Shilin Zhou

SAR Image Segmentation via Hierarchical Region Merging and Edge Evolving With Generalized Gamma Distribution

This letter proposes a novel segmentation algorithm for synthetic aperture radar (SAR) images based on hierarchical region merging and edge evolving. To cope with the influence of speckle in SAR images, a statistical stepwise criterion, the loss of log-likelihood function (LLF) of image partition, is utilized for region merging. For this merging procedure, precise distributions of image partitions are essential, and we employ the generalized gamma distribution (GΓD) for modeling SAR images. Besides, the traditional region merging methods often suffer from the initial image partition that may lead to coarse segment shapes. It motivates us introducing a novel edge evolving scheme into the segmentation algorithm. It consists of two iterative steps: the evolution of edge pixels with a maximum likelihood (ML) criterion and that with a maximum a posterior (MAP) criterion using a Markov random field (MRF) model. The performance of the proposed algorithm is validated on two actual SAR images from the AIRSAR and EMISAR systems.

Statistical modeling of sea clutter in high-resolution SAR images using generalized gamma distribution

Statistical modeling of sea clutter in synthetic aperture radar (SAR) imagery is fundamental for SAR image interpretation. In this paper, we adopt a recently proposed generalized gamma distribution (GrD) for modeling sea clutter in high-resolution SAR images. Based on parameter decoupling, an estimator of GrD, named as scale-independent scale estimation (SISE), is derived, which only refers to several basic operations and can be easily realized. Modeling experiments are carried out over the L-band polarimetric SAR images acquired by JPL/AIRSAR and a VV-polarized C-band TerraSAR-X SAR image. Experimental results show that the advantage of GrD for modeling sea clutter in high-resolution SAR images is evident comparing to the classic distributions of sea clutter in SAR images including the Weibull, Log-normal and K distributions.

Surrounding Moving Obstacle Detection for Autonomous Driving Using Stereo Vision

Detection and tracking surrounding moving obstacles such as vehicles and pedestrians are crucial for the safety of mobile robotics and autonomous vehicles. This is especially the case in urban driving scenarios. This paper presents a novel framework for surrounding moving obstacles detection using binocular stereo vision. The contributions of our work are threefold. Firstly, a multiview feature matching scheme is presented for simultaneous stereo correspondence and motion correspondence searching. Secondly, the multiview geometry constraint derived from the relative camera positions in pairs of consecutive stereo views is exploited for surrounding moving obstacles detection. Thirdly, an adaptive particle filter is proposed for tracking of multiple moving obstacles in surrounding areas. Experimental results from real-world driving sequences demonstrate the effectiveness and robustness of the proposed framework.

Point Pattern Matching based on point pair local nonuniform ODT and Spectral Matching

This article proposes a novel and robust point Pattern Matching Algorithm (PPM) which combines the invariant feature and Spectral Matching (SM). A new point-set based invariant feature, point pair local nonuniform ODT (Orientation and Distance Based Topology), is presented firstly. The matching measurement of point pair local nonuniform ODT descriptors statistic test is used to define new compatibility coefficients. Then on basis of the gained compatibility measurement, we can construct a matching graph and its affinity matrix. Finally, the correct matching results are achieved using the main eigenvector of affinity matrix of assignment graph and the mapping constraint conditions. Convictive experimental results on both synthetic point-sets and real world data indicate that the proposed algorithm is robust to outliers and noise. In addition, it performs better in the presence of similarity or even perspective transformation among point sets in the meantime comparing with the other state-of-art algorithms.

A point matching algorithm based on reference point pair

Outliers and occlusions are important degradation in the real application of point matching. In this paper, a novel point matching algorithm based on the reference point pairs is proposed. In each iteration, it firstly eliminates the dubious matches to obtain the relatively accurate matching points (reference point pairs), and then calculates the shape contexts of the removed points with reference to them. After re-matching the removed points, the reference point pairs are combined to achieve better correspondences. Experiments on synthetic data validate the advantages of our method in comparison with some classical methods.

Emitter Target Tracking by Tracklet Association Using Affinity Propagation

Due to electromagnetic silence, passive tracking systems for emitter targets usually produce track segments (i.e., tracklets) rather than an entire trajectory of the target. Therefore, a multistage method for emitter target tracking is proposed in this paper. In the stage of tracklet generation, the Gaussian mixture-probability hypothesis density tracker with adaptive estimation of target birth intensity is applied to generate reliable tracklets of the emitter targets. After that, in the stage of tracklet association, the multipoint motion information and emitter signal information are integrated to compute the similarities between the tracklets. The affinity propagation algorithm, which does not impose the constraint of one-to-one correspondence, is then used to cluster the tracklets. In the stage of association refining, the clustering result is adjusted to refine the final trajectories according to the spatial-temporal constraint of the tracklets. The simulation results show that the proposed method is robust and performs well.

Automatic non-rigid image registration based on deformation invariant feature and local geometric constraint

Image registration is an important research topic in the field of computer vision. Traditional non-rigid image registration methods are based on the correctly matched corresponding landmarks, which usually needs artificial markers. It is a rather challenging and demanding task to locate the accurate position of the points and get the correspondance. In order to get the most correctly matched point set automatically, a new point matching method based on deformation invariant feature and local affine-invariant geometric constraint is proposed in this paper. Particularly mention should be the geodesic-intensity histogram (GIH), an interesting deformation invariant descriptor, which is introduced to describe the local feature of a point. In addition, the local affine invariant structure is employed as a geometric constraint. Therefore, an objective function that combines both local features and geometric constraint is formulated and computed by linear programming efficiently. Then, the correspondence is obtained and thin-plate spline (TPS) is employed for non-rigid registration. Our method is demonstrated with deliberately designed synthetic data and real data and the proposed method can better improve the accuracy as compared to the traditional registration techniques.

Extended Emitter Target Tracking Using GM-PHD Filter

If equipped with several radar emitters, a target will produce more than one measurement per time step and is denoted as an extended target. However, due to the requirement of all possible measurement set partitions, the exact probability hypothesis density filter for extended target tracking is computationally intractable. To reduce the computational burden, a fast partitioning algorithm based on hierarchy clustering is proposed in this paper. It combines the two most similar cells to obtain new partitions step by step. The pseudo-likelihoods in the Gaussian-mixture probability hypothesis density filter can then be computed iteratively. Furthermore, considering the additional measurement information from the emitter target, the signal feature is also used in partitioning the measurement set to improve the tracking performance. The simulation results show that the proposed method can perform better with lower computational complexity in scenarios with different clutter densities.

Performance comparison and assessment of displaced phase center antenna and along-track interferometry techniques used in synthetic aperture radar-ground moving target indication

Abstract Displaced phase center antenna (DPCA) and along-track interferometry (ATI) are the two popular techniques used to determine synthetic aperture radar-ground moving target indication fields, and studies have shown that the combinations of these techniques can improve the target detection performance. However, a crucial problem is how to combine the two techniques, which requires a complete analysis and comparison of the individual techniques. Generally, it is well known that the performances of these techniques are closely related to clutter and noise. A detailed comparison of the detection performance of ATI and DPCA is presented, together with an assessment developed by theoretical analysis and simulations. The results show that the ATI is limited mainly by the clutter and noise, while DPCA is limited mainly by channel imbalance and noise. The ATI’s main drawback is its high false alarm rate, and DPCA is more sensitive to the channel imbalance. In most cases, DPCA is better than ATI, but for a high clutter-to-noise ratio, low signal-to-clutter power ratio, and channel imbalance, ATI has a better performance than DPCA. The real data experiments verify the theoretical findings. Meanwhile, the effects of target radial velocity, incidence angle, transmission bandwidth, and terrain type on the performance of the two detection approaches are also investigated.

A CFAR algorithm for layover and shadow detection in InSAR images based on kernel density estimation

In this paper, a novel CFAR algorithm for detecting layover and shadow areas in Interferometric synthetic aperture radar (InSAR) images is proposed. Firstly, the probability density function (PDF) of the square root amplitude of InSAR image is estimated by the kernel density estimation. Then, a CFAR algorithm combining with the morphological method for detecting both layover and shadow is presented. Finally, the proposed algorithm is evaluated on a real InSAR image obtained by TerraSAR-X system. The experimental results have validated the effectiveness of the proposed method.