Synchronization of user-generated videos through trajectory correspondence and a refinement procedure

Temporal synchronization of multiple video recordings of the same dynamic event is a critical task in many computer vision applications e.g. novel view synthesis and 3D reconstruction. Typically this information is implied through the time-stamp information embedded in the video streams. User-generated videos shot using consumer grade equipment do not contain this information; hence, there is a need to temporally synchronize signals using the visual information itself. Previous work in this area has either assumed good quality data with relatively simple dynamic content or the availability of precise camera geometry. Our first contribution is a synchronization technique which tries to establish correspondence between feature trajectories across views in a novel way, and specifically targets the kind of complex content found in consumer generated sports recordings, without assuming precise knowledge of fundamental matrices or homographies. We evaluate performance using a number of real video recordings and show that our method is able to synchronize to within 1 sec, which is significantly better than previous approaches. Our second contribution is a robust and unsupervised view-invariant activity recognition descriptor that exploits recurrence plot theory on spatial tiles. The descriptor is individually shown to better characterize the activities from different views under occlusions than state-of-the-art approaches. We combine this descriptor with our proposed synchronization method and show that it can further refine the synchronization index. © 2013 ACM.

Entropy of Kaluza-Klein black hole from Kerr/CFT correspondence

We extend the recently proposed Kerr/CFT correspondence to examine the dual conformal field theory of four-dimensional Kaluza-Klein black hole in Einstein-Maxwell-Dilaton theory. For the extremal Kaluza-Klein black hole, the central charge and temperature of the dual conformal field are calculated following the approach of Guica, Hartman, Song and Strominger. Meanwhile, we show that the microscopic entropy given by the Cardy formula agrees with Bekenstein-Hawking entropy of extremal Kaluza-Klein black hole. For the non-extremal case, by studying the near-region wave equation of a neutral massless scalar field, we investigate the hidden conformal symmetry of Kaluza-Klein black hole, and find the left and right temperatures of the dual conformal field theory. Furthermore, we find that the entropy of non-extremal Kaluza-Klein black hole is reproduced by Cardy formula. (C) 2010 Elsevier B.V. All rights reserved.

An Efficient Correspondence Based Algorithm for 2D and 3D Model Based Recognition

A polynomial time algorithm (pruned correspondence search, PCS) with good average case performance for solving a wide class of geometric maximal matching problems, including the problem of recognizing 3D objects from a single 2D image, is presented. Efficient verification algorithms, based on a linear representation of location constraints, are given for the case of affine transformations among vector spaces and for the case of rigid 2D and 3D transformations with scale. Some preliminary experiments suggest that PCS is a practical algorithm. Its similarity to existing correspondence based algorithms means that a number of existing techniques for speedup can be incorporated into PCS to improve its performance.

On The Uniqueness of Correspondence Under Orthographic and Perspective Projections

The task of shape recovery from a motion sequence requires the establishment of correspondence between image points. The two processes, the matching process and the shape recovery one, are traditionally viewed as independent. Yet, information obtained during the process of shape recovery can be used to guide the matching process. This paper discusses the mutual relationship between the two processes. The paper is divided into two parts. In the first part we review the constraints imposed on the correspondence by rigid transformations and extend them to objects that undergo general affine (non rigid) transformation (including stretch and shear), as well as to rigid objects with smooth surfaces. In all these cases corresponding points lie along epipolar lines, and these lines can be recovered from a small set of corresponding points. In the second part of the paper we discuss the potential use of epipolar lines in the matching process. We present an algorithm that recovers the correspondence from three contour images. The algorithm was implemented and used to construct object models for recognition. In addition we discuss how epipolar lines can be used to solve the aperture problem.

Modelo de balanço de nitrogênio para a cana-de-açúcar fase II - construção de modelo software STELLA.

A cultura da cana-de-açúcar vem sofrendo mudanças, de âmbitos tecnológicos e sociais, profundas nesta década, procurando se adaptar às demandas de produção com alta produtividade, competitividade e respeito ao meio ambiente. Apesar de o Brasil ser o maior produtor mundial de cana-de-açúcar, ainda pratica a queima da palha do canavial para facilitar a colheita, o que gera prejuízos econômicos, sociais e ambientais. Sem essa queima (Decreto n.° 42056 do Estado de SP), a cobertura do solo pela palhada irá provocar significativas mudanças no manejo da cultura e na dinâmica do nitrogênio. Dada a complexibilidade do ciclo de nitrogênio no solo, seus vários caminhos de transformação, e as variações climáticas, é difícil a determinação do melhor manejo do nitrogênio em sistemas de cultivo, pois não há análise de solo para apoiar o agricultor no seu manejo. Modelos de Simulação que descrevem as transformações do nitrogênio do solo podem prever valores e direcionar o melhor manejo do nitrogênio, tanto do ponto de vista da produtividade da cana como da qualidade ambiental. Assim, o modelo preliminar proposto na Fase I deste estudo em Relatório Técnico 22, da Embrapa informática Agropecuária, foi, nesta Fase II do projeto, ajustado com valores para solos tropicais e reconstruído no software de Simulação STELLA, agregando-se todo o conhecimento disponível em expressões matemáticas sobre esse assunto. Procedendo-se a simulação numérica em situações usuais, geraram-se como resultados, cenários que permitiram discussões técnicas sobre o melhoria do manejo do fertilizante nitrogenado. Concluiu-se que, apesar da complexa dinâmica do nitrogênio no sistema solo-planta e das dificuldades inerentes à medida de formas disponíveis de N, o modelo ajustado apresentou-se como uma alternativa para pesquisadores, técnicos e produtores no entendimento dos processos que envolvem o nitrogênio no sistema, auxiliando na busca por soluções para o melhor manejo de fertilizantes nitrogenados à cultura da cana-de-açúcar para manutenção de produtividades adequadas.

Two-Dimensional?Three-Dimensional Correspondence in Mammography

R. Marti, C. Rubin, E. Denton and R. Zwiggelaar, '2D-3D correspondence in mammography', Cybernetics and Systems 35 (1), 85-105 (2004)

Automatic point correspondence and registration based on linear structures

R. Marti, R. Zwiggelaar, C.M.E. Rubin, 'Automatic point correspondence and registration based on linear structures', International Journal of Pattern Recognition and Artificial Intelligence 16 (3), 331-340 (2002)

The Correspondence of Iolo Morganwg, 1770-1826

Jenkins, G.; Jones, F.; and Jones, D. (Eds.). (2007). The Correspondence of Iolo Morganwg: Vols. I, II and III. Cardiff: University of Wales Press. RAE2008

Modal Matching for Correspondence and Recognition

Modal matching is a new method for establishing correspondences and computing canonical descriptions. The method is based on the idea of describing objects in terms of generalized symmetries, as defined by each object's eigenmodes. The resulting modal description is used for object recognition and categorization, where shape similarities are expressed as the amounts of modal deformation energy needed to align the two objects. In general, modes provide a global-to-local ordering of shape deformation and thus allow for selecting which types of deformations are used in object alignment and comparison. In contrast to previous techniques, which required correspondence to be computed with an initial or prototype shape, modal matching utilizes a new type of finite element formulation that allows for an object's eigenmodes to be computed directly from available image information. This improved formulation provides greater generality and accuracy, and is applicable to data of any dimensionality. Correspondence results with 2-D contour and point feature data are shown, and recognition experiments with 2-D images of hand tools and airplanes are described.

Mathematical notation in formal specification: Too difficult for the masses? [Correspondence]

The phrase “not much mathematics required” can imply a variety of skill levels. When this phrase is applied to computer scientists, software engineers, and clients in the area of formal specification, the word “much” can be widely misinterpreted with disastrous consequences. A small experiment in reading specifications revealed that students already trained in discrete mathematics and the specification notation performed very poorly; much worse than could reasonably be expected if formal methods proponents are to be believed.

Correspondence between continuous-variable and discrete quantum systems of arbitrary dimensions

We establish a mapping between a continuous-variable (CV) quantum system and a discrete quantum system of arbitrary dimension. This opens up the general possibility to perform any quantum information task with a CV system as if it were a discrete system. The Einstein-Podolsky-Rosen state is mapped onto the maximally entangled state in any finite-dimensional Hilbert space and thus can be considered as a universal resource of entanglement. An explicit example of the map and a proposal for its experimental realization are discussed.