In this paper we consider the problem of estimating the quality of a decoded video that is transmitted over an unreliable packet-switched network. The goal is to allow the encoder to calculate the expected decoder distortion without any direct comparison between the original and the decoded sequence. This work is based on ROPE algorithm for the video quality estimate. ROPE calculates, at the encoder side, the expected decoded video distortion: therefore it is reasonably performing in estimating the average obtained distortion. The main question this paper would like to answer is how accurate ROPE distortion estimate is in the case of a single realization, i.e., in the case of distortion estimate for a single user

Nowadays the broadcasting of digital video contents is a common scenario. Evaluation of the quality of received information is an important issue for companies involved in this business. The goal is to obtain blind estimation of the quality - i.e. without information about the original video - like in the analog TV scenario. In this paper, we present a novel technique to perform this operation based on semi-fragile watermarking where the watermark is used as reference signal. The algorithm uses a watermarking technique in the transformed domain. A watermark is inserted in the original video. Then the video passes through different compression steps, it is transmitted and received. At the end of the distribution chain the video quality is estimate by using correlation between original watermark and received video. The algorithm is tested for typical digital television broadcast bit-rate. The results show that the proposed algorithm provides a good estimation for the video quality for MPEG compression in particular for digital TV bit-rates.

The major complexity source in H.264 is the rate distortion (R-D) optimization. This work proposes a method to reduce the complexity of R-D analysis, paying a little video degradation, by estimating the encoding modes that are more likely used by the encoder. Since the encoding modes depend mainly on the typology of the video and on the quantization parameter used to encode each block, the work proposes to group the modes into subsets that depend on the quantizer level and the characteristics of the video. In particular, the motion compensability of each frame modulates the intra modes, while texture difficulty addresses the inter modes. The R-D algorithm evaluates only the modes included into the resulting subset. The usage of subset modes reduces the complexity of the encoding process (40-70%) with respect to the original R-D optimized encoder, with a slight PSNR reduction (0-0,30 dB).

Video transcoding is a mechanism to convert video bit-streams from one coding format to other formats. In this operation, the computational complexity and picture quality are the two most important concerns. MPEG-7 standard defines media transcoding hints (THs) in order to both reduce the complexity and improve the visual quality during transcoding process. The basic assumption is that THs are generated in advance and they are stored together with the host video itself. Unfortunately, there exist some applications for which it is unpractical, for time or complexity constraints, to compute the THs in advance. This work proposes to estimate the THs exploiting the data coming from the compressed domain of a video in order to save computational complexity

In this paper, we address the problem of video transmission over unreliable networks, such as the Internet, where packet losses occur. The most recent literature indicates multiple description (MD) as a promising coding approach to handle this issue. Moreover, it has been shown also how important the use of motion compensation prediction is in an MD-coding scheme. This paper proposes two architectures for multiple description video coding, both of them are based on the motion compensation prediction loop. The common characteristic of the two architectures is the use of a polyphase down-sampling technique to create the MDs and to introduce cross-redundancy among the descriptions. The first scheme, that we call drift-compensation multiple description video coder (DC-MDVC) appears very robust when used in an error-prone environment, but it can provide only two descriptions. The second architecture, called independent flow multiple description video coder (IF-MDVC), generates multiple sets of data before the motion compensation loop; in this case, there are no severe limitations in the selection of the number of descriptions used by the coder.

The goal of the paper is to present a novel technique for automatic identification of videos. This technique is based on a hashing algorithm which analyzes the video in order to extract its fingerprinting or hash value. This fingerprint allows the unambiguous. Two main aspects are considered: the hash extraction process and the database strategy to retrieve information. We also propose an analysis of the false positive error probability in order to identify an identification threshold. The proposed technique is tested under different kinds of compression using the MPEG standard and DivX;-) algorithm. The results show that a reliable identification can be performed.

Compressed video streams are very exposed to channel losses when they are transmitted through an unreliable network. The predictive encoding scheme is efficient but even a single packet loss can cause decoding error propagation through all the frames following the erasure. An error-resilience approach to tackle this problem is the multiple description coding (MDC) technique. Another important issue connected to this approach is the problem of the error-concealment (EC) used to reconstruct the information lost during the transmission. In this paper, we deal with a sequence-based EC algorithm that performs the error-concealment by using the information coming from a certain number of frames in the future to minimize the effect of error propagation. The target of this work is applying such an EC strategy to a balanced MDC system. Simulation results show the great improvement that a sequence-based EC algorithm can give compared to classical EC approaches.

Recently new technologies are presented for automatic media identification based not only on watermarking. In this paper we present a new algorithm used to identify video sequences. It is based on perceptual hashing, which analyzes the signal in order to extract its fingerprint, called hash value. The idea is that this value could allow the unambiguous identification of the signal, such as human fingerprint with people. Different aspects are considered: the hash extraction process and the database strategy to retrieve stored information. For the second problem it is important to take into account the probability to not identify the video. An analytical analysis of error probability is presented. The proposed technique is tested under different kind of compression using different coding algorithm. The results show that a reliable identification can be performed even for low bit-rates.

This paper presents a hashing method for automatic song recognition. This technique works by analyzing the signal and taking into account its nature. The goal of automatic recognition is obtained by extracting different features, which are robust to signal processing and distinctive of the signal. They describe in a compact way the signal and can be efficiently stored in a database. The features are analyzed for short frames using a quantization approach, and a parameter for identification is proposed. Moreover we define also a confidence computed on the identification parameter. By combining the two parameters, a better identification is obtained. The algorithm is tested in different situations: compression, cropping, noise addition, subsampling, stereo to mono conversion, etc. The results show that the identification can be performed also using a short excerpt of the song

Compressed video sequences are very vulnerable to channel disturbances when they are transmitted through a packet loss networks. The predictive video encoders are very efficient but even a single packet loss can cause decoding error propagation through all the frames following the erasure. An approach to tackle this problem is applying multiple description coding (MDC) techniques. Another important issue in robust video transmission is the problem of error-recovery. In fact it is necessary applying an error-concealment (EC) strategy in order to reconstruct the information lost during the transmission. In this paper we deal with sequence-based EC algorithm that performs the error-recovery by using the information coming from a certain number of frames in the future to minimize the effect of error propagation. Target of this work is to apply such EC strategy to a balanced MD coding system. Simulation results show the great improvement that a sequence-based EC algorithm can give to a BMDC system.

In this paper we address the problem of video transmission over unreliable networks using multiple description (MD) coding approach. Recent literature on MD techniques has shown the success of using motion compensation prediction scheme. Even though these MD systems have proved to be robust to error environment, they are forced to use only two descriptions. For this reason this paper proposes two architectures of MD video coders. The first, called DC-MDVC, is based on the classical MD video codec architecture and the principle contribution is the use of a new MD algorithm based on a spatial domain polyphase down-sampling technique. The second architecture, called IF-MDVC, proposes multi-level scalability generating a flexible number of descriptions. The results of both architectures are interesting and the second architecture, the subject of the current research, appears to perform impressively.

In this paper we tackle the problem of video transmission over ADSL channel. Due to the delay constraint of the transmission, the Shannon's theorem is not strictly applicable and it seems challenging to evaluate which is the contribution of joint source/channel coding. The ADSL system is standardized to work at a bit error rate (BER) of 10/sup -7/. In this work we relax this constraint in order to understand if this constraint (suitable for data transmission) is optimum also in the case of video transmission. The aim of this work is twofold: first, it jointly optimize source and channel coding in order to find out the best point of work for the overall system and second, it compares in this scenario the single and multiple description video coding approaches.

In this paper we address the problem of image transmission over unreliable networks. The system is based on multiple description coding, that introducing redundancy in the produced stream is able to guarantee a useful quality reconstruction also in presence of high percentage of packet losses. The target of this work is providing a flexible redundancy insertion in order to make the system robust for any packet loss situation over different networks (the Internet or mobile). The simulation results show the capability of the system to achieve the optimal image quality reconstruction according to network behavior.

We present a video watermarking technique proposed as an indexing technique for video sequences. The watermarking approach is based on an algorithm working in the spatial video domain, in order to reduce the computational cost, while the invisibility is obtained by masks computed in space and time domains. Finally, to improve robustness we work with different error correcting codes and we test their performances. The proposed scheme has been implemented and tested. Our tests are mainly focused on compression and transcoding attacks that are the most important operations that the video suffers in a journalistic report production. The robustness is increased by using an error correction code. The obtained results show that this is a good approach.

In this paper we propose a fast and robust watermarking scheme for digital audio signals that allows automatic identification of musical pieces transmitted in TV broadcasting programs. Usually watermark is used as a way for hiding information on digital media. The watermarked information may be used to allow copyright protection or user and media identification. In our application the watermark must be, obviously, imperceptible to the users to mantain the quality of the source, should be robust to standard TV and radio editing and its processing has to require a very low complexity. This last item is essential to allow a software real-time implementation of the insertion and detection of watermarks using only a minimum amount of the computation power of a modern PC. Simulation results obtained on a long set of subjective test prove the quality and the robustness of the proposed approach.

Today the problem of transmitting data over heterogeneous networks has received considerable attention. In this paper we propose the design of a system to transmit in realtime high-quality video signal over Internet. To do that, we present a Multiple Description (MD) coding based on polyphase downsampling algorithm that splits an image source in an arbitrary number of balanced descriptions. Our goal is to obtain both the best reconstruction quality from the received descriptions (also only one) and a subjective indistinguishable reconstruction from the original, if all the descriptions are available.

We propose a fast and robust watermarking scheme for digital audio signals that allows automatic identification of musical pieces transmitted in TV broadcast programs. Usually the watermark is used as a way for hiding information on digital media. The watermarked information may allow copyright protection or user identification and media indexing. In our application the watermark must be, obviously, imperceptible to the users to maintain the quality of the source, should be robust to standard TV and radio editing and its processing has to require a very low complexity. This last item is essential to allow a software real-time implementation of the insertion and detection of watermark using only a minimum amount of the computation power of a modern PC. In the proposed algorithm we divide the audio signal in frames, on each frame a masking function is computed based on the human auditory system (HAS), and the watermark is embedded using a spread spectrum technique. Simulation results obtained on a long set of subjective tests prove the quality and the robustness of the proposed approach.

In this paper a data hiding technique for MPEG-2 coded video sequences is presented. We have chosen to work in the bit stream domain in order to simplify the data embedding process in the case in which the original data are already in a compressed form. Thanks to the exploitation of an interleaved encoding technique and of some space and frequency masking considerations, we have been able to reduce the BER of the original algorithm. Some results underlining the improvements we have been able to obtain thanks to our technique are shown.

This paper presents a watermarking technique for MPEG-2 coded video sequences. We have chosen to work in the bit stream domain in order to simplify the data embedding process in the case in which the original data are already in a compressed form. Thanks to the exploitation of an interleaved encoding technique and of some space and frequency masking considerations, we have been able to reduce the BER of the original algorithm. Some results underlining the improvements we have been able to obtain thanks to our technique are shown.

The paper presents a wavelet domain watermarking technique for color images. The characteristics of this transform domain are well suited for masking consideration, due to its good localization in both space and frequency. The different color sensitivity can be exploited in order to increase the watermarking power, and therefore its reliability. Thanks to the multi-resolution nature of the discrete wavelet transform (DWT) the watermark detection can be obtained iteratively. The technique has been successfully evaluated against attacks such as JPEG and JPEG-2000 compression, filtering, cropping, dithering and digital to analog and analog to digital conversions.

Many different quality metrics have been proposed an order to evaluate the reconstructed quality of compressed sequences. The most used measures are quantitative metrics based on a simple difference between frames. Their main drawback is that they do not correlate well with subjective quality evaluations. Up to now the only standardized method used to estimate the perceived quality of a coding system is the subjective assessment: a series of test scenes is shown to a number of selected observers, in a controlled environment. This method of quality evaluation shows limits in term of time consumption and results' interpretation. The purpose of many recent studies is to develop objective measures having good correlation with subjective quality scores in relation to the same video system and test scenes. A number of parameters influence the viewers' judgment of the sequence quality; in this paper we analyze the sequence motion effects on the viewers video quality perception. This paper proposes preliminary results in terms of the correlation between a linear model, that takes into account the “criticality” of the scene motion, and the results of formal subjective assessments.

Many different quality metrics have been proposed in order to evaluate the reconstructed quality of compressed sequences. The most used measures are quantitative metrics based on a simple difference between frames. They are easily analytically tractable, reliable and can be reproduced at any time. Their main drawback is that they do not correlate well with subjective quality evaluations. Up to now, the only standardized method used to estimate the perceived quality of a coding system has been subjective assessment: a series of test scenes is shown to a number of selected observers in a controlled environment. This method of quality evaluation shows limits in term of time consumption and interpretation of results; this is mainly due to a multiplicity of elements: viewing conditions, choice of the test materials, timing of the presentation, scale of rating, etc., whose effects on the subjective quality scores are difficult to estimate. The purpose of many recent studies has been to develop objective measures having good correlation with the subjective quality scores in relation to the same video system and test scenes. A number of parameters influence the viewers' judgment of the sequence quality; in this paper, we analyze the sequence motion effects on the viewers' video quality perception. The paper proposes preliminary results in terms of the correlation between a linear model, that takes into account the "criticality" of the scene motion, and the results of formal subjective assessments.

An effective motion compensated image interpolation technique is presented. The proposed algorithm has been developed for the interpolation of missing frames in an image sequence and it is based on two principal elements. The first is a region-based motion estimation and representation technique, which combines, for each known image, an approximate initial motion field estimate and an initial image over-segmentation (obtained using both luminance and chrominance information) to produce a very accurate affine-model regularized motion field. The proposed algorithm uses a robust identification technique for the estimation of the motion parameters associated to each region. The second important element is the use of an interpolation technique, that starting from the available motion information defines, for each point of the image to be interpolated a suitable reconstruction strategy taking into account the different situations that can appear (for example a moving object can occlude either a stationary background or an another object and so on). The principal aim of the proposed algorithm is the reconstruction of the missing frames in a reasonable way, without introducing significant artifacts and assuring a pleasant representation of object displacement.

The paper presents applications of neural network algorithms to the design of an adaptive vector quantizer. Vector quantization has been applied to the problem of displaying natural images with a reduced set of colors (colormap) and to the interframe coding of image sequences. The first step was to test classical Linde Buzo Gray (LGB), self organizing feature maps (SOFM) and Competitive Learning (CL) algorithms for the codebook design. The best results for the reconstructed quality image and the computational time are obtained using a CL algorithm with a new initialization strategy that solves the problem of underutilized nodes. An adaptive vector quantization algorithm is proposed and tested in a motion compensated image coder. The results of the simulations are very promising. In fact the coder performance, compared with that using a fixed VQ, is considerably improved and the subjective quality of the coded images is much better than that obtained using standard vector quantization, especially when rapid motion is present in the scene.>

A new and effective video coding scheme for contribution quality is proposed. The CMTT/2, a joint committee of CCIR and CCITT, has proposed a video coding scheme (already approved at European level by ETS) working at 34-45 Mbit/s. Basically this proposal includes a DCT transform for spatial correlation removal and motion compensation for temporal correlation removal. The individual transform coefficients are then scalar quantized with a non uniform bit assignment. Starting from the CMTT/2 proposal, the study presents a new video coding scheme designed using a vector quantizer solution instead of the scalar one. Specifically, the pyramid vector quantization (PVQ) has been chosen as the vector quantization method as it is able to reduce the DCT coefficients Laplacian distribution. Simulation results show that the proposed video coding scheme gives the same contribution quality at 22 Mbit/s as the one obtained with the CMTT/2 proposal at 45 Mbit/s.

A new effective still image coding scheme based on overlapped projections and pyramid vector quantization is presented. In standard image coding the spatial redundancy of the images is reduced subdividing the incoming data into small blocks and applying to these a linear transformation (DCT) to obtain highly independent coefficients, that are scalar quantized. This block by block coding takes advantage of the spatial correlation but it induces visually annoying blocking artifacts (especially at high compression ratios). The authors resent a different coding scheme where the image is subdivided into circular partially overlapped regions and then the projections along predefined directions are determined and vector quantized. Simulations show that the projection technique allows the detection of the most important information locally present on the image while the use of circular overlapped regions reduces blocking artifacts.>

We present a progressive image transmission coder, where geometrical vector quantization is applied to overlapped image projections. Progressive image transmission is widely used in many applications, because it offers successive improved reconstructions of an image. It is possible to have a rough version of information available in a very short time and, then, the viewer can decide whether further transmission is necessary or not. In the proposed coding scheme the still image is subdivided into circular partially overlapped regions and, then, some projections along predefined directions are determined and vector quantized by using geometrical VQ. The utilization of overlapped circular regions exploits the spatial redundancy present on the image, as the block subdivision does, and at the same time, it avoids the problem of blocking artifacts. The projection technique allows the detection of the most important information locally present on the image.>

The problem of adaptive vector quantization (VQ) for image sequence coding is addressed. The goal of this work is to overcome the limits that reduce the possibility of a hardware implementation of the schemes already presented in the literature. The limits principally concern the complexity of the implementation in real time of the classical Linde-Buzo-Gray (LBG) algorithm, which is necessary to introduce some adaptive capabilities in a VQ. Neural network methods, because of their fast codebook design, seem an interesting alternative to solve this problem. The authors have used an unsupervised neural network approach to introduce adaptivity in a vector quantizer by using a codebook replenishment method. The proposed adaptive VQ algorithm has been tested in a motion compensated interframe image coding scheme. The results of the simulations are very promising. A considerable rise of the coder performance with respect to the use of fixed VQ has been obtained.>