We propose a new Hidden Markov Model with time-dependent states. Estimation of this model is shown to be as fast and easy as the estimation of regular HMMs. We demonstrate the usefulness and feasibility of such time-d...
详细信息
We propose a new Hidden Markov Model with time-dependent states. Estimation of this model is shown to be as fast and easy as the estimation of regular HMMs. We demonstrate the usefulness and feasibility of such time-dependent HMMs with an application in which illegitimate access to personnel-only rooms in airports etc. can be distinguished from access by legitimate personnel, based on differences in the time of access or differences in the motion trajectories.
In Augmented Reality (AR) real imagery is superimposed by computer graphics renderings of virtual objects. This paper addresses the problem of creating the illusion that the virtual objects cast credible shadows in th...
详细信息
Human perception is a complex nonlinear dynamics. On the one hand it is periodic dynamics and on the other hand it is chaotic. Thus, we wish to propose a hybrid - the spatial chaotic dynamics for the associative recal...
详细信息
Human perception is a complex nonlinear dynamics. On the one hand it is periodic dynamics and on the other hand it is chaotic. Thus, we wish to propose a hybrid - the spatial chaotic dynamics for the associative recall to retrieve patterns, similar to Walter Freeman's discovery, and the fixed point dynamics for memory storage, similar to Hopfield and Grossberg's discoveries. In this model, each neuron in the network could be a chaotic map, whose phase space is divided into two states: one is periodic dynamic state with period-V, which is used to represent a V-value retrieved pattern;another is chaotic dynamic state. Firstly, patterns are stored in the memory by fixed point learning algorithm. In the retrieving process, all neurons are initially set in the chaotic region. Due to the ergodicity property of chaos, each neuron will approximate the periodic points covered by the chaotic attractor at same instants. When this occurs, the control is activated to drive the dynamic of each neuron to their corresponding stable periodic point. computer simulations confirm the theoretical prediction.
A major obstacle to the broader use of 3D object reconstruction and modeling is the extent of manual intervention needed. Such interventions are currently extensive and exist throughout every phase of a 3D reconstruct...
详细信息
A major obstacle to the broader use of 3D object reconstruction and modeling is the extent of manual intervention needed. Such interventions are currently extensive and exist throughout every phase of a 3D reconstruction project: collection of images, image management, establishment of sensor position and image orientation, extracting the geometric information describing an object, and merging geometric, texture and semantic data. We present a fully automated approach to pottery reconstruction based on the fragment profile, which is the cross-section of the fragment in the direction of the rotational axis of symmetry. We demonstrate the method and give results on synthetic and real data.
The new non-parametric approach to unsegmented text recognition builds two bipartite graphs that result from the feature-level and lexical comparisons of the same word against a reference string which need not include...
详细信息
The new non-parametric approach to unsegmented text recognition builds two bipartite graphs that result from the feature-level and lexical comparisons of the same word against a reference string which need not include the query word. The lexical graph preserves the relative order of edges in the feature graph corresponding to correctly recognized features. This observation leads to a subgraph-matching formulation of the recognition problem. An initial implementation proves the robustness of the approach for up-to 20% noise introduced in the feature-level graph.
With the advent of laboratories containing dozens of cameras, and the possibility of laboratories containing hundreds of cameras, the question of how to calibrate all the cameras has become pressing. While it is certa...
详细信息
With the advent of laboratories containing dozens of cameras, and the possibility of laboratories containing hundreds of cameras, the question of how to calibrate all the cameras has become pressing. While it is certainly possible to calibrate these networks in a labor intensive manner, a simple, stable, and accurate calibration method is still needed. This paper presents such a method, based on textures printable on a laser printer and mounted on a board. We will show what the problems with the current methods are, and show how these problems can be overcome with a novel use of a trilinear constraint related to the vanishing point constraint, which we call the primsatic line constraint. High accuracy with little user effort is achieved with this method.
Splines can be used to approximate noisy data with a few control points. This paper presents a new curve matching method for deformable shapes using two-dimensional splines. In contrast to the residual error criterion...
详细信息
Splines can be used to approximate noisy data with a few control points. This paper presents a new curve matching method for deformable shapes using two-dimensional splines. In contrast to the residual error criterion [7], which is based on relative locations of corresponding knot points such that is reliable primarily for dense point sets, we use deformation energy of thin-plate-spline mapping between sparse knot points and normalized local curvature information. This method has been tested successfully for the detection and recognition of deformable shapes.
A pair of stereo images are said to be rectified if corresponding image points have the same y-coordinate in their respective images. In this paper we consider the rectification of two omnidirectional cameras, specifi...
详细信息
A pair of stereo images are said to be rectified if corresponding image points have the same y-coordinate in their respective images. In this paper we consider the rectification of two omnidirectional cameras, specifically two parabolic catadioptric cameras. Such systems consist of a parabolic mirror and an orthographically projecting lens. We show that if the image coordinates are represented as a point z in the complex plane, then the rectification is specified by coth -1z. This rectification is shown to be conformal, in that it is locally distortionless, and furthermore, it is unique up to scale and transformation. We show an experiment in which two real images have been rectified and a stereo matching performed.
Catadioptric sensors are combinations of mirrors and lenses made in order to obtain a wide field of view. In this paper we propose a new sensor that has omnidirectional viewing ability and it also provides depth infor...
详细信息
Catadioptric sensors are combinations of mirrors and lenses made in order to obtain a wide field of view. In this paper we propose a new sensor that has omnidirectional viewing ability and it also provides depth information about the nearby surrounding. The sensor is based on a conventional camera coupled with a laser emitter and two hyperbolic mirrors. Mathematical formulation and precise specifications of the intrinsic and extrinsic parameters of the sensor are discussed. Our approach overcomes limitations of the existing omni-directional sensors and eventually leads to reduced costs of production.
This paper overviews our research on digital preservation of cultural assets and digital restoration of their original appearance. Geometric models are digitally achieved through a pipeline consisting of scanning, reg...
详细信息
This paper overviews our research on digital preservation of cultural assets and digital restoration of their original appearance. Geometric models are digitally achieved through a pipeline consisting of scanning, registering and merging multiple range images. We have developed a robust simultaneous registration method and an efficient and robust voxel-based integration method. On the geometric models created, we have to align texture images acquired from a color camera. We have developed two texture mapping methods. In an attempt to restore the original appearance of historical heritage objects, we have synthesized several buildings and statues using scanned data and literature survey with advice from experts.
暂无评论