title:Mathematical Biosciences and Engineering
-
language:
-
Short-container-title:MBE
Author:
Zheng Yuhui1, Wang Dongwei1, Jin Ning2, Zhao Xueguan3, Li Fengmei4, Sun Fengbo5, Dou Gang6, Bai Haoran1
Affiliation:
1. College of Mechanical and Electrical Engineering, Qingdao Agricultural University, Qingdao 266109, China 2. Graduate School, Shenyang Jianzhu University, Shenyang 110168, China 3. Beijing PAIDE Science and Technology Development Co., Ltd., Beijing 100097, China 4. College of Food Science and Engineering, Qingdao Agricultural University, Qingdao 266109, China 5. China Zhongxin Construction Engineering Co., Ltd., Qingdao 266205, China 6. Weichai Lovol Intelligent Agricultural Technology Co., Ltd., Weifang 261000, China
Abstract
<abstract>
<p>Segmenting plant organs is a crucial step in extracting plant phenotypes. Despite the advancements in point-based neural networks, the field of plant point cloud segmentation suffers from a lack of adequate datasets. In this study, we addressed this issue by generating Arabidopsis models using L-system and proposing the surface-weighted sampling method. This approach enables automated point sampling and annotation, resulting in fully annotated point clouds. To create the Arabidopsis dataset, we employed Voxel Centroid Sampling and Random Sampling as point cloud downsampling methods, effectively reducing the number of points. To enhance the efficiency of semantic segmentation in plant point clouds, we introduced the Plant Stratified Transformer. This network is an improved version of the Stratified Transformer, incorporating the Fast Downsample Layer. Our improved network underwent training and testing on our dataset, and we compared its performance with PointNet++, PAConv, and the original Stratified Transformer network. For semantic segmentation, our improved network achieved mean Precision, Recall, F1-score and IoU of 84.20, 83.03, 83.61 and 73.11%, respectively. It outperformed PointNet++ and PAConv and performed similarly to the original network. Regarding efficiency, the training time and inference time were 714.3 and 597.9 ms, respectively, which were reduced by 320.9 and 271.8 ms, respectively, compared to the original network. The improved network significantly accelerated the speed of feeding point clouds into the network while maintaining segmentation performance. We demonstrated the potential of virtual plants and deep learning methods in rapidly extracting plant phenotypes, contributing to the advancement of plant phenotype research.</p>
</abstract>
Publisher
American Institute of Mathematical Sciences (AIMS)
Reference69 articles.
1. R. Pieruschka, U. Schurr, Plant phenotyping: past, present, and future, Plant Phenomics, 2019 (2019). https://doi.org/10.34133/2019/7507131 2. C. Costa, U. Schurr, F. Loreto, P. Menesatti, S. Carpentier, Plant phenotyping research trends, a science mapping approach, Front. Plant Sci., 9 (2019), 1933. https://doi.org/10.3389/fpls.2018.01933 3. A. K. Singh, B. Ganapathysubramanian, S. Sarkar, A. Singh, Deep learning for plant stress phenotyping: trends and future perspectives, Trends Plant Sci., 23 (2018), 883–898. https://doi.org/10.1016/j.tplants.2018.07.004 4. S. Arya, K. S. Sandhu, J. Singh, S. Kumar, Deep learning: as the new frontier in high-throughput plant phenotyping, Euphytica, 218 (2022), 47. https://doi.org/10.1007/s10681-022-02992-3 5. S. Bhagat, M. Kokare, V. Haswani, P. Hambarde, R. Kamble, Eff-UNet++: A novel architecture for plant leaf segmentation and counting, Ecol. Inf., 68 (2022), 101583. https://doi.org/10.1016/j.ecoinf.2022.101583
|
|