Jixiang Sun

National University of Defense Technology, Ch’ang-sha-shih, Hunan, China

Are you Jixiang Sun?

Claim your profile

Publications (22)6.37 Total impact

  • [Show abstract] [Hide abstract]
    ABSTRACT: When applying the constant false alarm rate (CFAR) detector to ship detection on synthetic aperture radar (SAR) imagery, multiple interferers such as upwelling, breaking waves, ambiguities, and neighboring ships in a dense traffic area will degrade the probability of detection. In this paper, we propose a novel variable index and excision CFAR (VIE-CFAR) based ship detection method to alleviate the masking effect of multiple interferers. Firstly, we improve the variable index (VI) CFAR with an excision procedure, which censors the multiple interferers from the reference cells. And then, the paper integrates the novel CFAR concept into a ship detection scheme on SAR imagery, which adopts the VIE-CFAR to screen reference cells and the distribution to derive detection threshold. Finally, we analyze the performances of the VIE-CFAR under different environments and validate the proposed method on both ENVISAT and TerraSAR-X SAR data. The results demonstrate that the proposed method outperforms other existing detectors, especially in the presence of multiple interferers.
    Journal of Sensors 01/2015; 2015:1-10. DOI:10.1155/2015/437083
  • [Show abstract] [Hide abstract]
    ABSTRACT: The paper focuses on the modeling of visual saliency. We present a novel model to simulate the two stages of visual processing that are involved in attention. Firstly, the proto-object features are extracted in the pre-attentive stage. On the one hand, the salient pixels and regions are extracted. On the other hand, the semantic proto-objects, which involve all possible states of the observer's memories such as face, person, car, and text, are detected. Then, the support vector machines are utilized to simulate the learning process. As a consequence, the association between the proto-object features and the salient information is established. A visual attention model is built via the method of machine learning, and the saliency information of a new image can be obtained by the way of reasoning. To validate the model, the eye fixations prediction problem on the MIT dataset is studied. Experimental results indicate that the proposed model effectively improves the predictive accuracy rates compared with other approaches.
    Cognitive Computation 12/2014; 6(4):841-848. DOI:10.1007/s12559-014-9266-z · 1.10 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: As a method of representing the test sample with few training samples from an overcomplete dictionary, sparse representation classification (SRC) has attracted much attention in synthetic aperture radar (SAR) automatic target recognition (ATR) recently. In this paper, we develop a novel SAR vehicle recognition method based on sparse representation classification along with aspect information (SRCA), in which the correlation between the vehicle's aspect angle and the sparse representation vector is exploited. The detailed procedure presented in this paper can be summarized as follows. Initially, the sparse representation vector of a test sample is solved by sparse representation algorithm with a principle component analysis (PCA) feature-based dictionary. Then, the coefficient vector is projected onto a sparser one within a certain range of the vehicle's aspect angle. Finally, the vehicle is classified into a certain category that minimizes the reconstruction error with the novel sparse representation vector. Extensive experiments are conducted on the moving and stationary target acquisition and recognition (MSTAR) dataset and the results demonstrate that the proposed method performs robustly under the variations of depression angle and target configurations, as well as incomplete observation.
    04/2014; 2014:834140. DOI:10.1155/2014/834140
  • [Show abstract] [Hide abstract]
    ABSTRACT: Target decomposition is an important method for ship detection in polarimetric synthetic aperture radar SAR imagery. Parameters such as the polarization entropy and alpha angle deduced from the coherency matrix eigenvalue decomposition capture the differences between the target and background from different views separately. However, under the conditions of a relatively high resolution and a rough sea, the contrast between ship and sea reduces in the aforementioned space. Based on the analyses of target decomposition theory and the target’s scattering mechanism, multi-polarization parameters can be used to characterize different scattering behaviours of the ship target and sea clutter. Moreover, each parameter has its own diverse significance in the practical detection problem. This article proposes a feature selection and weighted support vector machine FSWSVM classifier-based algorithm to detect ships in polarimetric SAR PolSAR imagery. First, the method constructs a feature vector that consists of multi-polarization parameters. Then, different polarization parameters are refined and weighted according to their significance in the support vector machine SVM classifier. Finally, ships are classified from the sea background and other false alarms by the classifier. The validation results on National Aeronautics and Space Administration/Jet Propulsion Laboratory NASA/JPL airborne synthetic aperture radar AIRSAR and Radarsat-2 quad polarimetric data illustrate that the method detects ship targets more precisely and reduces false alarms effectively.
    International Journal of Remote Sensing 11/2013; 34(22):7925-7944. DOI:10.1080/01431161.2013.827812 · 1.36 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Ship classification is the key step in maritime surveillance using synthetic aperture radar (SAR) imagery. In this letter, we develop a new ship classification method in TerraSAR-X images based on sparse representation in feature space, in which the sparse representation classification (SRC) method is exploited. In particular, to describe the ship more accurately and to reduce the dimension of the dictionary in SRC, we propose to employ a representative feature vector to construct the dictionary instead of utilizing the image pixels directly. By testing on a ship data set collected from TerraSAR-X images, we show that the proposed method is superior to traditional methods such as the template matching (TM), K-nearest neighbor (K-NN), Bayes and Support Vector Machines (SVM).
    IEEE Geoscience and Remote Sensing Letters 11/2013; 10(6):1562-1566. DOI:10.1109/LGRS.2013.2262073 · 1.81 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: As a method of representing the test sample with few training samples from an overcomplete dictionary, sparse representation has attracted much attention in target classification recently. In this paper, we develop a new SAR vehicle classification method based on sparse representation, in which the correlation between the vehicle's aspect angle and the sparse representation coefficients is exploited. The detail procedure presented in this paper can be summarized as follows. Initially, the sparse coefficient vector of a test sample is solved by sparse representation algorithm with a pixel based dictionary. Then the coefficient vector is projected onto a sparser one with the constraint of vehicle's aspect angle. Finally, the vehicle is classified to a certain category that minimizes the reconstruct error with the sparse coefficient vector. We present promising results of applying the proposed method to the MSTAR dataset.
    Proceedings of SPIE - The International Society for Optical Engineering 10/2013; DOI:10.1117/12.2031412 · 0.20 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Precise segmentation is crucial for the feature extraction and classification of ships in SAR imagery. To alleviate the Doppler shift and the cross ambiguity, this paper propose to segment the ship area from its background based on the radon transform. Assuming that the region of interest (ROI) of ship in SAR imagery has been extracted, the detail procedures of the proposed refined segmentation can be summarized as follows. First, the ship's ROI image is transformed to radon domain, in which pixel intensities are cumulated along different directions. Then, the peak areas are separated to extract the ship's orientation and the main image area of the ship that orthogonal to the principal axis. Finally, the refined segmentation is achieved in the main image area. Experiments, accomplished over measured medium and high resolution SAR ship images, show the effectiveness of the proposed approach.
    Proceedings of SPIE - The International Society for Optical Engineering 10/2013; DOI:10.1117/12.2031494 · 0.20 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: This paper focuses on the problem of scene classification for mobile robots in an outdoor environment. We present a novel model that combines biologically inspired features and cortex-like memory patterns. The biologically inspired gist feature is used to characterize the content of a scene image. The Incremental Hierarchical Discriminant Regression tree is used to simulate the generation and recall process of human memory. The association between the gist feature and the scene label is established in an incremental way. A cognitive model of the world is constructed using real-time online learning, and a new scene differentiated by reasoning. Using the biologically motivated model, we solved the outdoor scene classification problem on the University of Southern California data set. Experimental results indicate the incremental model improves the classification accuracy rates to nearly 100 % and significantly reduces training costs compared with other biologically inspired feature-based approaches. The new scene classification system achieves state-of-the-art performance.
    Cognitive Computation 02/2013; 7(1). DOI:10.1007/s12559-013-9227-y · 1.10 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Blind Restoration of adaptive optics images is important in the field of astronomical imaging and space object surveillance. Using multi frame blind deconvolution as main technique means for high resolution restoration, a general cost function is deduced to deconvolve Poisson noise model image under the Bayesian-MAP estimate framework. To minimize the cost function, a solution algorithm based on alternating recursion method is proposed. In addition, asymmetric iteration method is introduced into solution process to avoid converging to local minima and maintain robustness of restored image. Experimental results show that the proposed method can recover high quality image from turbulence degraded images effectively and alleviate the negative influence of noise on the restoration result.
    Virtual Reality and Visualization (ICVRV), 2013 International Conference on; 01/2013
  • Afeng Yang, Min Lu, Shuhua Teng, Jixiang Sun
    [Show abstract] [Hide abstract]
    ABSTRACT: The resolution of space object images observed by ground-based telescope is greatly limited due to the influence of atmospheric turbulence. An improved blind deconvolution method is presented to enhance the performance of turbulence degraded images restoration. Firstly, a mixed noise model based blind deconvolution cost function is deduced under Gaussian and Poisson noise contamination of measurement. Then, point spread function (PSF) is described by wavefront phase aberrations in the pupil plane according to Fourier Optics theory. In this way, the estimation of PSF is generated from the wavefront phase parameterization instead of pixel domain value. Lastly, the cost function is converted from constrained optimization problem to non-constrained optimization problem by means of parameterization of object image and PSF. Experimental results show that the proposed method can recover high quality image from turbulence degraded images effectively.
    Virtual Reality and Visualization (ICVRV), 2013 International Conference on; 01/2013
  • Liangliang Wang, Zhiyong Li, Jixiang Sun
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, ISOMAP algorithm is applied into anomaly detection on the basis of feature analysis in hyperspectral images. Then an improved ISOMAP algorithm is developed against the limitation existed in ISOMAP algorithm. The improved ISOMAP algorithm selects neighborhood according to spectral angel, thus avoiding the instability of the neighborhood in the high-dimension spectral space. Experimental results show the effectiveness of the algorithm in improving the detection performance.
    Proceedings of SPIE - The International Society for Optical Engineering 12/2011; DOI:10.1117/12.920078 · 0.20 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: The currently known point pattern matching algorithms generally performs poorly when the two point patterns to be matched are not isomorphic. To improve the matching performance of the point pattern matching methods for non-isomorphic point patterns, a novel and robust inexact point pattern matching algorithm that combines with the invariant feature and probabilistic relaxation labelling is proposed. A new point-set based invariant feature, Relative Shape Context (RSC), is proposed firstly. Using the test statistic of relative shape context descriptor's matching scores as the foundation of compatibility coefficients, the new support function are constructed based on the compatibility coefficients. Finally, the correct matching results are achieved by using the probabilistic relaxation labelling and imposing the bijective constraints required by the overall correspondence mapping. Experiments on both synthetic point-sets and real image data show that the proposed algorithm is effective and robust.
    Computer Research and Development (ICCRD), 2011 3rd International Conference on; 04/2011
  • [Show abstract] [Hide abstract]
    ABSTRACT: The concept of "inspection robot" is born in the strong & smart grid. By studying on the mechanism of human visual attention, this paper presents a method to detect the encroachments on transmission Lines from the perspective of the saLiency-based visual attention system. There are conspicuous diffidence between the encroachments and transmission Lines and it is easy for human to distinguish the encroachments from the transmission Lines because the encroachments were always the saLient objects in the view, consequently, it is a reasonable way to detect the encroachments based on the mechanism of visual attention. The experiment results show that this method can effectively detect and locate different types of encroachments in different natural environments.
    Second International Conference on Digital Manufacturing and Automation, ICDMA 2011, Zhangjiajie, Hunan, China, August 5-7, 2011; 01/2011
  • [Show abstract] [Hide abstract]
    ABSTRACT: High resolution SAR imagery captures both the sea background and ship target more explicitly. This paper proposed an algorithm based on EXS-C-CFAR (excisionswitching context based CFAR) and Alpha-stable distribution to detect ships in high resolution SAR imagery. From experiment results, it is derived that the Alpha-stable distribution models spiky sea clutter well and the EXS-CCFAR has good ship detection performance on JPL/NASA AIRSAR data. Moreover, context information utilized in the detector preserves more ship structures. Index Terms— Synthetic aperture radar �ƒ SAR�≈ , high resolution, const false alarm rate (CFAR), ship detection�» Alpha-stable distribution
    2011 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2011, Vancouver, BC, Canada, July 24-29, 2011; 01/2011
  • [Show abstract] [Hide abstract]
    ABSTRACT: In order to classify specific objects extracted from videos, an improved algorithm is proposed in this paper. Firstly it extracts characters of proportion of skin color, ratio of area to perimeter, ratio of height to width and the statistical features of gray level dependence matrices (GLDM) to distinguish person, vehicle, crowd and the other class. It trains three kinds of support vector data description (SVDD) with features synthesized by the extracted characters. A decision tree is built with three nodes corresponding to the trained SVDDs. The experiments show that the features are properly to discriminate objects from each other and the decision tree classifier built by SVDD achieves an improved performance.
    01/2011; DOI:10.1109/wicom.2011.6040623
  • [Show abstract] [Hide abstract]
    ABSTRACT: Attribute reduction is one of the core contents in the theoretical research of rough sets. However, the inefficiency of attribute reduction algorithms limits the application of rough set. In this paper, we first point out some problems existing in the significance measure of attribute. Then a new measure, that is relative discernibility degree, is presented and proven to have the monotonicity property. Finally, a simplified consistent decision table is defined, based on which an efficient attribute reduction algorithm is designed. Theoretical analysis and experimental results show the effectiveness and practicability of this algorithm on the UCI data sets.
    Advanced Computer Control (ICACC), 2010 2nd International Conference on; 04/2010
  • [Show abstract] [Hide abstract]
    ABSTRACT: Rough set theory has been considered as a useful tool to deal with inexact, uncertain, or vague knowledge. In real-world, most of information systems are based on dominance relations, called ordered information systems. Although some uncertainty measures to evaluate the uncertainty of rough sets have been investigated in ordered information systems, the existing measures are not able to characterize well the imprecision of a rough set. So, it is necessary to find a new method to measure the roughness of rough sets in ordered information systems. In this paper, we give a well-justified measure, and some important properties are investigated. By an example, it is shown that our new method does not only overcome the limitations of the existing measures but also consist with human cognition in ordered information systems.
    Advanced Computer Control (ICACC), 2010 2nd International Conference on; 04/2010
  • [Show abstract] [Hide abstract]
    ABSTRACT: Uncertainty measure is a key issue for knowledge discovery and data mining. Rough set theory (RST) is an important tool for measuring and handling uncertain information. Although many RST-based methods to measure system uncertainty have been investigated, the existing measures are not able to characterize well the imprecision of a rough set. To overcome the shortcomings, we present a well-justified measure of uncertainty based on discernibility capability of attributes. The theoretical analysis is backed up with numerical examples to prove that our new method does not only overcome the limitations of the existing measures but also consist with human cognition.
    Robotics and Biomimetics (ROBIO), 2009 IEEE International Conference on; 01/2010
  • [Show abstract] [Hide abstract]
    ABSTRACT: This paper proposes a relative shape context and relaxation labeling (RSC-RL) based approach for point pattern matching (PPM). First of all, a new point set based invariant feature, Relative Shape Context (RSC), is proposed. Using the test statistic of relative shape context descriptor's matching scores as the foundation of support function, the point pattern matching probability matrix can be iteratively updated by relaxation labeling (RL). In the end, the one-to-one matching can be achieved by dual-normalization of rows and columns in the finally obtained matching probability matrix. Experiments on both synthetic point sets and real world data show that the performance of the proposed technique is favorable under rigid geometric distortion, noises and outliers.
  • [Show abstract] [Hide abstract]
    ABSTRACT: The kernel RX algorithm improves the separability between target and background pixels by mapping hyperspectral image data from the low dimensional space into high dimensional feature space. However, the kernel matrix of the background is generated by all image pixels without considering the interference of anomaly target pixels which will make the miss rate increase and consume large memory. To resolve the problem, an anomaly detection algorithm based on background endmember extraction and kernel RX algorithm is introduced. Firstly, the RX algorithm is applied for image processing to filter out obvious anomaly pixels. Then endmember extraction algorithm is used to extract the background endmember according to which the kernel matrix is generated. Experimental results show the effectiveness of the algorithm in improving the detection performance.