Xueqiang Zhao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xueqiang Zhao has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Qi Li
School of Civil Engineering and Architecture, Guangxi University of Science and Technology, Liuzhou 545006, China
3 shared publications - Xiangsuo Fan
School of Automation, Guangxi University of Science and Technology, Liuzhou 545006, China
3 shared publications - Yangbo Chen
School of Geography and Planning, Sun Yat-sen University, Guangzhou 510275, China
3 shared publications - Xuyang Li
School of Automation, Guangxi University of Science and Technology, Liuzhou, China
2 shared publications Fengmiao Tu
School of Mechatronic Engineering, Southwest Petroleum University, Chengdu, 610500, China
1 shared publication- Huaizhang Sun
School of Geography and Planning, Sun Yat-sen University, Guangzhou 510275, China
1 shared publication
Latest Publications
- Open Access
YOLO-DroneMS: Multi-Scale Object Detection Network for Unmanned Aerial Vehicle (UAV) Images
In recent years, research on Unmanned Aerial Vehicles (UAVs) has developed rapidly. Compared to traditional remote-sensing images, UAV images exhibit complex backgrounds, high resolution, and large differences in object scales. Therefore, UAV object detection is an essential yet challenging task. This paper proposes a multi-scale object detection network, namely YOLO-DroneMS (You Only Look Once for Drone Multi-Scale Object), for UAV images. Targeting the pivotal connection between the backbone and neck, the Large Separable Kernel Attention (LSKA) mechanism is adopted with the Spatial Pyramid Pooling Factor (SPPF), where weighted processing of multi-scale feature maps is performed to focus more on features. And Attentional Scale Sequence Fusion DySample (ASF-DySample) is introduced to perform attention scale sequence fusion and dynamic upsampling to conserve resources. Then, the faster cross-stage partial network bottleneck with two convolutions (named C2f) in the backbone is optimized using the Inverted Residual Mobile Block and Dilated Reparam Block (iRMB-DRB), which balances the advantages of dynamic global modeling and static local information fusion. This optimization effectively increases the model’s receptive field, enhancing its capability for downstream tasks. By replacing the original CIoU with WIoUv3, the model prioritizes anchoring boxes of superior quality, dynamically adjusting weights to enhance detection performance for small objects. Experimental findings on the VisDrone2019 dataset demonstrate that at an Intersection over Union (IoU) of 0.5, YOLO-DroneMS achieves a 3.6% increase in mAP@50 compared to the YOLOv8n model. Moreover, YOLO-DroneMS exhibits improved detection speed, increasing the number of frames per second (FPS) from 78.7 to 83.3. The enhanced model supports diverse target scales and achieves high recognition rates, making it well-suited for drone-based object detection tasks, particularly in scenarios involving multiple object clusters.
Open AccessYOLO-DroneMS: Multi-Scale Object Detection Network for Unmanned Aerial Vehicle (UAV) Images
In recent years, research on Unmanned Aerial Vehicles (UAVs) has developed rapidly. Compared to traditional remote-sensing images, UAV images exhibit complex backgrounds, high resolution, and large differences in object scales. Therefore, UAV object detection is an essential yet challenging task. This paper proposes a multi-scale object detection network, namely YOLO-DroneMS (You Only Look Once for Drone Multi-Scale Object), for UAV images. Targeting the pivotal connection between the backbone and neck, the Large Separable Kernel Attention (LSKA) mechanism is adopted with the Spatial Pyramid Pooling Factor (SPPF), where weighted processing of multi-scale feature maps is performed to focus more on features. And Attentional Scale Sequence Fusion DySample (ASF-DySample) is introduced to perform attention scale sequence fusion and dynamic upsampling to conserve resources. Then, the faster cross-stage partial network bottleneck with two convolutions (named C2f) in the backbone is optimized using the Inverted Residual Mobile Block and Dilated Reparam Block (iRMB-DRB), which balances the advantages of dynamic global modeling and static local information fusion. This optimization effectively increases the model’s receptive field, enhancing its capability for downstream tasks. By replacing the original CIoU with WIoUv3, the model prioritizes anchoring boxes of superior quality, dynamically adjusting weights to enhance detection performance for small objects. Experimental findings on the VisDrone2019 dataset demonstrate that at an Intersection over Union (IoU) of 0.5, YOLO-DroneMS achieves a 3.6% increase in mAP@50 compared to the YOLOv8n model. Moreover, YOLO-DroneMS exhibits improved detection speed, increasing the number of frames per second (FPS) from 78.7 to 83.3. The enhanced model supports diverse target scales and achieves high recognition rates, making it well-suited for drone-based object detection tasks, particularly in scenarios involving multiple object clusters.
- Open Access
DASR-Net: Land Cover Classification Methods for Hybrid Multiattention Multispectral High Spectral Resolution Remote Sensing Imagery
The prompt acquisition of precise land cover categorization data is indispensable for the strategic development of contemporary farming practices, especially within the realm of forestry oversight and preservation. Forests are complex ecosystems that require precise monitoring to assess their health, biodiversity, and response to environmental changes. The existing methods for classifying remotely sensed imagery often encounter challenges due to the intricate spacing of feature classes, intraclass diversity, and interclass similarity, which can lead to weak perceptual ability, insufficient feature expression, and a lack of distinction when classifying forested areas at various scales. In this study, we introduce the DASR-Net algorithm, which integrates a dual attention network (DAN) in parallel with the Residual Network (ResNet) to enhance land cover classification, specifically focusing on improving the classification of forested regions. The dual attention mechanism within DASR-Net is designed to address the complexities inherent in forested landscapes by effectively capturing multiscale semantic information. This is achieved through multiscale null attention, which allows for the detailed examination of forest structures across different scales, and channel attention, which assigns weights to each channel to enhance feature expression using an improved BSE-ResNet bilinear approach. The two-channel parallel architecture of DASR-Net is particularly adept at resolving structural differences within forested areas, thereby avoiding information loss and the excessive fusion of features that can occur with traditional methods. This results in a more discriminative classification of remote sensing imagery, which is essential for accurate forest monitoring and management. To assess the efficacy of DASR-Net, we carried out tests with 10m Sentinel-2 multispectral remote sensing images over the Heshan District, which is renowned for its varied forestry. The findings reveal that the DASR-Net algorithm attains an accuracy rate of 96.36%, outperforming classical neural network models and the transformer (ViT) model. This demonstrates the scientific robustness and promise of the DASR-Net model in assisting with automatic object recognition for precise forest classification. Furthermore, we emphasize the relevance of our proposed model to hyperspectral datasets, which are frequently utilized in agricultural and forest classification tasks. DASR-Net’s enhanced feature extraction and classification capabilities are particularly advantageous for hyperspectral data, where the rich spectral information can be effectively harnessed to differentiate between various forest types and conditions. By doing so, DASR-Net contributes to advancing remote sensing applications in forest monitoring, supporting sustainable forestry practices and environmental conservation efforts. The findings of this study have significant practical implications for urban forestry management. The DASR-Net algorithm can enhance the accuracy of forest cover classification, aiding urban planners in better understanding and monitoring the status of urban forests. This, in turn, facilitates the development of effective forest conservation and restoration strategies, promoting the sustainable development of the urban ecological environment.
Open AccessDASR-Net: Land Cover Classification Methods for Hybrid Multiattention Multispectral High Spectral Resolution Remote Sensing Imagery
The prompt acquisition of precise land cover categorization data is indispensable for the strategic development of contemporary farming practices, especially within the realm of forestry oversight and preservation. Forests are complex ecosystems that require precise monitoring to assess their health, biodiversity, and response to environmental changes. The existing methods for classifying remotely sensed imagery often encounter challenges due to the intricate spacing of feature classes, intraclass diversity, and interclass similarity, which can lead to weak perceptual ability, insufficient feature expression, and a lack of distinction when classifying forested areas at various scales. In this study, we introduce the DASR-Net algorithm, which integrates a dual attention network (DAN) in parallel with the Residual Network (ResNet) to enhance land cover classification, specifically focusing on improving the classification of forested regions. The dual attention mechanism within DASR-Net is designed to address the complexities inherent in forested landscapes by effectively capturing multiscale semantic information. This is achieved through multiscale null attention, which allows for the detailed examination of forest structures across different scales, and channel attention, which assigns weights to each channel to enhance feature expression using an improved BSE-ResNet bilinear approach. The two-channel parallel architecture of DASR-Net is particularly adept at resolving structural differences within forested areas, thereby avoiding information loss and the excessive fusion of features that can occur with traditional methods. This results in a more discriminative classification of remote sensing imagery, which is essential for accurate forest monitoring and management. To assess the efficacy of DASR-Net, we carried out tests with 10m Sentinel-2 multispectral remote sensing images over the Heshan District, which is renowned for its varied forestry. The findings reveal that the DASR-Net algorithm attains an accuracy rate of 96.36%, outperforming classical neural network models and the transformer (ViT) model. This demonstrates the scientific robustness and promise of the DASR-Net model in assisting with automatic object recognition for precise forest classification. Furthermore, we emphasize the relevance of our proposed model to hyperspectral datasets, which are frequently utilized in agricultural and forest classification tasks. DASR-Net’s enhanced feature extraction and classification capabilities are particularly advantageous for hyperspectral data, where the rich spectral information can be effectively harnessed to differentiate between various forest types and conditions. By doing so, DASR-Net contributes to advancing remote sensing applications in forest monitoring, supporting sustainable forestry practices and environmental conservation efforts. The findings of this study have significant practical implications for urban forestry management. The DASR-Net algorithm can enhance the accuracy of forest cover classification, aiding urban planners in better understanding and monitoring the status of urban forests. This, in turn, facilitates the development of effective forest conservation and restoration strategies, promoting the sustainable development of the urban ecological environment.
- Open Access
- 14 October 2024
- Published by MDPI AG in Electronics
- Vol. 13 (20) , 4046
RS-Net: Hyperspectral Image Land Cover Classification Based on Spectral Imager Combined with Random Forest Algorithm
Recursive neural networks and transformers have recently become dominant in hyperspectral (HS) image classification due to their ability to capture long-range dependencies in spectral sequences. Despite the success of these sequential architectures, mainstream deep learning methods primarily handle two-dimensional structured data. However, challenges such as the curse of dimensionality, spectral variability, and confounding factors in hyperspectral remote sensing images limit their effectiveness, especially in remote sensing applications. To address this issue, this paper proposes a novel land cover classification algorithm that integrates random forests with a spectral transformer network structure (RS-Net). Firstly, this paper presents a combination of the Gramian Angular Field (GASF) and Gramian Angular Difference Field (GADF) algorithms, which effectively maps the multidimensional time series constructed for each pixel onto two-dimensional image features, enabling precise extraction and recognition in the backend network algorithms and improving the classification accuracy of land cover types. Secondly, to capture the relationships between features at different scales, this paper proposes a SpectralFormer network architecture using the Context and Structure Encoding (CASE) module to effectively learn dependencies between channels. This architecture enhances important features and suppresses unimportant ones, thereby addressing the semantic gap and improving the recognition capability of land cover features. Finally, the final prediction results are determined by a voting mechanism from the Random Forest algorithm, which synthesizes predictions from multiple decision trees to enhance classification stability and accuracy. To better compare the performance of RS-Net, this paper conducted extensive experiments on three benchmark HS datasets obtained from satellite and airborne imagers, comparing various classic neural network models. Surprisingly, the RS-Net algorithm achieves high performance and efficiency, offering a new and effective tool for land cover classification.
- 14 October 2024
- Published by MDPI AG in Electronics
- Vol. 13 (20) , 4046
Open AccessRS-Net: Hyperspectral Image Land Cover Classification Based on Spectral Imager Combined with Random Forest Algorithm
Recursive neural networks and transformers have recently become dominant in hyperspectral (HS) image classification due to their ability to capture long-range dependencies in spectral sequences. Despite the success of these sequential architectures, mainstream deep learning methods primarily handle two-dimensional structured data. However, challenges such as the curse of dimensionality, spectral variability, and confounding factors in hyperspectral remote sensing images limit their effectiveness, especially in remote sensing applications. To address this issue, this paper proposes a novel land cover classification algorithm that integrates random forests with a spectral transformer network structure (RS-Net). Firstly, this paper presents a combination of the Gramian Angular Field (GASF) and Gramian Angular Difference Field (GADF) algorithms, which effectively maps the multidimensional time series constructed for each pixel onto two-dimensional image features, enabling precise extraction and recognition in the backend network algorithms and improving the classification accuracy of land cover types. Secondly, to capture the relationships between features at different scales, this paper proposes a SpectralFormer network architecture using the Context and Structure Encoding (CASE) module to effectively learn dependencies between channels. This architecture enhances important features and suppresses unimportant ones, thereby addressing the semantic gap and improving the recognition capability of land cover features. Finally, the final prediction results are determined by a voting mechanism from the Random Forest algorithm, which synthesizes predictions from multiple decision trees to enhance classification stability and accuracy. To better compare the performance of RS-Net, this paper conducted extensive experiments on three benchmark HS datasets obtained from satellite and airborne imagers, comparing various classic neural network models. Surprisingly, the RS-Net algorithm achieves high performance and efficiency, offering a new and effective tool for land cover classification.
- Open Access
- 2 October 2024
- Published by MDPI AG in Applied Sciences
- Vol. 14 (19) , 8904
Monitoring of Vegetation Drought Index in Laibin City Based on Landsat Multispectral Remote Sensing Data
Due to the impact of global warming, drought has caused serious damage to China’s ecological environment and social status. This article selects Laibin City in the Guangxi Zhuang Autonomous Region as the research area, utilizing multispectral remote sensing data as the data source and Landsat series image data for relevant preprocessing. It calculates the monthly normalized vegetation index (NDVI) and surface temperature (LST) data for Laibin City. Based on the ecological environment and surface coverage conditions of the research area, the ratio vegetation index (RVI), normalized vegetation moisture index (NDWI), temperature vegetation drought index (TVDI), and conditional vegetation temperature drought index (VTCI) were selected to calculate and invert the drought monitoring results of Laibin City. The drought monitoring results were obtained and overlaid with the vegetation area map to generate the vegetation drought monitoring results of Laibin City. Based on the climate, geography, and ecological characteristics of the monitored area in Laibin City, a specific analysis will be conducted to develop an appropriate TVDI index drought level, and generate vegetation drought level result maps for Laibin City in 2021, 2022, and 2023. Then, a detailed analysis of the vegetation drought situation in Laibin City is conducted according to time and space. Among them, in the past three years, the vegetation areas in Laibin City have experienced drought seasons mostly in summer and autumn. The interannual drought is mainly mild drought, and the proportion of areas with mild drought shows a relatively stable trend. In conclusion, TVDI proves to be a valuable tool for monitoring vegetation drought in Laibin City, offering insights for efficient water resource management strategies.
- 2 October 2024
- Published by MDPI AG in Applied Sciences
- Vol. 14 (19) , 8904
Open AccessMonitoring of Vegetation Drought Index in Laibin City Based on Landsat Multispectral Remote Sensing Data
Due to the impact of global warming, drought has caused serious damage to China’s ecological environment and social status. This article selects Laibin City in the Guangxi Zhuang Autonomous Region as the research area, utilizing multispectral remote sensing data as the data source and Landsat series image data for relevant preprocessing. It calculates the monthly normalized vegetation index (NDVI) and surface temperature (LST) data for Laibin City. Based on the ecological environment and surface coverage conditions of the research area, the ratio vegetation index (RVI), normalized vegetation moisture index (NDWI), temperature vegetation drought index (TVDI), and conditional vegetation temperature drought index (VTCI) were selected to calculate and invert the drought monitoring results of Laibin City. The drought monitoring results were obtained and overlaid with the vegetation area map to generate the vegetation drought monitoring results of Laibin City. Based on the climate, geography, and ecological characteristics of the monitored area in Laibin City, a specific analysis will be conducted to develop an appropriate TVDI index drought level, and generate vegetation drought level result maps for Laibin City in 2021, 2022, and 2023. Then, a detailed analysis of the vegetation drought situation in Laibin City is conducted according to time and space. Among them, in the past three years, the vegetation areas in Laibin City have experienced drought seasons mostly in summer and autumn. The interannual drought is mainly mild drought, and the proportion of areas with mild drought shows a relatively stable trend. In conclusion, TVDI proves to be a valuable tool for monitoring vegetation drought in Laibin City, offering insights for efficient water resource management strategies.
- Open Access
- 28 September 2024
- Published by MDPI AG in Remote Sensing
- Vol. 16 (19) , 3620
Fine-Grained High-Resolution Remote Sensing Image Change Detection by SAM-UNet Change Detection Model
Remote sensing image change detection is crucial for urban planning, environmental monitoring, and disaster assessment, as it identifies temporal variations of specific targets, such as surface buildings, by analyzing differences between images from different time periods. Current research faces challenges, including the accurate extraction of change features and the handling of complex and varied image contexts. To address these issues, this study proposes an innovative model named the Segment Anything Model-UNet Change Detection Model (SCDM), which incorporates the proposed center expansion and reduction method (CERM), Segment Anything Model (SAM), UNet, and fine-grained loss function. The global feature map of the environment is extracted, the difference measurement features are extracted, and then the global feature map and the difference measurement features are fused. Finally, a global decoder is constructed to predict the changes of the same region in different periods. Detailed ablation experiments and comparative experiments are conducted on the WHU-CD and LEVIR-CD public datasets to evaluate the performance of the proposed method. At the same time, validation on more complex DTX datasets for scenarios is supplemented. The experimental results demonstrate that compared to traditional fixed-size partitioning methods, the CERM proposed in this study significantly improves the accuracy of SOTA models, including ChangeFormer, ChangerEx, Tiny-CD, BIT, DTCDSCN, and STANet. Additionally, compared with other methods, the SCDM demonstrates superior performance and generalization, showcasing its effectiveness in overcoming the limitations of existing methods.
- 28 September 2024
- Published by MDPI AG in Remote Sensing
- Vol. 16 (19) , 3620
Open AccessFine-Grained High-Resolution Remote Sensing Image Change Detection by SAM-UNet Change Detection Model
Remote sensing image change detection is crucial for urban planning, environmental monitoring, and disaster assessment, as it identifies temporal variations of specific targets, such as surface buildings, by analyzing differences between images from different time periods. Current research faces challenges, including the accurate extraction of change features and the handling of complex and varied image contexts. To address these issues, this study proposes an innovative model named the Segment Anything Model-UNet Change Detection Model (SCDM), which incorporates the proposed center expansion and reduction method (CERM), Segment Anything Model (SAM), UNet, and fine-grained loss function. The global feature map of the environment is extracted, the difference measurement features are extracted, and then the global feature map and the difference measurement features are fused. Finally, a global decoder is constructed to predict the changes of the same region in different periods. Detailed ablation experiments and comparative experiments are conducted on the WHU-CD and LEVIR-CD public datasets to evaluate the performance of the proposed method. At the same time, validation on more complex DTX datasets for scenarios is supplemented. The experimental results demonstrate that compared to traditional fixed-size partitioning methods, the CERM proposed in this study significantly improves the accuracy of SOTA models, including ChangeFormer, ChangerEx, Tiny-CD, BIT, DTCDSCN, and STANet. Additionally, compared with other methods, the SCDM demonstrates superior performance and generalization, showcasing its effectiveness in overcoming the limitations of existing methods.
- 19 May 2023
- Published by Elsevier in Journal of Environmental Management
- Vol. 342, 118125
An integrated model chain for future flood risk prediction under land-use changes
- 19 May 2023
- Published by Elsevier in Journal of Environmental Management
- Vol. 342, 118125
An integrated model chain for future flood risk prediction under land-use changes