Spline Subdivision Schemes for Compact Sets. A Survey

Dedicated to the memory of our colleague Vasil Popov January 14, 1942 – May 31, 1990 * Partially supported by ISF-Center of Excellence, and by The Hermann Minkowski Center for Geometry at Tel Aviv University, Israel

Self-organising zooms for decentralised redundancy management in visual sensor networks

When visual sensor networks are composed of cameras which can adjust the zoom factor of their own lens, one must determine the optimal zoom levels for the cameras, for a given task. This gives rise to an important trade-off between the overlap of the different cameras’ fields of view, providing redundancy, and image quality. In an object tracking task, having multiple cameras observe the same area allows for quicker recovery, when a camera fails. In contrast having narrow zooms allow for a higher pixel count on regions of interest, leading to increased tracking confidence. In this paper we propose an approach for the self-organisation of redundancy in a distributed visual sensor network, based on decentralised multi-objective online learning using only local information to approximate the global state. We explore the impact of different zoom levels on these trade-offs, when tasking omnidirectional cameras, having perfect 360-degree view, with keeping track of a varying number of moving objects. We further show how employing decentralised reinforcement learning enables zoom configurations to be achieved dynamically at runtime according to an operator’s preference for maximising either the proportion of objects tracked, confidence associated with tracking, or redundancy in expectation of camera failure. We show that explicitly taking account of the level of overlap, even based only on local knowledge, improves resilience when cameras fail. Our results illustrate the trade-off between maintaining high confidence and object coverage, and maintaining redundancy, in anticipation of future failure. Our approach provides a fully tunable decentralised method for the self-organisation of redundancy in a changing environment, according to an operator’s preferences.

A multimedia indexing and retrieval framework for multimedia database systems

The main challenges of multimedia data retrieval lie in the effective mapping between low-level features and high-level concepts, and in the individual users' subjective perceptions of multimedia content. ^ The objectives of this dissertation are to develop an integrated multimedia indexing and retrieval framework with the aim to bridge the gap between semantic concepts and low-level features. To achieve this goal, a set of core techniques have been developed, including image segmentation, content-based image retrieval, object tracking, video indexing, and video event detection. These core techniques are integrated in a systematic way to enable the semantic search for images/videos, and can be tailored to solve the problems in other multimedia related domains. In image retrieval, two new methods of bridging the semantic gap are proposed: (1) for general content-based image retrieval, a stochastic mechanism is utilized to enable the long-term learning of high-level concepts from a set of training data, such as user access frequencies and access patterns of images. (2) In addition to whole-image retrieval, a novel multiple instance learning framework is proposed for object-based image retrieval, by which a user is allowed to more effectively search for images that contain multiple objects of interest. An enhanced image segmentation algorithm is developed to extract the object information from images. This segmentation algorithm is further used in video indexing and retrieval, by which a robust video shot/scene segmentation method is developed based on low-level visual feature comparison, object tracking, and audio analysis. Based on shot boundaries, a novel data mining framework is further proposed to detect events in soccer videos, while fully utilizing the multi-modality features and object information obtained through video shot/scene detection. ^ Another contribution of this dissertation is the potential of the above techniques to be tailored and applied to other multimedia applications. This is demonstrated by their utilization in traffic video surveillance applications. The enhanced image segmentation algorithm, coupled with an adaptive background learning algorithm, improves the performance of vehicle identification. A sophisticated object tracking algorithm is proposed to track individual vehicles, while the spatial and temporal relationships of vehicle objects are modeled by an abstract semantic model. ^

An incremental multilinear system for human face learning and recognition

This dissertation establishes a novel system for human face learning and recognition based on incremental multilinear Principal Component Analysis (PCA). Most of the existing face recognition systems need training data during the learning process. The system as proposed in this dissertation utilizes an unsupervised or weakly supervised learning approach, in which the learning phase requires a minimal amount of training data. It also overcomes the inability of traditional systems to adapt to the testing phase as the decision process for the newly acquired images continues to rely on that same old training data set. Consequently when a new training set is to be used, the traditional approach will require that the entire eigensystem will have to be generated again. However, as a means to speed up this computational process, the proposed method uses the eigensystem generated from the old training set together with the new images to generate more effectively the new eigensystem in a so-called incremental learning process. In the empirical evaluation phase, there are two key factors that are essential in evaluating the performance of the proposed method: (1) recognition accuracy and (2) computational complexity. In order to establish the most suitable algorithm for this research, a comparative analysis of the best performing methods has been carried out first. The results of the comparative analysis advocated for the initial utilization of the multilinear PCA in our research. As for the consideration of the issue of computational complexity for the subspace update procedure, a novel incremental algorithm, which combines the traditional sequential Karhunen-Loeve (SKL) algorithm with the newly developed incremental modified fast PCA algorithm, was established. In order to utilize the multilinear PCA in the incremental process, a new unfolding method was developed to affix the newly added data at the end of the previous data. The results of the incremental process based on these two methods were obtained to bear out these new theoretical improvements. Some object tracking results using video images are also provided as another challenging task to prove the soundness of this incremental multilinear learning method.

Valutazione della cardiotossicità in pazienti oncologici mediante tecniche ecocardiografiche

L'elaborato si inserisce in un progetto sviluppato presso l'Istituto Scientifico Romagnolo per lo Studio e la Cura dei Tumori (I.R.S.T.) di Meldola che riguarda la valutazione di parametri cardiologici che possano risultare indici predittivi di uno scompenso cardiaco in pazienti affetti da linfoma. Tutti i soggetti considerati nel progetto sono stati sottoposti a trattamenti chemioterapici facenti uso di antracicline e la cui funzionalità cardiaca è stata controllata periodicamente tramite ecografia bidimensionale e volumetrica, utilizzando il sistema VividE9 della GE Healthcare. L'obiettivo dell'analisi è quello di ricercare se oltre alla frazione di eiezione esistono parametri più predittivi di una eventuale cardiotossicità come gli strain, calcolati attraverso l'ausilio della tecnica ecografica.

Statistical methods for polyhedral shape classification with incomplete data - application to cryo-electron tomographic images

A certain type of bacterial inclusion, known as a bacterial microcompartment, was recently identified and imaged through cryo-electron tomography. A reconstructed 3D object from single-axis limited angle tilt-series cryo-electron tomography contains missing regions and this problem is known as the missing wedge problem. Due to missing regions on the reconstructed images, analyzing their 3D structures is a challenging problem. The existing methods overcome this problem by aligning and averaging several similar shaped objects. These schemes work well if the objects are symmetric and several objects with almost similar shapes and sizes are available. Since the bacterial inclusions studied here are not symmetric, are deformed, and show a wide range of shapes and sizes, the existing approaches are not appropriate. This research develops new statistical methods for analyzing geometric properties, such as volume, symmetry, aspect ratio, polyhedral structures etc., of these bacterial inclusions in presence of missing data. These methods work with deformed and non-symmetric varied shaped objects and do not necessitate multiple objects for handling the missing wedge problem. The developed methods and contributions include: (a) an improved method for manual image segmentation, (b) a new approach to 'complete' the segmented and reconstructed incomplete 3D images, (c) a polyhedral structural distance model to predict the polyhedral shapes of these microstructures, (d) a new shape descriptor for polyhedral shapes, named as polyhedron profile statistic, and (e) the Bayes classifier, linear discriminant analysis and support vector machine based classifiers for supervised incomplete polyhedral shape classification. Finally, the predicted 3D shapes for these bacterial microstructures belong to the Johnson solids family, and these shapes along with their other geometric properties are important for better understanding of their chemical and biological characteristics.

On the motion planning & control of nonlinear robotic systems

In the last decades, we saw a soaring interest in autonomous robots boosted not only by academia and industry, but also by the ever in- creasing demand from civil users. As a matter of fact, autonomous robots are fast spreading in all aspects of human life, we can see them clean houses, navigate through city traffic, or harvest fruits and vegetables. Almost all commercial drones already exhibit unprecedented and sophisticated skills which makes them suitable for these applications, such as obstacle avoidance, simultaneous localisation and mapping, path planning, visual-inertial odometry, and object tracking. The major limitations of such robotic platforms lie in the limited payload that can carry, in their costs, and in the limited autonomy due to finite battery capability. For this reason researchers start to develop new algorithms able to run even on resource constrained platforms both in terms of computation capabilities and limited types of endowed sensors, focusing especially on very cheap sensors and hardware. The possibility to use a limited number of sensors allowed to scale a lot the UAVs size, while the implementation of new efficient algorithms, performing the same task in lower time, allows for lower autonomy. However, the developed robots are not mature enough to completely operate autonomously without human supervision due to still too big dimensions (especially for aerial vehicles), which make these platforms unsafe for humans, and the high probability of numerical, and decision, errors that robots may make. In this perspective, this thesis aims to review and improve the current state-of-the-art solutions for autonomous navigation from a purely practical point of view. In particular, we deeply focused on the problems of robot control, trajectory planning, environments exploration, and obstacle avoidance.

Video stimuli reduce object-directed imitation accuracy: a novel two-person motion-tracking approach

Imitation is an important form of social behavior, and research has aimed to discover and explain the neural and kinematic aspects of imitation. However, much of this research has featured single participants imitating in response to pre-recorded video stimuli. This is in spite of findings that show reduced neural activation to video vs. real life movement stimuli, particularly in the motor cortex. We investigated the degree to which video stimuli may affect the imitation process using a novel motion tracking paradigm with high spatial and temporal resolution. We recorded 14 positions on the hands, arms, and heads of two individuals in an imitation experiment. One individual freely moved within given parameters (moving balls across a series of pegs) and a second participant imitated. This task was performed with either simple (one ball) or complex (three balls) movement difficulty, and either face-to-face or via a live video projection. After an exploratory analysis, three dependent variables were chosen for examination: 3D grip position, joint angles in the arm, and grip aperture. A cross-correlation and multivariate analysis revealed that object-directed imitation task accuracy (as represented by grip position) was reduced in video compared to face-to-face feedback, and in complex compared to simple difficulty. This was most prevalent in the left-right and forward-back motions, relevant to the imitator sitting face-to-face with the actor or with a live projected video of the same actor. The results suggest that for tasks which require object-directed imitation, video stimuli may not be an ecologically valid way to present task materials. However, no similar effects were found in the joint angle and grip aperture variables, suggesting that there are limits to the influence of video stimuli on imitation. The implications of these results are discussed with regards to previous findings, and with suggestions for future experimentation.

Smart object for 3D interaction

This paper reports on the creation of an interface for 3D virtual environments, computer-aided design applications or computer games. Standard computer interfaces are bound to 2D surfaces, e.g., computer mouses, keyboards, touch pads or touch screens. The Smart Object is intended to provide the user with a 3D interface by using sensors that register movement (inertial measurement unit), touch (touch screen) and voice (microphone). The design and development process as well as the tests and results are presented in this paper. The Smart Object was developed by a team of four third-year engineering students from diverse scientific backgrounds and nationalities during one semester.

Analysis of warm season thunderstorms using an object-oriented tracking method based on radar and total lightning data

Monitoring thunderstorms activity is an essential part of operational weather surveillance given their potential hazards, including lightning, hail, heavy rainfall, strong winds or even tornadoes. This study has two main objectives: firstly, the description of a methodology, based on radar and total lightning data to characterise thunderstorms in real-time; secondly, the application of this methodology to 66 thunderstorms that affected Catalonia (NE Spain) in the summer of 2006. An object-oriented tracking procedure is employed, where different observation data types generate four different types of objects (radar 1-km CAPPI reflectivity composites, radar reflectivity volumetric data, cloud-to-ground lightning data and intra-cloud lightning data). In the framework proposed, these objects are the building blocks of a higher level object, the thunderstorm. The methodology is demonstrated with a dataset of thunderstorms whose main characteristics, along the complete life cycle of the convective structures (development, maturity and dissipation), are described statistically. The development and dissipation stages present similar durations in most cases examined. On the contrary, the duration of the maturity phase is much more variable and related to the thunderstorm intensity, defined here in terms of lightning flash rate. Most of the activity of IC and CG flashes is registered in the maturity stage. In the development stage little CG flashes are observed (2% to 5%), while for the dissipation phase is possible to observe a few more CG flashes (10% to 15%). Additionally, a selection of thunderstorms is used to examine general life cycle patterns, obtained from the analysis of normalized (with respect to thunderstorm total duration and maximum value of variables considered) thunderstorm parameters. Among other findings, the study indicates that the normalized duration of the three stages of thunderstorm life cycle is similar in most thunderstorms, with the longest duration corresponding to the maturity stage (approximately 80% of the total time).

Bi-planar 2D-to-3D registration in Fourier domain for stereoscopic X-ray motion tracking

In this paper we present a new method to track bonemovements in stereoscopic X-ray image series of the kneejoint. The method is based on two different X-ray imagesets: a rotational series of acquisitions of the stillsubject knee that will allow the tomographicreconstruction of the three-dimensional volume (model),and a stereoscopic image series of orthogonal projectionsas the subject performs movements. Tracking the movementsof bones throughout the stereoscopic image series meansto determine, for each frame, the best pose of everymoving element (bone) previously identified in the 3Dreconstructed model. The quality of a pose is reflectedin the similarity between its simulated projections andthe actual radiographs. We use direct Fourierreconstruction to approximate the three-dimensionalvolume of the knee joint. Then, to avoid the expensivecomputation of digitally rendered radiographs (DRR) forpose recovery, we reformulate the tracking problem in theFourier domain. Under the hypothesis of parallel X-raybeams, we use the central-slice-projection theorem toreplace the heavy 2D-to-3D registration of projections inthe signal domain by efficient slice-to-volumeregistration in the Fourier domain. Focusing onrotational movements, the translation-relevant phaseinformation can be discarded and we only consider scalarFourier amplitudes. The core of our motion trackingalgorithm can be implemented as a classical frame-wiseslice-to-volume registration task. Preliminary results onboth synthetic and real images confirm the validity ofour approach.

Cell viability and noninvasive in vivo MRI tracking of 3D cell encapsulating self-assembled microcontainers.

Several molecular therapies require the implantation of cells that secrete biotherapeutic molecules and imaging the location and microenvironment of the cellular implant to ascertain its function. We demonstrate noninvasive in vivo magnetic resonance imaging (MRI) of self-assembled microcontainers that are capable of cell encapsulation. Negative contrast was obtained to discern the microcontainer with MRI; positive contrast was obtained in the complete absence of background signal. MRI on a clinical scanner highlights the translational nature of this research. The microcontainers were loaded with cells that were dispersed in an extracellular matrix, and implanted both subcutaneously and in human tumor xenografts in SCID mice. MRI was performed on the implants, and microcontainers retrieved postimplantation showed cell viability both within and proximal to the implant. The microcontainers are characterized by their small size, three dimensionality, controlled porosity, ease of parallel fabrication, chemical and mechanical stability, and noninvasive traceability in vivo.

Scene representation for object monitoring

In robotics, having a 3D representation of the environment where a robot is working can be very useful. In real-life scenarios, this environment is constantly changing for example by human interaction, external agents or by the robot itself. Thus, the representation needs to be constantly updated and extended to account for these dynamic scene changes. In this work we face the problem of representing the scene where a robot is acting. Moreover, we ought to improve this representation by reusing the information obtained in previous scenes. Our goal is to build a method to represent a scene and to update it while changes are produced. In order to achieve that, different aspects of computer vision such as space representation or feature tracking are discussed

Prospective motion correction of 3D echo-planar imaging data for functional MRI using optical tracking.

We evaluated the performance of an optical camera based prospective motion correction (PMC) system in improving the quality of 3D echo-planar imaging functional MRI data. An optical camera and external marker were used to dynamically track the head movement of subjects during fMRI scanning. PMC was performed by using the motion information to dynamically update the sequence's RF excitation and gradient waveforms such that the field-of-view was realigned to match the subject's head movement. Task-free fMRI experiments on five healthy volunteers followed a 2×2×3 factorial design with the following factors: PMC on or off; 3.0mm or 1.5mm isotropic resolution; and no, slow, or fast head movements. Visual and motor fMRI experiments were additionally performed on one of the volunteers at 1.5mm resolution comparing PMC on vs PMC off for no and slow head movements. Metrics were developed to quantify the amount of motion as it occurred relative to k-space data acquisition. The motion quantification metric collapsed the very rich camera tracking data into one scalar value for each image volume that was strongly predictive of motion-induced artifacts. The PMC system did not introduce extraneous artifacts for the no motion conditions and improved the time series temporal signal-to-noise by 30% to 40% for all combinations of low/high resolution and slow/fast head movement relative to the standard acquisition with no prospective correction. The numbers of activated voxels (p<0.001, uncorrected) in both task-based experiments were comparable for the no motion cases and increased by 78% and 330%, respectively, for PMC on versus PMC off in the slow motion cases. The PMC system is a robust solution to decrease the motion sensitivity of multi-shot 3D EPI sequences and thereby overcome one of the main roadblocks to their widespread use in fMRI studies.

Group stochastic search for object detection and tracking

A technique is presented for locating and tracking objects in cluttered environments. Agents are randomly distributed across the image, and subsequently grouped around targets. Each agent uses a weightless neural network and a histogram intersection technique to score its location. The system has been used to locate and track a head in 320x240 resolution video at up to 15fps.