检索结果-内蒙古大学图书馆

Signal, information and Data processing (ICSIDP), IEEE International Conference on

作者： Jinghong Nan Baojun Zhao Tingting Cui Yongfeng Xie Beijing Institute of Aerospace Systems Engineering Beijing China Beijing Key Laboratory of Embedded Real-time Information Processing Technology Beijing China

ISBN: (数字)9781728123455

ISBN: (纸本)9781728123462

Robust and efficient air infrared small target detection is widely used in reconnaissance and early warning system. However, there exist two critical difficulties, i.e., the limited detection range and the poor detection performance of single infrared sensor. To overcome those difficulties, in this paper, we propose a novel cooperative detection method of multiple infrared sensors for air small target. Specifically, a multiscale block local contrast measurement method is introduced to achieve the target detection of each infrared sensor. Afterwards, a double-layer ring grid corner feature extraction method is proposed to achieve the image stitching accurately between multiple infrared sensors. In addition, the gray correlation analysis with position constraint based feature level fusion method is exploited to match targets in different sensors. Experimental results on testing image sequences demonstrate that the proposed method can improve the detection rate and reduce the false alarm rate effectively on the condition of limited detection range of each single sensor.

关键词：

来源：评论

学校读者我要写书评

暂无评论

real-time Remote Sensing Video Compression for On-orbit Heterogeneous Platform

Real-time Remote Sensing Video Compression for On-orbit Hete...

引用

Signal, information and Data processing (ICSIDP), IEEE International Conference on

作者： Chenhui Duan Linbo Tang Chen Wu Cheng Li Chen Li Baojun Zhao Beijing Key Laboratory of Embedded Real-Time Information Processing Technology Beijing China School of Computer Science North China University of Technology Beijing China

ISBN: (数字)9781728123455

ISBN: (纸本)9781728123462

With the rapid advancement of optical remote sensing (RS) satellites, RS video has replaced RS image as the main way to obtain information in orbit environment. However, the storage and transmission of on-orbit RS video faces enormous challenges: the contradiction between limited power, space and bandwidth and massive video data volume is becoming increasingly acute. To solve this problem, this paper proposes an effective implementation of spaceborne real-time RS video compression based on CPU+GPU heterogeneous framework. First, we propose a new rate control method based on HEVC for on-orbit RS video compression, which allocates less bitrate for low complexity code blocks (CBs) and more bitrate for high complexity CBs, which can improve the accuracy of rate control algorithm while ensuring compression quality. Then this paper makes full use of the CPU + GPU heterogeneous framework to speed up the whole compression processing. The experimental results show that the proposed compression framework realizes 200x real-time compression of 1080p spaceborne RS video with a PSNR greater than 38.7 dB.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Network Pruning Method for Remote Sensing Image Scene Classification

A Network Pruning Method for Remote Sensing Image Scene Clas...

引用

2019 IEEE International Conference on Signal, information and Data processing, ICSIDP 2019

作者： Qi, Baogui Chen, He Zhuang, Yin Liu, Shaorong Chen, Liang Beijing Key Laboratory of Embedded Real-time Information Processing Technology Beijing Institute of Technology Beijing100081 China School of Electronic Engineering and Computer Science Peking University Beijing100087 China Beijing Institute of Spacecraft System Engineering Beijing100094 China Beijing Institute of Technology Chongqing Innovation Center Chongqing401120 China

ISBN: (纸本)9781728123455

Deep convolutional neural networks have been widely used to improve remote sensing image scene classification performance. However, most of these networks include many parameters and need many computational resources. Which hinders the applications of these networks when facing the satellite, plane or other mobile platforms. In this paper, we introduce a network pruning framework which can reduce the size of the network model and maintain the classification accuracy. In this framework, we train the pruned model using both the original unpruned model's output and training dataset. Which can learn more information than retrain using dataset only. In our experiments, we evaluate our method for remote sensing scene classification on NWPU-RESISC45 dataset. The results demonstrate that our method was effective and maintained the model classification accuracy. © 2019 IEEE.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Aircraft detection in Remote Sensing image for Space-borne platform

Aircraft detection in Remote Sensing image for Space-borne p...

引用

Signal, information and Data processing (ICSIDP), IEEE International Conference on

作者： Wei Tang Baozhao Jun Linbo Tang Yu Pan Dongling Jin Zhengpiao Quan Beijing Key Laboratory of Embedded Real-time Information Processing Technology Beijing China Radar Research Lab School of Information and Electronics Beijing Institute of Technology Beijing China

ISBN: (数字)9781728123455

ISBN: (纸本)9781728123462

Aircraft detection in optical remote sensing image is an important research direction in the field of remote sensing. The existing detection methods are difficult to achieve satisfactory results. Traditional detection methods are low robustness, due to manual feature modeling are difficult and subject to background interference; The deep learning target detection method, which improves the detection performance at the cost of complexity improvement, cannot be widely used in space-borne platforms limited resources. In view of the above problems, this paper proposes an aircraft target deep learning detection method of lightweight and multi-scale features. On the basis of the multi-scale target detection framework (SSD), the method firstly uses the dense connection structure and the double convolution channels to form the basic backbone networks with feature reuse and high computational efficiency. To improve the detection performance of the small aircraft target, the basis backbone network connects a residual module and deconvolution to compose the multi-scale feature fusion detection module. Compared with the current classical deep learning object detection methods, the experimental results show that the proposed method has the advantages of maintaining low computational complexity and achieving high detection accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SAR Image Scattering Center Estimation via Atomic Norm Minimization

SAR Image Scattering Center Estimation via Atomic Norm Minim...

引用

Asian and Pacific Conference on Synthetic Aperture Radar (APSAR)

作者： Ying Xi Haibo Liu Yanhua Wang Yang Li Radar Research Lab School of Information and Electronics Beijing Institute of Technology Beijing Key Laboratory of Embedded Real-time Information Processing Technology Beijing Institute of Technology Beijing China

ISBN: (数字)9781728129129

ISBN: (纸本)9781728129136

Scatter center matching is one of the choke points of radar automatic target recognition (RATR) based on Synthetic Aperture Radar (SAR). Accuracy of scattering center extraction is an important factor affecting target recognition performance. This paper proposes a SAR images scattering center estimation method based on atomic norm minimization (ANM) model. This method models the scattering center estimation problem as a two-dimensional line spectrum estimation problem, then the estimation is performed in a continuous domain via ANM. The experimental results indicate the superiorities of the proposed method in terms of accuracy and robustness.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Reconfigurable Pipelined Variable-point FFT Processor Design

The Reconfigurable Pipelined Variable-point FFT Processor De...

引用

Signal, information and Data processing (ICSIDP), IEEE International Conference on

作者： Jiale Wang Yizhuang Xie Bingyi Li Chen Yang Shankang Hu Radar Research Lab School of Information and Electronics Beijing Institute of Technology Beijing China Beijing Key Laboratory of Embedded Real-time Information Processing Technology Beijing China

ISBN: (数字)9781728123455

ISBN: (纸本)9781728123462

In the multi-mode SAR imaging processing targeted in this paper, the FFT requirement granularity ranges from 1024 to 32768. Therefore, this paper mainly describes the method of implementing reconfigurable and variable-level FFT units using radix-2 k , By analyzing and comparing the radix 2 k algorithm, the radix-2 3 is selected as the basis of the single-channel FFT butterfly, and the range of the point representation is extended by the butterfly transformation downward compatible with the radix-2 2 /radix-2. This paper realizes an architecture of the single channel delay feedback variable-point, high precision FFT processor.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A novel DEM reconstruction strategy based on multi-frequency In SAR in highly sloped terrain

引用

Science China(information Sciences) 2017年第8期60卷 243-245页

作者： Tao ZENG Tiandong LIU Zegang DING Qi ZHANG Zhen WANG Teng LONG Beijing Key Laboratory of Embedded Real-time Information Processing Technology Beijing Institute of Technology

Interferometric Synthetic Aperture Radar(InSAR)has been proposed as a technique for the reconstruction of the Digital Elevation Model(DEM),which is widely used in global terrain mapping mission[1].The DEM reconstruction methods of In SAR technique are usually based on the so-called phase unwrapping(PU)*** highly sloped terrain,the interferometric phase gradients(IPG)of the adjacent pixels are more thanπ.Therefore,the traditional PU methods

关键词： SAR In of DEM IPG on Figure LAPS A novel DEM reconstruction strategy based on multi-frequency In SAR in highly sloped terrain

来源：评论

学校读者我要写书评

暂无评论

Adaptive Mainlobe Interference Suppression in Sparse Distributed Array Radar Based on Synthetic Wideband Signal 2nd

引用

2nd International Conference on Machine Learning and Intelligent Communications, MLICOM 2017

作者： Luo, Jian Zhang, Honggang Song, Yuanyuan Beijing Key Laboratory of Embedded Real-Time Information Processing Technology Radar Research Laboratory School of Information and Electronics Beijing Institute of Technology Beijing100081 China

ISBN: (纸本)9783319734460

This paper proposes a mainlobe interference suppression method in distributed array radar (DAR) based on stepped frequency synthetic wideband signal. Due to the equivalent large aperture of DAR, it is possible to cancel the mainlobe interference without target signal suppression. The applying of stepped frequency synthetic wideband signal can avoid the different time delays arriving at each array compared with the traditional instantaneous wideband Chirp (linear frequency modulation) signal. Moreover, it can reduce the computational complexity. This method employs the narrowband adaptive processing to each sub-pulse of the stepped frequency signal, and then synthesizes the high resolution range profile (HRRP). As a result, mainlobe interference suppression under wideband signal is accomplished. Mainlobe interference suppression experiment is carried out by using an S-band experimental radar system, an S-band noise jammer and a target simulator. The measured data is processed employing the proposed method, and the result verifies the effectiveness of this algorithm. © 2018, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

关键词： Beamforming

来源：评论

学校读者我要写书评

暂无评论

High-Squint SAR Imaging for Noncooperative Moving Ship Target Based on High Velocity Motion Platform

High-Squint SAR Imaging for Noncooperative Moving Ship Targe...

引用

2018 China International SAR Symposium, CISS 2018

作者： Zhou, Zhichao Ding, Zegang Zhang, Tianyi Wang, Yan Radar Research Lab School of Information and Electronics Beijing Institute of Technology Beijing Key Laboratory of Embedded Real-time Information Processing Technology Beijing China

ISBN: (纸本)9781538671931

For high velocity motion platform, it usually takes a shorter azimuth accumulation time to achieve high-squint synthetic aperture radar (SAR) imaging for noncooperative moving ship target with meter-level resolutions. In this case, three-dimensional relative motion of the ship target can be neglected approximately, mainly the translational motion should be considered. However, the magnitude and direction of the target's translational velocity are unknown. To solve the above problem, a two-step imaging method is proposed in this paper. Firstly, the entire scene is coarsely imaged by using the parameters provided by inertial navigation system. The position of the ship target can be judged by two-dimensional order statistics constant false alarm rate (OS-CFAR) detection and ship target pixel clustering. By constructing the band-pass filter in azimuth frequency domain, the data of the target can be obtained effectively, and to a certain extent, sea clutter and noise are suppressed. Then the motion parameters are estimated. Finally, the target is secondarily imaged with the estimated parameters to achieve precise focus. The results of simulation verify the correctness of the analysis and the validity of the proposed method. © 2018 IEEE.

关键词： Parameter estimation

来源：评论

学校读者我要写书评

暂无评论

Remote Sensing Image Classification Based on Markov Random Field

Remote Sensing Image Classification Based on Markov Random F...

引用

Signal, information and Data processing (ICSIDP), IEEE International Conference on

作者： Tong Zhang Yin Zhuang Beijing Key Laboratory of Embedded Real-time Information Processing Technology Beijing China School of Electronic Engineering and Computer Science Peking University Beijing China

ISBN: (数字)9781728123455

ISBN: (纸本)9781728123462

With the continuous development of optical remote sensing technology, the segmentation of high resolution remote sensing images has become a hot research field. The high resolution and complex remote sensing images make the general natural image segmentation become a challenge task. Here, Markov random field (MRF) can well combine the spatial information of remote sensing image with the domain information between pixels for image segmentation, which is currently a hot research direction. In this paper, the wavelet and MRF are combined to achieve multi-scale analysis and produce more accurate segmentation results, the extensive experiments demonstrated that proposed method is more suitable for remote sensing image segmentation, and it provides a good boundary local mapping results and is robust with image non-stationary signal. In addition, in view of the disadvantage of fixed potential function parameters of traditional MRF, we put forward the method of variable weight. On this basis, Kullback-Leibler (KL) divergence is proposed to calculate the similarity between the segmented regions to further optimize the segmentation results.

关键词：

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：