检索结果-内蒙古大学图书馆

Cost-Benefit Analysis of Metavariable Variation in Convolutional Autoencoders Applied to Acoustic Backscattering data from small Underwater targets

Cost-Benefit Analysis of Metavariable Variation in Convoluti...

引用

OCEANS Hampton Roads Conference

作者： Linhardt, Timothy Sen Gupta, Ananya Univ Iowa Dept Elect & Comp Engn Iowa City IA 52242 USA

ISBN: (数字)9781665468091

ISBN: (纸本)9781665468091

With an end goal of physically interpretable results, we build on progress towards finding generalized low dimension encodings of acoustic backscattering data from sonar measurements of small targets submerged in water. The data set in use is TREX-13. The initial effort succeeded in learning non-invertible mappings (encodings) of the data to a low-dimensional vector space with convolutional autoencoders and sparse convolutional autoencoders. The prior work largely used default values for various "metavariables" according to the Keras and Tensorflow library specifications. Mitigating the failure rate of network training as well as ancillary increases in signal reconstruction accuracy and network training speed are the goals of our current efforts. The metavariables in question are the number of convolutional kernels in each network layer, the layer count, the size of the convolutional kernels, the technique for randomly initializing the values of the kernels, and the choice of nonlinear activation functions between network layers. We perform some cost benefit analysis for the modifications in terms of training time, reconstruction accuracy, and GPU memory utilization, and decide whether to continue using the variations in further research.

关键词： machine learning autoencoder signal processing metavariable acoustics

来源：评论

学校读者我要写书评

暂无评论

FBI-Net: Frequency Band Integration Network for Infrared small Target Segmentation

FBI-Net: Frequency Band Integration Network for Infrared Sma...

引用

International Conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Biqiao Xin Qiang Li Qianchen Mao Jinbao Wang Bingshu Wang School of Software Northwestern Polytechnical University Xi’an China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

small targets in infrared imagery exhibit challenging characteristics due to their minimal semantic information and the extremely imbalanced distribution between the targets and the background. In this paper, we propose a frequency band integration network to extract salient features of infrared small targets in both the spatial and frequency domains. To excavate the high-frequency features of the small targets, we propose a frequency decoupling-fusion module. To decrease the semantic loss that occurs in deep networks, we propose a semantic injection mechanism to assist in retaining critical information from shallow layers. Experimental results show that our proposed method reaches higher prediction accuracy and robustness in the infrared small target segmentation task compared with other state-of-the-art approaches.

关键词： Wavelet transforms Frequency-domain analysis Semantics signal processing Feature extraction Excavation Robustness Real-time systems Complexity theory Speech processing

来源：评论

学校读者我要写书评

暂无评论

CNN-based infrared dim small target detection algorithm using target-oriented shallow-deep features and effective small anchor

引用

IET IMAGE processing 2021年第1期15卷 1-15页

作者： Du, Jinming Lu, Huanzhang Hu, Moufa Zhang, Luping Shen, Xinglin Natl Univ Def Technol Coll Elect Sci & Technol Changsha 410073 Peoples R China

For the extremely small size and low signal-to-clutter ratio, target detection in infrared images is still a considerable challenge. Specifically, it is very difficult to detect the point targets because there is no texture and shape information can be used. A target-oriented shallow-deep feature-based detection algorithm is proposed, opening up a promising direction for convolutional neural network-based infrared dim small target detection algorithms. To ensure that small target instances can be used correctly for networks, the effective small anchor is designed according to the shallow layer of ResNet50. To determine whether a detection result belongs to the target, the authors depend on whether the detection centre is included in the ground truth area, rather than on the Intersection Over Union overlap rate, which avoids misjudging the detection result. In this way, small targets can be trained and detected correctly through ResNet50. More importantly, the authors demonstrate that spatially finer shallow features are crucial for small target detection and that semantically stronger deep features are helpful for improving detection probability. Experimental results on simulation data sets and real data sets show that the proposed algorithm can detect the point target when the local signal-to-clutter ratio is approximately 1.3, displaying infinite advantage and great potentiality.

关键词： Instrumentation and techniques for geophysical, hydrospheric and lower atmosphere research Optical, image and video signal processing Computer vision and image processing techniques

来源：评论

学校读者我要写书评

暂无评论

Research on Enterprise Innovation Interaction Model Based on Complex Network and Big data Analysis 4

Research on Enterprise Innovation Interaction Model Based on...

引用

4th International signal processing, Communications and Engineering Management Conference, ISPCEM 2024

作者： Zhang, Lili Guangxi Vocational Normal University Nanning Guangxi China

ISBN: (纸本)9798331528676

This paper proposes an enterprise innovation interaction model based on complex network and big data analysis. The model uses PageRank algorithm to analyze the importance of each node in the enterprise innovation network, identify the core enterprises in the innovation activities and their key roles in the cooperation network. By constructing a complex network, the cooperation relationship in the enterprise innovation system is visualized, and valuable interaction patterns are extracted by combining big data analysis. The system design includes modules such as data preprocessing, complex network construction and PageRank algorithm implementation, which can effectively improve the accuracy of enterprise innovation interaction. During the simulation process, the paper used a real data set containing 500 enterprises and 2000 cooperation projects. The results show that the system can significantly improve the efficiency of identifying key nodes in the cooperation network between enterprises. The node importance identification accuracy of the PageRank algorithm reaches 93.2%, which is about 10% higher than the traditional method. In addition, the simulation results show that the prediction accuracy of core node identification and innovation interaction patterns in complex networks has also been significantly improved. ©2024 IEEE.

关键词： data accuracy

来源：评论

学校读者我要写书评

暂无评论

A Low Slow small Target Stable Tracking Method for Vehicle-Borne Radar During Movement 4

A Low Slow Small Target Stable Tracking Method for Vehicle-B...

引用

4th China International SAR Symposium, CISS 2023

作者： Feng, Zhengkang Zhang, Jiayi Huang, Panpan Xu, Jiahui Chen, Junji Ye, Zhou Shanghai Aerospace Electronic Technology Institute Shanghai China Aerospace System Engineering Shanghai Shanghai China

ISBN: (纸本)9798350307955

When the vehicle is working in motion, firstly, combined with the characteristics of low slow small targets, the problems affecting radar stable tracking are analyzed, including the impact on target detection and target tracking. Then, starting from the radar system software module, the Doppler frequency is compensated in the signal processing software. In the data processing software. the attitude and position of the point are finely compensated. In the resource management software, the predicted attitude is used to compensate the beam, and the shaking state of the vehicle is judged to arrange the beam management. Finally, through the multiple flight tests of a phased array radar on the UAV target, it is shown that the method can effectively complete the function of stable target tracking. © 2023 IEEE.

关键词： Target tracking

来源：评论

学校读者我要写书评

暂无评论

Holographic Radar Tracking Algorithm for "Low-Slow-small" Maneuvering targets

Holographic Radar Tracking Algorithm for "Low-Slow-Small" Ma...

引用

IET International Radar Conference 2023, IRC 2023

作者： Niu, Guo Zhu, Nannan Fang, Xueqing Lei, Xueyue Wang, Yifan Zhong, Fuli Foshan University Foshan China Sun Yat-Sen Univiersity Guangzhou China Jinan University Guangzhou China Guangzhou Communications Technician Institute Guangzhou China

ISBN: (纸本)9781839539954

The proliferation of unauthorized flights and incidents involving "low-slow-small" maneuvering targets presents an increasing threat to national security and the normal progression of the national economy. Effectively addressing the threat has emerged as a vital task in upholding the security of the nation, society, and economy. This paper focuses on the attributes of "low-slow-small" targets and leverages the characteristics of holographic radar echoes to propose a Doppler-based Interaction Multiple Model Multiple Hypothesis Tracking (DIMM-TOMHT) algorithm. This algorithm yields the following advantages: 1) The tracking gate constructed by a single prediction step of the DIMM-TOMHT algorithm encompasses dimensions of Doppler velocity components. Owing to distinct disparities in position and velocity between targets and clutter, the multi-dimensional tracking gate containing Doppler components eliminates numerous irrelevant measurements, thereby reducing computational burden of the tracking algorithm while enhancing the accuracy of correlation and precision of target tracking. 2) To attain optimal global hypothesis trajectories, the DIMM-TOMHT algorithm computes scores for each hypothetical trajectory iteratively, which is employed for confirming transient trajectories and eliminating old trajectories. The algorithm inherently integrates aspects of trajectory management, thereby mitigating the complexity of multi-object tracking systems. Empirical data validate the efficacy of this algorithm in tracking "low-slow-small" targets. © The Institution of Engineering & Technology 2023.

关键词： Object tracking

来源：评论

学校读者我要写书评

暂无评论

基于多域雷达回波数据融合的海面小目标分类网络模型

引用

电子与信息学报 2025年第3期47卷 696-706页

作者：赵子健许述文水鹏朗西安电子科技大学雷达信号处理全国重点实验室西安710071

海面小目标识别是海事雷达监视任务中一个重要且具有挑战性的问题。由于海面小目标类型多样、环境复杂多变,对其进行有效分类存在较大困难。在高分辨体制雷达下,海面小目标通常只占据一或几个距离单元,缺乏足够的空间散射结构信息,因此... 详细信息

海面小目标识别是海事雷达监视任务中一个重要且具有挑战性的问题。由于海面小目标类型多样、环境复杂多变,对其进行有效分类存在较大困难。在高分辨体制雷达下,海面小目标通常只占据一或几个距离单元,缺乏足够的空间散射结构信息,因此目标的雷达截面积(RCS)起伏和径向速度变化成为分类的主要依据。为此,该文提出一种基于多域雷达回波数据融合的分类网络模型,用于海面小目标的分类任务。由于不同域的数据具有其特殊的物理意义,因此该文构建了时域LeNet(T-LeNet)神经网络模块和时频特征提取神经网络模块,分别从雷达海面回波信号的幅度序列和时频分布(TFD)即时频图中提取特征。其中幅度序列主要反映了目标RCS的起伏特性,而时频图不仅反映RCS起伏特性,还能体现目标径向速度的变化。最后,利用IPIX,CSIR数据库和自测的无人机数据集构建了包括4种海面小目标的数据集:锚定漂浮小球、漂浮船只、低空无人机(UAV)和移动的快艇。实验结果表明所提方法具有良好的识别能力。

关键词：海面小目标目标分类多特征融合神经网络

来源：评论

学校读者我要写书评

暂无评论

Imaging Detection and Classification for Near-space Dim targets 7

Imaging Detection and Classification for Near-space Dim Targ...

引用

7th International Conference on Vision, Image and signal processing, ICVISP 2023

作者： Yuan, Yupu Xi, Runping Chen, Qian School of Computer Science Northwestern Polytechnical University Xi'an China Shaanxi Province Key Laboratory of Speech & Image Processing Xi'an China National Engineering Laboratory of Integrated Aero-Space-Ground-Ocean Big Data Application Technology Xi'an China

ISBN: (纸本)9781839539848

The motion mode of near-space targets is complex due to their high threat level. The target imaging faces low SNR and susceptibility to background noise. The existing detection and classification algorithms struggle to meet the demands of performance and speed on such targets. To address these issues, a YOLOv5-based target detection algorithm utilizes CARAFE upsampling and the small detection head to extract internal features and edge information of dim target. The algorithm adeptly captures dim target features, enhancing real-time performance and detection accuracy while overcoming subtle feature granularity and extraction difficulties. Aiming at the problem that there is no existing trajectory classification algorithm in the near-space field, we propose an infrared dim target trajectory classification algorithm. The improved attention module is used to enhance the extraction of motion features, and the target category is accurately identified by the prediction module, improving the capacity to extract dependencies between trajectory fragments. We execute comparative experiments on common infrared dim target dataset, near-space infrared dim target dataset and real dataset to confirm the viability of our methods. The outcomes indicate that our proposed method can be applied to the above three types of dim targets and significantly outperforms state-of-the-art methods. © The Institution of Engineering & Technology 2023.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Three-dimensional SAR imaging with sparse linear array using tensor completion in embedded space

引用

EURASIP JOURNAL ON ADVANCES IN signal processing 2022年第1期2022卷 1-18页

作者： Zhang, Siqian Ding, Ding Zhao, Chenxi Zhao, Lingjun Natl Univ Def Technol Coll Elect Sci State Key Lab Complex Electromagnet Environm Effe Changsha 410073 Peoples R China Natl Univ Def Technol Ctr Teaching & Res Serv Changsha 410073 Peoples R China

Due to the huge data storage and transmission pressure, sparse data collection strategy has provided opportunities and challenges for 3D SAR imaging. However, sparse data brought by the sparse linear array will produce high-level side-lobes, as well as the aliasing and the false-alarm targets. Simultaneously, the vectorizing or matrixing of 3D data makes high computational complexity and huge memory usage, which is not practicable in real applications. To deal with these problems, tensor completion (TC), as a convex optimization problem, is used to solve the 3D sparse imaging problem efficiently. Unfortunately, the traditional TC methods are invalid to the incomplete tensor data with missing slices brought by sparse linear arrays. In this paper, a novel 3D imaging algorithm using TC in embedded space is proposed to produce 3D images with efficient side-lobes suppression. With the help of sparsity and low-rank property hidden in the 3D radar signal, the incomplete tensor data is taken as the input and converted into a higher order incomplete Hankel tensor by multiway delay embedding transform (MDT). Then, the tucker decomposition with incremental rank has been applied for completion. Subsequently, any traditional 3D imaging methods can be employed to obtain excellent imaging performance for the completed tensor. The proposed method achieves high resolution and low-level side-lobes compared with the traditional TC-based methods. It is verified by several numerical simulations and multiple comparative studies on real data. Results clearly demonstrate that the proposed method can generate 3D images with small reconstruction error even when the sparse sampling rate or signal to noise ratio is low, which confirms the validity and advantage of the proposed method.

关键词： 3D SAR Incomplete data Low rank Tensor completion signal reconstruction

来源：评论

学校读者我要写书评

暂无评论

AN AUTONOMOUS FEATURE DETECTION METHOD FOR SLOW small targets ON SEA SURFACE BASED ON CONTEXTUAL BANDIT APPROACH

AN AUTONOMOUS FEATURE DETECTION METHOD FOR SLOW SMALL TARGET...

引用

IET International Radar Conference 2023, IRC 2023

作者： Wu, Xijie Liu, Tianpeng Liu, Yongxiang Liu, Li Xu, Jianfeng Zhu, Jing National University of Defense Technology Changsha410005 China Rocket Force University of Engineering Xi'an710025 China Unit 92192 of the PLA China

ISBN: (纸本)9781839539954

This paper combines the contextual bandit approach with existing feature detection process, and then proposes an autonomous feature detection method of slow small targets on sea surface based on contextual bandit approach. The method is divided into the training stage and detection stage. In training stage, the method utilizes a large amount of sea clutter data collected in advance to generate the decision regions corresponding to existing feature detectors. In detection stage, every time the radar receives a frame of data, the method selects a feature detector in real time through the modified kernel-based upper confidence bound policy proposed in this paper. Finally, the decision region of real-time detector is used to detect the target in current frame. The superior performance of proposed method is verified by the measured sea clutter datasets. © The Institution of Engineering & Technology 2023.

关键词： Radar clutter

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：