检索结果-内蒙古大学图书馆

Artificial Intelligence, Networking and Information technology (AINIT), International Seminar on

作者： Jiaxuan Liu Jiahao Qi Ping Zhong Junhe Jiang Key Laboratory of Science and Technology on Automatic Target Recognition National University of Defense Technology Changsha China Science and Technology on Near-Surface Detection Laboratory Wuxi China

ISBN: (数字)9798350385557

ISBN: (纸本)9798350385564

The existing hyperspectral underwater target detection algorithms are ineffective in adapting to nearshore environments, owing to the difficulty of extracting target signals from cluttered nearshore backgrounds combined with weak target signals. To this end, hyperspectral unmixing (HU) is well suited in this paper for nearshore underwater target detection (UTD) task to address these issues, by extracting background endmembers and separating out weak target signals simultaneously. Specifically, we propose a novel nonlinear unmixing network for nearshore underwater target detection (NUN-UTD). It comprises an unsymmetrical autoencoder and a target prior preservation module to adapt to the complex nearshore environment. Experiments demonstrate that NUN-UTD achieves the best detection performances and visual results compared with other state-of-the-art methods.

关键词： Seminars Visualization Object detection Task analysis Information technology Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

3D object tracking with transformer

arXiv

引用

arXiv 2021年

作者： Cui, Yubo Fang, Zheng Shan, Jiayao Gu, Zuoxu Zhou, Sifan Northeastern University Shenyang China Science and Technology on Near-Surface Detection Laboratory Wuxi China

Feature fusion and similarity computation are two core problems in 3D object tracking, especially for object tracking using sparse and disordered point clouds. Feature fusion could make similarity computing more efficient by including target object information. However, most existing LiDAR-based approaches directly use the extracted point cloud feature to compute similarity while ignoring the attention changes of object regions during tracking. In this paper, we propose a feature fusion network based on transformer architecture. Benefiting from the self-attention mechanism, the transformer encoder captures the inter- and intra- relations among different regions of the point cloud. By using cross-attention, the transformer decoder fuses features and includes more target cues into the current point cloud feature to compute the region attentions, which makes the similarity computing more efficient. Based on this feature fusion network, we propose an end-to-end point cloud object tracking framework, a simple yet effective method for 3D object tracking using point clouds. Comprehensive experimental results on the KITTI dataset show that our method achieves new state-of-the-art performance. Code is available at: https://***/3bobo/lttr. © 2021, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Semantic Segmentation for Evaluation of Defects on Smartphone Screens 5th

Semantic Segmentation for Evaluation of Defects on Smartphon...

引用

5th International Conference on Cognitive Systems and Signal Processing, ICCSIP 2020

作者： Zhu, Huijie Shen, Zhuohao Yuan, Shenggui Chen, Fuliang Li, Jinhui Science and Technology on Near-Surface Detection Laboratory Wuxi214035 China Department of Automation Shanghai Jiao Tong University Shanghai200240 China School of Software Engineering Shanghai Jiao Tong University Shanghai200240 China

ISBN: (纸本)9789811623356

Smartphone recycling is a heated topic recently because of environmental and economical concerns. However, the limited recognition ability of naked eyes to find defects on phones impedes further growth of the second-hand markets. Related work for this problem focuses on detection and feature extraction, which can be tough because of the thin shapes of the defects and similar characteristics obstructing discrimination between scratches and cracks. In this paper, we propose an algorithm using semantic segmentation based on HRNet to build an effective model to evaluate defects of screens quickly and precisely. We improve the performance of the model by introducing the Lovász-Softmax loss function and data augmentation. Peripheral methods including subdivision and postprocessing are proposed to reduce misprediction on small scratches and enforce reliability in practice. We compare our model with other networks on mIoU and Kappa scores, concluding on an empirical basis. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Priority Based Adaptive MAC Protocol for UAV Ad Hoc Networks 7

Priority Based Adaptive MAC Protocol for UAV Ad Hoc Networks

引用

7th International Conference on Computer and Communications, ICCC 2021

作者： Mou, Xinglin Li, Hao Yan, Feng Ding, Kai Wu, Tao Xia, Weiwei Shen, Lianfeng Southeast University National Mobile Communications Research Laboratory Nanjing210096 China Science and Technology On Near-Surface Detection Laboratory Wuxi214035 China Jiangsu ZhongLi Electronic Information Sci-Tech Co. Ltd Changshu215542 China

ISBN: (纸本)9781665409506

In this paper, a priority based adaptive MAC protocol (PM-MAC) is proposed for UAV ad hoc networks. Firstly, in the protocol, the arriving packets are classified into different queues according to the priority of services. A Markov chain model is proposed to analyze the channel access probabilities of different queues. and it is ensured that packets with high priority can access the channel with high probability. Secondly, the size of contention window is adaptively adjusted based on backoff times and the current packet size. Finally, simulation results show that PM-MAC can guarantee the access requirements of high priority packets, and compared with the traditional backoff method, the backoff mechanism in PM-MAC achieves better performance in access success rate, channel utilization and backoff delay. © 2021 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Generative Adversarial Networks for Exo-atmospheric Infrared Objects Discrimination

Generative Adversarial Networks for Exo-atmospheric Infrared...

引用

Signal, Information and Data Processing (ICSIDP), IEEE International Conference on

作者： Dongya Wu Huanzhang Lu Huamin Tao Bendong Zhao Ming Zhao National University of Defense Technology Changsha China Science and Technology on Near-Surface Detection Laboratory Wuxi China

ISBN: (数字)9781728123455

ISBN: (纸本)9781728123462

External atmospheric infrared (IR) target recognition is an important research topic of space surveillance systems. The different micromotion states of the target result in respective features in the obtained sequence of IR radiation intensities, and such differences are difficult to visually describe and difficult to extract efficiently. Due to the difficulty of spatial experiments, the target sample data is very limited. In the case of limited labeled samples, there are few methods that can effectively classify time series effectively, resulting in low classification accuracy and difficulty in meeting practical application requirements. We use generative adversarial networks(GAN) for semi-supervised learning, combining neural network classifiers with adversarial generation models for the classification of infrared grayscale time series of spatial targets. The effective classification of the target is achieved with a small number of labeled target samples. The experiment proves the effectiveness of the method and the classification effect is better than other methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Wavelet Packet Energy Entropy Based Feature Analysis of Seismic Signals from Vehicle Targets 5th

Wavelet Packet Energy Entropy Based Feature Analysis of Seis...

引用

5th International Conference on Intelligent Computing, Communication and Devices, ICCD 2019

作者： Ding, Kai Li, Xinghua Li, Hao Ma, Huayuan Fan, Lei Qi, Xiaogang Science and Technology on Near-Surface Detection Laboratory The First Scientific Research Institute of Wuxi Wuxi214035 China Army Engineering University of PLA Nanjing210007 China School of Mathematics and Statistics Xidian University Xi’an710071 China

ISBN: (纸本)9789811558863

The seismic signals of two typical types of vehicle targets—wheeled vehicles and tracked ones—were collected in field test, and decomposed at multiple levels using wavelet packet transformation (WPT), which has a multiresolution feature, to obtain detailed energy distribution. A method for computing the energy entropy of the seismic signals from a vehicle target was derived on the concept of information entropy based on probability statistics. The energy entropies of the seismic signals from the two types of vehicles were then analyzed, and the results indicate that the energy entropy reflects the seismic signals of different types of vehicles: the energy entropies of the seismic signals of the wheeled vehicles were greater than that of the tracked vehicles. In conclusion, this paper proposes to use the energy entropy as a new characteristic quantity of seismic signals from vehicle targets for feature extraction, which may pave a new way for identification of seismic signals from different vehicles. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

A resonant cavity based on birdcage coil for overhauser geomagnetic sensor

A resonant cavity based on birdcage coil for overhauser geom...

引用

2018 IEEE International Instrumentation and Measurement technology Conference, I2MTC 2018

作者： Bai, Bingjie Dong, Haobin Ge, Jian Liu, Huan Zhang, Cheng Wang, Luo Institute of Geophysics and Geomatics China University of Geosciences Hubei Wuhan China School of Automation China University of Geosciences Hubei Wuhan China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Hubei Wuhan China Science and Technology on Near-Surface Detection Laboratory Jiangsu Wuxi China

ISBN: (纸本)9781538622223

The resonant cavity is an important component of Overhauser magnetometer sensor. Its function is to make the working substance generate dynamic nuclear polarization effect in the sensor. An alternative design of resonant cavity based on the birdcage coil structure was proposed to make the resonant frequency in accordance with the polarization frequency of the working substance. The structure and equivalent circuit of resonant cavity were analyzed. The model of resonant cavity was established and S-parameter is calculated to verify the frequency consistency of the resonant cavity and working substance. In addition, output signal experiment and simultaneous comparison testing of sensor prototype were conducted. Overall, this design has the advantages of high performance and strong anti-interference. © 2018 IEEE.

关键词： Equivalent circuits

来源：评论

学校读者我要写书评

暂无评论

A UWB/IMU-Assisted Fingerprinting Localization Framework with Low Human Efforts

引用

China Communications 2024年第6期21卷 40-52页

作者： Pan Hao Chen Yu Qi Xiaogang Liu Meili School of Mathematics and Statistics Xidian UniversityXi’an 710126China Science and Technology on Near-Surface Detection Laboratory Wuxi 214035China School of Software Nanchang Hangkong UniversityNanchang 330063China

With the rapid development of smart phone,the location-based services(LBS)have received great attention in the past *** to the widespread use of WiFi and Bluetooth devices,Received Signal Strength Indication(RSSI)fingerprintbased localization method has obtained much development in both academia and *** this work,we introduce an efficient way to reduce the labor-intensive site survey process,which uses an UWB/IMU-assisted fingerprint construction(UAFC)and localization framework based on the principle of Automatic radio map generation scheme(ARMGS)is proposed to replace the traditional manual *** be specific,UWB devices are employed to estimate the coordinates when the collector is moved in a reference point(RP).An anchor self-localization method is investigated to further reduce manual measurement work in a wide and complex environment,which is also a grueling,time-consuming process that is lead to artificial ***,the measurements of IMU are incorporated into the UWB localization algorithm and improve the label accuracy in *** addition,the weighted k-nearest neighbor(WKNN)algorithm is applied to online localization ***,filed experiments are carried out and the results confirm the effectiveness of the proposed approach.

关键词： indoor localization machine learning ultra wideband WiFi fingerprint

来源：评论

学校读者我要写书评

暂无评论

An improved tuning control algorithm based on SVD for FID signal

An improved tuning control algorithm based on SVD for FID si...

引用

作者： Liu, Huan Dong, Hao Bin Ge, Jian Guo, Pei Pei Bai, Bing Jie Zhang, Cheng Department of School of Automation China University of Geosciences Wuhan Hubei430074 China Department of Institute of Geophysics and Geomatics China University of Geosciences Wuhan Hubei430074 China Science and Technology on Near-Surface Detection Laboratory Wuxi214035 China

The free induction decay (FID) quality signal of a proton precession magnetometer is closely related to tuning precision. To solve the commonly used current tuning problem method, we propose improving control algorithm tuning based on singular value decomposition (SVD). The space matrix is constructed by acquiring an analog-to-digital converter (ADC) for untuned FID signals, then conducting SVD to eliminate noise and obtain a useful signal. The fast Fourier transform (FFT) is then applied to the denoised FID signal to extract the time-frequency feature. Based on theory analysis, simulation modeling and actual FID signal testing, results show that compared to general tuning methods such as peak detection and auto correlation, our proposed algorithm improves sensor tuning precision and shortens tuning process time to one second or less.

关键词： Singular value decomposition

来源：评论

学校读者我要写书评

暂无评论

A compact air-coupled SFCW ground penetrating radar and its application in the earthen sites 20

A compact air-coupled SFCW ground penetrating radar and its ...

引用

20th International Conference on Ground Penetrating Radar, GPR, 2024

作者： Ye, Shengbo Li, Xu Li, Xinhui Liu, Xiaojun Fang, Guangyou Jiang, Hejun Lyu, Rongqi Aerospace Information Research Institute Chinese Academy of Sciences Beijing100190 China Key Laboratory of Electromagnetic Radiation and Sensing Technology Chinese Academy of Sciences Beijing100190 China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing100049 China Science and Technology on Near-surface Detection Laboratory Wuxi214035 China

As a non-destructive testing technology, ground-penetrating radar (GPR) has been widely used in archaeological investigations of the earthen sites. Traditionally, a GPR antenna is ground-couple. It is attached to the measured object and thus may cause damage to the earthen sites. This paper develops a lightweight and compact air-coupled stepped frequency continuous waveform (SFCW) GPR system with frequency range from 1GHz up to 6GHz. We suppress the nonlinear variables of the radar system by calibration. And we perform tests on different weathering samples from the earthen sites. Our system is verified that can discriminate layered structures in samples and the results of tests are consistent with the simulations of the gprMax model. In general, this radar system can assess the weathering degree and provide technical support for the preservation of the earthen sites. © Published under licence by IOP Publishing Ltd.

关键词： Antenna grounds

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：