Search

This paper presents a classification method for hyperspectral images utilizing Differential Morphological Profiles (DMPs) which permit to include in the analysis spatial information since they can provide an estimate of the size and contrast characteristics of the structures in an image. Due to the wide variety of objects present in a scene, the pixels belonging to the same semantic structure may not have homogeneous spatial and spectral features. In addition, instead of a single peak (which can be related to a measure of the scale), multiple local maxima and multiple responses are usually observed in the DMP. In order to handle such intra-class variability, class-specific weighting functions are employed in order to differently modulate the DMP values according to the different characteristics of the land cover types. In such way, it is possible to differentiate the behaviors of the DMP for each pixel in the image according to its semantic, providing an increase of the separability of the classes. At first, a DMP computed with opening by reconstruction (DMPO) and one with closing by reconstruction (DMPC) are derived on each of the first principle components extracted from the hyperspectral image. Then, both profiles are weighted by each class-specific weighting function and concatenated in a single data structure. The constructed feature vectors are considered by a random forest classifier. [ABSTRACT FROM PUBLISHER]

With respect to satellite and aerial RGB images, ground-based acquisitions can provide a more detailed representation of a natural landscape, especially for steep slopes. Moreover, for some applications the generation of a new ‘virtual’ view-point can provide a valuable visualization tool. Using such a technique, the visual appearance of a landscape (generated from one or several geo-registered images) can be seen from a new, specified vantage point. In this paper, we propose a method of generating a visual appearance model and subsequent virtual views, through a direct re-projection of visual content from source geo-registered images. [ABSTRACT FROM PUBLISHER]

Dealing with a high number of features belonging to different types of data such as Hyperspectral image and Morphological Attribute Profiles (MAPs) might lead to a poor predictive performance of the classifier and hence low final accuracies of classification. This is due to the Hughes effect that consistently decreases the power of prediction of the classifier, in case of a limited and fixed number of training samples. In order to reduce the number of features and only keeping those which are more informative, a novel supervised feature selection technique based on GAs and the measure of the relevance of the features is presented in this work. Moreover, the effectiveness of the proposed technique was demonstrated by experimenting on an optical remote sensed dataset. [ABSTRACT FROM PUBLISHER]

Augmented Reality (AR) offers a means to inject virtual information into real scenes. In the past few years, AR has been receiving greater attention thanks to considerable advancements in the hardware of consumer-level portable devices. In this paper, we illustrate how mobile AR can be exploited to intuitively visualize, and moreover generate new, geo-data. We explore these two concepts through i) the visualization and interaction modality of geo-data as AR layers and ii) the exploitation of mobile devices as opportunistic sensors for generating information relating to a user's immediate surroundings. [ABSTRACT FROM PUBLISHER]

Digital Elevation Models (DEMs) are a valuable resource in geoscience and remote sensing. However, not all DEMs demonstrate the same level of accuracy, resolution and precision. Moreover, in some regions of the globe coverage is either sparse or non-existent, for example at the poles where ice also hampers accurate readings. In this paper, we propose to use collective archives of geo-located landscape photos acquired at ground-level to correct, validate and possibly reconstruct DEMs. [ABSTRACT FROM PUBLISHER]