Reconstructed canola point cloud samples.

<div><p>Accurate analysis of plant phenotypic traits is crucial for crop breeding and precision agriculture. This study proposes a lightweight semantic segmentation model named KAN-GLNet (Kolmogorov–Arnold Network with Global–Local Feature Modulation), based on an enhanced PointNet++ arc...

Full description

Saved in:

Bibliographic Details
Main Author:	Jiajun Liu (692586) (author)
Other Authors:	Bei Zhou (5219792) (author), Jie Liu (15128) (author), Xike Zhang (2848757) (author), Jiangshu Wei (22634246) (author), Yao Zhang (134381) (author), Junjie Wu (393541) (author), Changping Wu (52884) (author), Di Hu (12438) (author)
Published:	2025
Subjects:	Space Science Biological Sciences not elsewhere classified Information Systems not elsewhere classified throughput plant phenotyping plant phenotypic traits made publicly available based spatial clustering semantic segmentation tasks instance segmentation task div >< p canola silique segmentation counting </ p segmentation accuracy precision segmentation canola siliques counting accuracy automatic counting study proposes precision agriculture model complexity method achieves excellent balance efficient solution crop breeding contrastive learning baseline models achieves 94 accurate analysis 72m parameters 6432 /</
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	<div><p>Accurate analysis of plant phenotypic traits is crucial for crop breeding and precision agriculture. This study proposes a lightweight semantic segmentation model named KAN-GLNet (Kolmogorov–Arnold Network with Global–Local Feature Modulation), based on an enhanced PointNet++ architecture and integrated with an optimized Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm, to achieve high-precision segmentation and automatic counting of canola siliques. A multi-view point cloud acquisition platform was built, and high-fidelity canola point clouds were reconstructed using Neural Radiance Fields (NeRF) technology. The proposed model includes three key modules: Reverse Bottleneck Kolmogorov–Arnold Network Convolution, a Global–Local Feature Modulation (GLFN) block, and a contrastive learning-based normalization module called ContraNorm. KAN-GLNet contains only 5.72M parameters and achieves 94.50% mIoU, 96.72% mAcc, and 97.77% OAcc in semantic segmentation tasks, outperforming all baseline models. In addition, the DBSCAN workflow was optimized, achieving a counting accuracy of 97.45% in the instance segmentation task. This method achieves an excellent balance between segmentation accuracy and model complexity, providing an efficient solution for high-throughput plant phenotyping. The code and dataset have been made publicly available at: <a href="https://anonymous.4open.science/r/KAN-GLNet-6432/" target="_blank">https://anonymous.4open.science/r/KAN-GLNet-6432/</a>.</p></div>

Reconstructed canola point cloud samples.

Similar Items