Efficient Semantic Segmentation for Large-Scale Agricultural Nursery Managements via Point Cloud-Based Neural Network

被引:0
|
作者
Liu, Hui [1 ]
Xu, Jie [1 ]
Chen, Wen-Hua [2 ]
Shen, Yue [1 ]
Kai, Jinru [1 ]
机构
[1] Jiangsu Univ, Sch Elect & Informat Engn, Zhenjiang 212000, Peoples R China
[2] Loughborough Univ, Dept Aeronaut & Automot Engn, Loughborough LE11 3TU, Leics, England
基金
中国国家自然科学基金;
关键词
remote sensing technology; semantic segmentation task; nursery managements; large-scale point clouds; neural network models; SLAM; CONSTRUCTION;
D O I
10.3390/rs16214011
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Remote sensing technology has found extensive application in agriculture, providing critical data for analysis. The advancement of semantic segmentation models significantly enhances the utilization of point cloud data, offering innovative technical support for modern horticulture in nursery environments, particularly in the area of plant cultivation. Semantic segmentation results aid in obtaining tree components, like canopies and trunks, and detailed data on tree growth environments. However, obtaining precise semantic segmentation results from large-scale areas can be challenging due to the vast number of points involved. Therefore, this paper introduces an improved model aimed at achieving superior performance for large-scale points. The model incorporates direction angles between points to improve local feature extraction and ensure rotational invariance. It also uses geometric and relative distance information for better adjustment of different neighboring point features. An external attention module extracts global spatial features, and an upsampling feature adjustment strategy integrates features from the encoder and decoder. A specialized dataset was created from real nursery environments for experiments. Results show that the improved model surpasses several point-based models, achieving a Mean Intersection over Union (mIoU) of 87.18%. This enhances the precision of nursery environment analysis and supports the advancement of autonomous nursery managements.
引用
收藏
页数:20
相关论文
共 50 条
  • [21] A lightweight Transformer-based neural network for large-scale masonry arch bridge point cloud segmentation
    Jing, Yixiong
    Sheil, Brian
    Acikgoz, Sinan
    COMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING, 2024, 39 (16) : 2427 - 2438
  • [22] Semantic Segmentation of Large-Scale Laser Point Cloud in Mines Based on Local Feature Enhancement
    Dong, Hongxiang
    Yi, An
    Xie, Lirong
    Yang, Zhiyong
    Kai, Zhang
    CHINESE JOURNAL OF LASERS-ZHONGGUO JIGUANG, 2024, 51 (17):
  • [23] 3D point cloud semantic segmentation toward large-scale unstructured agricultural scene classification
    Chen, Yi
    Xiong, Yingjun
    Zhang, Baohua
    Zhou, Jun
    Zhang, Qian
    COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2021, 190
  • [24] LEARD-Net: Semantic segmentation for large-scale point cloud scene
    Zeng, Ziyin
    Xu, Yongyang
    Xie, Zhong
    Tang, Wei
    Wan, Jie
    Wu, Weichao
    INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION, 2022, 112
  • [25] Hybrid Offset Position Encoding for Large-Scale Point Cloud Semantic Segmentation
    Xiao, Yu
    Wu, Hui
    Chen, Yisheng
    Chen, Chongcheng
    Dong, Ruihai
    Lin, Ding
    REMOTE SENSING, 2025, 17 (02)
  • [26] STSD:A large-scale benchmark for semantic segmentation of subway tunnel point cloud
    Cui, Hao
    Li, Jian
    Mao, Qingzhou
    Hu, Qingwu
    Dong, Cuijun
    Tao, Yiwen
    TUNNELLING AND UNDERGROUND SPACE TECHNOLOGY, 2024, 150
  • [27] Radial Transformer for Large-Scale Outdoor LiDAR Point Cloud Semantic Segmentation
    He, Xiang
    Li, Xu
    Ni, Peizhou
    Xu, Wang
    Xu, Qimin
    Liu, Xixiang
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2024, 62
  • [28] Point and voxel cross perception with lightweight cosformer for large-scale point cloud semantic segmentation
    Zhang, Shuai
    Wang, Biao
    Chen, Yiping
    Zhang, Shuhang
    Zhang, Wuming
    INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION, 2024, 131
  • [29] LPFE-Net: a local parallel feature extraction network for large-scale point cloud semantic segmentation
    Ai, Da
    Zhang, Xiaoyang
    Xu, Ce
    Liu, Xinlong
    Yuan, Hui
    Liu, Ying
    JOURNAL OF ELECTRONIC IMAGING, 2023, 32 (05)
  • [30] HFA-Net: hybrid feature-aware network for large-scale point cloud semantic segmentation
    Wen, Changji
    Zhang, Long
    Ren, Junfeng
    Hong, Rundong
    Li, Chenshuang
    Yang, Ce
    Lv, Yanfeng
    Chen, Hongbing
    Yang, Ning
    ARTIFICIAL INTELLIGENCE REVIEW, 2025, 58 (04)