Real-time semantic segmentation of orchard LiDAR point clouds with a spherical-image convolutional neural network

Computers and Electronics in Agriculture一手来源 · 原始研究11月1日 · 周日阅读 0

核心看点

核心期刊论文，提出基于球面图像CNN的果园LiDAR点云实时语义分割方法，方法有新颖性但属细分技术进展，公共影响有限。

关注点

该研究将果园LiDAR点云投影为球面图像并用CNN实现实时语义分割，为果园三维感知提供轻量化技术路径，但摘要未给出精度与实时性数据，适用性需看原文实验。

发布主体的原始资料；自述数据与结论仍以原文限定为准。

论文信息

Qiujie Li / Simiao Jing

Computers and Electronics in Agriculture

DOI: 10.1016/j.compag.2026.112634

论文摘要

Real-time semantic segmentation of orchard LiDAR point clouds with a spherical-image convolutional neural network。Computers and Electronics in Agriculture

论文原文与出版信息

Computers and Electronics in Agriculture

查看论文原文

继续探索

技术

农业人工智能

其他

智慧农业语义分割果园管理激光雷达

论文信息

论文摘要

继续探索

技术

其他

相关检索

相关阅读

Orchard worker detection using spatial-context attention on 2D LiDAR data

Visuomotor Robotic Pruning in Planar Orchills Using Hybrid Reinforcement Learning（基于混合强化学习的平面果园视觉运动机器人修剪）

Early diagnosis of ring rot and prediction of SPAD values in apple leaves using hyperspectral imaging and a CNN-LSTM hybrid model

Boundary-Aware and Structure-Guided semantic segmentation of green orchard fruits with hierarchical Coarse-to-Fine refinement

广东省农科院'粤强智农'亮相杨凌农高会 荔枝AI生产管理智能体受关注

An Explainable Software-Based Framework for Pre-Symptomatic Grape Disease Risk Assessment Using MobileNetV2, Grad-CAM, and Weather Data

Balancing accuracy, completeness, and efficiency for rice 3D reconstruction through CBAM-UNet-based multi-view segmentation and camera configuration optimization

AgriPoinTr: Point cloud completion with geometry-aware transformers for crops with complex structures

A multispectral reflectance field framework for radiometrically accurate three-dimensional point cloud generation of plants at close range

Latent-space feature reconstruction-enhanced semantic segmentation for agricultural field roads under visual degradation

Radial Loss for Few-Shot Instance Segmentation of Densely Cultivated Crops

UGV based multi-RGBD SLAM framework for high-throughput in-situ 3D phenotyping of field maize

A deep learning perception framework for farm digital twins: weed species classification, semantic segmentation, and gradient-based visual interpretability

FusFormer: An efficient transformer-based semantic segmentation method for grafting excision point localization

广东省农科院'粤强智农'亮相杨凌农高会荔枝AI生产管理智能体受关注