Shenming Qu

Prof. Dr. Shenming Qu


Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

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

Representative Publications

View All Publications
16 September 2021 in PLOS ONE
Verified
Journal Article
Open access
PDF file
SLShengbin Liang
Shengbin Liang
TJTongtong Jiao
Tongtong Jiao
WDWencai Du
Wencai Du
SQShenming Qu
Shenming Qu
To solve the problem of one-sided pursuit of the shortest distance but ignoring the tourist experience in the process of tourism route planning, an improved ant colony optimization algorithm is proposed for tourism route planning. Contextual information of scenic spots significantly effect people’s choice of tourism destination, so the pheromone update strategy is combined with the contextual information such as weather and comfort degree of the scenic spot in the process of searching the global optimal route, so that the pheromone update tends to the path suitable for tourists. At the same time, in order to avoid falling into local optimization, the sub-path support degree is introduced. The experimental results show that the optimized tourism route has greatly improved the tourist experience, the route distance is shortened by 20.5% and the convergence speed is increased by 21.2% compared with the basic algorithm, which proves that the improved algorithm is notably effective.

12 July 2025 in Remote Sensing
Verified
Journal Article
Open access
PDF file
SQShenming Qu
Shenming Qu
CDChaoxu Dang
Chaoxu Dang
WCWangyou Chen
Wangyou Chen
YLYanhong Liu
Yanhong Liu
With special consideration for complex scenes and densely distributed small objects, this frequently leads to serious false and missed detections for unmanned aerial vehicle (UAV) images in small object detection scenarios. Consequently, we propose a UAV image small object detection algorithm, termed SMA-YOLO. Firstly, a parameter-free simple slicing convolution (SSC) module is integrated in the backbone network to slice the feature maps and enhance the features so as to effectively retain the features of small objects. Subsequently, to enhance the information exchange between upper and lower layers, we design a special multi-cross-scale feature pyramid network (M-FPN). The C2f-Hierarchical-Phantom Convolution (C2f-HPC) module in the network effectively reduces information loss by fine-grained multi-scale feature fusion. Ultimately, adaptive spatial feature fusion detection Head (ASFFDHead) introduces an additional P2 detection head to enhance the resolution of feature maps to better locate small objects. Moreover, the ASFF mechanism is employed to optimize the detection process by filtering out information conflicts during multi-scale feature fusion, thereby significantly optimizing small object detection capability. Using YOLOv8n as the baseline, SMA-YOLO is evaluated on the VisDrone2019 dataset, achieving a 7.4% improvement in mAP@0.5 and a 13.3% reduction in model parameters, and we also verified its generalization ability on VAUDT and RSOD datasets, which demonstrates the effectiveness of our approach.

18 April 2022 in Applied Sciences
Verified
Journal Article
Open access
PDF file
SQShenming Qu
Shenming Qu
HZHuafei Zhou
Huafei Zhou
BZBo Zhang
Bo Zhang
SLShengbin Liang
Shengbin Liang
Extracting roads from remote sensing images can support a range of geo-information applications. However, it is challenging due to factors such as the complex distribution of ground objects and occlusion of buildings, trees, shadows, etc. Pixel-wise classification often fails to predict road connectivity and thus produces fragmented road segments. In this paper, we propose a multi-scale strip pooling network (MSPNet) to learn the linear features of roads. Motivated by the strip pooling being more aligned with the shape of roads, which are long-span and narrow, we develop a multi-scale strip pooling (MSP) module that utilizes strip pooling layers with long but narrow kernel shapes to capture multi-scale long-range context from horizontal and vertical directions. The proposed MSP module focuses on establishing relationships along the road region to guarantee the connectivity of roads. Considering the complex distribution of ground objects, the spatial pyramid pooling is applied to enhance the learning ability of complex features in different sub-regions. In addition, to alleviate the problem caused by an imbalanced distribution of road and non-road pixels, we use binary cross-entropy and dice-coefficient loss functions to jointly train our proposed deep learning model. Then, we perform ablation experiments to adjust the loss contributions to suit the task of road extraction. Comparative experiments on a popular benchmark DeepGlobe dataset demonstrate that our proposed MSPNet establishes new competitive results in both IoU and F1-score.

1 August 2023 in Big Data
Verified
Journal Article
Closed access
SLShengbin Liang
Shengbin Liang
JJJiangyong Jin
Jiangyong Jin
JRJia Ren
Jia Ren
WDWencai Du
Wencai Du
SQShenming Qu
Shenming Qu
Tourism recommendation results are affected by many factors. Traditional recommendation methods have problems such as low recommendation accuracy and lack of personalization due to sparse data. This article uses implicit features such as contextual information, time-series travel trajectories, and comment data to address these issues. First, the Long Short-Term Memory (LSTM) network is introduced as the model basis, and deals with the input data of the model such as contextual information, scenic spot information, and tourist comments and so on for feature extraction. Then, the online behavior and long-term interest preference of users are analyzed, using positive feedback and negative feedback mechanism, the Deep Q-Network (DQN) value function of dual-channel mechanism is constructed. Finally, we propose a recommendation strategy, in which, a value evaluation network and a target network are proposed for each agent to learn the optimal strategy. The model is trained on the Yelp, DP, and Tourism datasets covering multiple scenarios to provide users with tourism recommendation services. Compared with baseline models such as Ultra Simplification of Graph Convolutional Networks, DQN, Actor-Critic, and Latent Factor Model, this model has an average increase of 76.61% in accuracy compared with the comparison model, and an average increase of 43.48% in the normalized discounted cumulative gain compared with the baseline model.

11 April 2024 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
XLXuan Liu
Xuan Liu
SLSuchen Liu
Suchen Liu
WCWangyou Chen
Wangyou Chen
SQShenming Qu
Shenming Qu
A hyperspectral image (HSI) classification algorithm that combines graph convolutional networks (GCNs) and convolutional neural networks (CNNs) aims to generate complementary spatial-spectral joint information at the superpixel and pixel levels. However, the CNN part is typically a single 2-D or 3-D network that cannot fully capture the middle or long-range spatial relationships between pixels. Additionally, the GCNs part is commonly under-segmented in the superpixel segmentation process and does not consider the weight between neighboring superpixels when calculating the adjacency matrix. Therefore, this article proposes a multiscale dynamic tuning parameter, where the dual superpixel segmentation GCN strategy joins the enhanced hybrid 3-D–2-D CNN framework to enhance the superpixel and pixel complementary nature. The hybrid enhanced CNN branch uses the groupable convolutions with a mixed spectral stacking and residual nonlocal block at the hybrid convolution output to overcome the accuracy degradation problem caused by long convolutional layers and poor generalization performance of a single network structure. An additional branch performs simple linear iterative clustering and entropy rate superpixel (ERS) segmentation, which are sequentially implemented on the HSI to solve the under-segmentation problem. This strategy is important, as dynamically calculating the tuning parameters for feature segmentation maps increases the number of the multiscale GCN layers and fully extracts contextual spatial information. Experiments on three public datasets, Indian Pines, Kennedy Space Center, and the University of Pavia, demonstrate that the proposed framework achieves the optimal OA, AA, and Kappa coefficients. The source code is available at https://github.com/henulx/HDECGCN-Framework .

19 March 2025 in Remote Sensing
Verified
Journal Article
Open access
PDF file
WCWangyou Chen
Wangyou Chen
SQShenming Qu
Shenming Qu
LLLaigan Luo
Laigan Luo
YLYongyong Lu
Yongyong Lu
In the field of remote sensing, super-resolution methods based on deep learning have made significant progress. However, redundant feature extraction and inefficient feature fusion can, respectively, result in excessive parameters and restrict the precise reconstruction of features, making the model difficult to deploy in practical remote-sensing tasks. To address this issue, we propose a lightweight Dual Attention Fusion Enhancement Network (DAFEN) for remote-sensing image super-resolution. Firstly, we design a lightweight Channel-Spatial Lattice Block (CSLB), which consists of Group Residual Shuffle Blocks (GRSB) and a Channel-Spatial Attention Interaction Module (CSAIM). The GRSB improves the efficiency of redundant convolution operations, while the CSAIM enhances interactive learning. Secondly, to achieve superior feature fusion and enhancement, we design a Forward Fusion Enhancement Module (FFEM). Through the forward fusion strategy, more high-level feature details are retained for better adaptation to remote-sensing tasks. In addition, the fused features are further refined and rescaled by Self-Calibrated Group Convolution (SCGC) and Contrast-aware Channel Attention (CCA), respectively. Extensive experiments demonstrate that DAFEN achieves better or comparable performance compared with state-of-the-art lightweight super-resolution models while reducing complexity by approximately 10∼48%.