Yucel Altunbasak

A fast method of reconstructing high-resolution panoramic stills from MPEG-compressed video

Creating high quality still pictures from video presents a challenging problem due to the low spatial resolution of most video signals. Many algorithms have been proposed in the literature that utilize multiple video frames to increase spatial resolution. These algorithms depend on two critical assumptions: first, that the scene does not change significantly in the temporal vicinity of the frame of interest, and second that the motion estimation between video frames is extremely accurate. Noting that panoramic views are not only visually pleasing, but also fit the aforementioned assumptions, we propose the use of a scene change detection algorithm to locate scenes containing mainly pan/tilt types of motion. Since many digital video sequences are compressed using MPEG, it is desirable to perform all computations with minimal decompression. To this end, we also propose methods to locate pans from MPEG-compressed video. Once the pan segments are located, a number of highly accurate motion estimation methods can be successfully applied to the video segment. Given the resulting accurate motion, there exist various methods of attacking the resolution enhancement problem and creating a panoramic still image. These, for the most part, are computationally expensive. Therefore, we propose a fast method of obtaining enhanced resolution panoramas from the lower resolution video signal.

Simultaneous object segmentation, multiple object tracking and alpha map generation

This paper presents an object-based video modeling. Motion segmentation is performed at the initial frame to identify different coherently moving regions, called motion-objects. These regions are grouped to form objects. Each motion-object is fitted a content-based mesh, and tracked subsequently to the next frame via mesh motion estimation and compensation. The uncovered background region(s), which emerges when objects move, will be segmented so as to identify the new objects or occluded parts of already existing objects. The mesh model is modified to reflect the changes in object boundaries.

Object-scalable mesh-based coding of synthetic and natural image objects

This paper presents an object-based image coding scheme, where each image object is encoded individually, provided that their boundaries are specified. This allows object-based quality scalability, in addition to mixing lossy and lossless coding modes depending on the requirements of each image object. Furthermore, we propose a new object coding method using 2-D mesh-based image sampling in which the quadrilateral mesh patches are warped into square blocks, and encoded by traditional data/waveform coding methods. Experimental results on test images are provided.

Scalable mesh-based interpolative coding of synthethic and natural image objects

This paper presents an object-based synthetic-natural hybrid image coding scheme, where each image object is encoded individually, provided that their boundaries are specified. This allows coding natural and synthetic image objects using different methods which are best suited their content. It also allows object-based quality scalability, in addition to mixing lossy and lossless coding modes depending on the requirements of each image object. Furthermore, we propose a new object coding method using 2D mesh-based image sampling and interpolation, followed by encoding of the interpolation error image by a traditional data/waveform coding methods. Experimental results on synthetic-natural hybrid test images are provided.

On global parametric motion estimation with lens distortion correction

In this paper, two-dimensional (2-D) motion estimation techniques based on the well-known optical-flow equation are treated. Cost functions are defined for various motion models that allow the optical flow equation (OFE) to be used in an optimization framework for the purpose of estimating the 2-D motion parameters. A method of extending these cost functions to include camera parameters is then proposed. The resulting sometimes non-linear optimization framework takes into account motion-model parameter estimation in the presence of geometric lens distortions. Linearization, when necessary, results in an OFE-like motion estimation method.