Chen-Feng Long
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Chen-Feng Long has a total of 36 co-authors. Here are the top co-authors by number of shared publications:
- Yang-Jun Deng
College of Information and Intelligence, Hunan Agricultural University, Changsha, China
8 shared publications - Xing-Hui Zhu
School of Information Science and Technology, Hunan Agricultural University, No. 1 Nongda Road, Furong District, Changsha 410128, China
5 shared publications - Xiaoyong Tang
School of Computer Science and Technology, Changsha University of Science and Technology, Changsha, China
3 shared publications Gelan Yang
Department of Computer Science, Hunan City University, Yiyang, China
2 shared publications- Jinling Liu
Hunan Provincial Key Laboratory of Crop Gene Engineering, College of Agronomy, Hunan Agricultural University, Changsha 410128, China
2 shared publications - Kai-Run Li
College of Information and Intelligence, Hunan Agricultural University, Changsha 410128, China
2 shared publications
Latest Publications
- Open Access
A ConvNeXt–LiteMamba Dual-Branch Network for Detection of Rice Blast Disease via Hyperspectral Imaging
Rice blast, caused by Magnaporthe oryzae, is a devastating fungal disease threatening global rice production, with annual yield losses ranging from 10% to 30% in epidemic regions. Conventional detection methods rely on visual inspection and laboratory diagnosis, which are limited by subjectivity, time-consuming procedures, and the inability to detect early-stage infections. Hyperspectral imaging technology offers a highly promising method for detecting rice blast disease. It can capture the physiological and biochemical changes that occur in plant tissues before the appearance of visible symptoms. In this study, we propose a Convolutional-State Space Hybrid Network (CS-HybridNet) featuring a dual-branch deep learning architecture that synergistically combines a ConvNeXt-based spatial branch with a LiteMamba-based global spatial branch (which models long-range spatial dependencies with spectral embeddings). Principal component analysis was employed to reduce the dimensionality from 360 hyperspectral bands to 16 principal components, retaining 99.09% of the original information while significantly improving computational efficiency. An adaptive feature fusion module effectively integrates spatial texture features with spectral features, enabling complementary information utilization. Experimental results on a dataset comprising 166 hyperspectral images demonstrate that CS-HybridNet achieves 96.30% ± 1.38% accuracy, 98.33% precision, 95.16% recall, and an AUC–ROC value of 0.971 on the independent test set, outperforming traditional machine learning methods and existing deep learning models by 3.5–12.8% in accuracy. Ablation studies validate the effectiveness of each component. This research demonstrates the efficacy of spatial-spectral fusion architecture for automated plant disease detection and establishes a technical foundation for the development of intelligent crop disease monitoring systems.
Open AccessA ConvNeXt–LiteMamba Dual-Branch Network for Detection of Rice Blast Disease via Hyperspectral Imaging
Rice blast, caused by Magnaporthe oryzae, is a devastating fungal disease threatening global rice production, with annual yield losses ranging from 10% to 30% in epidemic regions. Conventional detection methods rely on visual inspection and laboratory diagnosis, which are limited by subjectivity, time-consuming procedures, and the inability to detect early-stage infections. Hyperspectral imaging technology offers a highly promising method for detecting rice blast disease. It can capture the physiological and biochemical changes that occur in plant tissues before the appearance of visible symptoms. In this study, we propose a Convolutional-State Space Hybrid Network (CS-HybridNet) featuring a dual-branch deep learning architecture that synergistically combines a ConvNeXt-based spatial branch with a LiteMamba-based global spatial branch (which models long-range spatial dependencies with spectral embeddings). Principal component analysis was employed to reduce the dimensionality from 360 hyperspectral bands to 16 principal components, retaining 99.09% of the original information while significantly improving computational efficiency. An adaptive feature fusion module effectively integrates spatial texture features with spectral features, enabling complementary information utilization. Experimental results on a dataset comprising 166 hyperspectral images demonstrate that CS-HybridNet achieves 96.30% ± 1.38% accuracy, 98.33% precision, 95.16% recall, and an AUC–ROC value of 0.971 on the independent test set, outperforming traditional machine learning methods and existing deep learning models by 3.5–12.8% in accuracy. Ablation studies validate the effectiveness of each component. This research demonstrates the efficacy of spatial-spectral fusion architecture for automated plant disease detection and establishes a technical foundation for the development of intelligent crop disease monitoring systems.
- Open Access
An Approach for Detecting Tomato Under a Complicated Environment
Tomato is one of the most popular and widely cultivated fruits and vegetables in the world. In large-scale cultivation, manual picking is inefficient and labor-intensive, which is likely to lead to a decline in the quality of the fruits. Although mechanical picking can improve efficiency, it is affected by factors such as leaf occlusion and changes in light conditions in the tomato growth environment, resulting in poor detection and recognition results. To address these challenges, this study proposes a tomato detection method based on Graph-CenterNet. The method employs Vision Graph Convolution (ViG) to replace traditional convolutions, thereby enhancing the flexibility of feature extraction, while reducing one downsampling layer to strengthen global information capture. Furthermore, the Coordinate Attention (CA) module is introduced to optimize the processing of key information through correlation computation and weight allocation mechanisms. Experiments conducted on the Tomato Detection dataset demonstrate that the proposed method achieves average precision improvements of 7.94%, 10.58%, and 1.24% compared to Faster R-CNN, CenterNet, and YOLOv8, respectively. The results indicate that the improved Graph-CenterNet method significantly enhances the accuracy and robustness of tomato detection in complex environments.
Open AccessAn Approach for Detecting Tomato Under a Complicated Environment
Tomato is one of the most popular and widely cultivated fruits and vegetables in the world. In large-scale cultivation, manual picking is inefficient and labor-intensive, which is likely to lead to a decline in the quality of the fruits. Although mechanical picking can improve efficiency, it is affected by factors such as leaf occlusion and changes in light conditions in the tomato growth environment, resulting in poor detection and recognition results. To address these challenges, this study proposes a tomato detection method based on Graph-CenterNet. The method employs Vision Graph Convolution (ViG) to replace traditional convolutions, thereby enhancing the flexibility of feature extraction, while reducing one downsampling layer to strengthen global information capture. Furthermore, the Coordinate Attention (CA) module is introduced to optimize the processing of key information through correlation computation and weight allocation mechanisms. Experiments conducted on the Tomato Detection dataset demonstrate that the proposed method achieves average precision improvements of 7.94%, 10.58%, and 1.24% compared to Faster R-CNN, CenterNet, and YOLOv8, respectively. The results indicate that the improved Graph-CenterNet method significantly enhances the accuracy and robustness of tomato detection in complex environments.
- Open Access
L2,1-Norm Regularized Double Non-Negative Matrix Factorization for Hyperspectral Change Detection
Hyperspectral image (HSI) change detection (CD) is an important technology for identifying surface changes using multi-temporal HSIs. Nevertheless, the high dimensionality of HSIs presents significant challenges for CD tasks, including issues such as lack of robustness and high computational costs in existing methods. To address those issues, this paper proposes an unsupervised simple and effective HSI CD model termed -norm regularized double non-negative matrix factorization (-DNMF). Specifically, the proposed model employs a symmetric double non-negative matrix factorization (NMF) framework to jointly analyze multitemporal HSIs, capturing their common and invariant structural information to construct a shared feature basis. Meanwhile, two non-negative feature weight matrices are learned to generate a differential image matrix that directly reflects the change regions. To enhance robustness against noise, an -norm constraint is imposed on the difference image matrix, ensuring that unchanged areas exhibit near-zero values while changed areas present nonzero values. Finally, comprehensive experiments performed on three benchmark hyperspectral datasets validated the efficacy of the proposed method, which is superior to some state-of-the-art ones regarding detection performance and computational cost.Open AccessL2,1-Norm Regularized Double Non-Negative Matrix Factorization for Hyperspectral Change Detection
Hyperspectral image (HSI) change detection (CD) is an important technology for identifying surface changes using multi-temporal HSIs. Nevertheless, the high dimensionality of HSIs presents significant challenges for CD tasks, including issues such as lack of robustness and high computational costs in existing methods. To address those issues, this paper proposes an unsupervised simple and effective HSI CD model termed -norm regularized double non-negative matrix factorization (-DNMF). Specifically, the proposed model employs a symmetric double non-negative matrix factorization (NMF) framework to jointly analyze multitemporal HSIs, capturing their common and invariant structural information to construct a shared feature basis. Meanwhile, two non-negative feature weight matrices are learned to generate a differential image matrix that directly reflects the change regions. To enhance robustness against noise, an -norm constraint is imposed on the difference image matrix, ensuring that unchanged areas exhibit near-zero values while changed areas present nonzero values. Finally, comprehensive experiments performed on three benchmark hyperspectral datasets validated the efficacy of the proposed method, which is superior to some state-of-the-art ones regarding detection performance and computational cost. - Open Access
- 31 October 2024
- Published by MDPI AG in Remote Sensing
- Vol. 16 (21) , 4055
Center-Highlighted Multiscale CNN for Classification of Hyperspectral Images
Hyperspectral images (HSIs) capture a wide range of spectral features across multiple bands of light, from visible to near-infrared. Hyperspectral image classification technology enables researchers to accurately identify and analyze the composition and distribution of surface materials. Current mainstream deep learning methods typically use block sampling to capture spatial features for the model. However, this approach can affect classification results due to the influence of neighboring features within the sample block. To improve the model’s focus on the center of the sampling block, this study proposes a center highlight with multiscale CNN for hyperspectral image classification (CHMSC). The network utilizes an automatic channel selector (Auto-CHS) to fully consider every channel feature and capture the correlation between the channels. Then, CHMSC enhances the model’s ability to concentrate on the central features of the sampling block utilizing structures such as the center highlight. Finally, before outputting the prediction results, an SENet is employed to further refine the features and learn associate interactions between different scales of spatial features and spectral features. Experimental results from three hyperspectral datasets validate the effectiveness of the proposed method. Specifically, when 15 samples from each class are selected for training, CHMSC achieves the highest overall accuracy (OA) of 90.05%, 92.78%, and 90.15% on the three datasets, outperforming other methods with increases of more than 3.11%, 1.8%, and 2.01% in OA, respectively.
- 31 October 2024
- Published by MDPI AG in Remote Sensing
- Vol. 16 (21) , 4055
Open AccessCenter-Highlighted Multiscale CNN for Classification of Hyperspectral Images
Hyperspectral images (HSIs) capture a wide range of spectral features across multiple bands of light, from visible to near-infrared. Hyperspectral image classification technology enables researchers to accurately identify and analyze the composition and distribution of surface materials. Current mainstream deep learning methods typically use block sampling to capture spatial features for the model. However, this approach can affect classification results due to the influence of neighboring features within the sample block. To improve the model’s focus on the center of the sampling block, this study proposes a center highlight with multiscale CNN for hyperspectral image classification (CHMSC). The network utilizes an automatic channel selector (Auto-CHS) to fully consider every channel feature and capture the correlation between the channels. Then, CHMSC enhances the model’s ability to concentrate on the central features of the sampling block utilizing structures such as the center highlight. Finally, before outputting the prediction results, an SENet is employed to further refine the features and learn associate interactions between different scales of spatial features and spectral features. Experimental results from three hyperspectral datasets validate the effectiveness of the proposed method. Specifically, when 15 samples from each class are selected for training, CHMSC achieves the highest overall accuracy (OA) of 90.05%, 92.78%, and 90.15% on the three datasets, outperforming other methods with increases of more than 3.11%, 1.8%, and 2.01% in OA, respectively.
- Open Access
Pest Detection Based on Lightweight Locality-Aware Faster R-CNN
Accurate and timely monitoring of pests is an effective way to minimize the negative effects of pests in agriculture. Since deep learning-based methods have achieved good performance in object detection, they have been successfully applied for pest detection and monitoring. However, the current pest detection methods fail to balance the relationship between computational cost and model accuracy. Therefore, this paper proposes a lightweight, locality-aware faster R-CNN (LLA-RCNN) method for effective pest detection and real-time monitoring. The proposed model uses MobileNetV3 to replace the original backbone, reduce the computational complexity, and compress the size of the model to speed up pest detection. The coordinate attention (CA) blocks are utilized to enhance the locality information for highlighting the objects under complex backgrounds. Furthermore, the generalized intersection over union (GIoU) loss function and region of interest align (RoI Align) technology are used to improve pest detection accuracy. The experimental results on different types of datasets validate that the proposed model not only significantly reduces the number of parameters and floating-point operations (FLOPs), but also achieves better performance than some popular pest detection methods. This demonstrates strong generalization capabilities and provides a feasible method for pest detection on resource-constrained devices.
Open AccessPest Detection Based on Lightweight Locality-Aware Faster R-CNN
Accurate and timely monitoring of pests is an effective way to minimize the negative effects of pests in agriculture. Since deep learning-based methods have achieved good performance in object detection, they have been successfully applied for pest detection and monitoring. However, the current pest detection methods fail to balance the relationship between computational cost and model accuracy. Therefore, this paper proposes a lightweight, locality-aware faster R-CNN (LLA-RCNN) method for effective pest detection and real-time monitoring. The proposed model uses MobileNetV3 to replace the original backbone, reduce the computational complexity, and compress the size of the model to speed up pest detection. The coordinate attention (CA) blocks are utilized to enhance the locality information for highlighting the objects under complex backgrounds. Furthermore, the generalized intersection over union (GIoU) loss function and region of interest align (RoI Align) technology are used to improve pest detection accuracy. The experimental results on different types of datasets validate that the proposed model not only significantly reduces the number of parameters and floating-point operations (FLOPs), but also achieves better performance than some popular pest detection methods. This demonstrates strong generalization capabilities and provides a feasible method for pest detection on resource-constrained devices.
- Open Access
- 21 August 2024
- Published by MDPI AG in Remote Sensing
- Vol. 16 (16) , 3081
Low-Rank Discriminative Embedding Regression for Robust Feature Extraction of Hyperspectral Images via Weighted Schatten p-Norm Minimization
Low-rank representation (LRR) is widely utilized in image feature extraction, as it can reveal the underlying correlation structure of data. However, the subspace learning methods based on LRR suffer from the problems of lacking robustness and discriminability. To address these issues, this paper proposes a new robust feature extraction method named the weighted Schatten p-norm minimization via low-rank discriminative embedding regression (WSNM-LRDER) method. This method works by integrating weighted Schatten p-norm and linear embedding regression into the LRR model. In WSNM-LRDER, the weighted Schatten p-norm is adopted to relax the low-rank function, which can discover the underlying structural information of the image, to enhance the robustness of projection learning. In order to improve the discriminability of the learned projection, an embedding regression regularization is constructed to make full use of prior information. The experimental results on three hyperspectral images datasets show that the proposed WSNM-LRDER achieves better performance than some advanced feature extraction methods. In particular, the proposed method yielded increases of more than 1.2%, 1.1%, and 2% in the overall accuracy (OA) for the Kennedy Space Center, Salinas, and Houston datasets, respectively, when comparing with the comparative methods.
- 21 August 2024
- Published by MDPI AG in Remote Sensing
- Vol. 16 (16) , 3081
Open AccessLow-Rank Discriminative Embedding Regression for Robust Feature Extraction of Hyperspectral Images via Weighted Schatten p-Norm Minimization
Low-rank representation (LRR) is widely utilized in image feature extraction, as it can reveal the underlying correlation structure of data. However, the subspace learning methods based on LRR suffer from the problems of lacking robustness and discriminability. To address these issues, this paper proposes a new robust feature extraction method named the weighted Schatten p-norm minimization via low-rank discriminative embedding regression (WSNM-LRDER) method. This method works by integrating weighted Schatten p-norm and linear embedding regression into the LRR model. In WSNM-LRDER, the weighted Schatten p-norm is adopted to relax the low-rank function, which can discover the underlying structural information of the image, to enhance the robustness of projection learning. In order to improve the discriminability of the learned projection, an embedding regression regularization is constructed to make full use of prior information. The experimental results on three hyperspectral images datasets show that the proposed WSNM-LRDER achieves better performance than some advanced feature extraction methods. In particular, the proposed method yielded increases of more than 1.2%, 1.1%, and 2% in the overall accuracy (OA) for the Kennedy Space Center, Salinas, and Houston datasets, respectively, when comparing with the comparative methods.
- Open Access
- 1 February 2024
- Published by Institution of Engineering and Technology (IET) in Electronics Letters
- Vol. 60 (3)
Relaxation linear regression with spectral–spatial constrained locality adaptive regularization for hyperspectral image classification
Recently, relaxation linear regression has received increasing attention in image analysis. However, the current relaxation linear regression methods fail to consider the local geometrical structure and spatial information while they are applied for hyperspectral image (HSI) classification. To address the above problems, this letter proposes a novel relaxation linear regression with spectral–spatial constrained locality adaptive regularization (SSLA‐RLR) method for HSI classification. The SSLA‐RLR method not only integrates the locality adaptive graph with relaxation linear regression to adaptively exploit the local geometrical structure for relieving the side effects of noise corruptions, but also takes the spatial correlations between each data point and its neighbours into consideration via spectral–spatial constraint. Finally, extensive experiments are conducted on three benchmark HSI datasets to demonstrate the effectiveness of the proposed method.
- 1 February 2024
- Published by Institution of Engineering and Technology (IET) in Electronics Letters
- Vol. 60 (3)
Open AccessRelaxation linear regression with spectral–spatial constrained locality adaptive regularization for hyperspectral image classification
Recently, relaxation linear regression has received increasing attention in image analysis. However, the current relaxation linear regression methods fail to consider the local geometrical structure and spatial information while they are applied for hyperspectral image (HSI) classification. To address the above problems, this letter proposes a novel relaxation linear regression with spectral–spatial constrained locality adaptive regularization (SSLA‐RLR) method for HSI classification. The SSLA‐RLR method not only integrates the locality adaptive graph with relaxation linear regression to adaptively exploit the local geometrical structure for relieving the side effects of noise corruptions, but also takes the spatial correlations between each data point and its neighbours into consideration via spectral–spatial constraint. Finally, extensive experiments are conducted on three benchmark HSI datasets to demonstrate the effectiveness of the proposed method.
- Open Access
Locality Preserved Selective Projection Learning for Rice Variety Identification Based on Leaf Hyperspectral Characteristics
Rice has an important position in China as well as in the world. With the wide application of rice hybridization technology, the problem of mixing between individual varieties has become more and more prominent, so the variety identification of rice is important for the agricultural production, the phenotype collection, and the scientific breeding. Traditional identification methods are highly subjective and time-consuming. To address this issue, we propose a novel locality preserved selective projection learning (LPSPL) method for non-destructive rice variety identification based on leaf hyperspectral characteristics. The proposed LPSPL method can select the most discriminative spectral features from the leaf hyperspectral characteristics of rice, which is helpful to distinguish different rice varieties. In the experiments, support vector machine (SVM) is adopted to conduct the rice variety identification based on the selected spectral features. The experimental results show that the proposed method here achieves higher identification rates, 96% for the early rice and 98% for the late rice, respectively, which are superior to some state-of-the-art methods.
Open AccessLocality Preserved Selective Projection Learning for Rice Variety Identification Based on Leaf Hyperspectral Characteristics
Rice has an important position in China as well as in the world. With the wide application of rice hybridization technology, the problem of mixing between individual varieties has become more and more prominent, so the variety identification of rice is important for the agricultural production, the phenotype collection, and the scientific breeding. Traditional identification methods are highly subjective and time-consuming. To address this issue, we propose a novel locality preserved selective projection learning (LPSPL) method for non-destructive rice variety identification based on leaf hyperspectral characteristics. The proposed LPSPL method can select the most discriminative spectral features from the leaf hyperspectral characteristics of rice, which is helpful to distinguish different rice varieties. In the experiments, support vector machine (SVM) is adopted to conduct the rice variety identification based on the selected spectral features. The experimental results show that the proposed method here achieves higher identification rates, 96% for the early rice and 98% for the late rice, respectively, which are superior to some state-of-the-art methods.
- 12 July 2022
- Published by Springer Nature in Neural Processing Letters
- Vol. 55 (2) , 1209-1229
A Multi-Task BERT-BiLSTM-AM-CRF Strategy for Chinese Named Entity Recognition
- 12 July 2022
- Published by Springer Nature in Neural Processing Letters
- Vol. 55 (2) , 1209-1229
A Multi-Task BERT-BiLSTM-AM-CRF Strategy for Chinese Named Entity Recognition
- Open Access
Dynamic Prediction of Chilo suppressalis Occurrence in Rice Based on Deep Learning
(1) Background: The striped rice stem borer (SRSB), Chilo suppressalis, has severely diminished the yield and quality of rice in China. A timely and accurate prediction of the rice pest population can facilitate the designation of a pest control strategy. (2) Methods: In this study, we applied multiple linear regression (MLR), gradient boosting decision tree (GBDT), and deep auto-regressive (DeepAR) models in the dynamic prediction of the SRSB population occurrence during the crop season from 2000 to 2020 in Hunan province, China, by using weather factors and time series of related pests. (3) Results: This research demonstrated the potential of the deep learning method used in integrated pest management through the qualitative and quantitative evaluation of a reasonable validating dataset (the average coefficient of determination for the DeepAR, GBDT, and MLR models were 0.952, 0.500, and 0.166, respectively). (4) Conclusions: The DeepAR model with integrated ground-based meteorological variables, time series of related pests, and time features achieved the most accurate dynamic forecasting of the population occurrence quantity of SRSB as compared with MLR and GBDT.Open AccessDynamic Prediction of Chilo suppressalis Occurrence in Rice Based on Deep Learning
(1) Background: The striped rice stem borer (SRSB), Chilo suppressalis, has severely diminished the yield and quality of rice in China. A timely and accurate prediction of the rice pest population can facilitate the designation of a pest control strategy. (2) Methods: In this study, we applied multiple linear regression (MLR), gradient boosting decision tree (GBDT), and deep auto-regressive (DeepAR) models in the dynamic prediction of the SRSB population occurrence during the crop season from 2000 to 2020 in Hunan province, China, by using weather factors and time series of related pests. (3) Results: This research demonstrated the potential of the deep learning method used in integrated pest management through the qualitative and quantitative evaluation of a reasonable validating dataset (the average coefficient of determination for the DeepAR, GBDT, and MLR models were 0.952, 0.500, and 0.166, respectively). (4) Conclusions: The DeepAR model with integrated ground-based meteorological variables, time series of related pests, and time features achieved the most accurate dynamic forecasting of the population occurrence quantity of SRSB as compared with MLR and GBDT.