Satellite synthetic aperture radar (SAR) systems currently offer both very high resolutions and multiresolution acquisition capability, thus presenting a great potential for environmental monitoring and damage assessment applications. In this framework, change detection methods play a central role. In this paper, a novel unsupervised change detection method is proposed for multitemporal SAR images acquired at multiple resolutions. The method combines Markov random field modeling, line processes, linear mixtures, Bayesian estimation, generalized Gaussian distributions, and graph cuts with the aim of fusing the available multiresolution information to generate a change map at the finest of the observed resolutions. The proposed method is experimentally validated with multitemporal COSMO-SkyMed stripmap and polarimetric data.

In the framework of the application of remote sensing to civil protection from floods, the problem of the detection of flooded areas in high-resolution images is addressed in this paper. Specifically, the high-resolution multitemporal observation capability offered by the current COSMO-SkyMed synthetic aperture radar (SAR) constellation is exploited. This work is framed in the context of the “OPERA - Civil protection from floods” pilot project funded by the Italian Space Agency in cooperation with the Italian Department for Civil Protection. Several SAR image processing methods are presented in order to identify flooded areas after a flood event. Both fast-ready and detailed maps are obtained from a pair of multitemporal images of the monitored area. Experiments are presented with COSMO-SkyMed images related to a flood in the areas of Alessandria (Italy).

Multichannel synthetic aperture radar (SAR) data present a good potential for environmental monitoring and disaster management, owing both to their insensitivity to atmospheric and sun-illumination conditions, and to the improved discrimination capability they may provide as compared to single-channel SAR. However, this requires accurate and possibly automatic techniques to generate change maps from multichannel SAR images acquired from the same geographic area at different times. In this letter, an automatic unsupervised contextual change-detection method is proposed for two-date multichannel SAR images, by integrating a SAR-specific extension of the Fisher transform with a variant of the expectation-maximization algorithm and with Markov random fields. The method is validated by experiments on SIR-C/XSAR data

Image processing has frequently to deal with thin structures that hold the information required. In natural images, there is a wide variability of conditions and the borders of objects are not always well defined. Progressive scan, an algorithm derived from fuzzy-connectedness theory, is described here as a specific case of more general /spl chi/-connectedness. Exploiting some analogies to the mechanical world, it allows one to track thin structures and consequently, is suitable for river, motorway or vessel extraction. In the computation of fuzzy connectedness, a widely used approach is based on an adaptive growing mechanism that follows the best paths starting from a reference seed point. The new algorithm uses three or more seed points in order to better drive that approach along the structure of interest. Results of the algorithm are the best path along an object and a connectivity map. The algorithm can deal with heterogeneous images ranging from medical to remote sensed ones.

The aim of this paper is to present a multi camera system for location estimation inspired to a model inherited from the Data Fusion domain: the Joint Directorate of Laboratories (JDL) model (E. Waltz et al., 1990). The problem specifically faced is the tracking of objects in two complementary applications: intelligent monitoring (video surveillance) and sport viewing (football players tracking), where multiple occluding objects have to be successfully segmented and located using different features such as color, position and dynamics.

In this paper a new automatic approach to road extraction from aerial images is proposed. This method improves a recently introduced promising approach to probabilistic contour tracking, originally semi-automatic, by adding a fully automatic initialization strategy and a merging methodology, able to combine the different obtained results. The initialization strategy is based on the Hough transform and on some topological considerations, and the merging step is based on a new introduced quality measure, based on color and gradient information. Experimental results on real highly complex images show that the proposed approach is a promising and fully automatic method for extracting roads from images, even in presence of highly urbanized areas, occlusions or shadows.

A significant improvement of block-based motion estimation strategies is presented, which supports fast computation and VLBR coding. For each block, a spatio-temporal context is defined based on nearest neighbors in the current and previous frames, and a prediction list is built. Then, the best matching vector within the list is chosen as an estimation of the block motion. An additional correction vector can be sent when the prediction error exceeds a threshold. Bit rate saving is achieved through an adaptive sorting of the prediction list of each block, which allows one to reduce the entropy of the motion indexes. Tests demonstrate a speed up above 1:200 as compared to full search, and a coding gain above 2, with a negligible loss of accuracy.

Texture analysis based on the extraction of contrast features is very effective in terms of both computational complexity and discrimination capability. In this framework, max–min approaches have been proposed in the past as a simple and powerful tool to characterize a statistical texture. In the present work, a method is proposed that allows exploiting the potential of max–min approaches to efficiently solve the problem of detecting local alterations in a uniform statistical texture. Experimental results show a high defect discrimination capability, and a good attitude to real-time applications, which make it particularly attractive for the development of industrial visual inspection systems.

An image stabilization algorithm is presented that is specifically oriented toward video-surveillance applications. The proposed approach is based on a novel motion-compensation method that is an adaptation of a well-known image-stabilization algorithm for visualization in video-surveillance applications. In particular, the illustrated methods take into account the specificity of typical video-surveillance applications, where objects moving in a scene often cover a large part of an image thus causing the failure of classic image-stabilization techniques. Evaluation methods for image stabilization algorithms are discussed.

A new method for modeling non-rigid objects in a multiple-camera guarded environment is proposed. The statistical model of the shape of a non-rigid object takes into account the correlations between different points of view. The model is automatically generated by processing a typical training set for the considered shape by a principal component analysis algorithm. Snakes and dynamic contours are used to describe the shape of the non-rigid object.

In this paper, the problem of DCT information recovery in the transmission of coded visual data over packet networks is addressed. The loss of a packet conveying coded block data leads to the unsuccessful reconstruction of the relevant area, with consequent degradation of the received image quality. The proposed method allows recovery of a subset of the missing DCT coefficients sufficient to achieve good reconstruction quality of the lost block, based on the available surrounding information. To this purpose, a neural predictor was carefully designed and suitably trained with an appropriate set of synthetic and natural patterns. An extensive testing phase, performed on a large set of images with different frequency characteristics, revealed that the method provides very good reconstruction capabilities.

In this paper, after briefly considering the reasons that prevented the development of hybrid systems for signal processing (SP), we point out the requirements for their future exploitation. The need for a better knowledge of different approaches in the scientific community and the definition of methodologies for designing hybrid systems are highlighted as two key points. Then we suggest that the well-known "task-structure analysis" design technique should be modified to make it suitable for hybrid systems. The proposed modification is based on the main need to choose the roles of different approaches and the mechanisms to integrate them. As an example we describe the design of a hybrid system for two-dimensional (2-D) image recognition; the system is based on the integration of a numerical, a symbolic, and a connectionist approach. We detail the integration of the symbolic and connectionist approaches to the generation of the models of the objects to be recognized. We describe the main problems involved and the solutions adopted. In particularly, we exploit the synergistic aspects of the two approaches in order to overcome the bottleneck of knowledge acquisition. Finally, we report experimental results on two applications to show some advantages of the proposed hybrid system.

We describe a framework for multivalued segmentation and demonstrate that some of the problems affecting common region-based algorithms can be overcome by integrating statistical and topological methods in a nonlinear fashion. We address the sensitivity to parameter setting, the difficulty with handling global contextual information, and the dependence of results on analysis order and on initial conditions. We develop our method within a theoretical framework and resort to the definition of image segmentation as an estimation problem. We show that, thanks to an adaptive image scanning mechanism, there is no need of iterations to propagate a global context efficiently. The keyword multivalued refers to a result property, which spans over a set of solutions. The advantage is twofold: first, there is no necessity for setting a priori input thresholds; secondly, we are able to cope successfully with the problem of uncertainties in the signal model. To this end, we adopt a modified version of fuzzy connectedness, which proves particularly useful to account for densitometric and topological information simultaneously. The algorithm was tested on several synthetic and real images. The peculiarities of the method are assessed both qualitatively and quantitatively.

The task of object identification is fundamental to the operations of an autonomous vehicle. It can be accomplished by using techniques based on a Multisensor Fusion framework, which allows the integration of data coming from different sensors. In this paper, an approach to the synergic interpretation of data provided by thermal and visual sensors is proposed. Such integration is justified by the necessity for solving the ambiguities that may arise from separate data interpretations. The architecture of a distributed Knowledge-Based system is described. It performs an Intelligent Data Fusion process by integrating, in an opportunistic way, data acquired with a thermal and a video (b/w) camera. Data integration is performed at various architecture levels in order to increase the robustness of the whole recognition process. A priori models allow the system to obtain interesting data from both sensors; to transform such data into intermediate symbolic objects; and, finally, to recognize environmental situations on which to perform further processing. Some results are reported for different environmental conditions (i.e. a road scene by day and by night, with and without the presence of obstacles).

This paper presents a methodology for integrating connectionist and symbolic approaches to 2D image recognition. The proposed integration paradigm exploits the synergy of the two approaches for both the training and the recognition phases of an image recognition system. In the training phase, a symbolic module provides an approximate solution to a given image-recognition problem in terms of symbolic models. Such models are hierarchically organized into different abstraction levels, and include contextual descriptions. After mapping such models into a complex neural architecture, a neural training process is carried out to optimize the solution of the recognition problem. The so-obtained neural networks are used during the recognition phase for pattern classification. In this phase, the role of symbolic modules consists of managing complex aspects of information processing: abstraction levels, contextual information, and global recognition hypotheses. A hybrid system implementing the proposed integration paradigm is presented, and its advantages over single approaches are assessed. Results on Magnetic Resonance image recognition are reported, and comparisons with some well-known classifiers are made.

The paper presents an adaptive scheme for image-data compression. It is a region-based approach that suitably integrates two different approaches to image coding, vector quantization (VQ) and polynomial approximation (PA). The scheme is adaptive from the point of view of the human observer: the perceptually most significant areas are those near edges or details. In smoothed areas, PA can be used with notable results, but there VQ must be employed to ensure high fidelity. The two techniques exhibit a complementarity in both advantages and drawbacks. PA is not efficient in compressing high-frequency areas, but yields the best results when applied to highly correlated data. VQ is unable to reach high-compression ratios because of its low adaptability, but is quite suitable for compressing uncorrelated data. The means to achieve the integration of the two techniques is a control image containing information about edge and texture locations. In the paper, edge encoding and restoration are also addressed, which are closely related to the proposed hybrid scheme; block prediction is also utilized to further reduce the residual redundancy between VQ blocks. The exploitation of the best features of both approaches results in high compression factors, and in perceivable good quality. In particular, bit rates range from 0.15 to 0.07 bpp. Main applications of this compression scheme are in the areas of very-low bit rate image transmission and image archiving.>

A new class of statistical morphological operators for binary image processing is introduced. These operators are based on a digitized version of the mean field approximation. The main advantage of the new operators is provided by the capability of taking into account both noise and shape information. Binary statistical dilation (BSD) and binary statistical erosion (BSE) are considered as a case study. Extensivity properties of BSD and BSE are also discussed.>

An innovative approach is proposed to overcome the usual drawbacks of computation complexity and insufficient robustness that affect most of contextual image segmentation techniques. Through the definition of a new connectivity measure for fuzzy image subsets, a transformation of the original set of grey levels is performed that makes it simpler to outline region boundaries. It is demonstrated that there is no need of iterations to efficiently propagate global contextual information. Some results are presented that prove the effectiveness of the method.>

In future telecommunications networks, an important role will be played by "intelligent control" techniques aimed at selecting and tuning signal processing (SP) algorithms. The authors first define the main problems of automatic control of SP algorithms; then, they propose a knowledge-based approach to carry out such a task. In the planning phase, a restricted set of algorithm sequences are selected. This set is used as a raw plan to be refined and corrected in the execution phase, based on quality tests on progressive results. In particular, the authors focus on the control strategies adopted and describe how expert knowledge is represented and applied to implement such strategies. As an example, the control of low-level image processing is detailed. Results on an image-compression application are also reported.>

This study deals with a learning system for generation of descriptions of objects to be recognized in 2-D images. After proposing a framework for handling fuzzy and relational descriptions, we present the system obtained by making such a framework manage a well-known learning methodology. Satisfactory results and comparisons are reported.>

A system for the processing and interpretation of underwater images acquired with an acoustic sensor is presented. As a first objective, the system aims to recognize simple objects with known characteristics located at different positions so as to create a scenario. The proposed recognition system exhibits the features of a knowledge-based system, as it is based on ideal models (provided by an expert) of the possible objects present in the scene, and the matching of such models with the real objects detected by processing data coming from the acquisition system. The numerical data provided by different types of sensors are first processed by some low-level modules. The high-level modules operate a matching of the objects detected with the models, according to criteria of maximum fuzzy reliability. Results are presented and discussed.>

An approach to setting the architecture and the initial weights of an artificial neural network for solving classification problems is presented. A nonneural phase finds an approximate solution to the classification problems by constraining the shape of classification regions. After an appropriate mapping into a neural net, neural training is applied to refine the solution. Results on an image recognition application are presented.>

A new approach is proposed to the fusion of 2D images, called the region overlapping technique. After registration of the original images, the single channel segmented images are overlapped and a new segmentation is obtained, where regions are labeled as kernel or silver on the basis of region parameters such as size, elongatedness, and adjacency. The knowledge-based (KB) interpretation of kernel regions is carried out by matching regions with models; sliver regions are interpreted in a second phase, considering their possible sources, provenance in the two original images, and the kernel interpretation results. Experimental results obtained both in the medical and in the remote sensing fields are reported and discussed.>

The application of a system of the blackboard type, IBIS, devoted to the processing and interpretation of real digital images, to magnetic resonance (MR) tomographic images is discussed, and the generation of a symbolic model, together with the performance and robustness of the approach, is examined. Peculiarities are represented by the mechanism of the model generation, which starts from real cases as a training set, and by the satisfactory performance reached by the matching process (based on the fuzzy sets for uncertainty management) on test cases referring to a different set of patients. The specific application considered deals with transaxial slices that are acquired from the first and second echo of a multiecho sequence, at the superorbital level, and that show signs of a lesion.>

In this paper, we propose a system aimed at interpreting 3-D scenes from 2-D image sequences in the case of scenes containing solid objects that can be described as being made up of polyhedral subparts. The major problems addressed are the definition of a suitable search strategy to reduce the computational complexity of the problem, and the exploitation of the information provided by motion analysis applied to the image sequence. The object models' representation is based on the definition of view classes. Experimental results on simple real scenes are presented.

An advanced vector quantizer for coding true-color images is presented. The starting point is the classical algorithm proposed by Y. Linde, A. Buzo, and A.M. Gray (LBG, 1980). On the basis of the LBG algorithm, a neural net able to furnish a starting codebook quite close to the optimal one is developed. As several vectors are infrequently used, a merge-and-split process has been performed to merge such vectors into adjacent ones, thus allowing free space to be reutilized to redistribute the most numerous partitions. Another aspect to be exploited is the existence of statistical redundancies between neighboring blocks. To sharply reduce the bit rate, an RGB predictor based on some transition matrices is developed. The basic idea of the development of an RGB predictor is provided by the address vector quantization (AVQ) technique. Results obtained by processing standard images are discussed.>

A knowledge-based vision system called DOORS (Distributed Object-Oriented Recognition System), for obstacle detection and tracking, is presented. It integrates multisensory information sources by adaptively selecting appropriate fusion strategies at the abstraction levels of both physical and virtual sensors. The basic methodology adopted for data representation and processing control has several points in common with object-oriented programming techniques and with blackboard approaches. Some preliminary results are presented for the case of an obstacle moving on a country-road scene.>

An algorithm is presented for solving conflicts between noise reduction and correct fractal dimension estimates. The basic idea has been derived from edge-preserving methods, which have been used for similar problems. Around each pixel, different masks are used; the most homogeneous neighborhood (in terms of fractal dimension) is then selected, and the fractal dimension D of the region is computed. An appropriate mask is selected for each pixel using an adaptive process, and, in particular, wide masks are used only for areas that do not exhibit any noticeable D variation.>

A knowledge-based system is developed that allows cooperation (drive by a control structure) among its different processing levels to attain high efficiency in the recognition task. In addition, an adaptive approach is applied to texture analysis by fractals, appropriate filterings, and Karhunen-Loeve methodology for image fusion. The architecture of the system is based on a heterarchical control structure, with a blackboard-type database, and on some backtracking facilities operating at the various processing levels.>

The system has been developed as a tool to measure in patients the evolution of idiopathic scoliosis during the age of development. The correspondent anatomical segment is treated as a 3D structure, because the interaction of both pathological components and physiological sagittal curvatures determines a well defined location in space for each vertebra involved in the scoliotic curve. The system is based on the acquisition of photographic orthogonal projections, directly from the patient, therefore avoiding X-ray exposure. According to a stack-like scheme, it is possible to obtain all the reconstructed sections, at various height. Various parameters are measured on the sections: in order to discriminate between normal and pathological "scoliotic" sections, the variations of the position of the center of mass and the inertia principal axes appear of importance. Eventually, full 3D capability of the "reconstructed" rib cage, from different points of view, is possible for the clinician.