Traditional optic flow algorithms rely on consecutive short-exposure images. In contrast, longexposed images contain integrated motion information directly in form of motion blur. In this paper, we show how the additi...
详细信息
ISBN:
(纸本)9783980487481
Traditional optic flow algorithms rely on consecutive short-exposure images. In contrast, longexposed images contain integrated motion information directly in form of motion blur. In this paper, we show how the additional information provided by a long exposure image can be used to improve robustness and accuracy of motion field estimation. Recently, an image formation model was introduced [23] that relates a long-exposure image to preceding and succeeding short-exposure images in terms of dense 2D motion and occlusion. We formulate the original two-step problem for motion and occlusion timings as a joint minimization problem and derive a global TV-L1 energy functional that can be minimized efficiently and accurately. The approach is able to calculate highly accurate motion fields, assigning motion to occluded and disoccluded image regions in one joint optimization procedure.
This paper presents a continuation of the study on a mathematical morphology based on left-continuous conjunctive uninorms given in [1]. Experimental results are displayed using the morphological Top-Hat transformatio...
详细信息
ISBN:
(纸本)9789899507968
This paper presents a continuation of the study on a mathematical morphology based on left-continuous conjunctive uninorms given in [1]. Experimental results are displayed using the morphological Top-Hat transformation, used to highlight certain components of the image, and on the reduction and elimination of noise using alternate filters that are generated with the operators of opening and closing associated with these morphological operators.
作者:
López, Francisco J. PeralesComputer Graphics
Vision and Antificial Inteligence Group Mathematics and Computer Science Department UIB Crta. Valldemossa Km 7.5 Palma de Mallorca 07122 Spain
The research of new human-computer interfaces has become a growing field in computerscience, which aims to attain the development of more natural, intuitive, unobtrusive and efficient interfaces. This objective has c...
详细信息
This work deals with the investigation on propagating hollow-conical liquid sheets formed by a pressure swirl atomizer during the process of sheet disintegration in quiescent air. In difference to the non-invasive ima...
详细信息
This article reports on the experience of conducting the program committee (PC) meeting for the IEEE VR 2009 conference in Second Life. More than 50 PC members from around the globe met virtually over a two-day period...
详细信息
This paper attempts to discuss the evolution of the retrieval techniques focusing on development, challenges and trends of the image retrieval. It highlights both the already addressed and outstanding issues. The expl...
详细信息
This paper attempts to discuss the evolution of the retrieval techniques focusing on development, challenges and trends of the image retrieval. It highlights both the already addressed and outstanding issues. The explosive growth of image data leads to the need of research and development of Image Retrieval. However, Image retrieval researches are moving from keyword, to low level features and to semantic features. Drive towards semantic features is due to the problem of the keywords which can be very subjective and time consuming while low level features cannot always describe high level concepts in the users' mind.
In many interactive computergraphics applications, users are represented as virtual characters called avatars. Collision detection is a pre-requisite in interactive computergraphics application so that appropriate r...
详细信息
In many interactive computergraphics applications, users are represented as virtual characters called avatars. Collision detection is a pre-requisite in interactive computergraphics application so that appropriate response and realistic behaviour can be generated. However, it will not be easy to anticipate collisions since objects' motion are dependant on user interaction and avatar manipulation. Ideally, collision detection needs to be done efficiently, with accurate result in the shortest time possible. However, due to its computationally intensive nature, collision detection could cause a bottleneck to the system. A variety of techniques, data structures and algorithms were proposed to accelerate the collision detection process. Acceleration data structures are widely used not only to promote faster collision detection, but also in the field of ray tracing and deformable objects simulation. This paper discusses the use of bounding volume hierarchy as an acceleration data structure in collision detection for avatar in virtual environment, as well as similar methods used in interactive ray tracing and deformable objects simulation. Based on these findings, method for fast bounding volume hierarchy construction is proposed as a first step towards efficient avatar collision detection.
In this paper, we propose a new patch-based texture synthesis method. The core of the proposed method consists of two main components: (1) a feature-weighted similarity measurement to search for the best match and (2)...
详细信息
In this paper, we propose a new patch-based texture synthesis method. The core of the proposed method consists of two main components: (1) a feature-weighted similarity measurement to search for the best match and (2) a dynamically prioritized-based pixel re-synthesis to reduce discontinuity at the boundary of adjacent patches. Examples and experimental comparisons with other previous methods are demonstrated to verify the usefulness of our proposed method. In addition, we enhance the proposed method with a view warping technique to better synthesize non-frontal-parallel textures (NFPTs) that can not be synthesized well by traditional texture synthesis methods.
Double counting is a major problem in distributed data fusion systems. To maintain flexibility and scalability, distributed data fusion algorithms should just use local information. However globally optimal solutions ...
详细信息
ISBN:
(纸本)9780982443804
Double counting is a major problem in distributed data fusion systems. To maintain flexibility and scalability, distributed data fusion algorithms should just use local information. However globally optimal solutions only exist in highly restricted circumstances. Suboptimal algorithms can be applied in a far wider range of cases, but can be very conservative. In this paper we present preliminary work to develop distributed data fusion algorithms that can estimate and exploit the correlations between the estimates stored in different nodes in a distributed data fusion network. We show that partial information can be modelled as kind of "overweighted" Covariance Intersection algorithm. We motivate the need for an adaptive scheme by analysing the correlation behaviour of a simple distributed data fusion network and show that it is complicated and counterintuitive. Two simple approaches to estimate the correlation structure are presented and their results analysed. We show that significant advantages can be obtained.
Structured data including sets, sequences, trees and graphs, pose significant challenges to fundamental aspects of data management such as efficient storage, indexing, and similarity search. With the fast accumulation...
详细信息
ISBN:
(纸本)9781605584225
Structured data including sets, sequences, trees and graphs, pose significant challenges to fundamental aspects of data management such as efficient storage, indexing, and similarity search. With the fast accumulation of graph databases, similarity search in graph databases has emerged as an important research topic. Graph similarity search has applications in a wide range of domains including cheminformatics, bioinformatics, sensor network management, social network management, and XML documents, among others. Most of the current graph indexing methods focus on subgraph query processing, i.e. determining the set of database graphs that contains the query graph and hence do not directly support similarity search. In data mining and machine learning, various graph kernel functions have been designed to capture the intrinsic similarity of graphs. Though successful in constructing accurate predictive and classification models for supervised learning, graph kernel functions have (i) high computational complexity and (ii) non-trivial difficulty to be indexed in a graph database. Our objective is to bridge graph kernel function and similarity search in graph databases by proposing (i) a novel kernel-based similarity measurement and (ii) an efficient indexing structure for graph data management. Our method of similarity measurement builds upon local features extracted from each node and their neighboring nodes in graphs. A hash table is utilized to support efficient storage and fast search of the extracted local features. Using the hash table, a graph kernel function is defined to capture the intrinsic similarity of graphs and for fast similarity query processing. We have implemented our method, which we have named G-hash, and have demonstrated its utility on large chemical graph databases. Our results show that the G-hash method achieves state-of-the-art performance for k-nearest neighbor (k-NN) classification. Most importantly, the new similarity measurement and the inde
暂无评论