Contextual modeling of remote sensing images with conditional random fields

Download
2013
Can, Gülcan
Large within-class variance is a challenging problem for classification tasks in remote sensing. Contextual models are promising to address this problem. In this thesis, a contextual conditional random field model is proposed for target detection in satellite imagery. The proposed algorithm has three stages. First, contextual cues of the target that come from domain knowledge are identified by sparse auto-encoders and shown to be statistically consistent. The region represented by the most repetitive feature learned by sparse autoencoders is used as central node in the proposed model and called candidate region. Other nodes of the model are chosen as land-use land-cover classes in the surroundings of the candidate regions, since the spatial context of the target class is defined over expected and unexpected classes in its neighborhood. Secondly, regions that represent these classes are obtained by merging segments with the same label according to support vector machines. These regions are called meta-segments. In the last stage, the same features are extracted from the meta-segments and candidate region to be used as unary features in the conditional random fields model. Pairwise features in conditional random fields are essential for representing contextual relations and they are designed as class co-occurrence frequencies in three di erent neighborhoods of the candidate region. For each candidate region, a dynamic conditional random fields model is generated. The proposed method is robust in terms of being threshold-free and selecting contextual cues via sparse auto-encoders. Performance of the method is competitive to rule-based methods and segmentation-based classification methods.

Suggestions

New change detection method using double segmentation and its application on remotely sensed images
Gedik, Ekin; Yarman Vural, Fatoş Tunay; Department of Computer Engineering (2013)
Change detection research, a branch of statistical data analysis, focuses on detecting changed samples between di erent observations of the same dataset. The proposed study presents a novel change detection procedure and its application as a complete framework which is designed to work on remotely sensed images. The scope of the study is defined as detecting man-made change objects between satellite images of the same region, acquired at di erent times. Proposed framework has three main steps as preprocessi...
Representation Learning for Contextual Object and Region Detection in Remote Sensing
Firat, Orhan; Can, Gulcan; Yarman Vural, Fatoş Tunay (2014-08-28)
The performance of object recognition and classification on remote sensing imagery is highly dependent on the quality of extracted features, amount of labelled data and the priors defined for contextual models. In this study, we examine the representation learning opportunities for remote sensing. First we attacked localization of contextual cues for complex object detection using disentangling factors learnt from a small amount of labelled data. The complex object, which consists of several sub-parts is fu...
Multi-target tracking with PHD filter using Doppler-only measurements
Guldogan, Mehmet B.; Lindgren, David; Gustafsson, Fredrik; Habberstad, Hans; Orguner, Umut (2014-04-01)
In this paper, we address the problem of multi-target detection and tracking over a network of separately located Doppler-shift measuring sensors. For this challenging problem, we propose to use the probability hypothesis density (PHD) filter and present two implementations of the PHD filter, namely the sequential Monte Carlo PHD (SMC-PHD) and the Gaussian mixture PHD (GM-PHD) filters. Performances of both filters are carefully studied and compared for the considered challenging tracking problem. Simulation...
Deterministic modeling and inference of biological systems
Seçilmiş, Deniz; Purutçuoğlu Gazi, Vilda; Department of Bioinformatics (2017)
The mathematical description of biological networks can be performed mainly by stochastic and deterministic models. The former gives more information about the system, whereas, it needs very detailed measurements. On the other hand, the latter is relatively less informative, but, the collection of their data is easier than the stochastic ones, rendering it a more preferable modeling approach. In this study, we implement the deterministic modeling of biological systems due to the underlying advantage. Among ...
Unit root problems in time series analysis
Purutcuoğlu, Vilda; Tiku, Moti Lal; Department of Statistics (2004)
In time series models, autoregressive processes are one of the most popular stochastic processes, which are stationary under certain conditions. In this study we consider nonstationary autoregressive models of order one, which have iid random errors. One of the important nonstationary time series models is the unit root process in AR (1), which simply implies that a shock to the system has permanent effect through time. Therefore, testing unit root is a very important problem. However, under nonstationarity...
Citation Formats
G. Can, “Contextual modeling of remote sensing images with conditional random fields,” M.S. - Master of Science, Middle East Technical University, 2013.