Jixiang Sun

An Improved Scheme for Parameter Estimation of G° Distribution Model in High-Resolution SAR Images

Statistical modeling of Synthetic Aperture Radar (SAR) images is of great importance for speckle noise flltering, target detection and classiflcation, etc. Moreover, it can provide a comprehensive understanding of terrain electromagnetics scattering mechanism. Over the past three decades, many sophisticated models have been developed for SAR images, such as Rayleigh, Gamma, K and G etc. The G 0 distribution is a special form of the G model, which can model the speckle ∞uctuations of many classes of objects like homogeneous, heterogeneous and extremely heterogeneous ones, and is widely used in SAR images interpretation. However, as many improvements have been performed on SAR sensors, the traditional parameter estimation methods of the G 0 distribution may be not su-cient, notably in high resolution SAR images. They cannot arrive at a solution frequently when modeling regions in high resolution SAR images, especially the extremely homogeneous regions. In order to deal with this problem, this paper proposes an improved parameter estimation scheme of the G 0 distribution, which combines the classical moment estimation with the mellin transform. To quantitatively assess the fltting precision of the proposed method, we adopt the Kullback- Leibler (KL) distance, Kolmogorov-Smirnov (KS) test and Mean Square Error (MSE) as similarity measurements. The advantage of this proposed parameter estimation method becomes evident through the analysis of a variety of areas (ground vegetation, trees and buildings) in two high resolution SAR images.

Semi-automatic road centerline extraction in high-resolution SAR images based on circular template matching

Because of the disturb of trees along roads, buildings to cover, cars getting on the road an etc, it is difficult to automatically extract centerline of roads from high-resolution SAR images. This paper presents a new semi-automatic road centerline extraction method based on circular template matching. Firstly, circular template and the road orientation are calculated by user-given input two points. Secondly, center points are searched by matching the template against the image along the orientation of the road under consideration. Finally, the extracted center points are linked by quadratic curve fitting. Human interactions are needed when center points searching failed. SAR images with 1 meter resolution taken by airborne SAR were used in the experiment. And the results show that the centerline extraction method mentioned above is effective in high resolution SAR images.

Notice of Retraction An efficient attribute reduction algorithm

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.

Road Extraction from High-Resolution SAR Images via Automatic Local Detecting and Human-Guided Global Tracking

Because of existence of various kinds of disturbances, layover effects, and shadowing, it is difficult to extract road from high-resolution SAR images. A new road center-point searching method is proposed by two alternant steps: local detection and global tracking. In local detection step, double window model is set, which consists of the outer fixed square window and the inner rotary rectangular one. The outer window is used to obtain the local road direction by using orientation histogram, based on the fact that the surrounding objects always range along with roads. The inner window rotates its orientation in accordance with the result of local road direction calculation and searches the center points of a road segment. In global tracking step, particle filter of variable-step is used to deal with the problem of tracking frequently broken by shelters along the roadside and obstacles on the road. Finally, the center-points are linked by quadratic curve fitting. In 1 m high-resolution airborne SAR image experiment, the results show that this method is effective.

Point pattern matching using Relative Shape Context and relaxation labeling

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 descriptors 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.

Inexact point pattern matching algorithm based on Relative Shape Context and probabilistic relaxation labelling

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 descriptors 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.

PDE image inpainting with texture synthesis based on damaged region classification

Image inpainting aims to restore lost information according to gray patterns from known area. PDE and texture synthesis are both widely applied in image inpainting. A new image inpainting algorithm combined those two kinds of methods are presented. Damaged region pixels are classified into texture pixels and structure pixels, which are inpainted with corresponding algorithms. Texture classification to the known image is also done to reduce the texture search region. The new algorithm require much less time than the classic inpainting algorithm.

Road junction extraction in high-resolution SAR images via morphological detection and shape identification

Road junctions are important components of a road network. Therefore, if road junctions are identified accurately, the quality of road extraction can be improved. However, they are often neglected by most methods for road extraction. This letter presents a road junction extraction method with two stages. First, global detection is performed to find the centre positions of the road junction candidates by using morphological operators. Second, the shape of a road junction is identified based on a valley-finding algorithm. The proposed method is validated by airborne synthetic aperture radar (SAR) images of 1 m resolution. The results indicate that the proposed method has a higher recognition rate than two other methods and is robust to various interferences.

Imaging of Transmission Equipment by Saliency-Based Compressive Sampling

The traditional intelligent inspection system often takes high-resolution images and then compressed through the codec for efficient storage purpose, which leads to the waste of image data and memory resources. The compressive sampling theory showed that under certain conditions, a signal can be precisely reconstructed from only a small set of measurements, however, the reconstruction algorithms are generally very expensive. By studying on the need of imaging of the transmission equipment, we adopt an imaging method based on saliency to balance the reconstruction complexities and the quality of image. The method first uses a low-resolution complementary sensor to obtain the saliency information of the scene, then obtains the saliency map of the imaging scene by the spectral residual approach, and then assigns higher sample rate to the area of transmission equipment and lower sample rate to the background area in compressive imaging. The simulation results show that the image of transmission equipment can be precisely reconstructed from only a small set of measurements.

An Outlier Detection Method for Robust Manifold Learning

Manifold learning algorithms have been widely used in data mining and pattern recognition. Despite their attractive properties, most manifold learning algorithms are not robust to outliers. In this paper, a novel outlier detection method for robust manifold learning is proposed. First, the contextual distance based reliability score is proposed to measure the likelihood of each sample to be a clean sample or an outlier. Second, we design an iterative scheme on the reliability score matrix to detect outliers. By considering both local and global manifold structure, the proposed method is more topologically stable than RPCA method. The proposed method can serve as a preprocessing procedure for manifold learning algorithms and make them more robust, as observed from our experimental results.