Tao Wen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Tao Wen has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Dapeng Li
School of Mechanical and Electrical Engineering, Central South University of Forestry and Technology, Changsha 410004, China
3 shared publications - Zhongliang Gong
School of Mechanical and Electrical Engineering, Central South University of Forestry and Technology, Changsha 410004, China
2 shared publications - Hailong Peng
School of Chemistry and Chemical Engineering, Nanchang University, Nanchang 330031, China
1 shared publication - Jiang Long
School of Mechanical and Electrical Engineering, Central South University of Forestry and Technology, Changsha 410004, China
1 shared publication - Jingxi Luo
Beihang University
1 shared publication - Jinwei Guan
School of Mechanical and Electrical Engineering, Central South University of Forestry and Technology, Changsha 410004, China
1 shared publication
Latest Publications
- Open Access
- 17 March 2025
- Published by MDPI AG in Agriculture
- Vol. 15 (6) , 630
RT-DETR-MCDAF: Multimodal Fusion of Visible Light and Near-Infrared Images for Citrus Surface Defect Detection in the Compound Domain
The accurate detection of citrus surface defects is essential for automated citrus sorting to enhance the commercialization of the citrus industry. However, previous studies have only focused on single-modal defect detection using visible light images (RGB) or near-infrared light images (NIR), without considering the feature fusion between these two modalities. This study proposed an RGB-NIR multimodal fusion method to extract and integrate key features from both modalities to enhance defect detection performance. First, an RGB-NIR multimodal dataset containing four types of citrus surface defects (cankers, pests, melanoses, and cracks) was constructed. Second, a Multimodal Compound Domain Attention Fusion (MCDAF) module was developed for multimodal channel fusion. Finally, MCDAF was integrated into the feature extraction network of Real-Time DEtection TRansformer (RT-DETR). The experimental results demonstrated that RT-DETR-MCDAF achieved Precision, Recall, mAP@0.5, and mAP@0.5:0.95 values of 0.914, 0.919, 0.90, and 0.937, respectively, with an average detection performance of 0.598. Compared with the model RT-DETR-RGB&NIR, which used simple channel concatenation fusion, RT-DETR-MCDAF improved the performance by 1.3%, 1.7%, 1%, 1.5%, and 1.7%, respectively. Overall, the proposed model outperformed traditional channel fusion methods and state-of-the-art single-modal models, providing innovative insights for commercial citrus sorting.
- 17 March 2025
- Published by MDPI AG in Agriculture
- Vol. 15 (6) , 630
Open AccessRT-DETR-MCDAF: Multimodal Fusion of Visible Light and Near-Infrared Images for Citrus Surface Defect Detection in the Compound Domain
The accurate detection of citrus surface defects is essential for automated citrus sorting to enhance the commercialization of the citrus industry. However, previous studies have only focused on single-modal defect detection using visible light images (RGB) or near-infrared light images (NIR), without considering the feature fusion between these two modalities. This study proposed an RGB-NIR multimodal fusion method to extract and integrate key features from both modalities to enhance defect detection performance. First, an RGB-NIR multimodal dataset containing four types of citrus surface defects (cankers, pests, melanoses, and cracks) was constructed. Second, a Multimodal Compound Domain Attention Fusion (MCDAF) module was developed for multimodal channel fusion. Finally, MCDAF was integrated into the feature extraction network of Real-Time DEtection TRansformer (RT-DETR). The experimental results demonstrated that RT-DETR-MCDAF achieved Precision, Recall, mAP@0.5, and mAP@0.5:0.95 values of 0.914, 0.919, 0.90, and 0.937, respectively, with an average detection performance of 0.598. Compared with the model RT-DETR-RGB&NIR, which used simple channel concatenation fusion, RT-DETR-MCDAF improved the performance by 1.3%, 1.7%, 1%, 1.5%, and 1.7%, respectively. Overall, the proposed model outperformed traditional channel fusion methods and state-of-the-art single-modal models, providing innovative insights for commercial citrus sorting.
- Open Access
- 21 August 2023
- Published by MDPI AG in Agriculture
- Vol. 13 (8) , 1642
Detection and Classification of Citrus Fruit Infestation by Bactrocera dorsalis (Hendel) Using a Multi-Path Vis/NIR Spectroscopy System
In this study, a multi-path Vis/NIR spectroscopy system was developed to detect the presence of Bactrocera dorsalis (Hendel) infestations of citrus fruit. Spectra were acquired for 252 citrus fruit, 126 of which were infested. Two hundred and fifty-two spectra were acquired for modeling in their un-infested stage, slightly infested stage, and seriously infested stage. The location of the infestation is unclear, and considering the impact of the light path on the location of the infestation, each citrus fruit was tested in three orientations (i.e., fruit stalks facing upward (A), fruit stalks facing horizontally (B), and fruit stalks facing downward (C)). Classification models based on joint X-Y distance, multiple transmittance calibration, competitive adaptive reweighted sampling, and partial least squares discriminant analysis (SPXY-MSC-CARS-PLS-DA) were developed on the spectra of each light path, and the average spectra of the four light paths was calculated, to compare their performance in infestation classification. The results show the classification result changed with the light path and fruit orientation. The average spectra for each fruit orientation consistently gave better classification results, with overall accuracies of 92.9%, 89.3%, and 90.5% for orientations A, B, and C, respectively. Moreover, the best model had a Kappa value of 0.89, and gave 95.2%, 80.1%, and 100.0% accuracy for un-infested, slightly infested, and seriously infested citrus fruit. Furthermore, the classification results for infested citrus fruits were better when using the average spectra than using the spectrum of each single light path. Therefore, the multi-path Vis/NIR spectroscopy system is conducive to the detection of B. dorsalis infestation in citrus fruits.
- 21 August 2023
- Published by MDPI AG in Agriculture
- Vol. 13 (8) , 1642
Open AccessDetection and Classification of Citrus Fruit Infestation by Bactrocera dorsalis (Hendel) Using a Multi-Path Vis/NIR Spectroscopy System
In this study, a multi-path Vis/NIR spectroscopy system was developed to detect the presence of Bactrocera dorsalis (Hendel) infestations of citrus fruit. Spectra were acquired for 252 citrus fruit, 126 of which were infested. Two hundred and fifty-two spectra were acquired for modeling in their un-infested stage, slightly infested stage, and seriously infested stage. The location of the infestation is unclear, and considering the impact of the light path on the location of the infestation, each citrus fruit was tested in three orientations (i.e., fruit stalks facing upward (A), fruit stalks facing horizontally (B), and fruit stalks facing downward (C)). Classification models based on joint X-Y distance, multiple transmittance calibration, competitive adaptive reweighted sampling, and partial least squares discriminant analysis (SPXY-MSC-CARS-PLS-DA) were developed on the spectra of each light path, and the average spectra of the four light paths was calculated, to compare their performance in infestation classification. The results show the classification result changed with the light path and fruit orientation. The average spectra for each fruit orientation consistently gave better classification results, with overall accuracies of 92.9%, 89.3%, and 90.5% for orientations A, B, and C, respectively. Moreover, the best model had a Kappa value of 0.89, and gave 95.2%, 80.1%, and 100.0% accuracy for un-infested, slightly infested, and seriously infested citrus fruit. Furthermore, the classification results for infested citrus fruits were better when using the average spectra than using the spectrum of each single light path. Therefore, the multi-path Vis/NIR spectroscopy system is conducive to the detection of B. dorsalis infestation in citrus fruits.
- Open Access
Rapid and Low-Cost Quantification of Adulteration Content in Camellia Oil Utilizing UV-Vis-NIR Spectroscopy Combined with Feature Selection Methods
This study aims to explore the potential use of low-cost ultraviolet-visible-near infrared (UV-Vis-NIR) spectroscopy to quantify adulteration content of soybean, rapeseed, corn and peanut oils in Camellia oil. To attain this aim, test oil samples were firstly prepared with different adulterant ratios ranging from 1% to 90% at varying intervals, and their spectra were collected by an in-house built experimental platform. Next, the spectra were preprocessed using Savitzky–Golay (SG)–Continuous Wavelet Transform (CWT) and the feature wavelengths were extracted using four different algorithms. Finally, Support Vector Regression (SVR) and Random Forest (RF) models were developed to rapidly predict adulteration content. The results indicated that SG–CWT with decomposition scale of 25 and the Iterative Variable Subset Optimization (IVSO) algorithm can effectively improve the accuracy of the models. Furthermore, the SVR model performed best for predicting adulteration of camellia oil with soybean oil, while the RF models were optimal for camellia oil adulterated with rapeseed, corn, or peanut oil. Additionally, we verified the models’ robustness by examining the correlation between the absorbance and adulteration content at certain feature wavelengths screened by IVSO. This study demonstrates the feasibility of using low-cost UV-Vis-NIR spectroscopy for the authentication of Camellia oil.
Open AccessRapid and Low-Cost Quantification of Adulteration Content in Camellia Oil Utilizing UV-Vis-NIR Spectroscopy Combined with Feature Selection Methods
This study aims to explore the potential use of low-cost ultraviolet-visible-near infrared (UV-Vis-NIR) spectroscopy to quantify adulteration content of soybean, rapeseed, corn and peanut oils in Camellia oil. To attain this aim, test oil samples were firstly prepared with different adulterant ratios ranging from 1% to 90% at varying intervals, and their spectra were collected by an in-house built experimental platform. Next, the spectra were preprocessed using Savitzky–Golay (SG)–Continuous Wavelet Transform (CWT) and the feature wavelengths were extracted using four different algorithms. Finally, Support Vector Regression (SVR) and Random Forest (RF) models were developed to rapidly predict adulteration content. The results indicated that SG–CWT with decomposition scale of 25 and the Iterative Variable Subset Optimization (IVSO) algorithm can effectively improve the accuracy of the models. Furthermore, the SVR model performed best for predicting adulteration of camellia oil with soybean oil, while the RF models were optimal for camellia oil adulterated with rapeseed, corn, or peanut oil. Additionally, we verified the models’ robustness by examining the correlation between the absorbance and adulteration content at certain feature wavelengths screened by IVSO. This study demonstrates the feasibility of using low-cost UV-Vis-NIR spectroscopy for the authentication of Camellia oil.