检索结果-内蒙古大学图书馆

Channel selection and local attention transformer model for semantic segmentation on UAV remote sensing scene

IET IMAGE PROCESSING 2025年第1期19卷

作者： Liu, Da Long, Hao Liu, Zhenbao Beijing Union Univ Beijing Key Lab Informat Serv Engn Beijing Peoples R China Beijing Union Univ Coll Robot Beijing Peoples R China Northwestern Polytech Univ Sch Civil Aviat Xian Peoples R China

Compared with common urban landscape semantic segmentation, unmanned aerial vehicle (UAV) image semantic segmentation is more challenging because small targets have very low pixel percentages and multi-scale features due to the influence of flight altitude. Yet, the commonly used successive grid downsampling strategy in the current transformer-based methods omits some important features of small targets. Furthermore, due to the complex background interference, it can lead to even worse results. In reaction to this, existing strategies aim to maintain superior resolution. Nevertheless, the application of this method incurs considerable computational costs, which brings challenges for the practical applications of UAVs. So it is significant to design a novel framework to balance retaining more pixels representing small objects during downsampling and reducing computational costs. For this, the Channel Selection and the Local Attention Transformer Model (CSLFormer) are proposed. During the overlap patch embedding process of feature maps, the model allocates half of the important channels to global attention and local attention. These two types of attention focus on different aspects: one learns the relationships and importance among various patches, while the other emphasizes the features of individual patches. The method shows superior performance on two public datasets: AeroScapes and Vaihingen, achieving mean intersection over union (mIoU) of 75.57% and 78.93%, respectively. The proposed CSLFormer has been released on GitHub: .

关键词： aircraft computer vision convolutional neural nets feedforward neural nets image segmentation

来源：评论

学校读者我要写书评

暂无评论

Zero-shot moving ship segmentation based on segment anything network and optical flow network

引用

ELECTRONICS LETTERS 2025年第1期61卷

作者： Liu, Wenhui Qiao, Yulong Xing, Zhengyi Zhao, Yue Harbin Engn Univ Coll Informat & Commun Engn Harbin Peoples R China

The wake of the ship and the waves on the water surface increased the difficulty of video-based ship segmentation. To address this challenging problem, we propose a zero-shot segmentation method based on the segment anything model (SAM) and optical flow network. Specifically, the dark channel filtering technology is employed as a preprocessing step to partly eliminate the noise from the sea surface. Then, the SAM with the point prompt is utilized to detect and segment ship targets in conjunction with finding the best mask algorithms, in which a supervision mechanism is introduced to determine the ship moving in or out of the surveillance region. Finally, we use the optical flow network to predict the position of the ship target and leverage the segmentation by using the network SAM with bounding boxes as prompts. The experiments on the benchmark dataset IPATCH demonstrate the performance of the proposed zero-shot moving ship segmentation method.

关键词： artificial intelligence computer vision convolutional neural nets image segmentation ships video signal processing

来源：评论

学校读者我要写书评

暂无评论

SMGNFORMER: Fusion Mamba-graph transformer network for human pose estimation

引用

IET COMPUTER VISION 2025年第1期19卷

作者： Li, Yi Wang, Zan Niu, Weiran Henan Univ Kaifeng City Intelligent Mfg Engn Technol Res Ctr Sch Phys & Elect Kaifeng Peoples R China

In the field of 3D human pose estimation (HPE), many deep learning algorithms overlook the topological relationships between 2D keypoints, resulting in imprecise regression of 3D coordinates and a notable decline in estimation performance. To address this limitation, this paper proposes a novel approach to 3D HPE, termed the Spatial Mamba Graph convolutional neural Network (GCN) Former (SMGNFormer). The proposed method utilises the Mamba architecture to extract spatial information from 2D keypoints and integrates GCNs with multi-head attention mechanisms to build a relational graph of 2D keypoints across a global receptive field. The outputs are subsequently processed by a Time-Frequency Feature Fusion Transformer to estimate 3D human poses. SMGNFormer demonstrates superior estimation performance on the Human3.6M dataset and real-world video data compared to most Transformer-based algorithms. Moreover, the proposed method achieves a training speed comparable to PoseFormerv2, providing a clear advantage over other methods in its category.

关键词： convolutional neural nets learning (artificial intelligence)

来源：评论

学校读者我要写书评

暂无评论

Re-identification of patterned animals by multi-image feature aggregation and geometric similarity

引用

IET COMPUTER VISION 2025年第1期19卷

作者： Nepovinnykh, Ekaterina Immonen, Veikka Eerola, Tuomas Stewart, Charles V. Kalviainen, Heikki Lappeenranta Lahti Univ Technol LUT Dept Computat Engn Comp Vis & Pattern Recognit Lab Lappeenranta Finland Rensselaer Polytech Inst Dept Comp Sci Troy NY 12180 USA

Image-based re-identification of animal individuals allows gathering of information such as population size and migration patterns of the animals over time. This, together with large image volumes collected using camera traps and crowdsourcing, opens novel possibilities to study animal populations. For many species, the re-identification can be done by analysing the permanent fur, feather, or skin patterns that are unique to each individual. In this paper, the authors study pattern feature aggregation based re-identification and consider two ways of improving accuracy: (1) aggregating pattern image features over multiple images and (2) combining the pattern appearance similarity obtained by feature aggregation and geometric pattern similarity. Aggregation over multiple database images of the same individual allows to obtain more comprehensive and robust descriptors while reducing the computation time. On the other hand, combining the two similarity measures allows to efficiently utilise both the local and global pattern features, providing a general re-identification approach that can be applied to a wide variety of different pattern types. In the experimental part of the work, the authors demonstrate that the proposed method achieves promising re-identification accuracies for Saimaa ringed seals and whale sharks without species-specific training or fine-tuning.

关键词： computer vision convolutional neural nets image retrieval pattern recognition

来源：评论

学校读者我要写书评

暂无评论

A deep learning-based method for detecting and identifying surface defects in polyimide foam

引用

IET IMAGE PROCESSING 2025年第1期19卷

作者： Song, Xianhui Hu, Guangzhong Lu, Jing Tuo, Xianguo Li, Yuedong Sichuan Univ Sci & Engn Sch Mech Engn Zigong Peoples R China Key Lab Intelligent Mfg Construct Machinery Hefei Peoples R China Sichuan Univ Sci & Engn Sch Automat & Informat Engn Zigong Peoples R China

Currently, the detection and identification of surface defects in polyimide foam products mainly rely on on-site work experience, which has issues such as low detection accuracy, strong subjectivity, and low efficiency. Existing research on foam product defect detection primarily targets internal defects, lacking studies on the detection, identification, and classification of surface defects. Therefore, this article proposes a method for identifying and classifying surface defects in polyimide foam based on an improved GoogLeNet, aiming to quickly and accurately detect and identify surface defects in foam products. By optimizing the Inception blocks, introducing the ECA attention mechanism, and adding an LSTM network module, the model's recognition accuracy and generalization ability are effectively improved. In experiments, the model proposed in this article performed excellently on the foam surface defect dataset, showing a significant advantage in detection accuracy compared to other convolutional neural network models. The detection accuracy for pits and cracks reached 98.24% and 98.25%, respectively, providing a reliable reference for the detection of surface defects in industrial foam production.

关键词： computer vision convolutional neural nets flaw detection image classification

来源：评论

学校读者我要写书评

暂无评论

Knowledge distillation approach for skin cancer classification on lightweight deep learning model

引用

HEALTHCARE TECHNOLOGY LETTERS 2025年第1期12卷 e12120页

作者： Saha, Suman Hemal, Md. Moniruzzaman Eidmum, Md. Zunead Abedin Mridha, Muhammad Firoz Bangabandhu Sheikh Mujibur Rahman Digital Univ Dept IoT & Robot Engn Kaliakair Gazipur Bangladesh Amer Int Univ Bangladesh Dept Comp Sci Dhaka Bangladesh

Over the past decade, there has been a global increase in the incidence of skin cancers. Skin cancer has serious consequences if left untreated, potentially leading to more advanced cancer stages. In recent years, deep learning based convolutional neural network have emerged as powerful tools for skin cancer detection. Generally, deep learning approaches are computationally expensive and require large storage space. Therefore, deploying such a large complex model on resource-constrained devices is challenging. An ultra-light and accurate deep learning model is highly desirable for better inference time and memory in low-power-consuming devices. Knowledge distillation is an approach for transferring knowledge from a large network to a small network. This small network is easily compatible with resource-constrained embedded devices while maintaining accuracy. The main aim of this study is to develop a deep learning-based lightweight network based on knowledge distillation that identifies the presence of skin cancer. Here, different training strategies are implemented for the modified benchmark (Phase 1) and custom-made model (Phase 2) and demonstrated various distillation configurations on two datasets: HAM10000 and ISIC2019. In Phase 1, the student model using knowledge distillation achieved accuracies ranging from 88.69% to 93.24% for HAM10000 and from 82.14% to 84.13% on ISIC2019. In Phase 2, the accuracies ranged from 88.63% to 88.89% on HAM10000 and from 81.39% to 83.42% on ISIC2019. These results highlight the effectiveness of knowledge distillation in improving the classification performance across diverse datasets and enabling the student model to approach the performance of the teacher model. In addition, the distilled student model can be easily deployed on resource-constrained devices for automated skin cancer detection due to its lower computational complexity.

关键词： convolutional neural nets health care learning (artificial intelligence)

来源：评论

学校读者我要写书评

暂无评论

Improving Biomedical Image Pattern Identification by Deep B4-GraftingNet: Application to Pneumonia Detection

引用

IET IMAGE PROCESSING 2025年第1期19卷

作者： Shah, Syed Adil Hussain Shah, Syed Taimoor Hussain Fayyaz, Abdul Muiz Shah, Syed Baqir Hussain Yasmin, Mussarat Raza, Mudassar Di Terlizzi, Angelo Deriu, Marco Agostino Politecn Torino PolitoBIOMed Lab Dept Mech & Aerosp Engn Turin Italy GPI SpA Dept Res & Dev R&D Trento Italy Univ Teknol PETRONAS Comp & Informat Sci Dept Seri Iskandar Perak Malaysia COMSATS Univ Islamabad CUI Dept Comp Sci Wah Pakistan Univ Taxila HITEC Dept Comp Sci Taxila Pakistan Namal Univ Mianwali Dept Comp Sci Mianwali Pakistan

VGG-16 and Inception are widely used CNN architectures for image classification, but they face challenges in target categorization. This study introduces B4-GraftingNet, a novel deep learning model that integrates VGG-16's hierarchical feature extraction with Inception's diversified receptive field strategy. The model is trained on the OCT-CXR dataset and evaluated on the NIH-CXR dataset to ensure robust generalization. Unlike conventional approaches, B4-GraftingNet incorporates binary particle swarm optimization (BPSO) for feature selection and grad-CAM for interpretability. Additionally, deep feature extraction is performed, and multiple machine learning classifiers (SVM, KNN, random forest, na & iuml;ve Bayes) are evaluated to determine the optimal feature representation. The model achieves 94.01% accuracy, 94.22% sensitivity, 93.36% specificity, and 95.18% F1-score on OCT-CXR and maintains 87.34% accuracy on NIH-CXR despite not being trained on it. These results highlight the model's superior classification performance, feature adaptability, and potential for real-world deployment in both medical and general image classification tasks.

关键词： biomedical imaging convolutional neural nets decision making feature extraction feature selection image classification nearest neighbour methods pattern classification supervised learning X-ray imaging

来源：评论

学校读者我要写书评

暂无评论

A unified multi-class anomaly detection model based on reverse distillation

引用

IET IMAGE PROCESSING 2025年第1期19卷

作者： Fu, Maoli Fu, Zhongliang Chinese Acad Sci ChengDu Inst Comp Applicat Chengdu Sichuan Peoples R China Univ Chinese Acad Sci Chengdu Inst Comp Applicat Beijing Peoples R China Shenzhen CBPM KEXIN Banking Technol CO LTD R&D Dept Banknote Printing Prod Line Shenzhen Peoples R China

The multi-class single-model detection paradigm is a prevalent design for industrial anomaly detection, exhibiting suitability for varying industrial classes and dynamic, flexible production scenarios. This approach not only enhances model adaptability but also minimizes maintenance costs. However, the current popular methods are susceptible to the 'copying shortcut' phenomenon, which constrains their performance on benchmark datasets. To overcome this limitation, this article proposes a multi-class anomaly detection model: UniRD, based on the reverse distillation method. This model creates an image corruptor that expands the dataset and generates 'normal-corrupt' image pairs. During the training process, their correspondence is used to optimize the reverse distillation. This process greatly exploits and releases the potential of the student decoder. Furthermore, a teacher feature adaptation module is devised to enhance the compatibility between the pre-trained model and the anomaly detection task. This has the effect of reducing the discrepancy between teacher and student features while ensuring the consistency of normal sample features. The comprehensive evaluation results in two mainstream datasets, MVTec and VisA, and demonstrates that the proposed method exhibits improvement in all indicators compared to benchmark methods. The proposed method attains the state-of-the-art, substantiating its effectiveness and advancement.

关键词： computer vision convolution convolutional neural nets encoding feature extraction image processing

来源：评论

学校读者我要写书评

暂无评论

From pixels to prognosis: Attention-CNN model for COVID-19 diagnosis using chest CT images

引用

IET IMAGE PROCESSING 2025年第1期19卷

作者： Suseela, Suba Parekh, Nita Int Inst Informat Technol Ctr Computat Nat Sci & Bioinformat Prof CR Rao Rd Hyderabad 500032 Telangana India

Deep learning assisted diagnosis for assessing the severity of various respiratory infections using chest computed tomography (CT) scan images has gained much attention after the COVID-19 pandemic. Major tasks while building such models require an understanding of the characteristic features associated with the disease, patient-to-patient variations and changes associated with disease severity. In this work, an attention-based convolutional neural network (CNN) model with customized bottleneck residual module (Attn-CNN) is proposed for classifying CT images into three classes: COVID-19, normal, and other pneumonia. The efficacy of the model is evaluated by carrying out various experiments, such as effect of class imbalance, impact of attention module, generalizability of the model and providing visualization of model's prediction for the interpretability of results. Comparative performance evaluation with five state-of-the-art deep architectures such as MobileNet, EfficientNet-B7, Inceptionv3, ResNet-50 and VGG-16, and with published models such as COVIDNet-CT, COVNet, COVID-Net CT2, etc. is discussed.

关键词： computerised tomography convolutional neural nets health care image classification learning (artificial intelligence) lung medical image processing neural net architecture

来源：评论

学校读者我要写书评

暂无评论

FMR-YOLO: An improved YOLOv8 algorithm for steel surface defect detection

引用

IET IMAGE PROCESSING 2025年第1期19卷

作者： Ni, Yongjing Wu, Qi Zhang, Xiuqing Hebei Univ Sci & Technol Sch Informat Sci & Engn Shijiazhuang 050018 Peoples R China

To address the insufficient feature extraction capability for steel surface defects in industrial production, as well as issues such as low detection speed and poor accuracy caused by large model parameters, a metal surface defect detection algorithm named FMR-YOLO, based on an improved YOLOv8n, is proposed. The algorithm incorporates a fast lightweight feature extraction structure, the number of parameters and computation of the model are reduced while preserving the spatial information, thus improving the target detection performance. A multi-scale feature fusion module is introduced, enabling the extraction of more comprehensive and richer features compared to traditional single-scale methods, to better support defect detection tasks. Additionally, a receptive field attention structure, Receptive Field Attention Neck, is designed in the Neck part to expand the model's receptive field and reduce computational complexity, significantly improving detection accuracy for small defects. This allows the model to effectively capture both global and local features in complex industrial scenarios. The effectiveness of the improved FMR-YOLO algorithm is validated on two industrial surface defect datasets: GC10-DET and NEU-DET. Experimental results show that the mAP@0.5 detection accuracy has increased by 4.5% and 5.1% on the GC10-DET and NEU-DET datasets, respectively, with a parameter size of merely 2.7 M.

关键词： computer vision convolutional neural nets feature extraction image processing iron surface cracks

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：