In this letter, we propose a new level-set-based energy functional for the purpose of synthetic aperture radar (SAR) image segmentation into Gamma homogeneous regions. The segmentation of SAR images is a difficult problem due to the presence of speckles, which can be modeled as strong multiplicative noise. Our proposed energy functional is designed to get a stationary global minimum. As a result, the level set function that evolves by the Euler-Lagrange equation of the energy functional has a unique stationary convergence state. Moreover, it is easy to set a termination criterion on the curve evolution via a level set by using our energy functional. The experimental results on both synthetic and real SAR images demonstrate the effectiveness of our method.

Device-free localization (DFL) based on wireless sensor networks (WSNs) is expected to detect and locate a person without the need for any wireless devices. Radio tomographic imaging (RTI) has attracted wide attention from researchers as an emerging important technology in WSNs. However, there is much room for improvement in localization estimation accuracy. In this paper, we propose a geometry-based elliptical model and adopt the orthogonal matching pursuit (OMP) algorithm. The new elliptical model uses not only line-of-sight information, but also non-line-of-sight information, which divides one ellipse into several areas with different weights. Meanwhile the OMP, which can eliminate extra bright spots in image reconstruction, is used to derive an image estimator. The experimental results demonstrate that the proposed algorithm could improve the accuracy of positioning by up to 23.8% for one person and 33.3% for two persons over some state-of-the-art RTI methods.

Local region description of multi-sensor images remains a challenging task in remote sensing image analysis and applications due to the non-linear radiation variations between images. This paper presents a novel descriptor based on the combination of the magnitude and phase congruency information of local regions to capture the common features of images with non-linear radiation changes. We first propose oriented phase congruency maps (PCMs) and oriented magnitude binary maps (MBMs) using the multi-oriented phase congruency and magnitude information of log-Gabor filters. The two feature vectors are then quickly constructed based on the convolved PCMs and MBMs. Finally, a dense descriptor named the histograms of oriented magnitude and phase congruency (HOMPC) is developed by combining the histograms of oriented phase congruency (HPC) and the histograms of oriented magnitude (HOM) to capture the structure and shape properties of local regions. HOMPC was evaluated with three datasets composed of multi-sensor remote sensing images obtained from unmanned ground vehicle, unmanned aerial vehicle, and satellite platforms. The descriptor performance was evaluated by recall, precision, F1-measure, and area under the precision-recall curve. The experimental results showed the advantages of the HOM and HPC combination and confirmed that HOMPC is far superior to the current state-of-the-art local feature descriptors.

This paper proposes a multi-level max-margin discriminative analysis (M³DA) framework, which takes both coarse and fine semantics into consideration, for the annotation of high-resolution satellite images. In order to generate more discriminative topic-level features, the M³DA uses the maximum entropy discrimination latent Dirichlet Allocation (MedLDA) model. Moreover, for improving the spatial coherence of visual words neglected by M³DA, conditional random field (CRF) is employed to optimize the soft label field composed of multiple label posteriors. The framework of M³DA enables one to combine word-level features (generated by support vector machines) and topic-level features (generated by MedLDA) via the bag-of-words representation. The experimental results on high-resolution satellite images have demonstrated that, using the proposed method can not only obtain suitable semantic interpretation, but also improve the annotation performance by taking into account the multi-level semantics and the contextual information.

A fast approach to obtain segmentation of SAR images has been suggested here based on the local statistical characteristics using Markov random field (MRF) model on region adjacency graph (RAG). First, an initially over-segmented image derived from the watershed segmentation algorithm as well as the original SAR image is taken as the inputs of the proposed method. Secondly, a MRF is defined on RAG of the initial over segmented regions, with a novel multilevel logistic (MLL) model for the region class labels and Gamma distribution for the marginal distribution of each class in the SAR images. The criterion used for getting the optimal segmentation is the maximization of the posterior marginal (MPM), which minimizing the expected value of the number of the misclassified regions in the over-segmented image. In the implementation, the expectation maximization (EM) algorithm is used to estimate the parameters of Gamma distribution, and the parameters of the MLL model is derived from the RAG. Experimental results on real SAR images show that the proposed method can reduce the computational complexity greatly and provide precise segmentation results