Search

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]

In this paper, we propose a method for automatic enhancement and identification of partial curvilinear structures. The accurate identification of line structures in geophysical images plays an important role in geophysical interpretation and the detection of subsurface structures. The method was applied on geophysical images in an effort to recognize the linear patterns of subsurface architectural structures that exist in archaeological sites. To our knowledge, the problem of identification of curvilinear structures in geophysical images for archaeological sites is faced for the first time. The method efficiently combines a rotation- and scale-invariant filter and a pixel-labeling method, providing a robust enhancement and detection of mostly line structures in 2-D grayscale images, respectively. Experimental results on real and synthetic images and comparison with existing methods in the literature indicated the reliable performance of the proposed scheme. [ABSTRACT FROM PUBLISHER]

Detailed information regarding land utilization/cover is a valuable resource in various fields. In recent years, remote sensing images, especially aerial images, have become higher in resolution and larger span in time and space, and the phenomenon that the objects in an identical category may yield a different spectrum would lead to the fact that relying on spectral features only is often insufficient to accurately segment the target objects. In convolutional neural networks, down-sampling operations are usually used to extract abstract semantic features, which leads to loss of details and fuzzy edges. To solve these problems, the paper proposes a Multi-level Feature Aggregation Network (MFANet), which is improved in two aspects: deep feature extraction and up-sampling feature fusion. Firstly, the proposed Channel Feature Compression module extracts the deep features and filters the redundant channel information from the backbone to optimize the learned context. Secondly, the proposed Multi-level Feature Aggregation Upsample module nestedly uses the idea that high-level features provide guidance information for low-level features, which is of great significance for positioning the restoration of high-resolution remote sensing images. Finally, the proposed Channel Ladder Refinement module is used to refine the restored high-resolution feature maps. Experimental results show that the proposed method achieves state-of-the-art performance 86.45% mean IOU on LandCover dataset. [ABSTRACT FROM AUTHOR]

The automatic extraction of geomorphologic features using digital elevation models (DEMs) belongs to the remote sensing techniques used to improve our understanding in a variety of disciplines in the geosciences (i.e. remote sensing, topography, geology, archaeology, oceanography and others) prior the fieldwork and later during data processing and interpretation. This approach highly contributes towards a rapid, objective and lower cost fieldwork. In the present work, recently developed techniques of pattern recognition in the context of European Projects (NEREIDs, Sea4All), are applied on digital elevation models (DEMs) from onshore and offshore areas of the Mediterranean aiming to a) demonstrate their efficiency, and b) partly compare the results of the automatic detection with geological data provided either from previous researches or ground truth data.Panagiotakis and Kokinou (2014, 2015, and 2017) have implemented the two-step methodology, to process digital elevation models. It was applied partly or in whole in previous onshore and offshore geological and environmental studies. The proposed approach is based on a) the automatic detection of topographic highs and computation of the geomorphologic features (orientation, eccentricity, average slope, and shape complexity) and b) the automatic detection of lineaments, possibly related to the presence of geological faults or other subsurface processes.The two-step methodology has been evaluated on real and synthetic digital elevation models of medium and high accuracy that correspond to onshore and offshore environment. The experimental results demonstrate the high performance of the proposed approach on several real and synthetic topographic data. In our tests major and accompanying geomorphologic structures (lineaments, geological faults, topographic highs and depressions und others) are estimated with high precision concerning their location, shape, and orientation. Furthermore, the financial cost of the fieldwork severely decreases, since prior to the fieldwork geomorphologic structures of interest are identified with great precision and scheduled to be examined. [ABSTRACT FROM AUTHOR]