Current Issue : July - September Volume : 2016 Issue Number : 3 Articles : 4 Articles
The delivery of video over wireless, error-prone transmission channels requires careful allocation of channel and\nsource code rates, given the available bandwidth. In this paper, we present a theoretical framework to find an optimal\njoint channel and source code rate allocation, by considering an intra-coded video compression standard such as\nMotion JPEG 2000 and an error-prone wireless transmission channel. Lagrangian optimization is used to find the\noptimal code rate allocation, from a PSNR perspective, starting from commonly available source coding outputs, such\nas intermediate rate-distortion traces. The algorithm is simple and adaptive both on the available bandwidth and on\nthe transmission channel conditions, and it has a low computational complexity. Simulation results, using\nReed-Solomon (R-S) coding, show that the achieved performance, in terms of PSNR and MSSIM, is comparable with\nthat of other methods reported in literature. In addition, a simplified and sub-optimal expression for determining the\nchannel code assignment is also provided....
In video annotation, instead of annotating every frame of a trajectory, usually only a sparse set of annotations is\nprovided by the user: typically its endpoints plus some key intermediate frames, interpolating the remaining\nannotations between these key frames in order to reduce the cost of the video labeling. While a number of video\nannotation tools have been proposed, some of which are freely available, and bounding box interpolation is mainly\nbased on image processing techniques whose performance is highly dependent on image quality, occlusions, etc. We\npropose an alternative method to interpolate bounding box annotations, based on cubic splines and the geometric\nproperties of the elements involved, rather than image processing techniques.\nThe algorithm proposed is compared with other bounding box interpolation methods described in the literature,\nusing a set of selected videos modeling different types of object and camera motion. Experiments show that the\naccuracy of the interpolated bounding boxes is higher than the accuracy of the other evaluated methods, especially\nwhen considering rigid objects. The main goal of this paper is related with the bounding box interpolation step, and\nwe believe that our design can be integrated seamlessly with any annotation tool already developed....
The paper proposes a new method that combines the decorrelation and shrinkage techniques to neural network-based approaches\nfor noise removal purposes.Theimages are represented as sequences of equal sized blocks, each block being distorted by a stationary\nstatistical correlated noise. Some significant amount of the induced noise in the blocks is removed in a preprocessing step, using a\ndecorrelation method combined with a standard shrinkage-based technique.The preprocessing step provides for each initial image\na sequence of blocks that are further compressed at a certain rate, each component of the resulting sequence being supplied as inputs\nto a feed-forward neural architecture ...
Images can be broadly classified into two types: isotropic and anisotropic. Isotropic images contain largely rounded\nobjects while anisotropics are made of flow-like structures. Regardless of the types, the acquisition process introduces\nnoise. A standard approach is to use diffusion for image smoothing. Based on the category, either isotropic or\nanisotropic diffusion can be used. Fundamentally, diffusion process is an iterated one, starting with a poor quality\nimage, and converging to a completely blurred mean-value image, with no significant structure left. Though the\nprocess starts by doing a desirable job of cleaning noise and filling gaps, called under-smoothing, it quickly passes\ninto an over-smoothing phase where it starts destroying the important structure. One relevant concern is to find the\nboundary between the under-smoothing and over-smoothing regions. The spatial entropy change is found to be one\nsuch measure that may be helpful in providing important clues to describe that boundary, and thus provides a\nreasonable stopping rule for isotropic as well as anisotropic diffusion. Numerical experiments with real fingerprint data\nconfirm the role of entropy-change in identification of a reasonable stopping point where most of the noise is\ndiminished and blurring is just started. The proposed criterion is directly related to the blurring phenomena that is an\nincreasing function of diffusion process. The proposed scheme is evaluated with the help of synthetic as well as the\nreal images and compared with other state-of-the-art schemes using a qualitative measure. Diffusions of some\nchallenging low-quality images from FVC2004 are also analyzed to provide a reasonable stopping rule using the\nproposed stopping rule....
Loading....