scispace - formally typeset
Search or ask a question
Author

Pengbo Wang

Other affiliations: University of Sheffield
Bio: Pengbo Wang is an academic researcher from Beihang University. The author has contributed to research in topics: Synthetic aperture radar & Inverse synthetic aperture radar. The author has an hindex of 12, co-authored 69 publications receiving 411 citations. Previous affiliations of Pengbo Wang include University of Sheffield.


Papers
More filters
Journal ArticleDOI
Pengbo Wang1, Wei Liu2, Jie Chen1, Mu Niu2, Wei Yang1 
TL;DR: A modified equivalent squint range model (MESRM) is developed by introducing equivalent radar acceleration into the equivalent squints range model, and it is more suitable for high-resolution spaceborne SAR.
Abstract: Two challenges have been faced in signal processing of ultrahigh-resolution spaceborne synthetic aperture radar (SAR). The first challenge is constructing a precise range model, and the second one is to develop an efficient imaging algorithm since traditional algorithms fail to process ultrahigh-resolution spaceborne SAR data effectively. In this paper, a novel high-order imaging algorithm for high-resolution spaceborne SAR is presented. First, a modified equivalent squint range model (MESRM) is developed by introducing equivalent radar acceleration into the equivalent squint range model, and it is more suitable for high-resolution spaceborne SAR. The signal model based on the MESRM is also presented. Second, a novel high-order imaging algorithm is derived. The insufficient pulse-repetition frequency problem is solved by an improved subaperture method, and accurate focusing is achieved through an extended hybrid correlation algorithm. Simulations are performed to validate the presented algorithm.

74 citations

Journal ArticleDOI
Jie Chen1, Gao Jianhu, Yanqing Zhu, Wei Yang, Pengbo Wang 
TL;DR: A novel sparse sampling scheme based on compressed sensing (CS) theory for azimuth DPCA SAR was proposed, by which only a small proportion of radar echoes are utilized for imaging to re- duce data rate on satellite downlink system.
Abstract: High-resolution wide-swath (HRWS) imaging with space- borne synthetic aperture radar (SAR) can be achieved by using az- imuth displacement phase center antenna (DPCA) technique How- ever, it will consequently leads to extremely high data rate on satellite downlink system A novel sparse sampling scheme based on compressed sensing (CS) theory for azimuth DPCA SAR was proposed, by which only a small proportion of radar echoes are utilized for imaging to re- duce data rate The corresponding image formation algorithm for the proposed scheme was presented in the paper The SAR echo signal of each channel can be reconstructed with high probability by using orthogonal matching pursuit (OMP) algorithm in Doppler frequency domain The reconstructed echo signals of each channel are jointly processed by means of spectrum reconstructing fllter for compensat- ing Doppler spectrum aliasing resulting from non-uniform sampling in azimuth direction The high quality SAR image can be obtained by us- ing chirp scaling algorithm The efiectiveness of the proposed approach was validated by computer simulations using both point targets and distributed targets

34 citations

Proceedings ArticleDOI
Xuan Li1, Chunsheng Li1, Pengbo Wang1, Zhirong Men1, Huaping Xu1 
01 Sep 2015
TL;DR: This paper proposes a fast training method for CNN in SAR automatic target recognition (ATR) that can tremendously reduce the training time with little loss of recognition rate.
Abstract: As for the problem of too long training time of convolution neural network (CNN), this paper proposes a fast training method for CNN in SAR automatic target recognition (ATR). The CNN is divided into two parts: one that contains all the convolution layers and sub-sampling layers is considered as convolutional auto-encoder (CAE) for unsupervised training to extract high-level features; the other that contains fully connected layers is regarded as shallow neural network (SNN) to work as a classifier. The experiment based on MSATR database shows that the proposed method can tremendously reduce the training time with little loss of recognition rate.

33 citations

Journal ArticleDOI
Mahboob Iqbal, Jie Chen1, Wei Yang, Pengbo Wang, Bing Sun 
TL;DR: In this article, a despeckling technique based on multiple image reconstruction and selective 3D flltering is proposed, where multiple subsets of pixels are selected from input SAR image by imposing restriction that each subset has at least 20% different pixels from any other subset.
Abstract: A despeckling technique based on multiple image reconstruction and selective 3-dimensional flltering is proposed. Multiple SAR images are reconstructed from a single SAR image by employing compressive sensing (CS) theory. In order to obtain multiple images from single SAR image, multiple subsets of pixels are selected from input SAR image by imposing restriction that each subset has at least 20% difierent pixels from any other subset. These subsets are taken as measurement vectors in CS framework to obtain multiple SAR images. A despeckled image is obtained by employing selective 3-dimensional flltering to multiple reconstructed SAR image. The proposed technique is tested on single look complex TerraSAT-X data set, and experimental results exhibit that the proposed technique outperformed benchmark despekling methods in terms of visual quality and despeckling quality metrics.

31 citations

Journal ArticleDOI
Jie Chen1, Mahboob Iqbal1, Wei Yang1, Pengbo Wang1, Bing Sun1 
TL;DR: Simulation results on a real TerraSAR-X data set demonstrated that the proposed scheme can effectively remove azimuth ambiguities and enhance SAR image quality.
Abstract: A novel framework is proposed for mitigating azimuth ambiguities in spaceborne stripmap synthetic aperture radar (SAR) images. The azimuth ambiguities in SAR images are localized by using a local mean SAR image, SAR system parameters, and a defined metric derived from azimuth antenna pattern. The defined metric helps isolate targets lying at locations of ambiguities. The mechanism for restoration of ambiguity regions is selected on the basis of size of ambiguity regions. A compressive imaging technique is employed to restore isolated ambiguity regions (smaller regions of interconnected pixels), whereas clustered regions (relatively bigger regions of interconnected pixels) are filled by using exemplar-based inpainting. The simulation results on a real TerraSAR-X data set demonstrated that the proposed scheme can effectively remove azimuth ambiguities and enhance SAR image quality.

29 citations


Cited by
More filters
Journal ArticleDOI
TL;DR: This paper describes a recently created image database, TID2013, intended for evaluation of full-reference visual quality assessment metrics, and methodology for determining drawbacks of existing visual quality metrics is described.
Abstract: This paper describes a recently created image database, TID2013, intended for evaluation of full-reference visual quality assessment metrics. With respect to TID2008, the new database contains a larger number (3000) of test images obtained from 25 reference images, 24 types of distortions for each reference image, and 5 levels for each type of distortion. Motivations for introducing 7 new types of distortions and one additional level of distortions are given; examples of distorted images are presented. Mean opinion scores (MOS) for the new database have been collected by performing 985 subjective experiments with volunteers (observers) from five countries (Finland, France, Italy, Ukraine, and USA). The availability of MOS allows the use of the designed database as a fundamental tool for assessing the effectiveness of visual quality. Furthermore, existing visual quality metrics have been tested with the proposed database and the collected results have been analyzed using rank order correlation coefficients between MOS and considered metrics. These correlation indices have been obtained both considering the full set of distorted images and specific image subsets, for highlighting advantages and drawbacks of existing, state of the art, quality metrics. Approaches to thorough performance analysis for a given metric are presented to detect practical situations or distortion types for which this metric is not adequate enough to human perception. The created image database and the collected MOS values are freely available for downloading and utilization for scientific purposes. We have created a new large database.This database contains larger number of distorted images and distortion types.MOS values for all images are obtained and provided.Analysis of correlation between MOS and a wide set of existing metrics is carried out.Methodology for determining drawbacks of existing visual quality metrics is described.

943 citations

01 Jan 2016
TL;DR: Thank you very much for downloading spotlight synthetic aperture radar signal processing algorithms, maybe you have knowledge that, people have search numerous times for their favorite books, but end up in malicious downloads.
Abstract: Thank you very much for downloading spotlight synthetic aperture radar signal processing algorithms. Maybe you have knowledge that, people have search numerous times for their favorite books like this spotlight synthetic aperture radar signal processing algorithms, but end up in malicious downloads. Rather than reading a good book with a cup of coffee in the afternoon, instead they juggled with some harmful virus inside their laptop.

455 citations

Journal ArticleDOI
TL;DR: It is concluded that the proposed DCNN method has significant potential to be exploited for SAR image target recognition, and can serve as a new benchmark for the research community.
Abstract: In an attempt to exploit the automatic feature extraction ability of biologically-inspired deep learning models, and enhance the learning of target features, we propose a novel deep learning algorithm. This is based on a deep convolutional neural network (DCNN) trained with an improved cost function, and combined with a support vector machine (SVM). Specifically, class separation information, which explicitly facilitates intra-class compactness and inter-class separability in the process of learning features, is added to an improved cost function as a regularization term, to enhance the DCNN’s feature extraction ability. The enhanced DCNN is applied to learn the features of Synthetic Aperture Radar (SAR) images, and the SVM is utilized to map features into output labels. Simulation experiments are performed using benchmark SAR image data from the Moving and Stationary Target Acquisition and Recognition (MSTAR) database. Comparative results demonstrate the effectiveness of our proposed method, with an average accuracy of 99% on ten types of targets, including variants and articulated targets. We conclude that our proposed DCNN method has significant potential to be exploited for SAR image target recognition, and can serve as a new benchmark for the research community.

101 citations

Book
01 May 1989

101 citations