Plants

Research

Jump to: Review

20 pages, 3443 KiB

Open AccessArticle

A Bottom-Up Multi-Feature Fusion Algorithm for Individual Tree Segmentation in Dense Rubber Tree Plantations Using Unmanned Aerial Vehicle–Light Detecting and Ranging

by Zhipeng Zeng, Junpeng Miao, Xiao Huang, Peng Chen, Ping Zhou, Junxiang Tan and Xiangjun Wang

Plants 2025, 14(11), 1640; https://doi.org/10.3390/plants14111640 - 27 May 2025

Abstract

Accurate individual tree segmentation (ITS) in dense rubber plantations is a challenging task due to overlapping canopies, indistinct tree apexes, and intricate branch structures. To address these challenges, we propose a bottom-up, multi-feature fusion method for segmenting rubber trees using UAV-LiDAR point clouds. [...] Read more.

Accurate individual tree segmentation (ITS) in dense rubber plantations is a challenging task due to overlapping canopies, indistinct tree apexes, and intricate branch structures. To address these challenges, we propose a bottom-up, multi-feature fusion method for segmenting rubber trees using UAV-LiDAR point clouds. Our approach first involves performing a trunk extraction based on branch-point density variations and neighborhood directional features, which allows for the precise separation of trunks from overlapping canopies. Next, we introduce a multi-feature fusion strategy that replaces single-threshold constraints, integrating geometric, directional, and density attributes to classify core canopy points, boundary points, and overlapping regions. Disputed points are then iteratively assigned to adjacent trees based on neighborhood growth angle consistency, enhancing the robustness of the segmentation. Experiments conducted in rubber plantations with varying canopy closure (low, medium, and high) show accuracies of 0.97, 0.98, and 0.95. Additionally, the crown width and canopy projection area derived from the segmented individual tree point clouds are highly consistent with ground truth data, with R² values exceeding 0.98 and 0.97, respectively. The proposed method provides a reliable foundation for 3D tree modeling and biomass estimation in structurally complex plantations, advancing precision forestry and ecosystem assessment by overcoming the critical limitations of existing ITS approaches in high-closure tropical agroforests. Full article

(This article belongs to the Special Issue Advances in Artificial Intelligence for Plant Research)

30 pages, 10238 KiB

Open AccessArticle

OE-YOLO: An EfficientNet-Based YOLO Network for Rice Panicle Detection

by Hongqing Wu, Maoxue Guan, Jiannan Chen, Yue Pan, Jiayu Zheng, Zichen Jin, Hai Li and Suiyan Tan

Plants 2025, 14(9), 1370; https://doi.org/10.3390/plants14091370 - 30 Apr 2025

Viewed by 340

Abstract

Accurately detecting rice panicles in complex field environments remains challenging due to their small size, dense distribution, diverse growth directions, and easy confusion with the background. To accurately detect rice panicles, this study proposes OE-YOLO, an enhanced framework derived from YOLOv11, incorporating three [...] Read more.

Accurately detecting rice panicles in complex field environments remains challenging due to their small size, dense distribution, diverse growth directions, and easy confusion with the background. To accurately detect rice panicles, this study proposes OE-YOLO, an enhanced framework derived from YOLOv11, incorporating three synergistic innovations. First, oriented bounding boxes (OBB) replace horizontal bounding boxes (HBB) to precisely capture features of rice panicles across different heights and growth stages. Second, the backbone network is redesigned with EfficientNetV2, leveraging its compound scaling strategy to balance multi-scale feature extraction and computational efficiency. Third, a C3k2_DConv module improved by dynamic convolution is introduced, enabling input-adaptive kernel fusion to amplify discriminative features while suppressing background interference. Extensive experiments on rice Unmanned Aerial Vehicle (UAV) imagery demonstrate OE-YOLO’s superiority, achieving 86.9% mAP50 and surpassing YOLOv8-obb and YOLOv11 by 2.8% and 8.3%, respectively, with only 2.45 M parameters and 4.8 GFLOPs. The model has also been validated at flight heights of 3 m and 10 m and during the heading and filling stages, achieving mAP50 improvements of 8.3%, 6.9%, 6.7%, and 16.6% compared to YOLOv11, respectively, demonstrating the generalization capability of the model. These advancements demonstrated OE-YOLO as a computationally frugal yet highly accurate solution for real-time crop monitoring, addressing critical needs in precision agriculture for robust, oriented detection under resource constraints. Full article

(This article belongs to the Special Issue Advances in Artificial Intelligence for Plant Research)

► Show Figures

Figure 1

20 pages, 2828 KiB

Open AccessArticle

CBSNet: An Effective Method for Potato Leaf Disease Classification

by Yongdong Chen and Wenfu Liu

Plants 2025, 14(5), 632; https://doi.org/10.3390/plants14050632 - 20 Feb 2025

Cited by 1 | Viewed by 471

Abstract

As potato is an important crop, potato disease detection and classification are of key significance in guaranteeing food security and enhancing agricultural production efficiency. Aiming at the problems of tiny spots, blurred disease edges, and susceptibility to noise interference during image acquisition and [...] Read more.

As potato is an important crop, potato disease detection and classification are of key significance in guaranteeing food security and enhancing agricultural production efficiency. Aiming at the problems of tiny spots, blurred disease edges, and susceptibility to noise interference during image acquisition and transmission in potato leaf diseases, we propose a CBSNet-based potato disease recognition method. Firstly, a convolution module called Channel Reconstruction Multi-Scale Convolution (CRMC) is designed to extract the upper and lower features by separating the channel features and applying a more optimized convolution to the upper and lower features, followed by a multi-scale convolution operation to capture the key changes more effectively. Secondly, a new attention mechanism, Spatial Triple Attention (STA), is developed, which first reconstructs the spatial dimensions of the input feature maps, then inputs the reconstructed three types of features into each of the three branches and carries out targeted processing according to the importance of the features, thereby improving the model performance. In addition, the Bat–Lion Algorithm (BLA) is introduced, which combines the Lion algorithm and the bat optimization algorithm and makes the optimization process more adaptive by using the bat algorithm to adjust the gradient direction during the updating process of the Lion algorithm. The BLA not only boosts the model’s ability to recognize potato disease features but also ensures training stability and enhances the model’s robustness in handling noisy images. Experimental results showed that CBSNet achieved an average Accuracy of 92.04% and a Precision of 91.58% on the self-built dataset. It effectively extracts subtle spots and blurry edges of potato leaf diseases, providing strong technical support for disease prevention and control in large-scale potato farming. Full article

(This article belongs to the Special Issue Advances in Artificial Intelligence for Plant Research)

► Show Figures

Figure 1

20 pages, 5647 KiB

Open AccessArticle

VM-YOLO: YOLO with VMamba for Strawberry Flowers Detection

by Yujin Wang, Xueying Lin, Zhaowei Xiang and Wen-Hao Su

Plants 2025, 14(3), 468; https://doi.org/10.3390/plants14030468 - 5 Feb 2025

Viewed by 1283

Abstract

Computer vision technology is widely used in smart agriculture, primarily because of its non-invasive nature, which avoids causing damage to delicate crops. Nevertheless, the deployment of computer vision algorithms on agricultural machinery with limited computing resources represents a significant challenge. Algorithm optimization with [...] Read more.

Computer vision technology is widely used in smart agriculture, primarily because of its non-invasive nature, which avoids causing damage to delicate crops. Nevertheless, the deployment of computer vision algorithms on agricultural machinery with limited computing resources represents a significant challenge. Algorithm optimization with the aim of achieving an equilibrium between accuracy and computational power represents a pivotal research topic and is the core focus of our work. In this paper, we put forward a lightweight hybrid network, named VM-YOLO, for the purpose of detecting strawberry flowers. Firstly, a multi-branch architecture-based fast convolutional sampling module, designated as Light C2f, is proposed to replace the C2f module in the backbone of YOLOv8, in order to enhance the network’s capacity to perceive multi-scale features. Secondly, a state space model-based lightweight neck with a global sensitivity field, designated as VMambaNeck, is proposed to replace the original neck of YOLOv8. After the training and testing of the improved algorithm on a self-constructed strawberry flower dataset, a series of experiments is conducted to evaluate the performance of the model, including ablation experiments, multi-dataset comparative experiments, and comparative experiments against state-of-the-art algorithms. The results show that the VM-YOLO network exhibits superior performance in object detection tasks across diverse datasets compared to the baseline. Furthermore, the results also demonstrate that VM-YOLO has better performances in the mAP, inference speed, and the number of parameters compared to the YOLOv6, Faster R-CNN, FCOS, and RetinaNet. Full article

(This article belongs to the Special Issue Advances in Artificial Intelligence for Plant Research)

► Show Figures

Figure 1

19 pages, 8945 KiB

Open AccessArticle

Multimodal Data Fusion for Precise Lettuce Phenotype Estimation Using Deep Learning Algorithms

by Lixin Hou, Yuxia Zhu, Mengke Wang, Ning Wei, Jiachi Dong, Yaodong Tao, Jing Zhou and Jian Zhang

Plants 2024, 13(22), 3217; https://doi.org/10.3390/plants13223217 - 15 Nov 2024

Cited by 3 | Viewed by 1198

Abstract

Effective lettuce cultivation requires precise monitoring of growth characteristics, quality assessment, and optimal harvest timing. In a recent study, a deep learning model based on multimodal data fusion was developed to estimate lettuce phenotypic traits accurately. A dual-modal network combining RGB and depth [...] Read more.

Effective lettuce cultivation requires precise monitoring of growth characteristics, quality assessment, and optimal harvest timing. In a recent study, a deep learning model based on multimodal data fusion was developed to estimate lettuce phenotypic traits accurately. A dual-modal network combining RGB and depth images was designed using an open lettuce dataset. The network incorporated both a feature correction module and a feature fusion module, significantly enhancing the performance in object detection, segmentation, and trait estimation. The model demonstrated high accuracy in estimating key traits, including fresh weight (fw), dry weight (dw), plant height (h), canopy diameter (d), and leaf area (la), achieving an R² of 0.9732 for fresh weight. Robustness and accuracy were further validated through 5-fold cross-validation, offering a promising approach for future crop phenotyping. Full article

(This article belongs to the Special Issue Advances in Artificial Intelligence for Plant Research)

► Show Figures

Figure 1

16 pages, 15828 KiB

Open AccessArticle

Artificial Intelligence Vision Methods for Robotic Harvesting of Edible Flowers

by Fabio Taddei Dalla Torre, Farid Melgani, Ilaria Pertot and Cesare Furlanello

Plants 2024, 13(22), 3197; https://doi.org/10.3390/plants13223197 - 14 Nov 2024

Viewed by 1219

Abstract

Edible flowers, with their increasing demand in the market, face a challenge in labor-intensive hand-picking practices, hindering their attractiveness for growers. This study explores the application of artificial intelligence vision for robotic harvesting, focusing on the fundamental elements: detection, pose estimation, and plucking [...] Read more.

Edible flowers, with their increasing demand in the market, face a challenge in labor-intensive hand-picking practices, hindering their attractiveness for growers. This study explores the application of artificial intelligence vision for robotic harvesting, focusing on the fundamental elements: detection, pose estimation, and plucking point estimation. The objective was to assess the adaptability of this technology across various species and varieties of edible flowers. The developed computer vision framework utilizes YOLOv5 for 2D flower detection and leverages the zero-shot capabilities of the Segmentation Anything Model for extracting points of interest from a 3D point cloud, facilitating 3D space flower localization. Additionally, we provide a pose estimation method, a key factor in plucking point identification. The plucking point is determined through a linear regression correlating flower diameter with the height of the plucking point. The results showed effective 2D detection. Further, the zero-shot and standard machine learning techniques employed achieved promising 3D localization, pose estimation, and plucking point estimation. Full article

(This article belongs to the Special Issue Advances in Artificial Intelligence for Plant Research)

► Show Figures

Figure 1

15 pages, 1750 KiB

Open AccessArticle

AIpollen: An Analytic Website for Pollen Identification Through Convolutional Neural Networks

by Xingchen Yu, Jiawen Zhao, Zhenxiu Xu, Junrong Wei, Qi Wang, Feng Shen, Xiaozeng Yang and Zhonglong Guo

Plants 2024, 13(22), 3118; https://doi.org/10.3390/plants13223118 - 5 Nov 2024

Cited by 2 | Viewed by 1406

Abstract

With the rapid development of artificial intelligence, deep learning has been widely applied to complex tasks such as computer vision and natural language processing, demonstrating its outstanding performance. This study aims to exploit the high precision and efficiency of deep learning to develop [...] Read more.

With the rapid development of artificial intelligence, deep learning has been widely applied to complex tasks such as computer vision and natural language processing, demonstrating its outstanding performance. This study aims to exploit the high precision and efficiency of deep learning to develop a system for the identification of pollen. To this end, we constructed a dataset across 36 distinct genera. In terms of model selection, we employed a pre-trained ResNet34 network and fine-tuned its architecture to suit our specific task. For the optimization algorithm, we opted for the Adam optimizer and utilized the cross-entropy loss function. Additionally, we implemented ELU activation function, data augmentation, learning rate decay, and early stopping strategies to enhance the training efficiency and generalization capability of the model. After training for 203 epochs, our model achieved an accuracy of 97.01% on the test set and 99.89% on the training set. Further evaluation metrics, such as an F1 score of 95.9%, indicate that the model exhibits good balance and robustness across all categories. To facilitate the use of the model, we develop a user-friendly web interface. Users can upload images of pollen grains through the URL link provided in this article) and immediately receive predicted results of their genus names. Altogether, this study has successfully trained and validated a high-precision pollen grain identification model, providing a powerful tool for the identification of pollen. Full article

(This article belongs to the Special Issue Advances in Artificial Intelligence for Plant Research)

► Show Figures

Figure 1

Review

Jump to: Research

24 pages, 1840 KiB

Open AccessReview

AI-Powered Plant Science: Transforming Forestry Monitoring, Disease Prediction, and Climate Adaptation

by Zuo Xu and Dalong Jiang

Plants 2025, 14(11), 1626; https://doi.org/10.3390/plants14111626 - 26 May 2025

Abstract

The integration of artificial intelligence (AI) and forestry is driving transformative advances in precision monitoring, disaster management, carbon sequestration, and biodiversity conservation. However, significant knowledge gaps persist in cross-ecological model generalisation, multi-source data fusion, and ethical implementation. This review provides a comprehensive overview [...] Read more.

The integration of artificial intelligence (AI) and forestry is driving transformative advances in precision monitoring, disaster management, carbon sequestration, and biodiversity conservation. However, significant knowledge gaps persist in cross-ecological model generalisation, multi-source data fusion, and ethical implementation. This review provides a comprehensive overview of AI’s transformative role in forestry, focusing on three key areas: resource monitoring, disaster management, and sustainability. Data were collected via a comprehensive literature search of academic databases from 2019 to 2025. The review identified several key applications of AI in forestry, including high-precision resource monitoring with sub-metre accuracy in delineating tree canopies, enhanced disaster management with high recall rates for wildfire detection, and optimised carbon sequestration in mangrove forests. Despite these advancements, challenges remain in cross-ecological model generalisation, multi-source data fusion, and ethical implementation. Future research should focus on developing robust, scalable AI models that can be integrated into existing forestry management systems. Policymakers and practitioners should collaborate to ensure that AI-driven solutions are implemented in a way that balances technological innovation with ecosystem resilience and ethical considerations. Full article

(This article belongs to the Special Issue Advances in Artificial Intelligence for Plant Research)

Journal Menu

Journal Browser

Advances in Artificial Intelligence for Plant Research

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (8 papers)

Research

Review

Further Information

Guidelines

MDPI Initiatives

Follow MDPI