检索结果-内蒙古大学图书馆

DWMFusion: A lightweight medical image fusion network based on discrete wavelet convolution and selective state space models

引用

Expert Systems with Applications 2025年 286卷

作者： Fan, Chao Yun, Mengyang Chen, Li Zhao, Huijun Peng, Bingcheng School of Artificial Intelligence and Big Data Henan University of Technology Henan Province Zhengzhou City China Ministry of Education Key Laboratory of Grain Information Processing and Control Henan Province Zhengzhou City China School of Information Science and Engineering Henan University of Technology Henan Province Zhengzhou City450001 China

Multimodal medical image fusion improves the accuracy of clinical diagnosis by integrating medical imaging information from different sensors into unified and complementary multi-scale fused information images. However, existing fusion methods still face challenges in capturing modality-specific features, balancing local and global contextual features, and preserving complementary information from different representations. To overcome these shortcomings, this study proposes a lightweight feature complementary fusion network(DWMFusion) to achieve effective fusion of functional and structural medical images under lightweight premise. Specifically, a cross-channel feature extraction unit based on discrete wavelet transform (DWT) and convolutional coupling structure is designed to enhance the modal intrinsic frequency domain features. Meanwhile, a visual state space block (VSSB) and a contextual modeling structure with multiple layers of Mamba are introduced to balance local details with global semantics and reduce computational redundancy. In the image fusion stage, a multilevel cross-fusion unit (CFFM) that introduces position coding is designed to realize deep cross-modal spatio-temporal feature interaction. A joint loss function incorporating wavelet decomposition properties is proposed to effectively adaptively constrain the frequency domain consistency and maintain the structural information. Validation on the Harvard Medical School database shows that DWMFusion is capable of generating visually satisfactory fusion images. And compared with other methods, it improves the SD metrics by an average of 17.59%, the SF metrics by an average of 17.64%, and the AG metrics by an average of 19.96% on the three datasets. These results confirm the robustness and adaptability of the model. © 2025 Elsevier Ltd

关键词： Wavelet decomposition

来源：评论

学校读者我要写书评

暂无评论

Azimuth signal reconstruction for hrws-sar from uniform resampling 2

Azimuth signal reconstruction for hrws-sar from uniform resa...

引用

2nd International Conference on Artificial Intelligence, Information processing and Cloud Computing, AIIPCC 2021

作者： Zhang, Hanqing Wu, Lin Li, Ning Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China College of Computer and Information Engineering Henan University Kaifeng China

ISBN: (纸本)9783800756162

Signal reconstruction is a key step in the azimuth multichannel high-resolution wide-swath synthetic aperture radar (HRWS-SAR) imaging algorithms. Krieger’s digital beam-forming (DBF) algorithm is currently one of the commonly used algorithms for processing HRWS-SAR data. However, this algorithm is only suitable for uniform space-time sampling and moderately non-uniform sampling. In the case of highly non-uniform sampling, the imaging performance of Krieger’s DBF algorithm will be seriously deteriorated. In this paper, a uniform resampling algorithm is presented to solve above problem. The proposed algorithm adopts modern sampling theory to reduce the approximate error. This algorithm consists of two key steps: 1. The given signal samples are projected onto a selected intermediate subspace, spanned by integer translations of a compactly supported kernel function. This process generates a sparse set of equations, which can be effectively solved by using a sparse equation solvers. 2. The results are projected onto the subspace where the sampled signal is known to reside. The orthogonal matching pursuit (OMP) algorithm is used to realize the second projection and reconstruction the signal effectively. Simulation results show that the newly proposed algorithm has a significant improvement in imaging performance than Krieger’s DBF algorithm. © 2021 AIIPCC 2021 - 2nd International Conference on Artificial Intelligence, Information processing and Cloud Computing. All rights reserved.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

Character Recognition Based on Multi-scale Feature Fusion Transfer Learning 6th

Character Recognition Based on Multi-scale Feature Fusion Tr...

引用

6th Conference on Signal and Information processing, Networking and Computers, ICSINC 2019

作者： Zhang, Miaohui Pang, Kangning Chen, Yunzhong Zhang, Bo Key Laboratory of Data Analysis and Processing of Henan Province Henan University Kaifeng China

ISBN: (纸本)9789811541629

Video surveillance has been using in daily life widely and has significant impact in security field. Reading time information in video has becoming an essential part. Because of the complex background of timestamp and the high similarity between targets, the features extracted by traditional machine learning algorithm cannot meet the requirements and cannot achieve the required detection speed and accuracy. In this paper, we improved the algorithm with multi-scale features. Features extracted from convolution layers of different scales are used to predict, which could improve the recognition accuracy of small targets. In addition, because the size of the collected dataset is 2860 and the amount of data is not large enough, we use data augmentation and transfer learning to train. Pre-training on the public dataset SVHN firstly, and then trains on the special dataset. Experiments show that the algorithm can recognize timestamps accurately. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

An Algorithm of data Classification Based on PCA and K-Means++

An Algorithm of Data Classification Based on PCA and K-Means...

引用

2021 IEEE Conference on Telecommunications, Optics and Computer Science, TOCS 2021

作者： Huang, Ruirui Cheng, Qianshuai Chen, Zhengquan Henan University Henan Key Laboratory of Big Data Analysis and Processing Kaifeng China Henan University School of Computer and Information Engineering Kaifeng China

ISBN: (纸本)9781665424981

Principal component analysis (PCA) and K-means++ algorithm are used to classify and analyze eight main variables of the average annual consumption expenditure of urban households in 31 provinces and cities in China in a given year, so as to better build the reasonable consumption level of each area. In this paper, a data classification method based on PCA and improved K-means++ is proposed. In this method, PCA was used to extract eight variable characteristics of consumer expenditure, and K-means++ algorithm was used to classify the data. The experimental results show that this method reduces the dependence of the characteristic dimension of variable data and the k-means++ algorithm on the initial classification center of gravity, and improves the accuracy and stability of data classification results. © 2021 IEEE.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Design and Research of Remote Sensing Process Language based on XML 2

Design and Research of Remote Sensing Process Language based...

引用

2nd IEEE International Conference on Information Technology, Big data and Artificial Intelligence, ICIBA 2021

作者： Zuo, Xianyu Li, Heng Zhou, Liming Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China School of Computer and Information Engineering Henan University Kaifeng China

ISBN: (纸本)9781665428767

In the era of rapid development of remote sensing technology, in order to improve the production efficiency of remote sensing data processing flow and further optimize the editing of remote sensing processes in the visual interface. In this paper we have analyzed the characteristics and attributes of remote sensing processes and algorithms. We made the production of processes and algorithms into scripts, and realizes to create remote sensing processes by inputting scripting language in the visual interface. A remote sensing language based on XML is designed to read and store key information. This language will use XML to drive the production of remote sensing process. With the language we design, a remote sensing process customization system has been implemented. It can improve the editing and production efficiency of remote sensing data processing flow. © 2021 IEEE.

关键词： XML

来源：评论

学校读者我要写书评

暂无评论

key-Point Based Distribution Probability Optimization for Object Detection in Remote Sensing Images 7

Key-Point Based Distribution Probability Optimization for Ob...

引用

7th International Conference on Computer and Communications, ICCC 2021

作者： Zhu, Xiaoke Wang, Yufei Chen, Xiaopan Li, Danyang Zhang, Jitong Cai, Yulong Henan University School of Computer and Information Engineering Kaifeng China Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China

ISBN: (纸本)9781665409506

Recently, object detection in remote sensing images has been an important topic in computer vision. As a mainstream approach to detectors, single-stage detectors usually compute the important points of the bounding box to get the location of the target, and optimize them by Focal Loss. One of the development trends for one-stage detectors is to combine with Localization Quality Estimation (LQE), which can provide accurate ranking scores, and thus bring benefits to the Non-Maximum Suppression as well as the following detection results. In this paper, we propose a one-stage detector, named key-point based Distribution Probability Optimization (KDPO), for remote sensing object detection. Specially, we first classify and locate the object through five key points. Then, we merge the quality estimation into the class prediction vector to form a joint representation of localization quality and classification. Next, we utilize a vector to represent arbitrary distribution of box locations. The improved representations avoid the inconsistency risk and accurately describe the flexible distribution of the data. Meanwhile, we use the improved Focal Loss for the succeed optimization. The proposed method is tested on two popular aerial image datasets, including HRSC2016 and DOTA. In all experiments, our approach achieves promising performance comparing to the state-of-the-art detectors. © 2021 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Character-Level Street View Text Spotting Based on Deep Multisegmentation Network for Smarter Autonomous Driving

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2022年第2期3卷 297-308页

作者： Zhang, Chongsheng Tao, Yuefeng Du, Kai Ding, Weiping Wang, Bin Liu, Ji Wang, Wei Henan Provincial Key Laboratory of Big Data Analysis and Processing Laboratory of the Yellow River Cultural Heritage Henan University Kaifeng475001 China School of Information Science and Technology Nantong University Nantong226019 China School of Electrical Engineering Zhejiang University Hangzhou310058 China Big Data Lab Baidu Inc. Beijing100044 China School of Computer and Information Technology Beijing Jiaotong University Beijing100044 China

Urban scenes are full of street entities with sign boards. Therefore, in autonomous driving, street view text spotting techniques will play a significant role in the precise understanding of surrounding scenes during driving, because texts contained in the images usually provide important clues for accurate image understanding, while it is often ambiguous for existing computer vision algorithms to understand scene images without texts. In this work, we propose a Multi-Segmentation network for character-level scene Text Detection (MSTD). The MSTD introduces a densely connected atrous spatial pyramid pooling module to enlarge the receptive field of the feature extraction layer, so as to localize long as well as large-sized text instances. Moreover, it devises a double segmentation subnetwork to utilize two independent but inherently complementary losses to co-optimize the network and increase the reliability of the confidence scores in predicting the text/nontext areas. With the character instances detected by the MSTD, one can easily perform scene text spotting with classic object recognition networks such as ResNet and DenseNet. We carried out extensive experiments on nine scene text datasets to demonstrate the outstanding performance of the MSTD on character-level and line-level text instance localization and scene text recognition, where the MSTD significantly outperforms the state-of-the-art scene text detection methods and the sequence-to-sequence-learning-based scene text recognizers. © 2020 IEEE.

关键词： Character recognition

来源：评论

学校读者我要写书评

暂无评论

Design of Offline analysis System for Remote Sensing data Service Based on Hive

Design of Offline Analysis System for Remote Sensing Data Se...

引用

2021 International Conference on Digital Society and Intelligent Systems, DSInS 2021

作者： Zhang, Hongkuo Zhang, Jiaxiang Tian, Meng Qiao, Baojun Heanan University Henan Key Laboratory of Big Data Analysis and Processing School of Computer and Information Engineering Kaifeng China

ISBN: (纸本)9781665406307

With the wide application of remote sensing data service platform, the platform accumulates more and more data, and the remote sensing users' demand for remote sensing data service becomes more and more diverse. Therefore, how to deal with remote sensing service data, make statistics and analyze its potential value, and meet the diverse needs of remote sensing users becomes particularly important. Based on big data technology, this paper firstly collects and stores remote sensing user behavior data and remote sensing service platform business data, then uses Hive to build offline data warehouse, performs dimensional modeling and hierarchical design of the data, and finally obtains relevant index data values by statistical analysis. Through the statistical analysis of remote sensing service data can not only provide data support for active service mode, but also provide support for the decision of remote sensing application department managers. © 2021 IEEE.

关键词： data warehouses

来源：评论

学校读者我要写书评

暂无评论

Object Detection Algorithm Based on Bimodal Feature Alignment 7th

Object Detection Algorithm Based on Bimodal Feature Alignme...

引用

7th Asian Conference on Pattern Recognition, ACPR 2023

作者： Sun, Ying Hou, Zhiqiang Yang, Chen Ma, Sugang Fan, Jiulun School of Computer Science and Technology Xi’an University of Posts and Telecommunications Xi’an710121 China Key Laboratory of Network Data Analysis and Intelligent Processing of Shaanxi Province Xi’an710121 China School of Communications and Information Engineering Xi’an University of Posts and Telecommunications Xi’an710121 China

ISBN: (纸本)9783031476334

A dual-modal feature alignment based object detection algorithm is proposed for the full fusion of visible and infrared image features. First, we propose a two stream detection model. The algorithm supports simultaneous input of visible and infrared image pairs. Secondly, a gated fusion network is designed, consisting of a dual-modal feature alignment module and a feature fusion module. Medium-term fusion is used, which will be used as the middle layer of the dual-stream backbone network. In particular, the dual-mode feature alignment module extracts detailed information of the dual-mode aligned features by computing a multi-scale dual-mode aligned feature vector. The feature fusion module recalibrates the bimodal fused features and then multiplies them with the bimodal aligned features to achieve cross-modal fusion with joint enhancement of the lower and higher level features. We validate the performance of the proposed algorithm using both the publicly available KAIST pedestrian dataset and a self-built GIR dataset. On the KAIST dataset, the algorithm achieves an accuracy of 77.1%, which is 17.3% and 5.6% better than the accuracy of the benchmark algorithm YOLOv5-s for detecting visible and infrared images alone;on the self-built GIR dataset, the detection accuracy is 91%, which is 1.2% and 14.2% better than the benchmark algorithm for detecting visible and infrared images alone respectively. And the speed meets the real time requirements. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Multiple granularity network and dynamic label for domain adaptive person re-identification 4

Multiple granularity network and dynamic label for domain ad...

引用

2021 4th International Conference on Computer Information Science and Application Technology, CISAT 2021

作者： Wang, Xile Zhang, Sihan Song, Junyu Zhang, Miaohui Henan Key Laboratory of Big Data Analysis and Processing Henan University Henan Kaifeng475004 China School of Artificial Intelligence Henan University Henan Kaifeng475004 China

The domain adaptive person re-identification (Re-ID) has be more popular among researchers. Because it can save a lot of resources as it only exploits the source domain knowledge and does not need the complex annotation efforts in target domain. It aims to extend a model trained on a labeled dataset to another dataset which is unlabeled. Many works reduce feature distribution gap between two different datasets to solve the problem. However, these works ignore the problem which is the variations within an unlabeled dataset. In the paper, we propose a domain adaptive person Re-ID framework based on multiple granularity network and dynamic label (MGDL). Specifically, we send the images of two different datasets into multiple granularity network at the same time for joint training to reduce feature distribution gap which is between the two different datasets. The network is trained by two different kinds of pseudo labels, namely, conservative label and radical label. The two kinds of pseudo labels are used to alternating pull and push the feature distribution in the target domain to reduce the variations within an unlabeled dataset. Experiments have shown that the MGDL achieves competitive performance in person Re-ID which is under the cross-domain setting. © Content from this work may be used under the terms of the Creative Commons Attribution 3.0 Licence.

关键词：

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：