Search

Your search keyword '"zheng, huimin"' showing total 10 results
Start Over Author "zheng, huimin" Publisher ieee
10 results on '"zheng, huimin"'

2. Deep Unfolding Contrast Source Inversion for Strong Scatterers via Generative Adversarial Mechanism.

Author

Zhou, Huilin, Cheng, Yang, Zheng, Huimin, Liu, Qiegen, and Wang, Yuhao

Subjects
GENERATIVE adversarial networks, SIGNAL-to-noise ratio, ELECTROMAGNETIC wave scattering, INVERSE problems, LEARNING strategies
Abstract

To alleviate the extremely intrinsical ill-posedness and nonlinearity of electromagnetic inverse scattering under high contrast and low signal to noise ratio (SNR), we propose a deep unfolding network based on generative adversarial network (GAN) under contrast source inversion (CSI) framework, termed UCSI-GAN. The method solves inverse scattering problems (ISPs) using end-to-end generating confrontation way by incorporating a physical model together with its iterative updating formulation into the internal architecture of GAN. First, the nonlinear iterative scheme is extended to a deep unfolding generator network, and the contrast source and contrast updates are mapped to each module of the generator network. Second, to stabilize the imaging process, we add a refinement network to each variable update. Finally, the discriminator network is employed to ensure the authenticity of reconstructed images. The generator network and discriminator network are alternately trained with a generative adversarial learning strategy to reconstruct the properties of the medium object. Numerical experiments demonstrated that the performance of UCSI-GAN is better than traditional CSI and state-of-the-art learning approaches under high contrast and low SNR condition. [ABSTRACT FROM AUTHOR]

Published
2022
Full Text
View/download PDF

3. Baseband Doppler Centroid Estimation for Ground Moving Target with Multichannel SAR

Author

Weidong Yu, Mingjie Zheng, Zhenning Zhang, Zheng Huimin, and Zi-Xuan Zhou

Subjects
Synthetic aperture radar, Computer science, business.industry, 0211 other engineering and technologies, Estimator, Ground moving target indication, 02 engineering and technology, Doppler centroid, Moving target indication, Ground moving target, Baseband, Computer vision, Artificial intelligence, Spectral reconstruction, business, 021101 geological & geomatics engineering
Abstract

In multichannel synthetic aperture radar (SAR) Ground Moving Target Indication (GMTI) systems, Doppler centroid (DC) is an essential parameter for spectral reconstruction and image focusing. However, conventional DC estimator for stationary scene faces many problems in moving target with multichannel SAR, such as low sampling rate and channels selection. To estimate the baseband DC of moving target, a modified CDE method for multichannel SAR GMTI system is proposed in this paper. Simulation results demonstrate the effectiveness of this method.

Published
2019

6. Fast and efficient estimation of the symmetric alpha-stable impulsive signal or noise parameters

Author

Xie Dan, Yang Yang, and Zheng Huimin

Subjects
Mathematical optimization, Signal processing, Noise measurement, Stochastic resonance, Estimation theory, Computer science, Noise (signal processing), Maximum likelihood, Initialization, Maximum likelihood sequence estimation, Multiplicative noise, symbols.namesake, Gaussian noise, symbols, Value noise, Signal transfer function, Algorithm
Abstract

Some methods to estimate parameters of symmetric alpha-stable impulsive signals or noise have been presented, such as Fama and Roll's method, Tsihrintzis's method and Brorsen's method, all with their advantages and disadvantages respectively. Synthesizing all these methods, we present a new method, which solves the problem of the large amount of computation resulting from the highly nonlinear optimization problem and no initialization when seeking the maximum value of the maximum likelihood function. It is shown by simulation that the estimation performance is better than Fama and Roll's method and at the same time, faster than Brorsen's method without loss of precision.

Published
2002

7. Design of distributed hardware preprocessor for realtime processing of telemetry data

Author

Zheng Huimin and Zhang Qishan

Subjects
Data stream, Data processing, business.industry, Computer science, ComputerApplications_COMPUTERSINOTHERSYSTEMS, Pipeline (software), Minicomputer, law.invention, Parallel processing (DSP implementation), law, Microcomputer, Digital image processing, Preprocessor, business, Computer hardware
Abstract

Even though minicomputers and microcomputers are larger and faster than ever before, they have not kept pace with the demands of telemetry users. Hardware preprocessor of telemetry data has been used in distributed telemetry computer system for processing all data at extremely high rates. According to the requirements and characteristics of telemetry data processing, a distributed multiple data stream hardware preprocessor with multiplex microcomputers of telemetry data is introduced in the paper. Each data stream is processed by three microcomputer models coupled in multi-computation architecture. The microcomputer models consist of TMS320C25 in the preprocessor. The preprocessor owns the features of wavefront array processors. A time-wait procedure can be done in pipeline processing and large data processing can be derived in parallel processing and pipeline processing. >

Published
2002

Catalog

Books, media, physical & digital resources
See catalog results