Rongli Gai
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Rongli Gai has a total of 36 co-authors. Here are the top co-authors by number of shared publications:
- Na Chen
School of Information Engineering, Dalian University, Dalian, China
2 shared publications Cang Yan
Dalian universityline, Dalian, China
1 shared publication- Chunming Huang
School of Earth and Space Science and Technology Wuhan University Wuhan China
1 shared publication - Dang Ngoc Hoang Thanh
University of Economics Ho Chi Minh City
1 shared publication - Guohui Xu
Institute of Modern Agricultural Research, Dalian University, Dalian 116622, China
1 shared publication - Guohui Xu
Dalian University
1 shared publication
Latest Publications
- Open Access
- 1 May 2026
- Published by KEAI Publishing in Horticultural Plant Journal
- Vol. 12 (5) , 1077-1088
Bulk segregated analysis, transcriptome, and functional analyses reveal the involvement of VcKCS19 and VcCER2 in regulating blueberry fruit wax accumulation
- 1 May 2026
- Published by KEAI Publishing in Horticultural Plant Journal
- Vol. 12 (5) , 1077-1088
Open AccessBulk segregated analysis, transcriptome, and functional analyses reveal the involvement of VcKCS19 and VcCER2 in regulating blueberry fruit wax accumulation
- Top Cited PapersOpen Access
- 18 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 86378-86390
TL-YOLOv8: A Blueberry Fruit Detection Algorithm Based on Improved YOLOv8 and Transfer Learning
Blueberry fruit in the picking process are characterized by small fruit particles, similar color characteristics of immature fruits to leaf, and not obvious characteristics of fruits obscured by leaves, which lead to low real-time detection accuracy of blueberry fruits and fail to meet the detection standard of automatic picking. To improve the detection accuracy, we propose a blueberry identification algorithm named TL-YOLOv8 based on the YOLOv8 algorithm. By introducing an improved MPCA (Multiplexed Coordinated Attention) in the last layer of the backbone network, we enhance the feature extraction capability during the training process. By replacing the C2f module with an OREPA(Online Convolutional Re-parameterization) module, not only the training is accelerated, but also the characterization is enhanced. Meanwhile, in order to cope with the fruit occlusion problem more effectively, we introduce the MultiSEAM (Multi-scale Separation and Occlusion-Aware Module). As a means of optimizing the model parameters, we pre-trained the model using Transfer Learning to improve the generalization ability of the network. The method achieved 84.6% Precision, 91.3% recall and 94.1% mAP on the blueberry dataset, where mAP was improved by 3.4% over the original algorithm, and the experiments showed that it can be effective for blueberry fruit detection.
- 18 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 86378-86390
Top Cited PapersOpen AccessTL-YOLOv8: A Blueberry Fruit Detection Algorithm Based on Improved YOLOv8 and Transfer Learning
Blueberry fruit in the picking process are characterized by small fruit particles, similar color characteristics of immature fruits to leaf, and not obvious characteristics of fruits obscured by leaves, which lead to low real-time detection accuracy of blueberry fruits and fail to meet the detection standard of automatic picking. To improve the detection accuracy, we propose a blueberry identification algorithm named TL-YOLOv8 based on the YOLOv8 algorithm. By introducing an improved MPCA (Multiplexed Coordinated Attention) in the last layer of the backbone network, we enhance the feature extraction capability during the training process. By replacing the C2f module with an OREPA(Online Convolutional Re-parameterization) module, not only the training is accelerated, but also the characterization is enhanced. Meanwhile, in order to cope with the fruit occlusion problem more effectively, we introduce the MultiSEAM (Multi-scale Separation and Occlusion-Aware Module). As a means of optimizing the model parameters, we pre-trained the model using Transfer Learning to improve the generalization ability of the network. The method achieved 84.6% Precision, 91.3% recall and 94.1% mAP on the blueberry dataset, where mAP was improved by 3.4% over the original algorithm, and the experiments showed that it can be effective for blueberry fruit detection.
- Open Access
HPPEM: A High-Precision Blueberry Cluster Phenotype Extraction Model Based on Hybrid Task Cascade
Blueberry fruit phenotypes are crucial agronomic trait indicators in blueberry breeding, and the number of fruits within the cluster, maturity, and compactness are important for evaluating blueberry harvesting methods and yield. However, the existing instance segmentation model cannot extract all these features. And due to the complex field environment and aggregated growth of blueberry fruits, the model is difficult to meet the demand for accurate segmentation and automatic phenotype extraction in the field environment. To solve the above problems, a high-precision phenotype extraction model based on hybrid task cascade (HTC) is proposed in this paper. ConvNeXt is used as the backbone network, and three Mask RCNN networks are cascaded to construct the model, rich feature learning through multi-scale training, and customized algorithms for phenotype extraction combined with contour detection techniques. Accurate segmentation of blueberry fruits and automatic extraction of fruit number, ripeness, and compactness under severe occlusion were successfully realized. Following experimental validation, the average precision for both bounding boxes (bbox) and masks stood at 0.974 and 0.975, respectively, with an intersection over union (IOU) threshold of 0.5. The linear regression of the extracted value of the fruit number against the true value showed that the coefficient of determination (R2) was 0.902, and the root mean squared error (RMSE) was 1.556. This confirms the effectiveness of the proposed model. It provides a new option for more efficient and accurate phenotypic extraction of blueberry clusters.
Open AccessHPPEM: A High-Precision Blueberry Cluster Phenotype Extraction Model Based on Hybrid Task Cascade
Blueberry fruit phenotypes are crucial agronomic trait indicators in blueberry breeding, and the number of fruits within the cluster, maturity, and compactness are important for evaluating blueberry harvesting methods and yield. However, the existing instance segmentation model cannot extract all these features. And due to the complex field environment and aggregated growth of blueberry fruits, the model is difficult to meet the demand for accurate segmentation and automatic phenotype extraction in the field environment. To solve the above problems, a high-precision phenotype extraction model based on hybrid task cascade (HTC) is proposed in this paper. ConvNeXt is used as the backbone network, and three Mask RCNN networks are cascaded to construct the model, rich feature learning through multi-scale training, and customized algorithms for phenotype extraction combined with contour detection techniques. Accurate segmentation of blueberry fruits and automatic extraction of fruit number, ripeness, and compactness under severe occlusion were successfully realized. Following experimental validation, the average precision for both bounding boxes (bbox) and masks stood at 0.974 and 0.975, respectively, with an intersection over union (IOU) threshold of 0.5. The linear regression of the extracted value of the fruit number against the true value showed that the coefficient of determination (R2) was 0.902, and the root mean squared error (RMSE) was 1.556. This confirms the effectiveness of the proposed model. It provides a new option for more efficient and accurate phenotypic extraction of blueberry clusters.
- 28 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-9
Revolutionize Cherry Tree Health by YOLO-CLD: An Advanced Model for Precise Detection of Cherry Leaf Diseases
The detection of cherry leaf diseases holds a crucial significance for maintaining the health status of cherry trees and improving their quality. This paper proposes an advanced model, YOLO-Cherry Leaf Disease (YOLO-CLD), for the efficient and accurate detection of three common cherry leaf diseases: cherry leaf brown spot, bacterial leaf shot hole, and Cherry lethal yellow. First, we built the model on the fast and efficient YOLOv7 network, and we enhanced it with an additional convolutional block attention module and a context Transformer module. The model has resulted in improved feature extraction and representation capabilities. The model is compressed using knowledge distillation to meet deployment requirements for different hardware conditions. The evaluation results on an embedded device show an average recognition accuracy of 85% with a frame rate of 18.5 frames per second (FPS). The proposed model demonstrates the potential of detecting cherry leaf diseases on the fly. The solution can be deployed on the cloud for optimal use.
- 28 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-9
Revolutionize Cherry Tree Health by YOLO-CLD: An Advanced Model for Precise Detection of Cherry Leaf Diseases
The detection of cherry leaf diseases holds a crucial significance for maintaining the health status of cherry trees and improving their quality. This paper proposes an advanced model, YOLO-Cherry Leaf Disease (YOLO-CLD), for the efficient and accurate detection of three common cherry leaf diseases: cherry leaf brown spot, bacterial leaf shot hole, and Cherry lethal yellow. First, we built the model on the fast and efficient YOLOv7 network, and we enhanced it with an additional convolutional block attention module and a context Transformer module. The model has resulted in improved feature extraction and representation capabilities. The model is compressed using knowledge distillation to meet deployment requirements for different hardware conditions. The evaluation results on an embedded device show an average recognition accuracy of 85% with a frame rate of 18.5 frames per second (FPS). The proposed model demonstrates the potential of detecting cherry leaf diseases on the fly. The solution can be deployed on the cloud for optimal use.
- Open Access
- 31 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 81378-81388
Efficient-Low Memory Path Planning Algorithm Based on Adaptive Thresholding
Aiming at the problem of low efficiency and large memory consumption in mobile robot path planning, this paper proposes an improved version of the RRT*Fixed Nodes( RRT*FN )algorithm based on the adaptive threshold, named A-RRT*FN. The algorithm constructs a sampling tree in the two directions of the starting point, and the target point and adaptively sets the threshold according to the environment on both sides to improve the environmental adaptability and search speed of the algorithm. Secondly, a node elimination strategy is proposed to quickly locate low-performance nodes and reduce the number of iterations of the algorithm and the memory occupation of low-performance nodes. Finally, the path smoothing strategy is used to smooth the obstacle-free path to obtain a path more suitable for robot tracking control. The proposed algorithm is compared with RRT* FN, Fast-RRT, and Improved Bi-RRT* algorithms under three different maps of simple, narrow, and complex. The results show that the proposed algorithm has better performance in convergence efficiency and memory consumption.
- 31 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 81378-81388
Open AccessEfficient-Low Memory Path Planning Algorithm Based on Adaptive Thresholding
Aiming at the problem of low efficiency and large memory consumption in mobile robot path planning, this paper proposes an improved version of the RRT*Fixed Nodes( RRT*FN )algorithm based on the adaptive threshold, named A-RRT*FN. The algorithm constructs a sampling tree in the two directions of the starting point, and the target point and adaptively sets the threshold according to the environment on both sides to improve the environmental adaptability and search speed of the algorithm. Secondly, a node elimination strategy is proposed to quickly locate low-performance nodes and reduce the number of iterations of the algorithm and the memory occupation of low-performance nodes. Finally, the path smoothing strategy is used to smooth the obstacle-free path to obtain a path more suitable for robot tracking control. The proposed algorithm is compared with RRT* FN, Fast-RRT, and Improved Bi-RRT* algorithms under three different maps of simple, narrow, and complex. The results show that the proposed algorithm has better performance in convergence efficiency and memory consumption.
- Open Access
- 25 April 2023
- Published by MDPI AG in Agriculture
- Vol. 13 (5) , 939
SSMDA: Self-Supervised Cherry Maturity Detection Algorithm Based on Multi-Feature Contrastive Learning
Due to the high cost of annotating dense fruit images, annotated target images are limited in some ripeness detection applications, which significantly restricts the generalization ability of small object detection networks in complex environments. To address this issue, this study proposes a self-supervised cherry ripeness detection algorithm based on multi-feature contrastive learning, consisting of a multi-feature contrastive self-supervised module and an object detection module. The self-supervised module enhances features of unlabeled fruit images through random contrastive augmentation, reducing interference from complex backgrounds. The object detection module establishes a connection with the self-supervised module and designs a shallow feature fusion network based on the input target scale to improve the detection performance of small-sample fruits. Finally, extensive experiments were conducted on a self-made cherry dataset. The proposed algorithm showed improved generalization ability compared to supervised baseline algorithms, with better accuracy in terms of mAP, particularly in detecting distant small cherries.
- 25 April 2023
- Published by MDPI AG in Agriculture
- Vol. 13 (5) , 939
Open AccessSSMDA: Self-Supervised Cherry Maturity Detection Algorithm Based on Multi-Feature Contrastive Learning
Due to the high cost of annotating dense fruit images, annotated target images are limited in some ripeness detection applications, which significantly restricts the generalization ability of small object detection networks in complex environments. To address this issue, this study proposes a self-supervised cherry ripeness detection algorithm based on multi-feature contrastive learning, consisting of a multi-feature contrastive self-supervised module and an object detection module. The self-supervised module enhances features of unlabeled fruit images through random contrastive augmentation, reducing interference from complex backgrounds. The object detection module establishes a connection with the self-supervised module and designs a shallow feature fusion network based on the input target scale to improve the detection performance of small-sample fruits. Finally, extensive experiments were conducted on a self-made cherry dataset. The proposed algorithm showed improved generalization ability compared to supervised baseline algorithms, with better accuracy in terms of mAP, particularly in detecting distant small cherries.
- 25 February 2023
- Published by World Scientific Pub Co Pte Ltd in Journal of Circuits, Systems and Computers
- Vol. 32 (12)
YOLOv5s-Cherry: Cherry Target Detection in Dense Scenes Based on Improved YOLOv5s Algorithm
Intelligent agriculture has become the development trend of agriculture in the future, and it has a wide range of research and application scenarios. Using machine learning to complete basic tasks for people has become a reality, and this ability is also used in machine vision. In order to save the time in the fruit picking process and reduce the cost of labor, the robot is used to achieve the automatic picking in the orchard environment. Cherry target detection algorithms based on deep learning are proposed to identify and pick cherries. However, most of the existing methods are aimed at relatively sparse fruits and cannot solve the detection problem of small and dense fruits. In this paper, we propose a cherry detection model based on YOLOv5s. First, the shallow feature information is enhanced by convolving the feature maps sampled by two times down in BackBone layer of the original network model to the input end of the second and third CSP modules. In addition, the depth of CSP module is adjusted and RFB module is added in feature extraction stage to enhance feature extraction capability. Finally, Soft- Non-Maximum Suppression (Soft-NMS) is used to minimize the target loss caused by occlusion. We test the performance of the model, and the results show that the improved YOLOv5s-cherry model has the best detection performance for small and dense cherry detection, which is conducive to intelligent picking.
- 25 February 2023
- Published by World Scientific Pub Co Pte Ltd in Journal of Circuits, Systems and Computers
- Vol. 32 (12)
YOLOv5s-Cherry: Cherry Target Detection in Dense Scenes Based on Improved YOLOv5s Algorithm
Intelligent agriculture has become the development trend of agriculture in the future, and it has a wide range of research and application scenarios. Using machine learning to complete basic tasks for people has become a reality, and this ability is also used in machine vision. In order to save the time in the fruit picking process and reduce the cost of labor, the robot is used to achieve the automatic picking in the orchard environment. Cherry target detection algorithms based on deep learning are proposed to identify and pick cherries. However, most of the existing methods are aimed at relatively sparse fruits and cannot solve the detection problem of small and dense fruits. In this paper, we propose a cherry detection model based on YOLOv5s. First, the shallow feature information is enhanced by convolving the feature maps sampled by two times down in BackBone layer of the original network model to the input end of the second and third CSP modules. In addition, the depth of CSP module is adjusted and RFB module is added in feature extraction stage to enhance feature extraction capability. Finally, Soft- Non-Maximum Suppression (Soft-NMS) is used to minimize the target loss caused by occlusion. We test the performance of the model, and the results show that the improved YOLOv5s-cherry model has the best detection performance for small and dense cherry detection, which is conducive to intelligent picking.
- Open Access
- 25 January 2023
- Published by Frontiers Media SA in Frontiers in Plant Science
- Vol. 14, 1099668
A water quality assessment method based on an improved grey relational analysis and particle swarm optimization multi-classification support vector machine
Most of the water quality indicators that affect the results of river water quality assessment are gray and localized, thus the correlation between water quality indicators can be calculated using gray correlation analysis (GRA).However, GRA takes equal weighting for water quality indicators and does not take into account the weighting of the indicators. Therefore, this paper proposes a river water quality assessment method based on improved grey correlation analysis (ACGRA) andparticle swarm optimization multi-classification support vector machine (PSO-MSVM) for assessing river water environment quality. Firstly, the combination weights of water quality indicators were calculated using Analytic Hierarchy Process (AHP)AHP and Criteria Importance Though Intercrieria Correlation (CRITIC)CRITIC, and then the correlation between water quality indicators was calculated for feature selection. Secondly, the PSO-MSVM model was established using the water quality indicators obtained by ACGRA as input parameters for water environment quality assessment. The river water environment assessment methods of ACGRA and PSO-MSVM were applied to the evaluation of water environment quality in different watersheds in the country. Accuracy, precision, recall and root mean square errorRMSE were also introduced as model evaluation criteria. The results show that the river water environment assessment methods based on ACGRA and PSO-MSVM can evaluate the water environment quality more accurately.
- 25 January 2023
- Published by Frontiers Media SA in Frontiers in Plant Science
- Vol. 14, 1099668
Open AccessA water quality assessment method based on an improved grey relational analysis and particle swarm optimization multi-classification support vector machine
Most of the water quality indicators that affect the results of river water quality assessment are gray and localized, thus the correlation between water quality indicators can be calculated using gray correlation analysis (GRA).However, GRA takes equal weighting for water quality indicators and does not take into account the weighting of the indicators. Therefore, this paper proposes a river water quality assessment method based on improved grey correlation analysis (ACGRA) andparticle swarm optimization multi-classification support vector machine (PSO-MSVM) for assessing river water environment quality. Firstly, the combination weights of water quality indicators were calculated using Analytic Hierarchy Process (AHP)AHP and Criteria Importance Though Intercrieria Correlation (CRITIC)CRITIC, and then the correlation between water quality indicators was calculated for feature selection. Secondly, the PSO-MSVM model was established using the water quality indicators obtained by ACGRA as input parameters for water environment quality assessment. The river water environment assessment methods of ACGRA and PSO-MSVM were applied to the evaluation of water environment quality in different watersheds in the country. Accuracy, precision, recall and root mean square errorRMSE were also introduced as model evaluation criteria. The results show that the river water environment assessment methods based on ACGRA and PSO-MSVM can evaluate the water environment quality more accurately.
- Open Access
- 1 January 2023
- Published by FapUNIFESP (SciELO) in Brazilian Archives of Biology and Technology
- Vol. 66, e23220365
A Big Data Cleaning Method for Drinking-Water Streaming Data
Proposing a drinking-water data cleaning model with the combination of nonlinear partial differential equations and the CART decision tree.
- 1 January 2023
- Published by FapUNIFESP (SciELO) in Brazilian Archives of Biology and Technology
- Vol. 66, e23220365
Open AccessA Big Data Cleaning Method for Drinking-Water Streaming Data
Proposing a drinking-water data cleaning model with the combination of nonlinear partial differential equations and the CART decision tree.
- Top Cited Papers
- 26 May 2021
- Published by Springer Nature in Neural Computing and Applications
- Vol. 35 (19) , 13895-13906
A detection algorithm for cherry fruits based on the improved YOLO-v4 model
- 26 May 2021
- Published by Springer Nature in Neural Computing and Applications
- Vol. 35 (19) , 13895-13906
Top Cited PapersA detection algorithm for cherry fruits based on the improved YOLO-v4 model