Search

We propose a novel unsupervised semantic segmentation method for fast and accurate flood area detection utilizing color images acquired from unmanned aerial vehicles (UAVs). To the best of our knowledge, this is the first fully unsupervised method for flood area segmentation in color images captured by UAVs, without the need of pre-disaster images. The proposed framework addresses the problem of flood segmentation based on parameter-free calculated masks and unsupervised image analysis techniques. First, a fully unsupervised algorithm gradually excludes areas classified as non-flood, utilizing calculated masks over each component of the LAB colorspace, as well as using an RGB vegetation index and the detected edges of the original image. Unsupervised image analysis techniques, such as distance transform, are then applied, producing a probability map for the location of flooded areas. Finally, flood detection is obtained by applying hysteresis thresholding segmentation. The proposed method is tested and compared with variations and other supervised methods in two public datasets, consisting of 953 color images in total, yielding high-performance results, with 87.4% and 80.9% overall accuracy and F1-score, respectively. The results and computational efficiency of the proposed method show that it is suitable for onboard data execution and decision-making during UAV flights. [ABSTRACT FROM AUTHOR]

We present a novel solution to the problem of detecting common actions in time series of motion capture data and videos. Given two action sequences, our method discovers all pairs of common subsequences, i.e. subsequences that represent the same or similar action. This is achieved in a completely unsupervised manner, i.e., without any prior knowledge of the type of actions, their number and their duration. These common subsequences (commonalities) may be located anywhere in the original sequences, may differ in duration and may be performed under different conditions e.g., by a different actor. The proposed method performs a very efficient graph-based search on the matrix of pairwise distances of frames of the two sequences. This search is supported by an objective function that captures the trade off between the similarity of the common subsequences and their lengths. The proposed method has been evaluated quantitatively on challenging datasets and in comparison to state of the art approaches. The obtained results demonstrate that the proposed method outperforms the state of the art methods both in the quality of the obtained solutions and in computational performance. [ABSTRACT FROM AUTHOR]

We present in this article a new method on unsupervised semantic parsing and structure recognition in peri-urban areas using satellite images. The automatic “building” and “road” detection is based on regions extracted by an unsupervised segmentation method. We propose a novel segmentation algorithm based on a Markov random field model and we give an extensive data analysis for determining relevant features for the classification problem. The novelty of the segmentation algorithm lies on the class-driven vector data quantization and clustering and the estimation of the likelihoods given the resulting clusters. We have evaluated the reachability of a good classification rate using the Random Forest method. We found that, with a limited number of features, among them some new defined in this article, we can obtain good classification performance. Our main contribution lies again on the data analysis and the estimation of likelihoods. Finally, we propose a new method for completing the road network exploiting its connectivity, and the local and global properties of the road network. [ABSTRACT FROM AUTHOR]

Geological faults comprise an interesting and of high-importance subject of study in geosciences, since they are responsible for seismic activity in regions where plate boundaries (divergent, convergent, transform) are present. In this paper, we propose a framework for automatic enhancement and identification of the linear patterns of geological fault structures. According to the proposed method, first, we compute the Slope and Aspect images, as well as their derivatives. Then, a rotation- and scale-invariant filter and a pixel-labeling method provide an enhancement of the geological faults and the detection of points that probably belong to them, respectively. The enhancement and detection results are efficiently combined to construct a weighted graph that represents the possible fault points and the connections between them taking into account the shape and topology of the faults. Thus, the detection of the linear fault patterns, which is the main goal of this framework, is reduced to the problem of suitable subset selection, corresponding to the graph edges of the most representative faults. Concerning the experimental results, the proposed method has been tested on several onshore and offshore real topographic images yielding high-performance results. [ABSTRACT FROM PUBLISHER]

Abstract: In this paper, we propose a framework for interactive image segmentation. The goal of interactive image segmentation is to classify the image pixels into foreground and background classes, when some foreground and background markers are given. The proposed method minimizes a min–max Bayesian criterion that has been successfully used on image segmentation problem and it consists of several steps in order to take into account visual information as well as the given markers, without any requirement of training. First, we partition the image into contiguous and perceptually similar regions (superpixels). Then, we construct a weighted graph that represents the superpixels and the connections between them. An efficient algorithm for graph clustering based on synthetic coordinates is used yielding an initial map of classified pixels. This method reduces the problem of graph clustering to the simpler problem of point clustering, instead of solving the problem on the graph data structure, as most of the known algorithms from literature do. Finally, having available the data modeling and the initial map of classified pixels, we use a Markov Random Field (MRF) model or a flooding algorithm to get the image segmentation by minimizing a min–max Bayesian criterion. Experimental results and comparisons with other methods from the literature are presented on LHI, Gulshan and Zhao datasets, demonstrating the high performance and accuracy of the proposed scheme. [Copyright &y& Elsevier]

We propose a general purpose image segmentation framework, which involves feature extraction and classification in feature space, followed by flooding and merging in spatial domain. Region growing is based on the computed local measurements and distances from the distribution of features describing the different classes. Using the properties of the label dependent distances spatial coherence is ensured, since the image features are described globally. The distribution of the features for the different classes are obtained by block-wise unsupervised clustering based on the construction of the minimum spanning tree of the blocks' grid using the Mallows distance and the equipartition of the resulting tree. The final clustering is obtained by using the k-centroids algorithm. With high probability and under topological constraints, connected components of the maximum likelihood classification map are used to compute a map of initially labelled pixels. An efficient flooding algorithm is introduced, namely, Priority Multi-Class Flooding Algorithm (PMCFA), that assign pixels to labels using Bayesian dissimilarity criteria. A new region merging method, which incorporates boundary information, is introduced for obtaining the final segmentation map. Therefore, the merging stage is based on region features and edge localization. Segmentation results on the Berkeley benchmark data set demonstrate the effectiveness of the proposed methods. [ABSTRACT FROM PUBLISHER]