Qi Li

Dr. Qi Li


Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 June 2024 in Sensors
Verified
Journal Article
Open access
PDF file
FXFan Xiangsuo
Fan Xiangsuo
DXDachuan Xiao
Dachuan Xiao
QLQi Li
Qi Li
GRGong Rui
Gong Rui
Although existing 3D object-detection methods have achieved promising results on conventional datasets, it is still challenging to detect objects in data collected under adverse weather conditions. Data distortion from LiDAR and cameras in such conditions leads to poor performance of traditional single-sensor detection methods. Multi-modal data-fusion methods struggle with data distortion and low alignment accuracy, making accurate target detection difficult. To address this, we propose a multi-modal object-detection algorithm, Snow-CLOCs, specifically for snowy conditions. In image detection, we improved the YOLOv5 algorithm by integrating the InceptionNeXt network to enhance feature extraction and using the Wise-IoU algorithm to reduce dependency on high-quality data. For LiDAR point-cloud detection, we built upon the SECOND algorithm and employed the DROR filter to remove noise, enhancing detection accuracy. We combined the detection results from the camera and LiDAR into a unified detection set, represented using a sparse tensor, and extracted features through a 2D convolutional neural network to achieve object detection and localization. Snow-CLOCs achieved a detection accuracy of 86.61% for vehicle detection in snowy conditions.

14 October 2024 in Electronics
Verified
Journal Article
Open access
PDF file
XLXuyang Li
Xuyang Li
FXFan Xiangsuo
Fan Xiangsuo
QLQi Li
Qi Li
XZXueqiang Zhao
Xueqiang Zhao
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.

23 August 2023 in Atmosphere
Verified
Journal Article
Open access
PDF file
QLQi Li
Qi Li
BMBESSAFI MILOUD
BESSAFI MILOUD
PLPeng Li
Peng Li
This paper presents a novel mapping prediction method for surface solar radiation with linear regression models. The dataset for surface solar radiation prediction is the daily surface incoming shortwave radiation (SIS) product from CM SAF SARAH-E. The spatial resolution is 0.05° × 0.05° and the temporal coverage is from 2007 to 2016. The first five years (2007–2011) are used as training data, and the remaining five years (2012–2016) are used as test data in the prediction model. Datasets were detrended, de-seasonalized, and normalized before being applied to multiple linear regression (MLR), principal component regression (PCR), stepwise regression (SR), and partial least squares regression (PLSR), which are used to perform prediction mapping. The statistical analysis using MAE, MSE, and RMSE shows that the PCR model had the smallest MAE, MSE, and RMSE as compared to the other three models. The PCR model seems better for SSR mapping prediction over Reunion Island. Although the PCR model provides better prediction results, its MAE, MSE, and RMSE are quite large.

19 October 2024 in Forests
Verified
Journal Article
Open access
PDF file
XLXuyang Li
Xuyang Li
FXFan Xiangsuo
Fan Xiangsuo
JFJinlong Fan
Jinlong Fan
QLQi Li
Qi Li
YGYuan Gao
Yuan Gao
XZXueqiang Zhao
Xueqiang Zhao
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.

11 September 2025 in Remote Sensing
Verified
Journal Article
Open access
PDF file
YMYong Mei
Yong Mei
JFJinlong Fan
Jinlong Fan
FXFan Xiangsuo
Fan Xiangsuo
QLQi Li
Qi Li
Convolutional neural networks have made significant progress in multimodal remote sensing image classification, but traditional convolutional neural networks are limited by fixed-size convolutional kernels, which are unable to effectively model and adequately extract contextual information; hyperspectral imagery and LiDAR data have comparatively large information differences, which do not allow for effective information interaction and fusion. Based on this, this paper proposes a multimodal dual fusion network (CSTC) based on the Vision Transformer for the collaborative classification of HSI and LiDAR data. The model is designed through a two-branch architecture: the HSI branch extracts spectral–spatial features by dimensionality reduction using principal component analysis and inputs them into the cross-connectivity feature fusion module; the LiDAR branch mines spatial elevation features through the stacked MobileNetV2 module. The features of the two branches are encoded by a Transformer, and the modal interaction fusion is realized by the cross-attention module for the first time. Then, the features are spliced and input into the secondary Transformer for deep cross-modal fusion, and finally, the classification is completed by the multilayer perceptron. Experiments show that the CSTC model achieves overall classification accuracies of 92.32%, 99.81%, 97.90%, and 99.37% on the publicly available MUUFL dataset, Trento dataset, Augsburg dataset, and Houston2013 dataset, respectively, which is superior to the latest HSI–LiDAR separate classification algorithms. The ablation experiments and model performance evaluation experiments further show that the proposed CSTC model achieves excellent results in terms of robustness, adaptability, and parameter scale.

5 July 2024 in IEEE Access
Verified
Journal Article
Open access
HMHaotian Ming
Haotian Ming
QLQi Li
Qi Li
HXHaibo Xia
Haibo Xia
PLPeng Li
Peng Li
With the development of stereo vision technology, the cost of 3D model reconstruction is gradually reduced. Compared with traditional aerial triangulation camera pose and parameter estimation methods, Structure from Motion (SFM) is more suitable for simplified recording and fine structure modelling due to its fully automated process. COLMAP and OpenMVG incremental SFM are used to perform sparse reconstruction of mobile phone and UAV images to obtain camera parameters, and different MVS methods are used for dense reconstruction. Finally, realistic and fine 3D models are generated. The experimental results show that the 3D models generated by different methods have differences in various parameters. COLMAP has low reprojection error and root mean square error in the SFM reconstruction process, and the average track length is 4.87487, showing excellent performance in accuracy and efficiency. In contrast, although OpenMVG has a sparser point cloud during SFM, it has higher reprojection error, root mean square error, and lower average track length than COLMAP. In the MVS process, although CMVS-PMVS can generate dense point clouds in a short time, the performance of other data is the worst. The total time of OpenMVG+OpenMVS was 228 minutes, which was 2.5 times that of COLMAP+OpenMVS. The accuracy and completeness of OpenMVG+OpenMVS were 95.6% and 97.2%, which were 2% and 2.6% lower than COLMAP+OpenMVS. In summary, the COLMAP combined with OpenMVS has advantages in terms of time and accuracy and is the preferred scheme for efficient and accurate 3D model reconstruction.