Abstract
Satellite SAR interferometry (InSAR) is proven as effective method for monitoring of deformations of both terrain and urban structures. By applying multi-temporal InSAR processing techniques (for example Persistent Scatterers InSAR-PS InSAR) to a series of radar images over the same region, it is possible to detect both vertical and horizontal movements of such structures and to evaluate rate of their movements in sensitivity of first millimeters in direction of satellite sight (usually inclined by 20-35 degrees from vertical axis). Therefore, it is possible to identify abnormal or excessive movement indicating potential problems requiring detailed ground investigation. Three case studies (in Bratislava, Ostrava and Hong Kong) presented within the paper demonstrate potential for monitoring deformations and movements due to thermal dilation of bridge structures.

Abstract
The Betic-Rif cordilleras are build-up in the western Mediterranean by the deformations related to the Eurasian-African plate boundary. The recent NW-SE convergence produces the simultaneous development of large folds and faults in the central part of the Internal Zones of the Betic Cordilleras, which continues active up to Present. The uplift of the mountain ranges is mainly related to the development of folds in this regional compressive setting. Sierra Tejeda constitutes a relief related to the development of a complex shaped recent antiform that is located near the coast line. At the northern limb of Sierra Tejeda is located the Zafarraya fault, a high-angle northwards dipping normal fault. Understanding the tectonic of the Zafarraya fault is crucial since one of the most destructive earthquakes (25th December 1884) on the Iberian Peninsula occurred along this fault (magnitude of 6.7). This paper investigates the applicability of satellite radar interferometry using ERS-1/2 SAR and Envisat ASAR datasets to help to constraint the geological hazard in this part of the Betic Cordillera.

Abstract
In this paper it is clearly demonstrated that InSAR techniques may be particularly useful as a hot spot indicator of relative structures deformation over large areas, making it possible to develop interferometric based methodologies for SHM. Different case studies from structural health monitoring of buildings, bridges and highways and dams in Slovakia, Czech Republic, Hong Kong and Portugal processed within the scope of "RemotWatch - Alert and Monitoring System for Physical Structures" project using non-linear and other SHM-optimized algorithms of SARPROZ software, are reported. For the future investigation it is expected, that due to the faster product delivery of new missions (e.g. SENTINEL-1), it will be possible to deliver new workflows suitable for near-real time analysis aimed to better understanding of the deformation characteristics of the structures in urban and extra urban areas, important for structure stability and risk management applications.

Abstract
Over the past years, inverse perspective mapping has been successfully applied to several problems in the field of Intelligent Transportation Systems. In brief, the method consists of mapping images to a new coordinate system where perspective effects are removed. The removal of perspective associated effects facilitates road and obstacle detection and also assists in free space estimation. There is, however, a significant limitation in the inverse perspective mapping: the presence of obstacles on the road disrupts the effectiveness of the mapping. The current paper proposes a robust solution based on the use of multimodal sensor fusion. Data from a laser range finder is fused with images from the cameras, so that the mapping is not computed in the regions where obstacles are present. As shown in the results, this considerably improves the effectiveness of the algorithm and reduces computation time when compared with the classical inverse perspective mapping. Furthermore, the proposed approach is also able to cope with several cameras with different lenses or image resolutions, as well as dynamic viewpoints.

Abstract
Over the past years, inverse perspective mapping has been successfully applied to several problems in the field of Intelligent Transportation Systems. In brief, the method consists of mapping images to a new coordinate system where perspective effects are removed. The removal of perspective associated effects facilitates road and obstacle detection and also assists in free space estimation. There is, however, a significant limitation in the inverse perspective mapping: the presence of obstacles on the road disrupts the effectiveness of the mapping. The current paper proposes a robust solution based on the use of multimodal sensor fusion. Data from a laser range finder is fused with images from the cameras, so that the mapping is not computed in the regions where obstacles are present. As shown in the results, this considerably improves the effectiveness of the algorithm and reduces computation time when compared with the classical inverse perspective mapping. Furthermore, the proposed approach is also able to cope with several cameras with different lenses or image resolutions, as well as dynamic viewpoints.

Abstract
In open-ended domains, robots must continuously learn new object categories. When the training sets are created offline, it is not possible to ensure their representativeness with respect to the object categories and features the system will find when operating online. In the Bag of Words model, visual codebooks are usually constructed from training sets created offline. This might lead to non-discriminative visual words and, as a consequence, to poor recognition performance. This paper proposes a visual object recognition system which concurrently learns in an incremental and online fashion both the visual object category representations as well as the codebook words used to encode them. The codebook is defined using Gaussian Mixture Models which are updated using new object views. The approach contains similarities with the human visual object recognition system: evidence suggests that the development of recognition capabilities occurs on multiple levels and is sustained over large periods of time. Results show that the proposed system with concurrent learning of object categories and codebooks is capable of learning more categories, requiring less examples, and with similar accuracies, when compared to the classical Bag of Words approach using codebooks constructed offline.