Wyniki wyszukiwania - BazTech

1

Object based segmentation of video using variational level sets

Cheng B., Wang Y., Zheng N., Bian Z.

Machine Graphics and Vision

|

2005

|

Vol. 14, No. 2

145-157

EN

The paper demonstrates a new approach to video segmentation which retains some of the attractive features of existing methods and overcomes some of their limitations. The video sequence is represented as a spatio-temporal volume, and is segmented by an extension of active contour model based on Mumford-Shah techniques. The energy function minimization is similar to 3D interface evolution with curvature-dependent speeds. The spatio-temporal volume need not to be smoothed before processing because our method is not sensitive to noise. Each object needs a closed interface, which is embedded as a level set of a higher-dimensional functions, and is propagated by solving a partial differential equation. The interface stops in the vicinity of object boundaries, which are not necessarily defined by the gradient and can be represented with complex topologies. Finally, an experiment is given to show the effectiveness and robustness of the method.

2

3D plenoptic representation of a linear scene

Cheng B., Zheng N., Quan W., Li X.

Machine Graphics and Vision

|

2001

|

Vol. 10, No. 4

431-446

EN

This paper presents a novel 3D plenoptic function. We constrain camera motion to a line, and create a linear mosaic using a manifold mosaic. The plenoptic function is represented with three parameters: camera position along the axis, the angle between the ray and the centric axis, and the rotation angle in the vertical plane. Novel views are renderend by combining the appropriate captured rays in an efficient manner at the rendering time. Like panoramas, our method does not require recovery of geometric and photometric scene models. Moreover, it provides a much richer user experience by allowing the user to move freely in a linear region and observe significant parallax and lighting changes. Compared with either Lightfield or Lumigraph, it has a much smaller file size because a 3D only plenoptic function is constructed. Finally, an experiment with a synthetic environment is given to demonstrate its efficiency in capturing construction and rendering of a linear scene.

3

Warping-based interactive visualization on PC

Li X., Zheng N.

Machine Graphics and Vision

|

1999

|

Vol. 8, No. 1

63-76

EN

Image--based rendering produces realistic--looking 3D graphics at relatively low cost. In this paper, an original post--warping redering system using more than two sample views to derive a new view is presented. Owing to the warp--based compression and incremental coputation, the computational expense is less or no more than conventional two-image synthesis approaches. The procedure consists of three steps. First, a set of sample images is selectively acquired with conventional geometry rendering or volume rendering or from photographs of the real scene. Next each of the neighboring image pair is compressed by warping transformation based on redundant pixels between them. Finally, the compressed sample images are directly re- projected to produce new images. In order to improve the speed more, an incremental warping flow is developed, which is computationally less expense. With the method described above, animation faster than fifty frames (300x 300) per second is achieved on PC.

4

Image coding based on flexible contour model

Zheng N., Song W., Li W.

Machine Graphics and Vision

|

1999

|

Vol. 8, No. 1

83-94

EN

This paper presents a new scheme of model-based image coding method. First a new image model called Flexible Contour Model that can extract features of nonrigid objects in images is proposed, then we deduce the fast algorithms for calculating the parameters of the model and for matching the model to images. Furthermore the combination of the model with multiscale analysis and the triangulation of the model has been studies. As a result, reconstrution of orginal images with high compression rate and unnaticeable distortion was obtained.

5

Light field rendering of dynamic scene

Li W., Ke Q., Huang X., Zheng N.

Machine Graphics and Vision

|

1998

|

Vol. 7, No. 3

551-563

EN

Image based rendering has displayed advantage in speed over traditional geometry based rendering algorithms. With the four dimensionl light field descriptions, static scene can be generated with interactive rate on ordinary computer. The limitation of the scheme is that it can only handle static scene and fixed illumination. This paper raises the idea to decompose the light field into sub-light-fields that do not change as scene changes. It expands the advantage of light field rendering to dynamic scenes where the position and orientation of objects, lights and viewpoint can be modified arbitrarily. The sub-light-fields include: ambient light field and spot light field. The latter is actually an eight-diamensional space. Because diffuse reflection is idenpendent on view direction, this paper presents a four-diamensional representation of spot light field. Considering the linearity of diffuse reflection to different spot light, the spot light fields of an object can be represented by the reflection light field to a pure-color light with unit intensity, to decrease storage and preprocessing. Owing to the coherency in thier data structures, data of the corresponding point in the ambient light field, diffuse light field and depth field are combined into a 5-dimensional vector which can be compressed efficiently with vector quantization. The algorithm given in this paper accurately computers typical characteristics of dynamic scene such as changes in surface color and shadow.