Yu Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yu Wang has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Chunyan Qi
Jilin Academy of Agricultural Sciences, Changchun 130033, China
1 shared publication - Haodong Sun
School of Electronic Information Engineering, Changchun University of Science and Technology, Changchun, China
1 shared publication - Huaqi Ji
School of Electronic Information Engineering, Changchun University of Science and Technology, Changchun 130022, China
1 shared publication - Hui Yu
School of Information and Control Engineering, Jilin Institute of Chemical Technology, Jilin 132022, China
1 shared publication Jin-Xiao Yang
School of Electronics and Information Engineering, Changchun University of Sciences and Technology, Changchun, China
1 shared publication- Liang Zheng
Jilin Agricultural Science and Technology University
1 shared publication
Latest Publications
- 2 November 2026
- Published by Springer Nature in Multimedia Systems
- Vol. 32 (11) , 681
A novel view synthesis method based on structural enhancement and fusion optimization
- 2 November 2026
- Published by Springer Nature in Multimedia Systems
- Vol. 32 (11) , 681
A novel view synthesis method based on structural enhancement and fusion optimization
- Open Access
- 27 August 2026
- Published by MDPI AG in Agriculture
- Vol. 16 (17) , 1847
A Stacking-Fusion Feature Selection Framework for Cross-Year and Cross-Cultivar Leaf Hyperspectral Rice Yield Estimation
Single-criterion feature selection for hyperspectral crop yield estimation suffers from methodological bias and limited generalisation. This study proposes a stacking-fusion feature selection framework with a ridge-regression meta-learner (STACKING_FUSION) that transfers the stacked-generalisation concept to the feature-evaluation space, integrating the Pearson correlation coefficient (PCC), grey relational analysis (GRA), and variable importance in projection (VIP) and using the out-of-fold as a meta-supervision signal for adaptive weighting. In field experiments (2024–2025, Gongzhuling, Jilin Province) on rice cultivars Jijing 830 and Jijing 855, leaf hyperspectral reflectance (400–2400 nm) was acquired under controlled indoor measurement conditions at the tillering, jointing, flowering, and milking stages; the study was thus conducted at the leaf scale rather than at the canopy scale of UAV or satellite remote sensing. Second-derivative spectra outperformed original and first-derivative spectra at most stages, and STACKING_FUSION with XGBoost achieved the highest accuracy ( = 0.948, RMSE = 0.018 kg m−2, ratio of performance to deviation (RPD) = 4.399). Joint interpretation using SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME), computed on a held-out test subset, identified flowering-stage indices as the leading predictors within the model and suggested a flowering–tillering cross-stage association. With the configuration fixed from the 2024 development dataset, the 2025 analysis showed that the framework was reusable as a locked feature-engineering and algorithmic configuration rather than as a directly portable fitted predictor: under strict zero-shot application it retained high predicted–measured correlations (Pearson r≈ 0.91–0.93) but showed a consistent negative bias together with additional scale and residual error, whereas recalibration on a target-domain calibration subset (70% of the 2025 samples) achieved RPD > 3.0 in both the cross-year and cross-cultivar evaluations. These results indicate that the reusable component is the locked feature-engineering and algorithmic setting rather than the fitted coefficients.- 27 August 2026
- Published by MDPI AG in Agriculture
- Vol. 16 (17) , 1847
Open AccessA Stacking-Fusion Feature Selection Framework for Cross-Year and Cross-Cultivar Leaf Hyperspectral Rice Yield Estimation
Single-criterion feature selection for hyperspectral crop yield estimation suffers from methodological bias and limited generalisation. This study proposes a stacking-fusion feature selection framework with a ridge-regression meta-learner (STACKING_FUSION) that transfers the stacked-generalisation concept to the feature-evaluation space, integrating the Pearson correlation coefficient (PCC), grey relational analysis (GRA), and variable importance in projection (VIP) and using the out-of-fold as a meta-supervision signal for adaptive weighting. In field experiments (2024–2025, Gongzhuling, Jilin Province) on rice cultivars Jijing 830 and Jijing 855, leaf hyperspectral reflectance (400–2400 nm) was acquired under controlled indoor measurement conditions at the tillering, jointing, flowering, and milking stages; the study was thus conducted at the leaf scale rather than at the canopy scale of UAV or satellite remote sensing. Second-derivative spectra outperformed original and first-derivative spectra at most stages, and STACKING_FUSION with XGBoost achieved the highest accuracy ( = 0.948, RMSE = 0.018 kg m−2, ratio of performance to deviation (RPD) = 4.399). Joint interpretation using SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME), computed on a held-out test subset, identified flowering-stage indices as the leading predictors within the model and suggested a flowering–tillering cross-stage association. With the configuration fixed from the 2024 development dataset, the 2025 analysis showed that the framework was reusable as a locked feature-engineering and algorithmic configuration rather than as a directly portable fitted predictor: under strict zero-shot application it retained high predicted–measured correlations (Pearson r≈ 0.91–0.93) but showed a consistent negative bias together with additional scale and residual error, whereas recalibration on a target-domain calibration subset (70% of the 2025 samples) achieved RPD > 3.0 in both the cross-year and cross-cultivar evaluations. These results indicate that the reusable component is the locked feature-engineering and algorithmic setting rather than the fitted coefficients. - Open Access
- 9 August 2025
- Published by Elsevier in SLAS Technology
- Vol. 34, 100338
Self-supervised disc and cup segmentation via non-local deformable convolution and adaptive transformer
- 9 August 2025
- Published by Elsevier in SLAS Technology
- Vol. 34, 100338
Open AccessSelf-supervised disc and cup segmentation via non-local deformable convolution and adaptive transformer
- Open Access
Enhancing Underwater Images of a Bionic Horseshoe Crab Robot Using an Artificial Lateral Inhibition Network
This paper proposes an underwater image enhancement technology based on an artificial lateral inhibition network (ALIN) generated in the compound eye of a bionic horseshoe crab robot (BHCR). The concept of a horizontal suppression network is applied to underwater image processing with the aim of achieving low energy consumption, high efficiency processing, and adaptability to limited computing resources. The lateral inhibition network has the effect of “enhancing the center and suppressing the surroundings”. In this paper, a pattern recognition algorithm is used to compare and analyze the images obtained by an artificial lateral inhibition network and eight main underwater enhancement algorithms (white balance, histogram equalization, multi-scale Retinex, and dark channel). Therefore, we can evaluate the application of the artificial lateral inhibition network in underwater image enhancement and the deficiency of the algorithm. The experimental results show that the ALIN plays an obvious role in enhancing the important information in underwater image processing technology. Compared with other algorithms, this algorithm can effectively improve the contrast between the highlight area and the shadow area in underwater image processing, solve the problem that the information of the characteristic points of the collected image is not prominent, and achieve the unique effect of suppressing the intensity of other pixel points without information. Finally, we conduct target recognition verification experiments to assess the ALIN’s performance in identifying targets underwater with the BHCR in static water environments. The experiments confirm that the BHCR can maneuver underwater using multiple degrees of freedom (MDOF) and successfully acquire underwater targets.
Open AccessEnhancing Underwater Images of a Bionic Horseshoe Crab Robot Using an Artificial Lateral Inhibition Network
This paper proposes an underwater image enhancement technology based on an artificial lateral inhibition network (ALIN) generated in the compound eye of a bionic horseshoe crab robot (BHCR). The concept of a horizontal suppression network is applied to underwater image processing with the aim of achieving low energy consumption, high efficiency processing, and adaptability to limited computing resources. The lateral inhibition network has the effect of “enhancing the center and suppressing the surroundings”. In this paper, a pattern recognition algorithm is used to compare and analyze the images obtained by an artificial lateral inhibition network and eight main underwater enhancement algorithms (white balance, histogram equalization, multi-scale Retinex, and dark channel). Therefore, we can evaluate the application of the artificial lateral inhibition network in underwater image enhancement and the deficiency of the algorithm. The experimental results show that the ALIN plays an obvious role in enhancing the important information in underwater image processing technology. Compared with other algorithms, this algorithm can effectively improve the contrast between the highlight area and the shadow area in underwater image processing, solve the problem that the information of the characteristic points of the collected image is not prominent, and achieve the unique effect of suppressing the intensity of other pixel points without information. Finally, we conduct target recognition verification experiments to assess the ALIN’s performance in identifying targets underwater with the BHCR in static water environments. The experiments confirm that the BHCR can maneuver underwater using multiple degrees of freedom (MDOF) and successfully acquire underwater targets.
- Open Access
- 28 October 2024
- Published by Springer Nature in Heritage Science
- Vol. 12 (1) , 1-11
Naked-eye 3D visualization of cultural relics based on integrated imaging
Digital technology has become crucial for the protection of cultural relics, enabling their acquisition, preservation, exhibition, and dissemination in a non-contact manner.At present, the three-dimensional(3D) visualization technology of cultural relics focuses on the research of non-true 3D visualization, which cannot provide continuous viewing angle and takes a long time to render. This paper focuses on the acquisition and reproduction of digital information related to cultural relics, and proposes to achieve the true 3D display of cultural relics from a continuous perspective based on integrated imaging(InIm). Building up on traditional InIm, an Element image array (EIA) generation algorithm based on local depth template matching is designed by using spatial geometry relation. Experimental results show that the algorithm not only enables naked-eye 3D visualization of cultural relics, but also the generation speed is more than twice that of the compared 3D display data source generation algorithm.
- 28 October 2024
- Published by Springer Nature in Heritage Science
- Vol. 12 (1) , 1-11
Open AccessNaked-eye 3D visualization of cultural relics based on integrated imaging
Digital technology has become crucial for the protection of cultural relics, enabling their acquisition, preservation, exhibition, and dissemination in a non-contact manner.At present, the three-dimensional(3D) visualization technology of cultural relics focuses on the research of non-true 3D visualization, which cannot provide continuous viewing angle and takes a long time to render. This paper focuses on the acquisition and reproduction of digital information related to cultural relics, and proposes to achieve the true 3D display of cultural relics from a continuous perspective based on integrated imaging(InIm). Building up on traditional InIm, an Element image array (EIA) generation algorithm based on local depth template matching is designed by using spatial geometry relation. Experimental results show that the algorithm not only enables naked-eye 3D visualization of cultural relics, but also the generation speed is more than twice that of the compared 3D display data source generation algorithm.
- 30 November 2023
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 18 (2) , 1683-1693
An adaptive guidance fusion network for RGB-D salient object detection
- 30 November 2023
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 18 (2) , 1683-1693
An adaptive guidance fusion network for RGB-D salient object detection
- 23 July 2020
- Published by Springer Nature in Journal of Russian Laser Research
- Vol. 41 (4) , 390-398
3D Integral Imaging Display Processing Using the Similarity of Corresponding Points in Axially Recorded Images
- 23 July 2020
- Published by Springer Nature in Journal of Russian Laser Research
- Vol. 41 (4) , 390-398
3D Integral Imaging Display Processing Using the Similarity of Corresponding Points in Axially Recorded Images