Extracting Salient Curves from Images: An Analysis of the Saliency Network

The Saliency Network proposed by Shashua and Ullman is a well-known approach to the problem of extracting salient curves from images while performing gap completion. This paper analyzes the Saliency Network. The Saliency Network is attractive for several reasons. First, the network generally prefers long and smooth curves over short or wiggly ones. While computing saliencies, the network also fills in gaps with smooth completions and tolerates noise. Finally, the network is locally connected, and its size is proportional to the size of the image. Nevertheless, our analysis reveals certain weaknesses with the method. In particular, we show cases in which the most salient element does not lie on the perceptually most salient curve. Furthermore, in some cases the saliency measure changes its preferences when curves are scaled uniformly. Also, we show that for certain fragmented curves the measure prefers large gaps over a few small gaps of the same total size. In addition, we analyze the time complexity required by the method. We show that the number of steps required for convergence in serial implementations is quadratic in the size of the network, and in parallel implementations is linear in the size of the network. We discuss problems due to coarse sampling of the range of possible orientations. We show that with proper sampling the complexity of the network becomes cubic in the size of the network. Finally, we consider the possibility of using the Saliency Network for grouping. We show that the Saliency Network recovers the most salient curve efficiently, but it has problems with identifying any salient curve other than the most salient one.

The Role of Fixation and Visual Attention in Object Recognition

This research project is a study of the role of fixation and visual attention in object recognition. In this project, we build an active vision system which can recognize a target object in a cluttered scene efficiently and reliably. Our system integrates visual cues like color and stereo to perform figure/ground separation, yielding candidate regions on which to focus attention. Within each image region, we use stereo to extract features that lie within a narrow disparity range about the fixation position. These selected features are then used as input to an alignment-style recognition system. We show that visual attention and fixation significantly reduce the complexity and the false identifications in model-based recognition using Alignment methods. We also demonstrate that stereo can be used effectively as a figure/ground separator without the need for accurate camera calibration.

Caratterizzazione geo-petrografica, petrologica e geochimica di rocce anatettiche del nord Sardegna

The High Grade Metamorphic Complex (HGMC) of Variscan basement of north Sardinia is characterized by the widespread of migmatites. This study is focused on two localities of NE Sardinia (Porto Ottiolu and Punta Sirenella) where ortho- and para-derivates migmatites outcrop. A geological and structural survey was carried out, leading to the realization of a geological schematic map of Punta Sirenella area. Several samples of different rocks were collected for petrographic, micro-structural minero-chemical and geochemical analyses. In the Porto Ottiolu area three main deformation phases have been identified; D1, characterized by tight folds with sub-horizontal axes, rarely preserved in paragneisses; D2, that produce a pervasive foliation oriented N100° 45°SW marked by biotite and sillimanite blastesis and locally transposed by shear zone oriented N170°; D3, late deformation phase caused symmetric folds with sub-horizontal axes with no axial plane schistosity. Leucosomes form pods and layers along S2 schistosity but also leucosomes along shear zones have been observed. In the Punta Sirenella area, three main deformation phases have been identified; D1, is manifested by the transposition of centimeter-sized leucosomes and is rarely observed in paragneisses were produce open folds with sub-vertical axes; D2, NW-SE oriented on whose XY plane three mineralogical lineation (quartz+plagioclase, fibrolite+quarz and muscovite) lie; D3, a ductile-brittle deformation phase that produce a mylonitc S3 foliation that locally become the most evident schistosity in the field oriented N140° steeply dipping toward NE. In both areas, leucosomes of sedimentary-derived migmatites are generally trondhjemitic pointing out for a H2O fluxed melting reaction, but also granitic leucosomes have been found, produced by muscovite dehydration melting. Leucosomes of migmatitic orthogneiss instead, have granitic compositions. Migmatization started early, during the compressional and crustal thickening (sin-D1, pre-D2) and was still active during exhumation stage. For each studied outcrop of migmatite pseudosections for the average mesosome composition have been calculated; these pseudosections have been used to model the P-T conditions of anatexis on the basis of the melt volume (%) of melt, Si/Al and Na/K molar ratios, modal content of garnet and Si content in metamorphic white mica. Further pseudosections have been calculated for the average composition of leucosomes in order to define the P-T conditions of the end of the crystallization through intersection of solidus curve and isopleths of Si content in white mica and/or XMg ratio in biotite. Thermodynamic modeling on ortho- and sedimentary-derived migmatites of Punta Sirenella yield P-T conditions of 1.1-1.3 GPa - 670-740°C for migmatitic event and 0.75-0.90 GPa - 660-730°C for the end of crystallization. These conditions are fit well with previous studies on adjacent rocks. Modeling of Porto Ottiolu ortho- and sedimentary-derived migmatites yield P-T conditions of 0.85-1.05 GPa - 690-730°C for migmatitic event and 0.35-0.55 GPa - 630-690°C strongly affected by re-equilibration during exhumation, expecially for crystallization conditions. Geochemical analyses of samples belonging to Porto Ottiolu and Punta Sirenella orthogneisses show a strong link with those of other orthogneisses outcropping in NE Sardinia (for instance, Lode-Mamone and Golfo Aranci) that are considered the intrusive counterparts of middle-Ordovician metavolcanics rocks outcropping in the Nappe Zone. Thus, the studied ortogneiss bodies, even lacking radiometric data, can be considered as belonging to the same magmatic cycle.

Copper phthalocyanine on InSb(111)A?interface bonding, growth mode and energy band alignment

Copper phthalocyanine on InSb(111)A?interface bonding, growth mode and energy band alignment, D.A. Evans, H.J. Steiner, S. Evans, R. Middleton, T.S. Jones, S. Park, T.U. Kampen, D.R.T. Zahn, G. Cabailh and I.T. McGovern, J. Phys.: Condens. Matter, 15, S2729?S2740, (2003)

Jurisdiction and the Internet: Regulatory Competence over Online Activity

null RAE2008

Cross-Border Unitization and Joint Development Agreements: An International Law Perspective

Okoye, Adaeze, et al, 'Cross-Border Unitization and Joint Development Agreements: An International Law Perspective', Houston Journal of International Law (2007) 29(2) pp.355-425 RAE2008

Osoby uczące się j. obcych jako partnerzy refleksji w procesie kształtowania kultury informacji zwrotnej w dydaktyce j.niemieckiego jako obcego na poziomie uniwersyteckim

Wydział Neofilologii:Instytut Lingwistyki Stosowanej

Hydrocarbon Potential of the Infra-salt Strata

This schematic geological cross-section of Angola offshore is representative of the majority of the Atlantic-type divergent margins. It illustrates the main geological features allowing to understand the different petroleum systems occurring, particularly, in South Atlantic divergent margins : (i) Pre-Pangea rocks (Precambrian granite-gneiss basement, volcanic rocks an/ or Paleozoic sediments, more or less, metamorphosed), which lie underneath the pre-rifting unconformity (PRU), in blue in the cross-section ; (ii) The rift-type basins developed during the lengthening of the Pangea supercontinent ; (iii) The breakup unconformity (BUU), which highlight the upper limit of the rift-type basins, in which organic rich lacustrine shales with a parallel internal configuration are potential source-rocks (organic matter type I) ; (iv) The SDRs (seaward dipping reflectors), which, generally, do not have any generating hydrocarbon potential (just 5 m of lacustrine shales are known in Austral basin) ; (v) The BUU is fossilized by SDRs (subaerial volcanism) or by margin infra-salt sediments (forming the mistakenly called by some American geoscientists "sag basin") ; (vi) The Loeme salt basin, which is a twin of the Brazilian salt basin, that is to say, that both basins have always been individualized ; (vii) The transgressive (backstepping) and regressive (forestepping) phases of the post-Pangea continental encroachment cycle ; (v) The interface between these sedimentary phases, correspond to the emplacement of potential marine source-rocks (organic matter type-II) ; (vi) Potential dispersive source rocks (organic matter type III) are possible in the regressive sedimentary interval.

A Lower-Bound Result on the Power of a Genetic Algorithm

This paper presents a lower-bound result on the computational power of a genetic algorithm in the context of combinatorial optimization. We describe a new genetic algorithm, the merged genetic algorithm, and prove that for the class of monotonic functions, the algorithm finds the optimal solution, and does so with an exponential convergence rate. The analysis pertains to the ideal behavior of the algorithm where the main task reduces to showing convergence of probability distributions over the search space of combinatorial structures to the optimal one. We take exponential convergence to be indicative of efficient solvability for the sample-bounded algorithm, although a sampling theory is needed to better relate the limit behavior to actual behavior. The paper concludes with a discussion of some immediate problems that lie ahead.

Contour Generator Points for Threshold Selection and a Novel Photo-Consistency Measure for Space Carving

Space carving has emerged as a powerful method for multiview scene reconstruction. Although a wide variety of methods have been proposed, the quality of the reconstruction remains highly-dependent on the photometric consistency measure, and the threshold used to carve away voxels. In this paper, we present a novel photo-consistency measure that is motivated by a multiset variant of the chamfer distance. The new measure is robust to high amounts of within-view color variance and also takes into account the projection angles of back-projected pixels. Another critical issue in space carving is the selection of the photo-consistency threshold used to determine what surface voxels are kept or carved away. In this paper, a reliable threshold selection technique is proposed that examines the photo-consistency values at contour generator points. Contour generators are points that lie on both the surface of the object and the visual hull. To determine the threshold, a percentile ranking of the photo-consistency values of these generator points is used. This improved technique is applicable to a wide variety of photo-consistency measures, including the new measure presented in this paper. Also presented in this paper is a method to choose between photo-consistency measures, and voxel array resolutions prior to carving using receiver operating characteristic (ROC) curves.

On trip planning queries in spatial databases

In this paper we discuss a new type of query in Spatial Databases, called Trip Planning Query (TPQ). Given a set of points P in space, where each point belongs to a category, and given two points s and e, TPQ asks for the best trip that starts at s, passes through exactly one point from each category, and ends at e. An example of a TPQ is when a user wants to visit a set of different places and at the same time minimize the total travelling cost, e.g. what is the shortest travelling plan for me to visit an automobile shop, a CVS pharmacy outlet, and a Best Buy shop along my trip from A to B? The trip planning query is an extension of the well-known TSP problem and therefore is NP-hard. The difficulty of this query lies in the existence of multiple choices for each category. In this paper, we first study fast approximation algorithms for the trip planning query in a metric space, assuming that the data set fits in main memory, and give the theory analysis of their approximation bounds. Then, the trip planning query is examined for data sets that do not fit in main memory and must be stored on disk. For the disk-resident data, we consider two cases. In one case, we assume that the points are located in Euclidean space and indexed with an Rtree. In the other case, we consider the problem of points that lie on the edges of a spatial network (e.g. road network) and the distance between two points is defined using the shortest distance over the network. Finally, we give an experimental evaluation of the proposed algorithms using synthetic data sets generated on real road networks.

Combinations of Deformable Shape Prototypes

We propose to investigate a model-based technique for encoding non-rigid object classes in terms of object prototypes. Objects from the same class can be parameterized by identifying shape and appearance invariants of the class to devise low-level representations. The approach presented here creates a flexible model for an object class from a set of prototypes. This model is then used to estimate the parameters of low-level representation of novel objects as combinations of the prototype parameters. Variations in the object shape are modeled as non-rigid deformations. Appearance variations are modeled as intensity variations. In the training phase, the system is presented with several example prototype images. These prototype images are registered to a reference image by a finite element-based technique called Active Blobs. The deformations of the finite element model to register a prototype image with the reference image provide the shape description or shape vector for the prototype. The shape vector for each prototype, is then used to warp the prototype image onto the reference image and obtain the corresponding texture vector. The prototype texture vectors, being warped onto the same reference image have a pixel by pixel correspondence with each other and hence are "shape normalized". Given sufficient number of prototypes that exhibit appropriate in-class variations, the shape and the texture vectors define a linear prototype subspace that spans the object class. Each prototype is a vector in this subspace. The matching phase involves the estimation of a set of combination parameters for synthesis of the novel object by combining the prototype shape and texture vectors. The strengths of this technique lie in the combined estimation of both shape and appearance parameters. This is in contrast with the previous approaches where shape and appearance parameters were estimated separately.

Recursive Estimation of Motion and Planar Structure

A specialized formulation of Azarbayejani and Pentland's framework for recursive recovery of motion, structure and focal length from feature correspondences tracked through an image sequence is presented. The specialized formulation addresses the case where all tracked points lie on a plane. This planarity constraint reduces the dimension of the original state vector, and consequently the number of feature points needed to estimate the state. Experiments with synthetic data and real imagery illustrate the system performance. The experiments confirm that the specialized formulation provides improved accuracy, stability to observation noise, and rate of convergence in estimation for the case where the tracked points lie on a plane.

An Invariant Representation for Matching Trajectories across Uncalibrated Video Streams

We introduce a view-point invariant representation of moving object trajectories that can be used in video database applications. It is assumed that trajectories lie on a surface that can be locally approximated with a plane. Raw trajectory data is first locally approximated with a cubic spline via least squares fitting. For each sampled point of the obtained curve, a projective invariant feature is computed using a small number of points in its neighborhood. The resulting sequence of invariant features computed along the entire trajectory forms the view invariant descriptor of the trajectory itself. Time parametrization has been exploited to compute cross ratios without ambiguity due to point ordering. Similarity between descriptors of different trajectories is measured with a distance that takes into account the statistical properties of the cross ratio, and its symmetry with respect to the point at infinity. In experiments, an overall correct classification rate of about 95% has been obtained on a dataset of 58 trajectories of players in soccer video, and an overall correct classification rate of about 80% has been obtained on matching partial segments of trajectories collected from two overlapping views of outdoor scenes with moving people and cars.

A Neural Theory of Attentive Visual Search: Interactions of Boundary, Surface, Spatial, and Object Representations

Visual search data are given a unified quantitative explanation by a model of how spatial maps in the parietal cortex and object recognition categories in the inferotemporal cortex deploy attentional resources as they reciprocally interact with visual representations in the prestriate cortex. The model visual representations arc organized into multiple boundary and surface representations. Visual search in the model is initiated by organizing multiple items that lie within a given boundary or surface representation into a candidate search grouping. These items arc compared with object recognition categories to test for matches or mismatches. Mismatches can trigger deeper searches and recursive selection of new groupings until a target object io identified. This search model is algorithmically specified to quantitatively simulate search data using a single set of parameters, as well as to qualitatively explain a still larger data base, including data of Aks and Enns (1992), Bravo and Blake (1990), Chellazzi, Miller, Duncan, and Desimone (1993), Egeth, Viri, and Garbart (1984), Cohen and Ivry (1991), Enno and Rensink (1990), He and Nakayarna (1992), Humphreys, Quinlan, and Riddoch (1989), Mordkoff, Yantis, and Egeth (1990), Nakayama and Silverman (1986), Treisman and Gelade (1980), Treisman and Sato (1990), Wolfe, Cave, and Franzel (1989), and Wolfe and Friedman-Hill (1992). The model hereby provides an alternative to recent variations on the Feature Integration and Guided Search models, and grounds the analysis of visual search in neural models of preattentive vision, attentive object learning and categorization, and attentive spatial localization and orientation.