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


Nan Mo has a total of 11 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    SAM3TGNet: A SAM3 Feature Encoding and Global Context Spatiotemporal Attention-Enhanced Change Detection Method for Optical Remote Sensing Images

    by Jiayin Zhang, Nan Mo, Gege Ma, Bangyan Tang

    Change detection in high-resolution optical remote sensing images is essential for dynamic surface monitoring and land resource management. However, existing methods still face challenges in representing multiscale change information, accurately locating change boundaries, and handling the imbalance between changed and unchanged samples. This study proposes SAM3TGNet, which transforms the general visual features of Segment Anything Model 3 (SAM3) into change-oriented representations through lightweight channel adaptation, multiscale cross-temporal interaction, and spatiotemporal feature fusion, while the Global Context Spatial Attention (GCSA) module and dynamic weighted loss enhance boundary representation and alleviate class imbalance, respectively. First, a SAM3-based bi-temporal remote sensing image feature encoder with channel adapters is developed, where intermediate multiscale feature layers are exploited to enhance semantic representation and generalization for diverse change patterns. Second, the GCSA module is introduced after spatiotemporal feature fusion to model global dependencies and enhance local details, improving boundary localization accuracy. Third, a dynamic weighted change loss function is designed to adaptively adjust the contribution of changed pixels according to their proportion in each batch, reducing background bias caused by sample imbalance and improving change localization and completeness. Experiments on the Wuhan University Change Detection (WHU-CD) and Sun Yat-sen University Change Detection (SYSU-CD) datasets demonstrate that the proposed method achieves F1-scores of 94.08 ± 0.12% and 82.91 ± 0.20%, respectively, outperforming existing approaches in multiscale change detection and boundary delineation.


  • Open Access

    A Physics-Guided Multibranch Adaptive Multilevel Attention Fusion Network for Sea Oil-Spill Detection in Sentinel-1 SAR Imagery

    by Jiaxing Tong, Dengfeng Xie, Jinghai Xu, Nan Mo

    Synthetic aperture radar (SAR) has been widely used for oil-spill monitoring because of its all-weather and all-day imaging capability. However, simple concatenation of multiple oil-spill features extracted from SAR images, such as polarization, intensity, texture, and wind speed, often introduces semantic interference and degrades detection performance. Moreover, these existing oil-spill detection methods still have limited ability to deal with the small-scale and fragmented oil spills under complex sea backgrounds and class imbalance. To address these issues, this paper proposes a physics-guided multi-branch adaptive multi-level attention fusion network (MAMAF-Net) based on Swin Transformer and deep convolutional neural network (DCNN). The network includes four independent branches to handle the features with different physical meanings, enabling feature decoupling and adaptive fusion. In addition, several specialized modules, such as edge enhancement module (EEM), multi-level attention fusion module (MAFM), hybrid Focal-Tversky (FT) Loss, and the entropy-weighted hysteresis enhancement (EHE), are incorporated into the network to enhance the feature representation of oil spills during the encoding stage and the precise reconstruction of oil-spill areas during the decoding stage. Comparative experiments conducted on a self-constructed SAR oil-spill datasets demonstrate that the proposed model achieves more complete region extraction and more accurate boundary localization under complex sea conditions, outperforming several mainstream deep-learning networks with the highest mean mIoU of 92.11% and BF1 of 83.56%. Ablation experiments of the modules and branches verify the effectiveness of individual components and the multi-branch collaborative mechanism for oil-spill detection, indicating that the proposed model achieves improved overall performance and enhanced robustness under complex sea conditions. Overall, the proposed MAMAF-Net has strong performance in feature decoupling, boundary recognition, and noise robustness, offering an efficient and reliable solution for marine oil-spill detection.

  • Open Access

    A Novel Transformer-Based Object Detection Method With Geometric and Object Co-Occurrence Prior Knowledge for Remote Sensing Images

    by Nan Mo, Ruixi Zhu

    Artificial target detection is a key technology for Earth observation applications in remote sensing images, including environmental monitoring, urban planning, intelligence reconnaissance, and land mapping. Recently, transformer-based object detectors achieved great success in computer vision through the attention mechanism. However, these detectors lack prior information, which may limit their multi-scale, multi-shape, and densely distributed target detection capabilities. To address these problems, we propose a novel transformer-based object detection method with geometric and object co-occurrence prior knowledge for remote sensing images, which makes improvements based on the deformable detection transformer (DETR). First, we introduce dynamic anchor object queries with multi-patterns to detect objects with multi-scale and dense distribution. Second, we propose a novel distance with geometrical invariance to measure the position deviation of multi-shape objects. Lastly, we design a graph convolutional reference module with co-occurrence prior knowledge to improve the inferential ability of the detector. Experimental results confirm that the proposed method outperforms most of the state-of-the-art methods with mean average precisions (mAP) of 70.2% in the DIOR, 91.0% in the HRRSD datasets and 91.4% in the NWPU VHR-10 dataset, respectively. The mAP values are more than 5% higher compared with those obtained by deformable DETR in above three public datasets. The code will be made available to public at https://github.com/momo91nj/GOCPK .


  • Open Access

    Semi-Supervised Subcategory Centroid Alignment-Based Scene Classification for High-Resolution Remote Sensing Images

    by Nan Mo, Ruixi Zhu

    It is usually hard to obtain adequate annotated data for delivering satisfactory scene classification results. Semi-supervised scene classification approaches can transfer the knowledge learned from previously annotated data to remote sensing images with scarce samples for satisfactory classification results. However, due to the differences between sensors, environments, seasons, and geographical locations, cross-domain remote sensing images exhibit feature distribution deviations. Therefore, semi-supervised scene classification methods may not achieve satisfactory classification accuracy. To address this problem, a novel semi-supervised subcategory centroid alignment (SSCA)-based scene classification approach is proposed. The SSCA framework is made up of two components, namely the rotation-robust convolutional feature extractor (RCFE) and the neighbor-based subcategory centroid alignment (NSCA). The RCFE aims to suppress the impact of rotation changes on remote sensing image representation, while the NSCA aims to decrease the impact of intra-category variety across domains on cross-domain scene classification. The SSCA algorithm and several competitive approaches are validated on two datasets to demonstrate its effectiveness. The results prove that the proposed SSCA approach performs better than most competitive approaches by no less than 2% overall accuracy.


  • Open Access

    Improved Faster RCNN Based on Feature Amplification and Oversampling Data Augmentation for Oriented Vehicle Detection in Aerial Images

    by Nan Mo, Li Yan

    Vehicles in aerial images are generally with small sizes and unbalanced number of samples, which leads to the poor performances of the existing vehicle detection algorithms. Therefore, an oriented vehicle detection framework based on improved Faster RCNN is proposed for aerial images. First of all, we propose an oversampling and stitching data augmentation method to decrease the negative effect of category imbalance in the training dataset and construct a new dataset with balanced number of samples. Then considering that the pooling operation may loss the discriminative ability of features for small objects, we propose to amplify the feature map so that detailed information hidden in the last feature map can be enriched. Finally, we design a joint training loss function including center loss for both horizontal and oriented bounding boxes, and reduce the impact of small inter-class diversity on vehicle detection. The proposed framework is evaluated on the VEDAI dataset that consists of 9 vehicle categories. The experimental results show that the proposed framework outperforms previous approaches with a mean average precision of 60.4% and 60.1% in detecting horizontal and oriented bounding boxes respectively, which is about 8% better than Faster RCNN.


  • Retraction
    Open Access

    RETRACTED: Zhu et al. Attention-Based Deep Feature Fusion for the Scene Classification of High-Resolution Remote Sensing Images. Remote Sens. 2019, 11, 1996

    by Ruixi Zhu, Li Yan, Nan Mo, Yi Liu

    We have been made aware that the innovative contributions, research method and the majority of the content of this article


  • Retracted
    Open Access

    RETRACTED: Attention-Based Deep Feature Fusion for the Scene Classification of High-Resolution Remote Sensing Images

    by Ruixi Zhu, Li Yan, Nan Mo, Yi Liu

    Scene classification of high-resolution remote sensing images (HRRSI) is one of the most important means of land-cover classification. Deep learning techniques, especially the convolutional neural network (CNN) have been widely applied to the scene classification of HRRSI due to the advancement of graphic processing units (GPU). However, they tend to extract features from the whole images rather than discriminative regions. The visual attention mechanism can force the CNN to focus on discriminative regions, but it may suffer from the influence of intra-class diversity and repeated texture. Motivated by these problems, we propose an attention-based deep feature fusion (ADFF) framework that constitutes three parts, namely attention maps generated by Gradient-weighted Class Activation Mapping (Grad-CAM), a multiplicative fusion of deep features and the center-based cross-entropy loss function. First of all, we propose to make attention maps generated by Grad-CAM as an explicit input in order to force the network to concentrate on discriminative regions. Then, deep features derived from original images and attention maps are proposed to be fused by multiplicative fusion in order to consider both improved abilities to distinguish scenes of repeated texture and the salient regions. Finally, the center-based cross-entropy loss function that utilizes both the cross-entropy loss and center loss function is proposed to backpropagate fused features so as to reduce the effect of intra-class diversity on feature representations. The proposed ADFF architecture is tested on three benchmark datasets to show its performance in scene classification. The experiments confirm that the proposed method outperforms most competitive scene classification methods with an average overall accuracy of 94% under different training ratios.


  • Open Access

    Class-Specific Anchor Based and Context-Guided Multi-Class Object Detection in High Resolution Remote Sensing Imagery with a Convolutional Neural Network

    by Nan Mo, Li Yan, Ruixi Zhu, Hong Xie

    In this paper, the problem of multi-scale geospatial object detection in High Resolution Remote Sensing Images (HRRSI) is tackled. The different flight heights, shooting angles and sizes of geographic objects in the HRRSI lead to large scale variance in geographic objects. The inappropriate anchor size to propose the objects and the indiscriminative ability of features for describing the objects are the main causes of missing detection and false detection in multi-scale geographic object detection. To address these challenges, we propose a class-specific anchor based and context-guided multi-class object detection method with a convolutional neural network (CNN), which can be divided into two parts: a class-specific anchor based region proposal network (RPN) and a discriminative feature with a context information classification network. A class-specific anchor block providing better initial values for RPN is proposed to generate the anchor of the most suitable scale for each category in order to increase the recall ratio. Meanwhile, we proposed to incorporate the context information into the original convolutional feature to improve the discriminative ability of the features and increase classification accuracy. Considering the quality of samples for classification, the soft filter is proposed to select effective boxes to improve the diversity of the samples for the classifier and avoid missing or false detection to some extent. We also introduced the focal loss in order to improve the classifier in classifying the hard samples. The proposed method is tested on a benchmark dataset of ten classes to prove the superiority. The proposed method outperforms some state-of-the-art methods with a mean average precision (mAP) of 90.4% and better detects the multi-scale objects, especially when objects show a minor shape change.


  • TrAdaBoost Based on Improved Particle Swarm Optimization for Cross-Domain Scene Classification With Limited Samples

    by Li Yan, Ruixi Zhu, Yi Liu, Nan Mo

    Scene classification is usually based on supervised learning, but collecting instances is expensive and time-consuming. TrAdaBoost has achieved great success in transferring source instances to target images, but it has problems, such as the excessive focus on instances harder to classify, the rapid convergence speed of the source instances, and the weight mismatch caused by the big gap between the number of source and target instances, leading to decreased classification accuracy. In this paper, in order to address these problems, classical particle swarm optimization (PSO) is modified to select the optimal feature subspace for classifying the “harder” and “easier” instances by reducing unimportant dimensions. A modified correction factor is proposed by considering the classification accuracy of the instances from both domains, to decrease the convergence speed. Iterative selective TrAdaBoost is also proposed to reduce the weight mismatch by removing the indiscriminate source instances. The experimental results obtained with three benchmark data sets confirm that the proposed method outperforms most of the previous methods of scene classification with limited target samples. It is also proved that modified PSO for optimal feature subspace selection, the modified correction factor, and iterative selective TrAdaBoost are all effective in improving the classification accuracy, giving improvements of 3.6%, 4.3%, and 2.7%, and these three contributions together increase the classification accuracy by about 8% in total.


  • Scene Capture and Selected Codebook-Based Refined Fuzzy Classification of Large High-Resolution Images

    by Li Yan, Ruixi Zhu, Yi Liu, Nan Mo

    Scene classification has been successfully applied to the semantic interpretation of large high-resolution images (HRIs). The bag-of-words (BOW) model has been proven to be effective but inadequate for HRIs because of the complex arrangement of the ground objects and the multiple types of land cover. How to define the scenes in HRIs is still a problem for scene classification. The previous methods involve selecting the scenes manually or with a fixed spatial distribution, leading to scenes with a mixture of objects from different categories. In this paper, to address these issues, a scene capture method using adjacent segmented images and a support vector machine classifier is proposed to generate scenes dominated by one category. The codebook in BOW is obtained from clustering features extracted from all the categories, which may lose the discrimination in some vocabularies. Thus, more discriminative visual vocabularies are selected by the introduced mutual information and the proposed intraclass variability balance in each category, to decrease the redundancy of the codebook. In addition, a refined fuzzy classification strategy is presented to avoid misclassification in similar categories. The experimental results obtained with three different types of HRI data sets confirm that the proposed method obtains classification results better than those obtained by most of the previous methods in all the large HRIs, demonstrating that the selection of representative vocabularies, the refined fuzzy classification, and the scene capture strategy are all effective in improving the performance of scene classification.