Yaxing Sun
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yaxing Sun has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Bowen Zhao
School of Electronic and Optical Engineering, Nanjing University of Science and Technology, Nanjing, China
2 shared publications - Feng Ju
School of Earth Sciences and Engineering, Hohai University, Nanjing 211100, China
2 shared publications - Feng Xiaoxing
Nanjing University of Science and Technology, China
2 shared publications - Zhou Jianlin
Nanjing University of Science and Technology, China
2 shared publications Bowen Zhao
School of Electronic Engineering and Optoelectronics Technology, Nanjing University of Science and Technology, Nanjing, China
1 shared publication- ChengZhi Tang
School of Microelectronics, Nanjing University of Science & Technology, Nanjing, Jiangsu, China
1 shared publication
Latest Publications
- Open Access
- 22 May 2026
- Published by Association for Computing Machinery (ACM)
- p. 22-26
Boundary-Aware Object Refinement and Mixed-Only Graph-Regularized FCLS for Multispectral Subpixel Mapping
- 22 May 2026
- Published by Association for Computing Machinery (ACM)
- p. 22-26
Open AccessBoundary-Aware Object Refinement and Mixed-Only Graph-Regularized FCLS for Multispectral Subpixel Mapping
- 21 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 21 (1545598X) , 1-5
PM-LSMN: A Physical-Model-Based Lightweight Self-Attention Multiscale Net for Thin Cloud Removal
Recently, deep learning based thin cloud removal methods have led to remarkable results. However, these deep learning models often have intricate structures, numerous parameters, and entail substantial training costs, rendering them impractical for widespread implementation in real-world applications. To overcome these challenges, a light-weight network for thin cloud removal, called PM-LSMN(a Physical-Model-based Lightweight Self-attention Multiscale convolution Network), was proposed in this letter. The LSMN module integrates spatial attention mechanism, channel attention mechanism, and multi-scale convolution net. This enhances the network’s ability to capture the distribution of thin clouds in the cloudy images. Base on the physical model of clouds in optical remote sensing images, the network performs element addition operations between the thin cloud distribution images and cloudy images to generate the final cloud-free image. To ensure color consistency in the reconstructed image, a color loss is incorporated into the design of the loss function. On the RICE1 datasets, the proposed method achieves satisfactory results with 25.90 dB in PSNR, 0.93 in SSIM, 4.115 in SAM, and 0.400 in ERGAS. Additionally, the network accomplishes this with a more efficient parameter with 0.33M in Params and computational footprint with 96.2M in FLOPs. The code is available at https://github.com/xizimi/PM-LSMN.git.
- 21 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 21 (1545598X) , 1-5
PM-LSMN: A Physical-Model-Based Lightweight Self-Attention Multiscale Net for Thin Cloud Removal
Recently, deep learning based thin cloud removal methods have led to remarkable results. However, these deep learning models often have intricate structures, numerous parameters, and entail substantial training costs, rendering them impractical for widespread implementation in real-world applications. To overcome these challenges, a light-weight network for thin cloud removal, called PM-LSMN(a Physical-Model-based Lightweight Self-attention Multiscale convolution Network), was proposed in this letter. The LSMN module integrates spatial attention mechanism, channel attention mechanism, and multi-scale convolution net. This enhances the network’s ability to capture the distribution of thin clouds in the cloudy images. Base on the physical model of clouds in optical remote sensing images, the network performs element addition operations between the thin cloud distribution images and cloudy images to generate the final cloud-free image. To ensure color consistency in the reconstructed image, a color loss is incorporated into the design of the loss function. On the RICE1 datasets, the proposed method achieves satisfactory results with 25.90 dB in PSNR, 0.93 in SSIM, 4.115 in SAM, and 0.400 in ERGAS. Additionally, the network accomplishes this with a more efficient parameter with 0.33M in Params and computational footprint with 96.2M in FLOPs. The code is available at https://github.com/xizimi/PM-LSMN.git.
- Open Access
- 22 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 396-402
Cloud detection in cloud-snow co-occurrence remote Sensing Images based on convolutional neural network
Cloud detection is an important step in remote sensing image preprocessing. With the development of technology, many cloud detection methods have been proposed. In high altitude areas, cloud and snow often exist at the same time. At present, most cloud detection methods in cloud-snow coexistence areas are for low-resolution remote sensing images and the accuracy is not high enough. In order to solve this problem, this paper proposes a cloud detection convolutional neural network (DFBnet) specifically for cloud-snow coexistence areas. DFBnet includes Feature Pyramid module (FBMR) and attention Feature fusion module (SCBR). The existence of the above modules makes the network constructed in this paper better obtain the multi-scale information of the cloud and integrate it, so that the network constructed in this paper has better performance. In this paper, the DFBnet network is trained and tested on the CloudS26 dataset composed of 26 WorldView02 remote sensing images. The results show that the proposed DFBnet can show good performance on the CloudS26 dataset, and can play a role in cloud detection in areas where clouds and snow coexist.
- 22 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 396-402
Open AccessCloud detection in cloud-snow co-occurrence remote Sensing Images based on convolutional neural network
Cloud detection is an important step in remote sensing image preprocessing. With the development of technology, many cloud detection methods have been proposed. In high altitude areas, cloud and snow often exist at the same time. At present, most cloud detection methods in cloud-snow coexistence areas are for low-resolution remote sensing images and the accuracy is not high enough. In order to solve this problem, this paper proposes a cloud detection convolutional neural network (DFBnet) specifically for cloud-snow coexistence areas. DFBnet includes Feature Pyramid module (FBMR) and attention Feature fusion module (SCBR). The existence of the above modules makes the network constructed in this paper better obtain the multi-scale information of the cloud and integrate it, so that the network constructed in this paper has better performance. In this paper, the DFBnet network is trained and tested on the CloudS26 dataset composed of 26 WorldView02 remote sensing images. The results show that the proposed DFBnet can show good performance on the CloudS26 dataset, and can play a role in cloud detection in areas where clouds and snow coexist.
- Open Access
- 21 July 2023
- Published by Association for Computing Machinery (ACM)
- p. 53-60
Diagnosis of Thyroid Nodule Based on Multi-Scale Se-Segnet and Resnet50
Thyroid nodule is a common chronic endocrine system disease, which may deteriorate into thyroid cancer without treatment. However, due to the distribution of many blood vessels, nerves and organs near the thyroid, the clarity of ultrasonic image is poor, and human eye recognition has great limitations.We propose a method for thyroid nodule diagnosis based on multi-scale Se-SegNet network and ResNet50. We improved and optimized the SegNet as the main backbone, and constructed a multi-scale Se-SegNet network to segment thyroid ultrasonography. Then we used ResNet50 to classify the segmented images and get the diagnosis results. The accuracy of the multi-scale Se-SegNet image segmentation model is 0.959.The accuracy of classification results was 0.967. This paper proposes a new diagnostic scheme for thyroid nodule, which can diagnose thyroid nodule quickly and accurately. The experimental results show that it has higher diagnostic accuracy than the traditional scheme..
- 21 July 2023
- Published by Association for Computing Machinery (ACM)
- p. 53-60
Open AccessDiagnosis of Thyroid Nodule Based on Multi-Scale Se-Segnet and Resnet50
Thyroid nodule is a common chronic endocrine system disease, which may deteriorate into thyroid cancer without treatment. However, due to the distribution of many blood vessels, nerves and organs near the thyroid, the clarity of ultrasonic image is poor, and human eye recognition has great limitations.We propose a method for thyroid nodule diagnosis based on multi-scale Se-SegNet network and ResNet50. We improved and optimized the SegNet as the main backbone, and constructed a multi-scale Se-SegNet network to segment thyroid ultrasonography. Then we used ResNet50 to classify the segmented images and get the diagnosis results. The accuracy of the multi-scale Se-SegNet image segmentation model is 0.959.The accuracy of classification results was 0.967. This paper proposes a new diagnostic scheme for thyroid nodule, which can diagnose thyroid nodule quickly and accurately. The experimental results show that it has higher diagnostic accuracy than the traditional scheme..
- Open Access
- 19 May 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Research on Cloud Detection Methods for Remote Sensing Images Based on Superpixel Segmentation and Multi-feature Fusion
- 19 May 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Open AccessResearch on Cloud Detection Methods for Remote Sensing Images Based on Superpixel Segmentation and Multi-feature Fusion
- Open Access
- 14 May 2020
- Published by MDPI AG in Remote Sensing
- Vol. 12 (10) , 1556
Assimilating SMOS Brightness Temperature for Hydrologic Model Parameters and Soil Moisture Estimation with an Immune Evolutionary Strategy
Hydrological models play an essential role in data assimilation (DA) systems. However, it is a challenging task to acquire the distributed hydrological model parameters that affect the accuracy of the simulations at a grid scale. Remote sensing data provide an ideal observation for DA to estimate parameters and state variables. In this study, a special assimilation scheme was proposed to jointly estimate parameters and soil moisture (SM) by assimilating brightness temperature (TB) from the Soil Moisture and Ocean Salinity (SMOS) mission. Variable infiltration capacity (VIC) hydrological model and L-band microwave emission of the biosphere model (L-MEB) are coupled as model and observation operators, respectively. The scheme combines two stages of estimators, one for the static model parameters and the other for the dynamic state variables. The estimators approximate the posterior probability distribution of an unknown target through sequential Monte Carlo (SMC) sampling. Markov chain Monte Carlo (MCMC) and immune evolution strategy are embedded in both stages to solve particle impoverishment problems. To evaluate the effectiveness of the scheme, the estimated SM sets are compared with in-situ observations and SMOS products in Maqu on the Tibetan Plateau. Specifically, the root mean square error decreased from 0.126 to 0.087 m3m−3 for surface SM, with a slight impact on the root zone. The temporal correlation between DA results and in-situ measurements increased to 0.808 and 0.755 for surface SM (+0.057) and root zone SM (+0.040), respectively. The results demonstrate that assimilating TB has tremendous potential as an approach to improve the estimation of distributed model parameters and SMs of surface and root zone at a grid scale, and the immune evolution strategy is effective for increasing the accuracy of approximation in sampling.
- 14 May 2020
- Published by MDPI AG in Remote Sensing
- Vol. 12 (10) , 1556
Open AccessAssimilating SMOS Brightness Temperature for Hydrologic Model Parameters and Soil Moisture Estimation with an Immune Evolutionary Strategy
Hydrological models play an essential role in data assimilation (DA) systems. However, it is a challenging task to acquire the distributed hydrological model parameters that affect the accuracy of the simulations at a grid scale. Remote sensing data provide an ideal observation for DA to estimate parameters and state variables. In this study, a special assimilation scheme was proposed to jointly estimate parameters and soil moisture (SM) by assimilating brightness temperature (TB) from the Soil Moisture and Ocean Salinity (SMOS) mission. Variable infiltration capacity (VIC) hydrological model and L-band microwave emission of the biosphere model (L-MEB) are coupled as model and observation operators, respectively. The scheme combines two stages of estimators, one for the static model parameters and the other for the dynamic state variables. The estimators approximate the posterior probability distribution of an unknown target through sequential Monte Carlo (SMC) sampling. Markov chain Monte Carlo (MCMC) and immune evolution strategy are embedded in both stages to solve particle impoverishment problems. To evaluate the effectiveness of the scheme, the estimated SM sets are compared with in-situ observations and SMOS products in Maqu on the Tibetan Plateau. Specifically, the root mean square error decreased from 0.126 to 0.087 m3m−3 for surface SM, with a slight impact on the root zone. The temporal correlation between DA results and in-situ measurements increased to 0.808 and 0.755 for surface SM (+0.057) and root zone SM (+0.040), respectively. The results demonstrate that assimilating TB has tremendous potential as an approach to improve the estimation of distributed model parameters and SMs of surface and root zone at a grid scale, and the immune evolution strategy is effective for increasing the accuracy of approximation in sampling.
- Open Access
Immune Evolution Particle Filter for Soil Moisture Data Assimilation
Data assimilation (DA) has been widely used in land surface models (LSM) to improve model state estimates. Among various DA methods, the particle filter (PF) with Markov chain Monte Carlo (MCMC) has become increasingly popular for estimating the states of the nonlinear and non-Gaussian LSMs. However, the standard PF always suffers from the particle impoverishment problem, characterized by loss of particle diversity. To solve this problem, an immune evolution particle filter with MCMC simulation inspired by the biological immune system, entitled IEPFM, is proposed for DA in this paper. The merit of this approach is in imitating the antibody diversity preservation mechanism to further improve particle diversity, thus increasing the accuracy of estimates. Furthermore, the immune memory function refers to promise particle evolution process towards optimal estimates. Effectiveness of the proposed approach is demonstrated by the numerical simulation experiment using a highly nonlinear atmospheric model. Finally, IEPFM is applied to a soil moisture (SM) assimilation experiment, which assimilates in situ observations into the Variable Infiltration Capacity (VIC) model to estimate SM in the MaQu network region of the Tibetan Plateau. Both synthetic and real case experiments demonstrate that IEPFM mitigates particle impoverishment and provides more accurate assimilation results compared with other popular DA algorithms.
Open AccessImmune Evolution Particle Filter for Soil Moisture Data Assimilation
Data assimilation (DA) has been widely used in land surface models (LSM) to improve model state estimates. Among various DA methods, the particle filter (PF) with Markov chain Monte Carlo (MCMC) has become increasingly popular for estimating the states of the nonlinear and non-Gaussian LSMs. However, the standard PF always suffers from the particle impoverishment problem, characterized by loss of particle diversity. To solve this problem, an immune evolution particle filter with MCMC simulation inspired by the biological immune system, entitled IEPFM, is proposed for DA in this paper. The merit of this approach is in imitating the antibody diversity preservation mechanism to further improve particle diversity, thus increasing the accuracy of estimates. Furthermore, the immune memory function refers to promise particle evolution process towards optimal estimates. Effectiveness of the proposed approach is demonstrated by the numerical simulation experiment using a highly nonlinear atmospheric model. Finally, IEPFM is applied to a soil moisture (SM) assimilation experiment, which assimilates in situ observations into the Variable Infiltration Capacity (VIC) model to estimate SM in the MaQu network region of the Tibetan Plateau. Both synthetic and real case experiments demonstrate that IEPFM mitigates particle impoverishment and provides more accurate assimilation results compared with other popular DA algorithms.