Markov random field

About: Markov random field is a research topic. Over the lifetime, 5669 publications have been published within this topic receiving 179568 citations. The topic is also known as: MRF.

Adaptive Markov random fields for example-based super-resolution of faces

Abstract: Image enhancement of low-resolution images can be done through methods such as interpolation, super-resolution using multiple video frames, and example-based super-resolution. Example-based super-resolution, in particular, is suited to images that have a strong prior (for those frameworks that work on only a single image, it is more like image restoration than traditional, multiframe super-resolution). For example, hallucination and Markov random field (MRF) methods use examples drawn from the same domain as the image being enhanced to determine what the missing high-frequency information is likely to be. We propose to use even stronger prior information by extending MRF-based super-resolution to use adaptive observation and transition functions, that is, to make these functions region-dependent. We show with face images how we can adapt the modeling for each image patch so as to improve the resolution.

An Active Deep Learning Approach for Minimally Supervised PolSAR Image Classification

Abstract: Recently, deep neural networks have received intense interests in polarimetric synthetic aperture radar (PolSAR) image classification. However, its success is subject to the availability of large amounts of annotated data which require great efforts of experienced human annotators. Aiming at improving the classification performance with greatly reduced annotation cost, this paper presents an active deep learning approach for minimally supervised PolSAR image classification, which integrates active learning and fine-tuned convolutional neural network (CNN) into a principled framework. Starting from a CNN trained using a very limited number of labeled pixels, we iteratively and actively select the most informative candidates for annotation, and incrementally fine-tune the CNN by incorporating the newly annotated pixels. Moreover, to boost the performance and robustness of the proposed method, we employ Markov random field (MRF) to enforce class label smoothness, and data augmentation technique to enlarge the training set. We conducted extensive experiments on four real benchmark PolSAR images, and experiments demonstrated that our approach achieved state-of-the-art classification results with significantly reduced annotation cost.

Conjugate gamma Markov random fields for modelling nonstationary sources

Abstract: In modelling nonstationary sources, one possible strategy is to define a latent process of strictly positive variables to model variations in second order statistics of the underlying process. This can be achieved, for example, by passing a Gaussian process through a positive nonlinearity or defining a discrete state Markov chain where each state encodes a certain regime. However, models with such constructs turn out to be either not very flexible or non-conjugate, making inference somewhat harder. In this paper, we introduce a conjugate (inverse-) gamma Markov Random field model that allows random fluctuations on variances which are useful as priors for nonstationary time-frequency energy distributions. The main idea is to introduce auxiliary variables such that full conditional distributions and sufficient statistics are readily available as closed form expressions. This allows straightforward implementation of a Gibbs sampler or a variational algorithm. We illustrate our approach on denoising and single channel source separation.

Estimating disparity and occlusions in stereo video sequences

Abstract: We propose an algorithm for estimating disparity and occlusion in stereo video sequences. The algorithm defines a prior on sequences of disparity maps using a 3D Markov random field, and approximately computes the MAP estimate for the disparity sequence using loopy belief propagation. In contrast to previous work on temporal stereo, the algorithm (i) correctly models half-occlusions - scene points visible in one camera but not the other - and (ii) enforces the so-called "monotonicity constraint" on the boundary of half-occluded regions. The algorithm is also able to exploit temporal coherence more appropriately than many previous approaches to temporal stereo, by employing additional states in the Markov random field. These additional states permit rudimentary motion estimation to be performed as part of the belief propagation, thus improving the quality of temporal inference. Parameters of the algorithm are learned from the ground truth disparities of a real stereo sequence. Qualitative results are shown on real sequences, including comparisons with competing approaches, and the performance of the algorithm is assessed quantitatively using the ground truth data.

Fast Probabilistic Labeling of City Maps

Abstract: This paper introduces a probabilistic, two-stage classification framework for the semantic annotation of urban maps as provided by a mobile robot. During the first stage, local scene properties are considered using a probabilistic bagof-words classifier. The second stage incorporates contextual information across a given scene via a Markov Random Field (MRF). Our approach is driven by data from an onboard camera and 3D laser scanner and uses a combination of appearancebased and geometric features. By framing the classification exercise probabilistically we are able to execute an informationtheoretic bail-out policy when evaluating appearance-based classconditional likelihoods. This efficiency, combined with low order MRFs resulting from our two-stage approach, allows us to generate scene labels at speeds suitable for online deployment and use. We demonstrate and analyze the performance of our technique on data gathered over almost 17 km of track through a city.