Learn More
In this paper, we describe a unique new paradigm for video database management known as ViBE (Video Indexing and Browsing Environment). ViBE is a browseable/searchable paradigm for organizing video data containing a large number of sequences. The system first segments video sequences into shots by using a new feature vector known as the Generalized Trace(More)
A common feature found in practically all technical approaches proposed for face recognition is the use of only the luminance information associated to the face image. One may wonder if this is due to the low importance of the color information in face recognition or due to other less technical reasons such as the no availability of color image database.(More)
Distributed Video Coding (DVC) is a new video coding paradigm based on two major Information Theory results: the Slepian–Wolf and Wyner–Ziv theorems. Recently, practical DVC solutions have been proposed with promising results; however, there is still a need to study in a more systematic way the set of application scenarios for which DVC may bring major(More)
Distributed Source Coding (DSC) aims at achieving efficient compression by locating the source redundancies at the decoder instead of the encoder. Moreover, DSC exhibits many properties like low-complexity encoding or embedded error resilience that make it very convenient for some emerging new applications. Among the many challenging topics related to DSC(More)
This paper presents a comparison of the performance of different side information generation methods for multiview distributed video coding scenarios. Existing literature on this topic relies on pure temporal interpolation (by means of motion compensation), pure inter-camera interpolation (by means of disparity compensation) or a combination of both. In(More)
The objective of this paper 1 is to provide a robust representation of moving images based on layers. To that goal, we have designed eecient motion estimation and segmentation techniques by aane model tting suitable for the construction of layers. Layered representations, originally introduced in 4] are important in several applications. In particular, they(More)
A new method for texture coding which combines 2-D linear prediction and stochastic vector quantization is presented in this paper. To encode a texture, a linear predictor is computed first. Next, a codebook following the prediction error model is generated and the prediction error is encoded with VQ, using an algorithm which takes into account the pixels(More)