检索结果-内蒙古大学图书馆

IET International Radar Conference (IRC 2023)

作者： Shujie Wu Wei Wang Feng Ruan Huiqiang Zhang Jie Deng Pengcheng Guo Hongqi Fan Xi’an Electronic Engineering Research Institute Xi’an People's Republic of China National Key Laboratory of Science and Technology on Automatic Target Recognition National University of Defense Technology Changsha People's Republic of China

ISBN: (数字)9781837240982

The scattering characteristics of inshore ships in SAR images are similar to those of buildings and other man-made targets on land, making it difficult to detect them. In order to accurately detect the inshore ships in high-resolution SAR images, this paper proposes a multi-feature fusion method. Firstly, coarse sea-land segmentation is achieved by OTSU method and ROI (region of interest) is quickly determined by the maximum stability extremal region (MSER) method. After dividing the ROI into grid slices, the features of candidate targets and their surrounding backgrounds in the ROI are computed. And finally, background resolution (BR) is constructed by feature fusion to distinguish false alarm targets from real targets. Experiments based on satellite-based SAR data show that the method proposed in this paper has good detection accuracy and timeliness.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Small target Detection Algorithm Based on Two-Stage Feature Extraction

Small Target Detection Algorithm Based on Two-Stage Feature ...

引用

Software Engineering and Computer science (CSECS), International Conference on

作者： Wei Li Zhilong Zhang Chuwei Li Jiangwei Zou National Laboratory of Science and Technology on Automatic Target Recognition College of Electronic Science and Technology National University of Defense Technology Hunan Changsha China Innovation Center for Advanced Detection and Warning College of Electronic Science and Technologym National University of Defense Technology Hunan Changsha China

In the field of target detection, the traditional general algorithms based on open data sets such as Imagenet and COCO can not detect small targets well because of their small size and insignificant features. Considering that the feature information of small targets is mostly retained in the shallow layer of the network, this paper adds a detection head on the shallow layer of the backbone network on the basis of the general target detection algorithm, and introduces the shuffle attention mechanism to deeply integrate the feature information from different layers, so as to enhance the expression ability of the network for small targets. Compared with the original network, mAP has improved by 6.25% on the VisDrone dataset. At the same time, considering the difficulty of extracting the feature information of small targets in single-stage detection, we propose a two-stage detection framework that can be used on any detection algorithm. We process the images into blocks according to the size characteristics of the targets, carry out interpolation and redetection on the region of interest with low confidence, which makes the recall ability of small targets significantly improved. When the inference confidence threshold is 0.5, compared with the original network, the performance is improved by 4.24 % , which can significantly improve the ability of small targets detection.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The video SAR simulation algorithm based on the DEM and SBR

The video SAR simulation algorithm based on the DEM and SBR

引用

IET International Radar Conference (IRC 2023)

作者： Yongqiang Zhang Zhiyong Song Gang Lei XI’AN Electronic Engineering Research Institute XI’AN People's Republic of China National Key Laboratory of Science and Technology on Automatic Target Recognition College of Electronic Science National University of Defense Technology Changsha People's Republic of China

ISBN: (数字)9781837240982

This paper presents a rapid video synthetic aperture radar (SAR) simulation algorithm aimed at addressing the challenge of acquiring video SAR images. The proposed method independently simulates both targets and ground clutter. Background clutter is generated using a digital elevation map (DEM), while target echoes are simulated using Shooting and Bouncing rays (SBR). By employing ray tracing techniques, occlusion areas for both background clutter and targets are computed, thereby ensuring that the simulation results are adaptable to various algorithm development requirements. Ultimately, through a series of fast algorithms and GPU acceleration, significant reduction in simulation time is achieved, enabling rapid simulation of multiple video SAR images. This research provides abundant data sources for the study of video SAR detection, tracking, and recognition algorithms, offering robust support for practical applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sparse Aperture Based Radar Observation Resource Allocation Algorithm for Space target 3D Imaging 3

Sparse Aperture Based Radar Observation Resource Allocation ...

引用

3rd IEEE International Conference on Computer and Communication Engineering technology, CCET 2020

作者： Yang, Qingwei Jiang, Libing Yu, Xiang Zhou, Chaoxiang Wang, Zhuang National Key Laboratory of Science and Technology on Automatic Target Recognition National University of Defense Technology China

ISBN: (纸本)9781728188119

Radar imaging has been one of the basic functions for modern radar as well as searching, detection and tracking, especially for those ground-based space surveillance phased array radars. Due to the periodic revisiting characteristics of the in-orbit objects, multi-pass observations for space targets (e.g. satellites) within small pitching angle variation can be accumulated, which lead to the 3D inverse synthetic aperture radar (ISAR) image formation. Consequently, the strategy of allocating the limited radar observation resource for a reliable 3D ISAR imaging result is becoming a fundamental but critical issue. In this letter, a sparse aperture based radar observation resource allocating method is proposed to facilitate the space target 3D ISAR imaging. According to the sparsity estimation of the target along the azimuth dimension, the required observation resource is calculated and assigned in accordance with the imaging task priority. Furthermore, the experimental boundary of the imaging performance with different signal-to-noise ratios (SNR) and pulse extraction rates are discussed in detail, which gives an intuitive guidance for the radar observation allocation under different application scenarios. The experimental results performed on simulated data validate the feasibility and effectiveness of the proposed method. © 2020 IEEE.

关键词： Inverse synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

VMD-Inspired Bidirectional LSTM for Anomaly Detection of Hyperspectral Images 3

VMD-Inspired Bidirectional LSTM for Anomaly Detection of Hyp...

引用

3rd International Conference on Geology, Mapping and Remote Sensing, ICGMRS 2022

作者： He, Zhi Xiao, Man He, Dan Lou, Anjun Li, Xinyuan School of Geography and Planning Guangzhou510275 China National Key Laboratory of Science and Technology on Automatic Target Recognition China Sun Yat-sen University School of Geography and Planning Guangzhou510275 China School of Computer and Information Dongguan City College Dongguan511700 China Macau University of Science and Technology School of Computer Science and Engineering Faculty of Innovation Engineering China

ISBN: (数字)9781665485951

ISBN: (纸本)9781665485951

Anomaly detection plays an essential role in hyperspectral remote sensing. Various widespread detectors, such as ReedXiaoli (RX), sparse representation, or deep learning-based methods, have been developed by using the original spectral or spatial-spectral features. However, most of the existing methods cannot adaptively extract spatial-spectral information by integrating traditional and deep learning methods. In this paper, we propose a variational mode decomposition (VMD)-inspired bidirectional long short-term memory (termed as VbiLSTM) for anomaly detection of hyperspectral images (HSI). The VbiLSTM consists of three main modules, i.e., noise reduction module, intrinsic feature extraction module, and anomaly detection module. First, wavelet transform is performed on the original HSI datasets to reduce the noise. Second, VMD-guided biLSTM is proposed for intrinsic feature extraction of the denoised image. Finally, a one-class support vector machine (OCSVM) is adopted for anomaly detection by feeding the extracted features and the final detection results are an ensemble of detection results over all the features. Experiments performed on two HSI datasets demonstrate that the VbiLSTM achieves superior detection results compared with current state-of-the-art methods. © 2022 IEEE.

关键词： Variational mode decomposition

来源：评论

学校读者我要写书评

暂无评论

A Robust Hough Transform-Based Track Initiation Method for Multiple target Tracking in Dense Clutter 8th

A Robust Hough Transform-Based Track Initiation Method for M...

引用

8th International Conference on Communications, Signal Processing, and Systems, CSPS 2019

作者： Zhu, Qian Hu, Panhe Pan, Jiameng Bao, Qinglong Science and Technology on Automatic Target Recognition Laboratory National University of Defense Technology Changsha410072 China

ISBN: (纸本)9789811394089

Existing multiple track initiation methods based on Hough Transform have flaws, such as huge computation load in dense clutter environment and performance degradation in measurement error. To improve those defects, we propose a robust Hough Transform-based track initiation method for multiple target tracking in dense clutter. The whole proposed method is divided into three steps. The first step is to screen data through the grid-based velocity test. The second step is to cluster the screened data into groups based on eight connectivity principle of grids. The last step is to respectively make Hough Transform on each group data to achieve track initiation. The experiment results illustrate the proposed algorithm outperforms traditional algorithms on Hough transform based track initiation. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Hough transforms

来源：评论

学校读者我要写书评

暂无评论

Efficient Visual Tracking via Hierarchical Cross-Attention Transformer

arXiv

引用

arXiv 2022年

作者： Chen, Xin Kang, Ben Wang, Dong Li, Dongdong Lu, Huchuan School of Information and Communication Engineering Dalian University of Technology China National Key Laboratory of Science and Technology on Automatic Target Recognition National University of Defense Technology China Peng Cheng Laboratory China

In recent years, target tracking has made great progress in accuracy. This development is mainly attributed to powerful networks (such as transformers) and additional modules (such as online update and refinement modules). However, less attention has been paid to tracking speed. Most state-of-the-art trackers are satisfied with the real-time speed on powerful GPUs. However, practical applications necessitate higher requirements for tracking speed, especially when edge platforms with limited resources are used. In this work, we present an efficient tracking method via a hierarchical cross-attention transformer named HCAT. Our model runs about 195 fps on GPU, 45 fps on CPU, and 55 fps on the edge AI platform of NVidia Jetson AGX Xavier. Experiments show that our HCAT achieves promising results on LaSOT, GOT-10k, TrackingNet, NFS, OTB100, UAV123, and VOT2020. Code and models are available at https://***/chenxin-dlut/HCAT. Copyright © 2022, The Authors. All rights reserved.

关键词： target tracking

来源：评论

学校读者我要写书评

暂无评论

Dynamic selection track fusion algorithm based on comprehensive measurement of local track quality

Dynamic selection track fusion algorithm based on comprehens...

引用

第四届材料科学应用与能源材料国际研讨会

作者： Xu Zhen Fang Liu National Key Laboratory of Science and Technology on Automatic Target Recognition National Defense Science and Technology University

The known track fusion algorithms do not select the local tracks, but fuse all the local tracks, resulting in the degradation of the system track quality after fusion. In order to improve the tracking performance, a dynamic selection track fusion algorithm based on the comprehensive measurement of local track quality is proposed. The algorithm generates local track and information entropy through Interactive Multiple Model(IMM) compensation filtering, and forms temporary systemic track. Based on local track, information entropy and temporary systemic track, local track similarity and the measurement of track quality based on information entropy are generated, which are used to modify temporary systemic track, realize dynamic selection fusion of local track, and improve track quality after fusion. The simulation results show that the tracking performance of the proposed algorithm is better than the known track fusion algorithm when considering different accuracies of sensors and incomplete measurement.

关键词： Dynamic selection track fusion algorithm based on comprehensive measurement of local track quality

来源：评论

学校读者我要写书评

暂无评论

Attention Scale-Aware Deformable Network for Inshore Ship Detection in Surveillance Videos 1st

Attention Scale-Aware Deformable Network for Inshore Ship D...

引用

1st CAAI International Conference on Artificial Intelligence, CICAI 2021

作者： Liu, Di Zhang, Yan Zhao, Yan Zhang, Yu National Key Laboratory of Science and Technology on Automatic Target Recognition College of Electronic Science and Technology National University of Defense Technology Changsha410073 China State Key Laboratory of Complex Electromagnetic Environment Effects on Electronics and Information System College of Electronic Science and Technology National University of Defense Technology Changsha410073 China

ISBN: (纸本)9783030930455

Aiming at detecting multi-scale inshore ships in surveillance videos, a one-stage detector namely Attention Scale-aware Deformable Network (ASDN) is proposed in this paper by employing two primary components including Attention Scale-aware Module (ASM) and Deformable Convolutional Network (DCN). Moreover, ASM composed of several branches of convolutions with specially designed kernels and a Convolutional Block Attention Modules (CBAM), is designed for extracting and refining non-local features of multi-scale inshore ships with large aspect ratios at the topmost feature layer. DCN is adopted to capture irregular significant features of ships by modulating input features using parameterized offsets and amplitudes at lateral connections of fine-grained feature pyramid. Experiments conducted on public Seaships7000 dataset demonstrate the contributions of ASM and DCN, and the effectiveness of our method for multi-scale inshore ship detection in surveillance videos in comparison with other Convolutional Neural Network (CNN) based methods, e.g., FPN, Libra R-CNN, SSD, YOLOv3, RefineDet. © 2021, Springer Nature Switzerland AG.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Multiple Frames Based Infrared Small target Detection Method Using CNN 21

Multiple Frames Based Infrared Small Target Detection Method...

引用

Proceedings of the 2021 4th International Conference on Algorithms, Computing and Artificial Intelligence

作者： Jinming Du Dongyang Li Yingjie Deng Luping Zhang Huanzhang Lu Moufa Hu Xinglin Shen Zhuoqun Liu Xuhuan Ji National Key Laboratory of Science and Technology on Automatic Target Recognition College of Electronic Science and Technology National University of Defense Technology China College of Military Basic Education National University of Defense Technology China

ISBN: (纸本)9781450385053

In the field of infrared, the detection of dim small target has been a challenging topic. Especially in the complex background, a large number of false alarms might appear when using traditional detection methods, this cannot meet the dual requirements of high detection rate and low false alarm rate. Therefore, in this paper, a CNN based target detection method is proposed for infrared sequence. For an image to be detected, firstly, aiming at the noise and interference which are spatially non-stationary but temporally stable, the method of registration and frame difference is used to suppress the background and extract the target, and the motion information between nearby frames is obtained; next, the extracted information is fed into the light CNN network for the extraction and fusion of different level features; finally, based on the fusion features the small target is detected. The proposed multiple frames based method relies on neural network to extract the motion information in infrared sequence to enhance the distinguishability of the target features under complex condition. Compared with the traditional methods, experimental results show that the proposed CNN method can achieve higher detection rate and lower false alarm rate, especially for the detection of dim small targets in complex background, the advantage is more obvious.

关键词： Multiple Frames target Detection CNN Deep learning

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：