Modified Markov Random Field Research Articles

Uncertainty based regional-decision fusion of multispectral and nDSM for ultra-high resolution UAV imagery

ABSTRACT The recent advancement in the pattern recognition technique has demonstrated the superiority of remote sensing technology. Deep neural networks use spatial feature representations such as convolution neural networks (CNN) to provide better generalisation capability. Our aim is two-fold: firstly, increase the reliability feature by performing the Dual-scale fusion via a modified Markov random field known as DuCNN-MMRF. Secondly, an integration framework was introduced to combine the multispectral image classification produced by DuCNN-MMRF and Normalised-Digital Surface Model (nDSM) information, using a novel approach known as constraint-based Dempster Shafer theory (C-DST). C-DST targeted DuCNN-MMRF’s uncertain information (ambiguous information) and rectified it with complementary information.

Fusion of Dual-Scale Convolution Neural Network for Urban Building Footprints

Building footprint has a significant role in urban design and management but, extracting the building feature is still challenging due to significant variations in scale and shape. Convolution neural networks (CNN) have shown effective results in extracting the high-level and discriminative urban features from high-resolution remote sensing imagery. The traditional CNN architecture has been modified two-scale input based architecture, known as Dual-scale CNN (Du-CNN). However, the repetitive usage of pooling operation leads to a fuzzy boundary of the extracted features. This paper has proposed the MRF-based fusion strategy to take full use of the blurred boundary and define the conditional relationship between classification maps. In the Preliminary stage, we have designed a Du-CNN framework to extract the building feature at different scales. Du-CNN contains a multiple-size asymmetric filter to provide the variation in the receptive field and the depth-wise convolution in the skip connection block for efficient computation. Finally, the classification maps of both CNN sub-architectures are fused using a Modified Markov random field (MMRF). The proposed MMRF technique inherits the properties of Classical MRF with the extension of overlap potential for associating additional terms between the inter-decision layer. The model was tested on Inria Aerial image labeling dataset and Mnih dataset. Experimental result has shown the superior performance of the proposed strategy for extracting the complex building architecture.

Single image super-resolution reconstruction of remotely sensed images using MRF-2D phase congruency model

Recently, the deep learning (DL)-based solution for single image super-resolution reconstruction has been extensively used. Though these methods have shown exceptional results, the computational requirement is very high and requires high-end graphic processors. Motivated to establish an efficient method without such requirement, we propose a modified Markov random field (MRF) model and two-dimensional (2D) phase congruency-based single-image super-resolution reconstruction method for remote sensing images. The 2D phase congruency-based feature extraction method is used to compute features such as edge and texture maps to achieve higher accuracy in finding similar example patches in feature space. To address an essential aspect of successful texture reconstruction, we have incorporated a texture prior for the computation of joint probability in our work. Image Euclidean distance (Ieuc) is integrated to achieve higher accuracy in finding the similarity between image patches in feature space and modeling compatibility functions. The experimental results demonstrate that the results of the proposed method are at par with the DL-based methods and outperform other state-of-the-art methods in perceptual quality as well as peak signal-to-noise ratio and structural similarity index parameters. Moreover, it shows significant improvement in the texture regions while reconstructing sharper edges for ×4 upscaling.

Tsallis-Entropy Segmentation through MRF and Alzheimer anatomic reference for Brain Magnetic Resonance Parcellation

Quantifying the intracranial tissue volume changes in magnetic resonance imaging (MRI) assists specialists to analyze the effects of natural or pathological changes. Since these changes can be subtle, the accuracy of the automatic compartmentalization method is always criticized by specialists. We propose and then evaluate an automatic segmentation method based on modified q-entropy (Mqe) through a modified Markov Random Field (MMRF) enhanced by Alzheimer anatomic reference (AAR) to provide a high accuracy brain tissues parcellation approach (Mqe-MMRF). We underwent two strategies to evaluate Mqe-MMRF; a simulation of different levels of noise and non-uniformity effect on MRI data (7 subjects) and a set of twenty MRI data available from MRBrainS13 as patient brain tissue segmentation challenge. We accessed eleven quality metrics compared to reference tissues delineations to evaluate Mqe-MMRF. MRI segmentation scores decreased by only 4.6% on quality metrics after noise and non-uniformity simulations of 40% and 9%, respectively. We found significant mean improvements in the metrics of the five training subjects, for whole-brain 0.86%, White Matter 3.20%, Gray Matter 3.99%, and Cerebrospinal Fluid 4.16% (p-values < 0.02) when Mqe-MMRF compared to the other reference methods. We also processed the Mqe-MMRF on 15 evaluation subjects group from MRBrainS13 online challenge, and the results held a higher rank than the reference tools; FreeSurfer, SPM, and FSL. Since the proposed method improved the precision of brain segmentation, specifically, for GM, and thus one can use it in quantitative and morphological brain studies.

Video object extraction using optimized smoothed dirichlet process multi-view learning with improved adaptive modified Markova random field

Video object extraction (VOE) using segmentation from a video sequence is a very important task in editing and multimedia analysis for film making. Most of the VOE approaches required prior knowledge about background and foreground to extract target objects. In this paper, an Optimized smoothed Dirichlet Process Multi-view learning with improved adaptive Modified Markov Random Field which is enhanced by adaptive shape prior modified graph cut (OsDPMVL-IASMMRF) model has been extended for video-based object extraction. The contour tracking has been additionally included OsDPMVL-IASMMRF for VOE. The Teh–Chin algorithm has been used with OsDPMVL-IASMMRF for predicting the contour in the current frame by matching the extracted object contour from the previous segmented frame. The contour tracking propagates the shape of the target object, whereas the OsDPMVL-IASMMRF segmentation refined the object boundary and the shape for enhancing the accuracy of video segmentation. The experimental outcomes show that the proposed approach provides better segmentation results in terms of accuracy, precision and recall.

Low-dose CT statistical iterative reconstruction via modified MRF regularization

It is desirable to reduce the excessive radiation exposure to patients in repeated medical CT applications. One of the most effective ways is to reduce the X-ray tube current (mAs) or tube voltage (kVp). However, it is difficult to achieve accurate reconstruction from the noisy measurements. Compared with the conventional filtered back-projection (FBP) algorithm leading to the excessive noise in the reconstructed images, the approaches using statistical iterative reconstruction (SIR) with low mAs show greater image quality. To eliminate the undesired artifacts and improve reconstruction quality, we proposed, in this work, an improved SIR algorithm for low-dose CT reconstruction, constrained by a modified Markov random field (MRF) regularization. Specifically, the edge-preserving total generalized variation (TGV), which is a generalization of total variation (TV) and can measure image characteristics up to a certain degree of differentiation, was introduced to modify the MRF regularization. In addition, a modified alternating iterative algorithm was utilized to optimize the cost function. Experimental results demonstrated that images reconstructed by the proposed method could not only generate high accuracy and resolution properties, but also ensure a higher peak signal-to-noise ratio (PSNR) in comparison with those using existing methods.

Development and evaluation of MRI based Bayesian image reconstruction methods for PET

A maximum a posteriori algorithm, which incorporates correlated magnetic resonance images into the processing of positron emission tomography reconstruction with the aim of improving image quality was developed. The line site map from MRI a priori is made up of a modified Markov random field or Canny edge detector with Gaussian smoothing filter. It is used in the MAP algorithm by a weighted line site method. We evaluate and compare the performance of these reconstruction methods. The results show that the Bayesian methods produce reconstructed images with less noise and better spatial resolution than those produced by the maximum likelihood–expectation maximization method.

Assessing the impact of temporal dynamics on land-use change modeling

Time is a fundamental dimension in dynamic land-use change modeling. An appropriate treatment of time is essential to realistically simulate landscape dynamics. Current land-use models provide little justification of their treatment of time. As a result, little is known about how the time dimension impacts the spatio-temporal patterns produced by land-use simulation models. This paper reports a first exploration on this issue. It examines the impact of the degree of temporal dynamics on the behavior of an urban growth model which is based on a modified Markov random field and probabilistic cellular automata. Experimental results from this case study suggest that the degree of temporal dynamics does have an important impact on the urban morphology produced by the model. Too much or too little dynamics could both lead to unrealistic patterns. However, the impact seems to vary for processes with different levels of change intensity. In the case of a process with moderate changes, the impact of temporal dynamics is also moderate. For a process with high change rate, the degree of temporal dynamics affects the model output significantly. The implication of these findings is discussed in the context of information accessibility and operational land-use modeling.

Urban Settlement Transitions

Urban growth dynamics attracts the efforts of scientists from many different disciplines with objectives ranging from theoretical understanding to the development of carefully tuned realistic models that can serve as planning and policy tools. Theoretical models are often abstract and of limited applied value while most applied models yield little theoretical understanding. Here we present a mathematically well-defined model based on a modified Markov random field with lattice-wide interactions that produces realistic growth patterns as well as behavior observed in a range of other models based on diffusion-limited aggregation, cellular automata, and similar models. We investigate the framework's ability to generate plausible patterns using minimal assumptions about the interaction parameters since the tuning and specific definition of these are outside of the scope of this paper. Typical universality classes of the simulated dynamics and the phase transitions between them are discussed in the context of real urban dynamics. Using suitability data derived from topography, we produce configurations quantitatively similar to real cities. Also, an intuitive class of interaction rules is found to produce fractal configurations, not unlike vascular systems, that resemble urban sprawl. The dynamics are driven by interactions, depicting human decisions, between all lattice points. This is realized in a computationally efficient way using a mean-field renormalization (area average) approach. The model provides a mathematically transparent framework to which any level of detail necessary for actual urban planning application can be added.

Markov random field for tumor detection in digital mammography

A technique is proposed for the detection of tumors in digital mammography. Detection is performed in two steps: segmentation and classification. In segmentation, regions of interest are first extracted from the images by adaptive thresholding. A further reliable segmentation is achieved by a modified Markov random field (MRF) model-based method. In classification, the MRF segmented regions are classified into suspicious and normal by a fuzzy binary decision tree based on a series of radiographic, density-related features. A set of normal (50) and abnormal (45) screen/film mammograms were tested. The latter contained 48 biopsy proven, malignant masses of various types and subtlety. The detection accuracy of the algorithm was evaluated by means of a free response receiver operating characteristic curve which shows the relationship between the detection of true positive masses and the number of false positive alarms per image. The results indicated that a 90% sensitivity can be achieved in the detection of different types of masses at the expense of two falsely detected signals per image. The algorithm was notably successful in the detection of minimal cancers manifested by masses </=10 mm in size. For the 16 such cases in the authors' dataset, a 94% sensitivity was observed with 1.5 false alarms per image. An extensive study of the effects of the algorithm's parameters on its sensitivity and specificity was also performed in order to optimize the method for a clinical, observer performance study.