检索结果-内蒙古大学图书馆

10th International Conference on Control, Automation and Information sciences, ICCAIS 2021

作者： Sun, Tianren Jiang, Libing Chen, Chen Zheng, Shuyu Ding, Rui National University of Defence Technology National Key Laboratory of Science and Technology on Automatic Target Recognition Changsha410072 China

ISBN: (纸本)9781665440295

Real-time detection of time-critical ground targets by wideband radar is a vital task for missiles and unmanned aerial vehicles. It is challenging to give consideration to efficiency and performance with low signal-to-noise ratio, non-uniform clutter distribution, radar cross section fluctuation, multiple-target overlapping, and interfering objects. This paper presents a complete method including integration, detection and tracking. First, an improved non-coherent integration algorithm based on velocity prediction via Keystone transform is designed to achieve fast energy focusing of weak targets. Then, an anti-false-alarm CCA-CFAR based on clutter energy balance process is used to extract reliable observations. Finally, a real-time multi-target tracking and error correction algorithm based on the estimation of the number of targets is proposed, which realizes real-time target tracking and elimination of false alarms, and reduces the missed detection caused by the phenomenon of radar cross section fluctuation and multiple-target overlapping. Experimental results based on practical data show that the proposed method effectively reduces false alarms and missed detections, and achieves real-time, continuous and accurate detections under complex condition. © 2021 IEEE.

关键词： Radar cross section

来源：评论

学校读者我要写书评

暂无评论

Cascaded GLRT Radar/Infrared Lidar Information Fusion Algorithm for Weak target Detection

Cascaded GLRT Radar/Infrared Lidar Information Fusion Algori...

引用

International Conference on Wireless Communications, Networking and Applications, WCNA 2021

作者： Wu, Peixuan Du, Xiaoyong Hu, Weidong National Key Laboratory of Science and Technology on Automatic Target Recognition National University of Defense Technology Changsha410073 China

ISBN: (纸本)9789811924552

To deal with the problem of weak target detection, a cascaded generalized likelihood ratio test (GLRT) radar/infrared lidar heterogeneous information fusion algorithm is proposed in this paper. The algorithm makes full use of the target characteristics in microwave/infrared spectrum and the scanning efficiency of different sensors. According to the correlation of target position in the multi-sensor view field, the GLRT statistic derived from the radar measurements is compared with a lower threshold so as to generate initial candidate targets with high detection probability. Subsequently, the lidar is guided to scan the candidate regions and the final decision is made by GLRT detector to discriminate the false alarm. To get the best detection performance, the optimal detection parameters are obtained by nonlinear optimization for the cascaded GLRT Radar/Infrared lidar heterogeneous information fusion detection algorithm. Simulation results show that the cascaded GLRT heterogeneous information fusion detector comprehensively utilizes the advantages of radar and infrared lidar sensors in detection efficiency and performance, which effectively improves the detection distance upon radar weak targets within the allowable time. © 2022, The Author(s).

关键词： Information fusion

来源：评论

学校读者我要写书评

暂无评论

Study on reflection separation based on orthogonal polarization images 4

Study on reflection separation based on orthogonal polarizat...

引用

2021 4th International Conference on Advanced Algorithms and Control Engineering, ICAACE 2021

作者： Zhang, Jinghua Zhang, Yan Shi, Zhiguang Li, Biao Zhang, Yu Ling, Feng Suo, Yuchang Liu, Di National Key Laboratory of Science and Technology on Automatic Target Recognition National University of Defense Technology Changsha410073 China

In this paper, a deep learning method based on polarization image is proposed. Firstly, the polarization characteristics of reflected light and transmitted light are analyzed by using the Fresnel's law. Then, based on the polarization characteristics that the reflected light is polarized in the perpendicular direction and the transmitted light is polarized in the parallel direction, the polarization images obtained from the parallel direction and the perpendicular direction are input into the Encoder-Decoder net at the same time, and the net is trained by L1 loss. The experimental results show that by combining the polarization information and deep learning method, the reflected component and transmitted component can be effectively separated. © Published under licence by IOP Publishing Ltd.

关键词： Light transmission

来源：评论

学校读者我要写书评

暂无评论

Calculation of the degree of polarization based on the correlation between reflection and transmission 2

Calculation of the degree of polarization based on the corre...

引用

2021 2nd International Workshop on Electronic communication and Artificial Intelligence, IWECAI 2021

作者： Zhang, Jinghua Zhang, Yan Shi, Zhiguang Yu, Zhang Feng, Ling Di, Liu Xiaoran, Shi Yuchang, Suo National Key Laboratory of Science and Technology on Automatic Target Recognition National University of Defense Technology Changsha410073 China

Polarization is a basic property of light. In nature, polarization is mainly caused by the refraction and reflection on the surface of objects. The polarization of light can be measured quantitatively by the degree of polarization. By calculating the degree of polarization of an object's surface, we can obtain the effective information for target detection, recognition, material judgment, and so on. The reflection and refraction effects occur simultaneously on the surface of transparent objects, so the measurement of the degree of reflection and transmission polarization is a challenge problem. In this paper, a method based on normalized crosscorrelation is proposed to extract the zero point pixels, and the degree of reflection and transmission polarization can be effectively calculated by using the zero point pixels. © Published under licence by IOP Publishing Ltd.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Multi-view robust adversarial attack: a method based on channel attention weighted feature similarity constraint 4

Multi-view robust adversarial attack: a method based on chan...

引用

4th International Conference on Signal Processing and Computer science, SPCS 2023

作者： Li, Yongqian Zhang, Yu Zhang, Yichuang Qi, Jiahao Zhong, Ping National Key Laboratory of Science and Technology on Automatic Target Recognition National University of Defense Technology Changsha410073 China

ISBN: (纸本)9781510672505

Although deep learning has developed rapidly in recent years, the existence of adversarial examples casts a shadow over its future. Deep neural networks (DNNs) can be unreliable when facing these carefully crafted adversarial examples, limiting their real-world applications. While adversarial examples usually lack robustness and tend to lose effect when the viewing angle is changed. Moreover, it is impossible to control the angle at which adversarial examples are seen by the airborne detector. Therefore, we propose a multi-view robust adversarial attack by introducing perspective transformation and feature similarity loss to mitigate the negative effect that viewing angle changes bring to the features. We evaluated our adversarial patch on our multi-view test dataset and the results show that our proposed method reduced the mAP by 73.4%. Furthermore, compared to other methods, our approach performs best in the data with low depression angles, demonstrating its excellent multi-view robustness. © 2023 SPIE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

A method of ISAR sequences quality assessment for aerospace target

A method of ISAR sequences quality assessment for aerospace ...

引用

作者： Li, Gang Hou, Qingkai Xu, Shiyou Chen, Zengping Science and Technology on Automatic Target Recognition Laboratory National University of Defense Technology Changsha China

ISBN: (纸本)9781934142301

In this paper, the traditional ISAR image quality evaluation standard and its limitation is analyzed. An ISAR quality evaluation method of aerospace targets is presented, combining with ISAR imaging mechanism and the structural characteristics of aerospace targets, referencing the standard of optical image quality evaluation. Beyond some current commonly used indications, a new indication based on the power spectrum is adopted in this method. The simulation data and real data show the validity of the algorithm.

关键词： Quality control

来源：评论

学校读者我要写书评

暂无评论

Entrepreneur and WIE STAR [Women to Watch]

引用

IEEE Women in Engineering Magazine 2016年第2期10卷 21-24页

作者： Williams, Katianne Science and Technology on Automatic Target Recognition Laboratory National University of Defense Technology Changsha Hunan China School of Economics and Management Tongji University Shanghai P.R. China

Min Chen was four years old when her family left China for a new life in Panama. Although her father was a skilled electrical and electronics engineer, Chen recalls the jobs waiting for him in Panama as typical immigrant labor. His father used his skills wherever he could-remodeling buildings, assembling equipment for restaurants, or repairing machines for factories. Chen's mother, who had worked in the electronics industry back in China, stayed home to take care of Min and her young brother. © 2016 IEEE.

关键词： Electronics industry

来源：评论

学校读者我要写书评

暂无评论

Enhanced Deeplab Network for Infrared Small target Detection 8

Enhanced Deeplab Network for Infrared Small Target Detection

引用

8th International Conference on Signal and Image Processing, ICSIP 2023

作者： Yao, Jiping Xiao, Shanzhu Tao, Huamin Wen, Gongjian Zhang, Luping Meng, Ying National University of Defense Technology Key Laboratory of Automatic Target Recognition Changsha China

ISBN: (纸本)9798350397932

With the development of deep-learning methods, convolutional neural networks are widely used to detect infrared small targets. But as the pooling layers get deeper, detailed information about infrared small targets will be lost since the infrared targets are dim and small. Thus we proposed an infrared small target detection network based on the deeplabv3+ model. In the proposed model, high-level semantic information and low-level high-resolution information are fused to extract the feature of infrared targets. Besides, SA attention module is adopted to extract the feature of infrared targets more precisely and suppress the noise of the background by using an attention mechanism before fusion. Experiments on open-source dataset sirstaug prove that our method EDeeplab is superior to other state-of-the-art methods. © 2023 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Knowledge Distillation Algorithm of Feature Reconstruction Based on Feature Maps of the Middle Layer 4

Knowledge Distillation Algorithm of Feature Reconstruction B...

引用

4th International Conference on Advances in Computer technology, Information science and Communications, CTISC 2022

作者： Peng, Xuan Liu, Fang School of Electronic Science National University of Defense Technology National Key Laboratory of Science and Technology on Automatic Target Recognition Changsha China

ISBN: (数字)9781665458726

ISBN: (纸本)9781665458726

Knowledge distillation is an effective model compression technology. As the main research branch, the knowledge distillation based on the middle layer focuses on extracting the network representation knowledge in the hidden layer to improve student learning performance. To fully utilize the process knowledge of the teacher model, an algorithm of the feature reconstruction based on middle-layer feature maps is proposed, which embeds middle-layer feature maps of the student network into the teacher network group by group. We introduce the intermediate soft-hard label contained process knowledge of the network with the help of pre-trained module group of the teacher network in loss function. This can increase the coupling of the teacher-student network in the process of knowledge transfer and improve the intrinsic knowledge inheritance of the compressed student model to the teacher network. The experimental results on the CIFAR-10 and CIFAR-100 verify the effectiveness and scalability of this method. © 2022 IEEE.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

An improved fast mean shift algorithm for segmentation

An improved fast mean shift algorithm for segmentation

引用

2010 International Conference on Computer Application and System Modeling, ICCASM 2010

作者： Qian, Zhiming Zhu, Changren Wang, Runsheng Automatic Target Recognition Laboratory National University of Defense Technology Changsha Hunan China

ISBN: (纸本)9781424472369

The mean shift algorithm is a statistical iterative algorithm based on kernel density estimation which has been widely used in many fields. This paper improves the mean shift algorithm by adopting the following approaches. Firstly, we present a novel approach named Random Sampling with Contexts (RSC) to speed up the mean shift algorithm. Secondly, we introduce Dempster-Shafer (D-S) theory for the fusion of features to improve the segmenting quality. Moreover, experimental results show that the new algorithm is superior to the typical mean shift algorithm. © 2010 IEEE.

关键词： Iterative methods

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：