Yongcai Pan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Yongcai Pan has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Binghai Wen
Guangxi Normal University
4 shared publications - Chuan Lin
School of Automation, Guangxi University of Science and Technology, Liuzhou, 545006, China
4 shared publications - Limin Zhou
Shanghai Synchrotron Radiation Facility, Shanghai Advanced Research Institute, Chinese Academy of Sciences, Shanghai 201204, China
2 shared publications - Qin Xu
Guangxi Key Laboratory of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin 541004, China
2 shared publications - Qingzheng Liu
MOE Joint International Research Laboratory of Animal Health and Food Safety, Engineering Laboratory of Animal Immunity of Jiangsu Province, College of Veterinary Medicine, Nanjing Agricultural University, Nanjing 210095, China
2 shared publications - Yuwei Zhang
School of Electrical and Information Engineering, Guangxi University of Science and Technology, Liuzhou
2 shared publications
Latest Publications
- 3 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (4) , 4021-4036
RSVDet: Remote Sensing Small Object Detection Model Inspired by Neuronal Mechanisms in Visual Pathways
Small object detection is a significant and challenging research area in aerospace. Small objects often face issues like background interference and inter-class similarity due to their small size and low boundary contrast in complex environments. Physiological studies indicate that the visual pathway’s neuronal mechanisms can effectively extract features such as contours, shapes, and colors, filter out background noise and thus recognize complex forms. Therefore, this paper proposes a remote sensing small object detection model inspired by neuronal mechanisms in visual pathways, called RSVDet. RSVDet simulates the information transmission of the ventral visual pathway (Retina-LGN-V1-V2-V4-IT) and meticulously models the involved visual areas. First, inspired by the “Retina-LGN-V1” pathway, we designed a feature enhancement module to capture low-level information. Second, based on the global-local receptive field mechanism of V2 neurons, we developed a feature extraction module for shape information. Additionally, inspired by the self-regulation mechanisms of V4 neurons, we created a self-feedback attention module to filter background noise. Finally, drawing from the orientation selectivity of IT neurons, we designed a hierarchical modulation detection head module to extract complex shape features. RSVDet achieves an AP50 of 50.1% on the Visdrone dataset with 1.72M parameters, achieving the best performance among lightweight models.The code for RSVDet can be found at:https://github.com/wxz0426/RSVDet/tree/main.
- 3 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (4) , 4021-4036
RSVDet: Remote Sensing Small Object Detection Model Inspired by Neuronal Mechanisms in Visual Pathways
Small object detection is a significant and challenging research area in aerospace. Small objects often face issues like background interference and inter-class similarity due to their small size and low boundary contrast in complex environments. Physiological studies indicate that the visual pathway’s neuronal mechanisms can effectively extract features such as contours, shapes, and colors, filter out background noise and thus recognize complex forms. Therefore, this paper proposes a remote sensing small object detection model inspired by neuronal mechanisms in visual pathways, called RSVDet. RSVDet simulates the information transmission of the ventral visual pathway (Retina-LGN-V1-V2-V4-IT) and meticulously models the involved visual areas. First, inspired by the “Retina-LGN-V1” pathway, we designed a feature enhancement module to capture low-level information. Second, based on the global-local receptive field mechanism of V2 neurons, we developed a feature extraction module for shape information. Additionally, inspired by the self-regulation mechanisms of V4 neurons, we created a self-feedback attention module to filter background noise. Finally, drawing from the orientation selectivity of IT neurons, we designed a hierarchical modulation detection head module to extract complex shape features. RSVDet achieves an AP50 of 50.1% on the Visdrone dataset with 1.72M parameters, achieving the best performance among lightweight models.The code for RSVDet can be found at:https://github.com/wxz0426/RSVDet/tree/main.
- 30 March 2025
- Published by Springer Nature in The Visual Computer
- Vol. 41 (11) , 8451-8466
Detail-enhanced lightweight network for small object detection in aerial images
- 30 March 2025
- Published by Springer Nature in The Visual Computer
- Vol. 41 (11) , 8451-8466
Detail-enhanced lightweight network for small object detection in aerial images
- 6 March 2025
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 19 (5) , 1-9
Bio-inspired enhancement network for object detection in adverse conditions
- 6 March 2025
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 19 (5) , 1-9
Bio-inspired enhancement network for object detection in adverse conditions
- 1 April 2024
- Published by AIP Publishing in Physics of Fluids
- Vol. 36 (4)
A deep-learning-based compact method for accelerating the electrowetting lattice Boltzmann simulations
Research on the electrowetting of micro- and nanoscale droplets is essential for microfluidics and nanomaterials applications. A lattice-Boltzmann-electrostatics (LBES) method is an effective and accurate method for simulating this process. However, the electric potential field in each time step requires numerous iterative calculations to converge. Therefore, there is a trade-off dilemma between using high-density lattice fields to improve simulation refinement and low-density lattice fields to reduce computing costs in simulations. Fortunately, deep learning techniques can enhance the computing efficiency of electric potential fields, providing an efficient and accurate solution for electrowetting studies in fine-grained fields. In this study, a compact LBES (C-LBES), a computationally accelerated model for an electric potential field with spatiotemporal prediction capability, is developed by combining the advantages of a recurrent residual convolutional unit and a convolutional long-short-term memory unit. A loss function incorporating a geometric boundary constraint term and a self-cyclic prediction scheme are introduced according to the characteristics of the prediction task, which further improves the prediction accuracy of the model and the computing efficiency of the electric potential field. The model is validated with small datasets, and the results show that the C-LBES model with the self-cyclic prediction scheme improves the computing efficiency of the conventional LBES method by a factor of 10 and provides high-precision results when predicting a two-dimensional convergent electric potential field with a lattice size of (110, 160). In the generalization experiments, the average absolute error of the calculated results remains in the same order of magnitude as the accuracy experimental results.
- 1 April 2024
- Published by AIP Publishing in Physics of Fluids
- Vol. 36 (4)
A deep-learning-based compact method for accelerating the electrowetting lattice Boltzmann simulations
Research on the electrowetting of micro- and nanoscale droplets is essential for microfluidics and nanomaterials applications. A lattice-Boltzmann-electrostatics (LBES) method is an effective and accurate method for simulating this process. However, the electric potential field in each time step requires numerous iterative calculations to converge. Therefore, there is a trade-off dilemma between using high-density lattice fields to improve simulation refinement and low-density lattice fields to reduce computing costs in simulations. Fortunately, deep learning techniques can enhance the computing efficiency of electric potential fields, providing an efficient and accurate solution for electrowetting studies in fine-grained fields. In this study, a compact LBES (C-LBES), a computationally accelerated model for an electric potential field with spatiotemporal prediction capability, is developed by combining the advantages of a recurrent residual convolutional unit and a convolutional long-short-term memory unit. A loss function incorporating a geometric boundary constraint term and a self-cyclic prediction scheme are introduced according to the characteristics of the prediction task, which further improves the prediction accuracy of the model and the computing efficiency of the electric potential field. The model is validated with small datasets, and the results show that the C-LBES model with the self-cyclic prediction scheme improves the computing efficiency of the conventional LBES method by a factor of 10 and provides high-precision results when predicting a two-dimensional convergent electric potential field with a lattice size of (110, 160). In the generalization experiments, the average absolute error of the calculated results remains in the same order of magnitude as the accuracy experimental results.
- 20 September 2023
- Published by Elsevier in Expert Systems with Applications
- Vol. 237
Bio-inspired XYW parallel pathway edge detection network
- 20 September 2023
- Published by Elsevier in Expert Systems with Applications
- Vol. 237
Bio-inspired XYW parallel pathway edge detection network
- Open Access
- 1 May 2023
- Published by AIP Publishing in Physics of Fluids
- Vol. 35 (5)
Super-resolution reconstruction of turbulent flows with a transformer-based deep learning framework
Details of flow field are highly relevant to understand the mechanism of turbulence, but obtaining high-resolution turbulence often requires enormous computing resources. Although the super-resolution reconstruction of turbulent flow fields is an efficient way to obtain the details, the traditional interpolation methods are difficult to reconstruct small-scale structures, and the results are too smooth. In this paper, based on the transformer backbone architecture, we present a super-resolution transformer for turbulence to reconstruct turbulent flow fields with high quality. It is supervised and has a broader perceptual field for better extraction of deep-level features. The model is applied to forced isotropic turbulence and turbulent channel flow dataset, and the reconstructed instantaneous flow fields are comprehensively compared and analyzed. The results show that SRTT can recover the turbulent flow fields with high spatial resolution and capture small-scale details. It can obtain either the isotropic or the anisotropic turbulent properties even in complex flow configurations.
- 1 May 2023
- Published by AIP Publishing in Physics of Fluids
- Vol. 35 (5)
Open AccessSuper-resolution reconstruction of turbulent flows with a transformer-based deep learning framework
Details of flow field are highly relevant to understand the mechanism of turbulence, but obtaining high-resolution turbulence often requires enormous computing resources. Although the super-resolution reconstruction of turbulent flow fields is an efficient way to obtain the details, the traditional interpolation methods are difficult to reconstruct small-scale structures, and the results are too smooth. In this paper, based on the transformer backbone architecture, we present a super-resolution transformer for turbulence to reconstruct turbulent flow fields with high quality. It is supervised and has a broader perceptual field for better extraction of deep-level features. The model is applied to forced isotropic turbulence and turbulent channel flow dataset, and the reconstructed instantaneous flow fields are comprehensively compared and analyzed. The results show that SRTT can recover the turbulent flow fields with high spatial resolution and capture small-scale details. It can obtain either the isotropic or the anisotropic turbulent properties even in complex flow configurations.
- 4 October 2022
- Published by American Physical Society (APS) in Physical Review Fluids
- Vol. 7 (10) , 103601
State transition of stable nanobubbles to unstable microbubbles on homogeneous surfaces
Experiments have revealed the remarkably long lifetime of surface nanobubbles, but experiments have also demonstrated the diffusive instability of bubbles above micrometers; thus a physical understanding on the transition of bubbles stability is in urgent need. Herein, we develop a model to capture the state transition from stable nanobubbles to unstable microbubbles on homogeneous surfaces. The transition explains the typical long lifetime, limited height, and small contact angle of surface nanobubbles observed in experiments. The phase diagram shows that the bubble size and dissolved gas saturation determine the dynamic behaviors of surface bubbles, namely growth, stability, shrinkage, or dissolution.
- 4 October 2022
- Published by American Physical Society (APS) in Physical Review Fluids
- Vol. 7 (10) , 103601
State transition of stable nanobubbles to unstable microbubbles on homogeneous surfaces
Experiments have revealed the remarkably long lifetime of surface nanobubbles, but experiments have also demonstrated the diffusive instability of bubbles above micrometers; thus a physical understanding on the transition of bubbles stability is in urgent need. Herein, we develop a model to capture the state transition from stable nanobubbles to unstable microbubbles on homogeneous surfaces. The transition explains the typical long lifetime, limited height, and small contact angle of surface nanobubbles observed in experiments. The phase diagram shows that the bubble size and dissolved gas saturation determine the dynamic behaviors of surface bubbles, namely growth, stability, shrinkage, or dissolution.
- 1 July 2022
- Published by AIP Publishing in Physics of Fluids
- Vol. 34 (7) , 072007
The stability and morphology of nanobubbles on homogeneous surfaces with different wettability
Surface nanobubbles were observed to survive with apparent long-term stability and small contact angles in contrast to larger microbubbles. Although the contact line pinning and hydrophobic attraction model can well explain the stability of pinned surface nanobubbles, their experimental morphology features on different surfaces are yet to be presented. With a linearized attraction potential related to surface wettability, in this work, we developed a model that distinguished the stability of nanobubbles and the instability of larger microbubbles reaching diffusive and mechanical equilibrium on homogeneous surfaces. The dynamic evolutions, stability, and morphology of nanobubbles on surfaces with different wettability were investigated. Its results demonstrated that bubbles with different initial sizes and gas oversaturation would present four dynamic states: shrinkage to dissolution, shrinkage or growth to the stable equilibrium, and expansion to burst. The bubbles at stable equilibrium have typical footprint radius ranges, limited heights, and small contact angles, as measured in experiments. Furthermore, with the increase in hydrophobicity, the stable contact radius of nanobubbles becomes larger while the required degree of gas saturation is alleviated. At the same contact radius, the height and contact angle of the bubble on hydrophilic surface are larger than that on hydrophobic surface, both increasing with the growing contact radius. These theoretical predictions are consistent with experimental observations and would be meaningful to understand the stability of surface nanobubbles.
- 1 July 2022
- Published by AIP Publishing in Physics of Fluids
- Vol. 34 (7) , 072007
The stability and morphology of nanobubbles on homogeneous surfaces with different wettability
Surface nanobubbles were observed to survive with apparent long-term stability and small contact angles in contrast to larger microbubbles. Although the contact line pinning and hydrophobic attraction model can well explain the stability of pinned surface nanobubbles, their experimental morphology features on different surfaces are yet to be presented. With a linearized attraction potential related to surface wettability, in this work, we developed a model that distinguished the stability of nanobubbles and the instability of larger microbubbles reaching diffusive and mechanical equilibrium on homogeneous surfaces. The dynamic evolutions, stability, and morphology of nanobubbles on surfaces with different wettability were investigated. Its results demonstrated that bubbles with different initial sizes and gas oversaturation would present four dynamic states: shrinkage to dissolution, shrinkage or growth to the stable equilibrium, and expansion to burst. The bubbles at stable equilibrium have typical footprint radius ranges, limited heights, and small contact angles, as measured in experiments. Furthermore, with the increase in hydrophobicity, the stable contact radius of nanobubbles becomes larger while the required degree of gas saturation is alleviated. At the same contact radius, the height and contact angle of the bubble on hydrophilic surface are larger than that on hydrophobic surface, both increasing with the growing contact radius. These theoretical predictions are consistent with experimental observations and would be meaningful to understand the stability of surface nanobubbles.
- 20 November 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 42-46
A Contour Detection Method Based on Image Saliency
The object contour detection in natural scenes is an important research problem in computer vision. The difficulty is that the integrity of contour extracted is interfered with a large number of texture edges in the background seriously. In recent years, some researchers have introduced image contour detection method with biological visual features and achieved preferable results. Such as, based on the fact of visual outer region suppression, they can suppress a certain amount of texture edge while extracting the contour of the object, and obtain the proper contour edge. However, when this method is used for contour detection in some image which the texture is similar to the contour, the texture edge still cannot be removed well, and the result is unsatisfactory. In consideration of the merit and demerit of the feature suppressed method, we propose an improved algorithm for object contour detection in natural scene based on image saliency. Firstly, the initial contour is obtained by using the suppression effect of non-classical receptive field, and the saliency map is obtained by using the hyper-complex Fourier transform image saliency detection method, and then the initial contour and the saliency map are integrated into the final contour. Compared with the traditional contour detection method, the contour extraction algorithm based on image saliency can remove more background information and improve the accuracy and integrity of object contour extracted in natural scenes.
- 20 November 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 42-46
A Contour Detection Method Based on Image Saliency
The object contour detection in natural scenes is an important research problem in computer vision. The difficulty is that the integrity of contour extracted is interfered with a large number of texture edges in the background seriously. In recent years, some researchers have introduced image contour detection method with biological visual features and achieved preferable results. Such as, based on the fact of visual outer region suppression, they can suppress a certain amount of texture edge while extracting the contour of the object, and obtain the proper contour edge. However, when this method is used for contour detection in some image which the texture is similar to the contour, the texture edge still cannot be removed well, and the result is unsatisfactory. In consideration of the merit and demerit of the feature suppressed method, we propose an improved algorithm for object contour detection in natural scene based on image saliency. Firstly, the initial contour is obtained by using the suppression effect of non-classical receptive field, and the saliency map is obtained by using the hyper-complex Fourier transform image saliency detection method, and then the initial contour and the saliency map are integrated into the final contour. Compared with the traditional contour detection method, the contour extraction algorithm based on image saliency can remove more background information and improve the accuracy and integrity of object contour extracted in natural scenes.
- Open Access
- 1 October 2019
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 1314 (1) , 012094
An improved saliency detection method based on hypercomplex Fourier transform
Saliency detection is a challenging direction in the field of computer vision. It can help us quickly obtain important information of image and video, and plays an important role in image compression, image segmentation, target recognition and other applications. Based on the Hypercomplex Fourier Transform (HFT) model, median filter and threshold segmentation are employed to obtain the image salient region, which solves the problem that the boundary is not clear and multiple targets cannot be separated, and achieves more accurate and stable detection effect.
- 1 October 2019
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 1314 (1) , 012094
Open AccessAn improved saliency detection method based on hypercomplex Fourier transform
Saliency detection is a challenging direction in the field of computer vision. It can help us quickly obtain important information of image and video, and plays an important role in image compression, image segmentation, target recognition and other applications. Based on the Hypercomplex Fourier Transform (HFT) model, median filter and threshold segmentation are employed to obtain the image salient region, which solves the problem that the boundary is not clear and multiple targets cannot be separated, and achieves more accurate and stable detection effect.