NeSTCount: Neighborhood structure-based tracking for robust sequential fruit counting under camera motion and occlusion

Computers and Electronics in Agriculture一手来源 · 原始研究2月1日 · 周一阅读 0

核心看点

提出基于邻域结构的果实跟踪计数方法，可提升相机运动与遮挡下的果园产量估算稳健性，但属细分方法论文且距发布尚早。

关注点

该方法针对相机运动和果实遮挡场景设计邻域结构跟踪，适用于果园视频序列自动计数，实际精度与部署成本需以田间数据验证。

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

Hengyue Guan / Yiannis Ampatzidis / Antonio de Oliveira Costa Neto

Computers and Electronics in Agriculture

DOI: 10.1016/j.compag.2026.112686

论文摘要

NeSTCount: Neighborhood structure-based tracking for robust sequential fruit counting under camera motion and occlusion。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

智慧农业果园管理果实计数目标跟踪

论文信息

论文摘要

继续探索

技术

其他

相关检索

相关阅读

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

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）

Fruit-OIC: An anti-occlusion flower and fruit detection algorithm for dragon fruit using dynamic case mining and global feature enhancement

Visual measurement for forage maize stubble height fusing cascaded neural networks and robust tracking

Adapting SAM3 for 3D fruit counting with cross-view contrastive learning and Hough voting

Video-based fruit detection and tracking: effects of scanning conditions on fruit load estimation

Monitorización continua y autónoma de árboles frutales mediante imagen

Autonomous apple fruitlet sizing and growth rate tracking using computer vision

Advances in Recognition Methods for Fruit and Vegetable Harvesting（MDPI Agriculture 2026, 16(17), 1924）

DeepPhenoTree-Apple Edition: a multi-site apple phenology RGB annotated dataset with deep learning baseline models

LeafTrackNet: A deep learning framework for robust leaf tracking in top-down plant phenotyping

DAC-Grad-CAM: Defect-aware explainable AI for automated mango quality classification

A lightweight domain-specific appearance embedding for Turkey re-identification in dense barn environments