检索结果-内蒙古大学图书馆

Detecting floating plastic marine debris using sentinel-2 data via modified infrared NDVI 18

Detecting floating plastic marine debris using sentinel-2 da...

18th International conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology, ECTI-CON 2021

作者： Khetkeeree, Suphongsa Liangrocapart, Sompong Mahakorn University of Technology Physics Department Bangkok Thailand

ISBN: (纸本)9780738111278

Floating marine debris is one of the significant marine pollutions that affect many living on the globe. Thanks to satellite technology, the Earth observation satellite has mostly constant frequency and wide area coverage. Moreover, some observation data are also openly and freely accessible for everyone, such as Sentinel platforms' data. However, most floating debris is difficult to observe by the above platform because it often has a smaller size than the highest spatial resolution of the Sentinel data. In this paper, we propose the method for detecting the floating marine debris via the Sentinel-2 data. The infrared normalized difference vegetation index (INDVI) was modified to increase plastic debris detection capability. The narrow near-infrared band (band 8A) was replaced by the highest near-infrared band (band 8). Two individual formulas of the modified version were proposed due to the INDVI is an empirical formula dependent on each platform sensor. The known targets of the floating plastic aggregation from two valuable experiments at Tsamakia beach, Greece, and Limassol old port, Cyprus, were used to observe and evaluate the detectable capability. The signal to Noise Ratio (SNR) was applied to indicate our method performance compared with many recent methods of floating plastic debris detection. The results show that our proposed method can be well used to detect floating aggregated plastic objects, although it has a small size than the Sentinel-2 spatial resolution. Besides, it can also observe some floating plastic patches that are difficult to notice by visible optical information. © 2021 IEEE.

关键词： Marine pollution

来源：评论

学校读者我要写书评

暂无评论

Overview of the Joint Services Lightweight Standoff Chemical Agent Detector (JSLSCAD)

Overview of the Joint Services Lightweight Standoff Chemical...

引用

conference on Chemical and Biological Sensing VI

作者： Hammond, B Popa, M Gen Dynam Armament & Tech Prod Charlotte NC 28273 USA

ISBN: (纸本)0819457809

This paper presents a system-level description of the Joint Services Lightweight Standoff Chemical Agent Detector (JSLSCAD). JSLSCAD is a passive Fourier Transform InfraRed (FTIR) based remote sensing system for detecting chemical warfare agents. Unlike predecessor systems, JSLSCAD is capable of operating while on the move to accomplish reconnaissance, surveillance, and contamination avoidance missions. Additionally, the system is designed to meet the needs for application on air and sea as well as ground mobile and fixed site platforms. The core of the system is a rugged Michelson interferometer with a flexure spring bearing mechanism and bi-directional data acquisition capability. The sensor is interfaced to a small, high performance spatial scanner that provides high-speed, two-axis area coverage. Command, control, and processing electronics have been coupled with real time control software and robust detection/discrimination algorithms. Operator interfaces include local and remote options in addition to interfaces to external communications networks. The modular system design facilitates interfacing to the many platforms targeted for JSLSCAD.

关键词： Scanners Spectroscopy Sensors Mirrors Control systems Electronics Digital signal processing Neural networks Standoff detection Telecommunications

来源：评论

学校读者我要写书评

暂无评论

Development of an adaptive approach for identification of targets (match box, pocket diary and cigarette box) under the cloth with MMW imaging system

引用

Progress In Electromagnetics Research B 2017年第1期77卷

作者： Kumar, Bambam Upadhyay, Rohit Singh, Dharmendra Department of Electronics and Communication Engineering Indian Institute of Technology Roorkee Roorkee Uttarakhand India

Non-metallic objects, such as match box and cigarette box, detection and identification are quite an essential task during personal screening from standoff distance to protect the public places like the airport. Although various imaging sensors such as microwave, THz, infrared and MMW with signal processing techniques have been demonstrated by the researchers for concealed weapon detection, it is still a challenging task to detect and identify different types of small size targets such as matchbox, pocket diary and cigarette box simultaneously. Therefore, in this paper, an attempt has been made to develop such an algorithm/methodology by which different types of small targets, such as a matchbox and cigarette box, which is fully or half-filled or empty and pocket diary at different orientations beneath various cloths can be detected and identified with an MMW radar system. For this purpose, an optimal method has been proposed to form an image, and after that, in post processing a novel adaptive approach for detection and identification of considered targets has been proposed. The data were collected by MMW system at V-band (59 GHz–61 GHz). The proposed algorithm/methodology gives a quite satisfactory result.

关键词： Image processing

来源：评论

学校读者我要写书评

暂无评论

Study on the echo signal model and R-D imaging algorithm for FMCW SAR

Study on the echo signal model and R-D imaging algorithm for...

引用

IET International Radar conference 2015

作者： Bin Wang Zhiyou Hu Wenshuo Guan Qingbao Liu Junwei Guo The 303th Institute of the Third Academy China Aerospace Science & Industry Corp. Beijing China

ISBN: (纸本)9781510822023

Frequency modulation continuous wave (FMCW) is often applied in miniature synthetic aperture radar (MINI SAR) . FMCW SAR sends linear frequency modulated (LFM) continuous wave signal with wide band, and the receiving echo of targets mixes with the sending signal. Therefore, the echo for imaging processing can be sampled in intermediate frequency (IF) band with low sampling rate, and the system can keep small and light. After imaging processing with the echos, FMCW SAR can obtain the image of the target with high resolution. In this paper, the observation geometry and the echo signal model of FMCW SAR are analyzed. Range-Doppler (R-D) algorithm for FMCW SAR imaging is deduced. Finally, the simulation experiments with R-D algorithm for point targets are given.

关键词： SAR FMCW R-D algorithm Echo signal model

来源：评论

学校读者我要写书评

暂无评论

Simulation Study About the Radar Cross Section of a Typical targets Based on FEKO 9th

Simulation Study About the Radar Cross Section of a Typical ...

引用

9th International conference on Communications, signal processing, and Systems, CSPS 2020

作者： Wang, Feng Liu, Pengyuan Wei, Zhonglin Army Engineering University Shijiazhuang Campus Shijiazhuang Hebei China

ISBN: (纸本)9789811584107

The radar cross section is an important parameter to characterize radar target characteristics. The fluctuation of the data represents the size and shape of the target. Target RCS depends not only on radar frequency and polarization mode but also on the attitude of target relative to radar. Taking a cruise missile as the research object and combining with FEKO software simulation platform. Set the corresponding working frequency, working wavelength, material parameters, geometric parameters, excitation, etc., and then define the plane wave, and then conduct mesh generation to generate the calculation model. This paper established an efficient RCS characteristic calculation based on the high-frequency approximation method. The influence of configuration materials and incident wave parameters on RCS characteristics of cruise missile was studied and some significant results were obtained. © 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Radar cross section

来源：评论

学校读者我要写书评

暂无评论

Dense Convolution Siamese Network for Hyperspectral Image Target Detection

Dense Convolution Siamese Network for Hyperspectral Image Ta...

引用

IEEE International conference on Information Communication and signal processing (ICICSP)

作者： Kun Shen Weixin Xie Haojin Tang Yanshan Li ATR National Key Laboratory of Defense Technology Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China

Compared with grayscale and RGB images, hyperspectral image (HSI) can provide both spatial and spectral information of ground targets, which makes it possible to improve the efficiency and accuracy of target detection. Therefore, the research of HSI target detection algorithms has attracted widespread concern in recent years. With the development of hardware devices and the arrival of big data era, deep learning algorithms have been successfully applied to image processing, text recognition and other fields. However, due to the complex gathering environment of HSI, it is so difficult to obtain a large number of labeled samples, which limits the application of deep learning algorithms in HSI target detection. Therefore, a dense convolution Siamese network (DCSN) is proposed for HSI target detection, which improves the accuracy in the scenery of small-scale training samples. The main contributions of this paper include the following three points. First, we design a target sample generation method based on improved autoencoder to enhance target training data. Then, a background selection method based on density estimation is presented, which can acquire typical background samples effectively. Finally, a spectral feature extraction method based on dense convolution is proposed to extract the more discriminative spectral features. The experimental results of HSI target detection on Muufl Gulfport and San Diego datasets indicate that our proposed DCSN is able to achieve superior performance than the existing target detectors.

关键词： Deep learning Training Convolution Text recognition signal processing algorithms Training data Object detection

来源：评论

学校读者我要写书评

暂无评论

DOA and Doppler frequency estimation based on sub-aperture MUSIC

DOA and Doppler frequency estimation based on sub-aperture M...

引用

3rd IFAC conference on Intelligent Control and Automation Science, ICONS 2013

作者： Liu, Xiaoli Liao, Guisheng College of Communication Engineering Hangzhou Dianzi University Hangzhou 310018 China Zhejiang Provincial Testing Institute of Electronic and Information Products China National Laboratory of Radar Signal Processing Xidian University Xi'an China

ISBN: (纸本)9783902823458

Most available algorithms for DOA estimation in monostatic MIMO radar involve the computation of covariance matrix and its inversion or eigendecomposition, of which the computational complexity is expensive, especially in the case that both the number of sensors and snapshots are large. To solve this problem, a high-resolution algorithm for joint direction-of-arrival (DOA) and Doppler Frequency estimation based on sub-aperture MUSIC in monostatic MIMO radar is presented. Firstly, the received data matrix form each transmitter is evenly divided into four sub-blocks. Then two-dimensional fast Fourier transforms (2D-FFTs) is applied to each sub-block in order to achieve coherent integration. By utilizing the data corresponding to the peaks of coherent integration in each sub-block, a reduceddimensional data vector is constructed for joint DOA and Doppler frequency estimation via root-MUSIC. Since the full-dimensional covariance matrix estimation and eigendecomposition are avoided, the computational complexity is relatively small. Simulation results demonstrate the effectiveness of the proposed method with slightly better performance than that of ESPRIT-based method. Copyright © 2013 IFAC.

关键词： Computational complexity

来源：评论

学校读者我要写书评

暂无评论

Simultaneous Tracking of Multiple targets using Interferometric FMCW Radar

Simultaneous Tracking of Multiple Targets using Interferomet...

引用

signal, Information and data processing (ICSIDP), IEEE International conference on

作者： Huaiyuan Liang Pengcheng Wang Xiangrong Wang Shenyuan Honors College Beihang University Beijing China School of Electronic and Information Engineering Beihang University Beijing China

ISBN: (数字)9781728123455

ISBN: (纸本)9781728123462

This paper presents an approach for simultaneous tracking of multiple targets using the interferometric frequency modulated continuous wave (FMCW) radar. A dual-channel receiver FMCW radar is utilized for interferometric measurement. The trajectory of each target is estimated separately based on two-dimensional position and velocity, which can be extracted by applying stretch processing and time-frequency analysis to the interferometric echo signals simultaneously. The two-dimensional positions and velocities are input to a Kalman filter to improve tracking performance. Simulation and experimental results of walking people are presented to validate the performance of the approach.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sea Surface small Target Detection Method Based on Improved YOLOv5

Sea Surface Small Target Detection Method Based on Improved ...

引用

Image processing, Computer Vision and Machine Learning (ICICML), International conference on

作者： Huiying Wen Jianzhong Tang Mingyang Lu Xiaowen Lv Ocean College Zhejiang University Hangzhou China School of Mechanical Engineering Zhejiang University Hangzhou China

At present, a complete and feasible detection system for sea surface targets has not yet been formed. Weak and small targets appear more frequently in sea scenes, and there is a lack of targeted algorithms to achieve better detection and identification. Therefore, this paper proposes a sea surface small target detection method based on improved YOLOv5. First, a data set of small targets on the sea surface is constructed, and the YOLOv5 model is selected to achieve target detection; then the sea antenna detection algorithm, attention module SE, CBAM, CA, feature fusion module BiFPN, and loss function EIoU are used to optimize the data, model, and strategy respectively. Finally, model training and verification testing are carried out. Experimental results show that compared with the baseline model (YOLOv5), the improved YOLOv5-sea-sky-line model has improved precision, recall, and average precision by 2.8%, 1.6%, and 0.8% respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Angular Super-resolution Imaging of Airborne Radar by Detect-reconstruct Approach

Angular Super-resolution Imaging of Airborne Radar by Detect...

引用

signal, Information and data processing (ICSIDP), IEEE International conference on

作者： Lu Jiao Jiahao Shen Yin Zhang Yulin Huang Deming Guo Huaigen Zhang School of Information and Communication Engineering UESTC Chengdu China Nanjing Research Institute of Electronics Technology Nanjing China

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

Angular resolution of airborne radar is usually poor because of its limited aperture size. The adjacent formation targets are difficult to be distinguished. To distinguish the adjacent targets by airborne radar, in this paper, a detect-reconstruct approach is proposed. First, the L1 norm is adopted to sparsely restrict the aerial targets. Second, because the targets are sparsely dispersed in the range dimension, a range pre-detection step is proposed to reduce the echo dimension, and the analyzed target range bins are reduced. Finally, a detect-reconstruct approach is proposed in the azimuthal super-resolution procedure to avoid the artificial targets. In simulation experiments, the angular resolution and efficiency of the proposed approach are demonstrated.

关键词： Image coding Superresolution Airborne radar Imaging Radar detection Radar imaging Entropy Doppler radar signal resolution Image reconstruction

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：