检索结果-内蒙古大学图书馆

Hybrid Shunted Transformer embedding UNet for remote sensing image semantic segmentation

Neural Computing and Applications 2024年第25期36卷 15705-15720页

作者： Zhou, Huacong Xiao, Xiangling Li, Huihui Liu, Xiaoyong Liang, Peng School of Computer Science Guangdong Polytechnic Normal University Guangdong Guangzhou510630 China Guangdong Provincial Key Laboratory of Intellectual Property and Big Data Guangdong Polytechnic Normal University Guangdong Guangzhou510665 China School of Data Science and Engineering Guangdong Polytechnic Normal University Guangdong Guangzhou510630 China Academy of Heyuan Guangdong Polytechnic Normal University Guangdong Heyuan517099 China The Cyberspace Institute of Advanced Technology Guangzhou University Guangdong Guangzhou510006 China

With the development of deep learning, Remote Sensing Image (RSI) semantic segmentation has produced significant advances. However, due to the sparse distribution of the objects and the high similarity between classes, the task of semantic segmentation in RSI is still extremely challenging. In this paper, we propose a novel semantic segmentation framework for RSI called HST-UNet that can overcome the shortcomings of the existing models and extract and recover the global and local features of RSI, which is a hybrid semantic segmentation model with Shunted Transformer as encoder and Multi-Scale Convolutional Attention Network (MSCAN) as decoder. Then, to better fuse the information from the Encoder and the Decoder and alleviate the ambiguity, we design a Learnable Weighted Fusion (LWF) module to effectively connect to the decoder features. Extensive experiments demonstrate that the proposed HST-UNet outperforms the state-of-the-art methods, achieving F1 score/MIoU accuracy of 71.44%/83.00% on the ISPRS Vaihingen dataset and 77.36%/87.09% on ISPRS Potsdam dataset. The code will be available at https://***/HC-Zhou/HST-UNet. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Research on MAC Protocol of Power Control Based on Node Location in Underwater Acoustic Sensor Network

Research on MAC Protocol of Power Control Based on Node Loca...

引用

International Conference on Communication technology (ICCT)

作者： Li Li Yongjie Yang Yulong Ma Zhengxin Hao Yongqi Guo School of Computer Science and Technology Shenyang University of Chemical Technology Liaoning Provincial Key Laboratory of Intelligent Technology for Chemical Process Industry Shenyang China School of Computer Science and Technology Shenyang University of Chemical Technology Shenyang China

ISBN: (数字)9798350363760

ISBN: (纸本)9798350363777

The problems of high energy consumption and low data transmission quality are common in underwater acoustic sensor networks. Based on the reservation-based MAC protocol (R-MAC), a power control reservation-based MAC protocol (PC-RMAC) which based on location information is proposed. According to the threshold of receiving power, the gain of transmitting and receiving antenna transducer of sensor nodes, the system loss factor, the sound frequency and the actual distance between nodes, the optimal transmitting power can be calculated and dynamically adjusted, so as to reduce the energy consumption generated by the nodes sending data, improve the network energy utilization rate and prolong the life of the network. The performance of the protocol is simulated and verified in star topology, multi-hop topology and hybrid clustering topology respectively. The results show that under the star topology and the distance between nodes is within 600m, the packet delivery ratio of PC-RMAC protocol is slightly higher than that of R-MAC protocol, with lower average energy consumption and lower average delay. The simulation results of PC-RMAC protocol in multi-hop topology show that with the increase of the traffic rate of nodes, when the traffic rate of nodes is about 0.04pkt/s-0.08pkt/s, the packet delivery ratio of PC-RMAC protocol is slightly higher than that of R-MAC protocol, the average energy consumption is slightly lower and the average delay is lower than that of the R-MAC protocol. Simulation experiments under mixed clustering topology showed that the packet delivery ratio of the PC-RMAC protocol is slightly higher than that of the R-MAC protocol as the traffic rate of the node increases. The average energy consumption of the R-MAC protocol shows fluctuations. The average energy consumption of the PC-RMAC protocol is stable and slightly lower than the average energy consumption of the R-MAC protocol, with an average delay of around 20%. By analyzing simulation of PC-RMAC

关键词： Energy consumption Protocols Network topology Simulation Power control Media Access Control Stars Topology Delays Underwater acoustics

来源：评论

学校读者我要写书评

暂无评论

An improved Criminisi method for image inpainting 2

An improved Criminisi method for image inpainting

引用

2022 2nd International Conference on Electrical, Electronics and Computing technology, EECT 2022

作者： Li, C. Chen, H. Han, X. Pan, X. Niu, D. Shandong Provincial Key Laboratory Of Network Based Intelligent Computing University Of Jinan China School Of Computer Science And Technology Shandong University Of Finance And Economics China

The Criminisi method is a classical image inpainting method, which has flaw of unreasonable priority calculation. To overcome this flaw, we propose an improved Criminisi method. To improve the accuracy of a repaired block's priority, we propose a novel method by considering the continuity of structure and color information between the repaired block and its adjacent blocks. When searching the matching block for a repaired block, we compute the similar between two blocks as the sum of squared differences (SSD). Since different blocks within an image may contain different levels of information, we set block to different sizes to determine the best matching block. Experimental results demonstrate the effectiveness of the proposed method. © Published under licence by IOP Publishing Ltd.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

DM-YOLOv5:An Improved Safety Helmet Detection Algorithm at Complex Construction Scenes

DM-YOLOv5:An Improved Safety Helmet Detection Algorithm at C...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Dexu Yao Aimin Li Deqi Liu Mengfan Cheng Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

At complex construction sites, detecting whether workers are wearing safety helmets is often affected by occlusion and sunlight change. In addition, the helmets are relatively small, which can easily lead to missed detection and false detection. This paper proposes an improved YOLOv5 model. Firstly, we added a 152×152 detection layer for scale of small objects, enhancing its feature extraction capabilities. Secondly, we added the Multi-Spectral Channel Attention (MSCA) mechanism to enhance feature learning for small objects, addressing the information loss problem caused by Global Average Pooling (GAP). Finally, different activation functions, bounding box regression loss functions, and post-processing methods were adopted for YOLOv5. The Mish function serves as the activation function to enhance the model’s generalization ability and mitigate the gradient vanishing problem associated with the Leaky Relu function. The CIoU loss was employed as the loss function to improve bounding box regression accuracy and accelerate prediction convergence. DIoU-NMS, instead of NMS, was used as the post-processing method to enhance the filtering ability for prediction boxes of occluded small objects. We tested our algorithm on a dataset with 7000 images and achieved an mAP of 95.1%, surpassing the YOLOv5 model by 2.9%. Our method significantly improves safety helmet detection performance at complex construction scenes.

关键词： YOLO Representation learning Head Filtering Federated learning Prediction algorithms Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Robust peer-to-peer learning via secure multi-party computation

引用

Journal of Information and Intelligence 2023年第4期1卷 341-351页

作者： Yongkang Luo Wenjian Luo Ruizhuo Zhang Hongwei Zhang Yuhui Shi Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies School of Computer Science and TechnologyHarbin Institute of TechnologyShenzhen 518055China Peng Cheng Laboratory Shenzhen 518055China Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Department of Computer Science and EngineeringSouthern University of Science and TechnologyShenzhen 518055China

To solve the data island problem,federated learning(FL)provides a solution paradigm where each client sends the model parameters but not the data to a server for model ***-to-peer(P2P)federated learning further improves the robustness of the system,in which there is no server and each client communicates directly with the *** secure aggregation,secure multi-party computing(SMPC)protocols have been utilized in peer-to-peer ***,the ideal SMPC protocols could fail when some clients drop *** this paper,we propose a robust peer-to-peer learning(RP2PL)algorithm via SMPC to resist clients dropping *** improve the segmentbased SMPC protocol by adding a check and designing the generation method of random seg*** RP2PL,each client aggregates their models by the improved robust secure multi-part computation protocol when finishes the local *** results demonstrate that the RP2PL paradigm can mitigate clients dropping out with no significant degradation in performance.

关键词： Federated learning Swarm learning Secure multi-party computation Peer-to-peer learning

来源：评论

学校读者我要写书评

暂无评论

Domain Adaptive Lung Nodule Detection in X-Ray Image

Domain Adaptive Lung Nodule Detection in X-Ray Image

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Haifeng Zhao Lixiang Jiang Leilei Ma Dengdi Sun Yanping Fu Anhui Provincial Key Laboratory of Multi-modal Cognitive Computation School of Computer Science and Technology Anhui University Hefei China

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

Medical images from different healthcare centers exhibit varied data distributions, posing significant challenges for adapting lung nodule detection due to the domain shift between training and application phases. Traditional unsupervised domain adaptive detection methods often struggle with this shift, leading to suboptimal outcomes. To overcome these challenges, we introduce a novel domain adaptive approach for lung nodule detection that leverages mean teacher self-training and contrastive learning. First, we propose a hierarchical contrastive learning strategy to refine nodule representations and enhance the distinction between nodules and background. Second, we introduce a nodule-level domain-invariant feature learning (NDL) module to capture domain-invariant features through adversarial learning across different domains. Additionally, we propose a new annotated dataset of X-ray images to aid in advancing lung nodule detection research. Extensive experiments conducted on multiple X-ray datasets demonstrate the efficacy of our approach in mitigating domain shift impacts.

关键词： Representation learning Training Adaptation models Lungs Contrastive learning Medical services Adversarial machine learning X-ray imaging Cybernetics Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

FSD-YOLO: An Improved Method for Steel Surface Defect Detection Based on YOLOv5

FSD-YOLO: An Improved Method for Steel Surface Defect Detect...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Yuechen Zhang Aimin Li Xiaotong Kong Wenqiang Li Zhiyao Li Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

Steel surface defect detection is very important in industrial quality inspection, and there have been many studies on Steel surface defect detection in recent years. Existing steel surface defect detection algorithms suffer from low detection accuracy and high model complexity. To improve the above problems, this paper proposes an optimized target detection algorithm based on YOLOv5. Firstly, the original spatial pyramid pooling (SPP) module is replaced by the SPPFCSPC module to better capture the target and scene information at different scales, and to improve the sensory field and feature expression ability of the model. Secondly, we propose the C2F-Faster module based on FasterNet and C2F module to replace the C3 module of the backbone network, which perfectly integrates the ideas of PConv and ELAN and ensures the detection accuracy while effectively reducing the model size. Finally, the Dynamic Head detection head is fused in the head of the model to improve the detection capability of the target detection head using the separated attention mechanism. We conducted experimental validation on the widely used NEU-DET dataset. The experimental results show that the improved model improves the original YOLOv5 model over the original YOLOv5 model by 3.6% in mAP @50 , 9.9% and 2.8% in AP and AR, respectively, and the amount of model parameters is reduced by 13.2%. The improved model also outperforms SSD, FasterRCNN, YOLOv5, YOLOv6, YOLOv7, YOLOv8 and other mainstream target detection models, which better meets the requirements of actual industrial production on the accuracy and speed of steel surface defects detection model.

关键词： YOLO Accuracy Attention mechanisms Computational modeling Heuristic algorithms Inspection Data models

来源：评论

学校读者我要写书评

暂无评论

Ultrasound SAM Adapter: Adapting SAM for Breast Lesion Segmentation in Ultrasound Images

arXiv

引用

arXiv 2024年

作者： Tu, Zhengzheng Gu, Le Wang, Xixi Jiang, Bo Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei230601 China

Segment Anything Model (SAM) has recently achieved amazing results in the field of natural image segmentation. However, it is not effective for medical image segmentation, owing to the large domain gap between natural and medical images. In this paper, we mainly focus on ultrasound image segmentation. As we know that it is very difficult to train a foundation model for ultrasound image data due to the lack of large-scale annotated ultrasound image data. To address these issues, in this paper, we develop a novel Breast Ultrasound SAM Adapter, termed Breast Ultrasound Segment Anything Model (BUSSAM), which migrates the SAM to the field of breast ultrasound image segmentation by using the adapter technique. To be specific, we first design a novel CNN image encoder, which is fully trained on the BUS dataset. Our CNN image encoder is more lightweight, and focuses more on features of local receptive field, which provides the complementary information to the ViT branch in SAM. Then, we design a novel Cross-Branch Adapter to allow the CNN image encoder to fully interact with the ViT image encoder in SAM module. Finally, we add both of the Position Adapter and the Feature Adapter to the ViT branch to fine-tune the original SAM. The experimental results on AMUBUS and BUSI datasets demonstrate that our proposed model outperforms other medical image segmentation models significantly. Our code will be available at: https://***/bscs12/BUSSAM. Copyright © 2024, The Authors. All rights reserved.

关键词： Ultrasonic applications

来源：评论

学校读者我要写书评

暂无评论

Braille-to-Chinese Translation System Based on Optical Braille Recognition 2

Braille-to-Chinese Translation System Based on Optical Brail...

引用

2nd Asia-Pacific Conference on Communications technology and computer science, ACCTCS 2022

作者： Shao, Zirui Yu, Zhi Gu, Yu Wang, Wei School of Software Technology Zhejiang University Hangzhou China College of Computer Science Zhejiang University Zhejiang Provincial Key Laboratory of Service Robot Hangzhou China

ISBN: (纸本)9781665400343

Braille is an essential tool for visually impaired people to receiving and transmitting information. However, sighted people without special training cannot read Braille, which will cause inconvenience to scenarios such as special education that require sighted people to read Braille. This paper implements a Braille-to-Chinese translation system composed of optical Braille recognition, Braille-to-pinyin conversion, and pinyin-to-character module. Experiments prove that our system can effectively and accurately translate Braille images into Chinese. Our system has broad application prospects, which can help the sighted people read Braille and help visually impaired people in their study and life. © 2022 IEEE.

关键词： Training computer science Braille Visualization Optical imaging Communications technology

来源：评论

学校读者我要写书评

暂无评论

RTS-DETR: Efficient Real-Time DETR for Small Object Detection

RTS-DETR: Efficient Real-Time DETR for Small Object Detectio...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Wenqiang Li Aimin Li Zhiyao Li Xiaotong Kong Yuechen Zhang Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

In recent years, object detection models DEtection TRansformer (DETR) series based on Transformer architecture have played a huge role in various fields. However, the DETR series models are not satisfactory in small object detection. Mainly due to the huge amount of calculation of DETR, a lot of feature information will be lost in the feature fusion stage and the low tolerance of small objects to Intersection over Union (IoU). In order to solve the above problems, we propose a near real-time detection model RTS-DETR. In this paper, we revisit Real-Time DEtection TRansformer (RT-DETR), which effectively handles multi-scale features by decoupling intra-scale interaction and cross-scale fusion, but this will lose a lot of positive local information. To this end, we have improved the efficient hybrid encoder. We propose a new positional encoding method that enables the hybrid encoder to more accurately convert the input feature sequence into a high-dimensional representation, and propose a new feature fusion module to enhance the model's ability to capture local features. Furthermore, in order to improve the tolerance of small objects to IoU, we combine Normalized Wasserstein Distance (NWD) with Shape-IoU for the optimization model. This method more accurately takes into account the shape and size of objects, thereby improving detection accuracy. Our model achieves an accuracy of 38.8% (in terms of mAP @0.5 ) on the widely used VisDrone dataset, which improves the accuracy by 2.5% compared to RT-DETR with ResNet-18 as the backbone network.

关键词： Accuracy Shape Fuses Optimization models Semantics Object detection Feature extraction Transformers Real-time systems Encoding

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：