Igor Kozintsev

Low-complexity image denoising based on statistical modeling of wavelet coefficients

We introduce a simple spatially adaptive statistical model for wavelet image coefficients and apply it to image denoising. Our model is inspired by a recent wavelet image compression algorithm, the estimation-quantization (EQ) coder. We model wavelet image coefficients as zero-mean Gaussian random variables with high local correlation. We assume a marginal prior distribution on wavelet coefficients variances and estimate them using an approximate maximum a posteriori probability rule. Then we apply an approximate minimum mean squared error estimation procedure to restore the noisy wavelet image coefficients. Despite the simplicity of our method, both in its concept and implementation, our denoising results are among the best reported in the literature.

Multicast and unicast real-time video streaming over wireless LANs

We address the problem of real-time video streaming over wireless LANs for both unicast and multicast transmission. The wireless channel is modeled as a packet-erasure channel at the IP level. For the unicast scenario, we describe a novel hybrid Automatic Repeat reQuest (ARQ) algorithm that efficiently combines forward error control (FEC) coding with the ARQ protocol. For the multiple-users scenario, we formulate the problem of real-time video multicast as an optimization of a maximum regret cost function across the multicast user space. The proposed solution efficiently combines progressive source coding with FEC coding. We present a theoretical analysis of the unicast and multicast cases, as well as experimental results that demonstrate the performance advantages of the proposed algorithms over existing methods.

Spatially adaptive statistical modeling of wavelet image coefficients and its application to denoising

This paper deals with the application to denoising of a very simple but effective local spatially adaptive statistical model for the wavelet image representation that was previously introduced successfully in a compression context. Motivated by the intimate connection between compression and denoising, this paper explores the significant role of the underlying statistical wavelet image model. The model used here, a simplified version of the one proposed by LoPresto, Ramchandran and Orchard (see Proc. IEEE Data Compression Conf., 1997), is that of a mixture process of independent component fields having a zero-mean Gaussian distribution with unknown variances /spl sigma//sub s//sup 2/ that are slowly spatially-varying with the wavelet coefficient location s. We propose to use this model for image denoising by initially estimating the underlying variance field using a maximum likelihood (ML) rule and then applying the minimum mean squared error (MMSE) estimation procedure. In the process of variance estimation, we assume that the variance field is locally smooth to allow its reliable estimation, and use an adaptive window-based estimation procedure to capture the effect of edges. Despite the simplicity of our method, our denoising results compare favorably with the best reported results in the denoising literature.

Factor graph framework for semantic video indexing

Video query by semantic keywords is one of the most challenging research issues in video data management. To go beyond low-level similarity and access video data content by semantics, we need to bridge the gap between the low-level representation and high-level semantics. This is a difficult multimedia understanding problem. We formulate this problem as a probabilistic pattern-recognition problem for modeling semantics in terms of concepts and context. To map low-level features to high-level semantics, we propose probabilistic multimedia objects (multijects). Examples of multijects in movies include explosion, mountain, beach, outdoor, music, etc. Semantic concepts in videos interact and appear in context. To model this interaction explicitly, we propose a network of multijects (multinet). To model the multinet computationally, we propose a factor graph framework which can enforce spatio-temporal constraints. Using probabilistic models for multijects, rocks, sky, snow, water-body, and forestry/greenery, and using a factor graph as the multinet, we demonstrate the application of this framework to semantic video indexing. We demonstrate how detection performance can be significantly improved using the multinet to take inter-conceptual relationships into account. Our experiments using a large video database consisting of clips from several movies and based on a set of five semantic concepts reveal a significant improvement in detection performance by over 22%. We also show how the multinet is extended to take temporal correlation into account. By constructing a dynamic multinet, we show that the detection performance is further enhanced by as much as 12%. With this framework, we show how keyword-based query and semantic filtering is possible for a predetermined set of concepts.

Image transmission using arithmetic coding based continuous error detection

Block cyclic redundancy check (CRC) codes represent a popular and powerful class of error detection techniques in modern data communication systems. Though efficient, CRCs can detect errors only after an entire block of data has been received and processed. We propose a new continuous error detection scheme using arithmetic coding that provides a novel tradeoff between the amount of added redundancy and the amount of time needed to detect an error once it occurs. We demonstrate how the new error detection framework improves the overall performance of transmission systems, and show how sizeable performance gains can be attained. We focus on two popular scenarios: (i) automatic repeat request (ARQ) based transmission; and (ii) forward error correction frameworks based on (serially) concatenated coding systems involving an inner error-correction code and an outer error-detection code.

Robust image transmission over energy-constrained time-varying channels using multiresolution joint source-channel coding

We explore joint source-channel coding (JSCC) for time-varying channels using a multiresolution framework for both source coding and transmission via novel multiresolution modulation constellations. We consider the problem of still image transmission over time-varying channels with the channel state information (CSI) available at (1) receiver only and (2) both transmitter and receiver being informed about the state of the channel, and we quantify the effect of CSI availability on the performance. Our source model is based on the wavelet image decomposition, which generates a collection of subbands modeled by the family of generalized Gaussian distributions. We describe an algorithm that jointly optimizes the design of the multiresolution source codebook, the multiresolution constellation, and the decoding strategy of optimally matching the source resolution and signal constellation resolution trees in accordance with the time-varying channel and show how this leads to improved performance over existing methods. The real-time operation needs only table lookups. Our results based on a wavelet image representation show that our multiresolution-based optimized system attains gains on the order of 2 dB in the reconstructed image quality over single-resolution systems using channel optimized source coding.

Continuous error detection (CED) for reliable communication

Block cyclic redundancy check (CRC) codes represent a popular and powerful class of error detection techniques used almost exclusively in modern data communication systems. Though efficient, CRCs can detect errors only after an entire block of data has been received and processed. In this work, we exploit the continuous nature of error detection that results from using arithmetic codes for error detection, which provides a novel tradeoff between the amount of added redundancy and the amount of time needed to detect an error once it occurs. We demonstrate how this continuous error detection framework improves the overall performance of communication systems, and show how considerable performance gains can be attained. We focus on several important scenarios: 1) automatic repeat request (ARQ) based transmission; 2) forward error correction (FEC frameworks based on (serially) concatenated coding systems involving an inner error-correction code and an outer error-detection code; and 3) reduced state sequence estimation (RSSE) for channels with memory. We demonstrate that the proposed CED framework improves the throughput of ARQ systems by up to 15% and reduces the computational/storage complexity of FEC and RSSE by a factor of two in the comparisons that we make against state-of-the-art systems.

Multiresolution joint source-channel coding using embedded constellations for power-constrained time-varying channels

We explore joint source-channel coding (JSCC) for time-varying (slow-fading Rayleigh) channels, using a multiresolution (MR) framework for both source coding and transmission (via a novel MR modulation constellation). We tackle the important case of the informed receiver but uninformed transmitter, i.e. where the receiver has access to the channel state information (CSI), but the transmitter does not. We describe an algorithm which jointly optimizes the design of the MR source codebook, the MR constellation, and the decoding strategy of optimally matching the source and signal constellation resolution trees according to the time-varying channel, and show how this leads to improved performance over separately designed source and channel coders.

Distributed Microphone Arrays for Digital Home and Office

With the proliferation of pervasive computing in digital home and office environment there is an increasing demand for hands-free audio and video interfaces. Microphone arrays are already present on desktops and mobile computers, and camera arrays are in transition from being highly sophisticated prototypes to become affordable consumer devices soon. Thanks to increasing CPU power of general-purpose computers and higher bandwidth in wired and wireless networks, it now becomes possible to perform array signal processing of audio using networked sensors, actuators and computers. This paper presents components of a prototype system developed to support hands-free audio capture for audio recording and voice recognition based on multiple wirelessly networked laptops with onboard microphone arrays. Several key technologies demonstrated in this system include: 1) time synchronization scheme for distributed audio input devices that uses wireless network; 2) localization algorithms to reconstruct the geometry of audio sensors and speakers in a room; 3) cascaded beamforming algorithms for signals captured by distributed microphone arrays. This paper discusses both theoretical and practical aspects of mapping array signal processing algorithms on a distributed network of general-purpose computers with integrated audio sensors. Our experimental results demonstrate great potential of distributed audio arrays for hands-free command-and-control when compared to an array located on a single platform

Hybrid compressed-uncompressed framework for wireless image transmission

We consider the problem of efficient image transmission over noisy time-varying channels subject to a low transmission energy constraint (and fixed bandwidth/delay constraints). We examine the limits of desirability of a highly compressed representation using a joint source-channel coding (JSCC) framework. Specifically, invoking as a platform a state-of-the-art wavelet image coder, we demonstrate how the resulting highly compressed digital stream, appropriately protected against channel noise, is not always the best solution. We show how a hybrid scheme based on simple partitioning of the wavelet image representation into compressed and uncompressed components can lead to significantly improved performance (of the order of 3 dB in PSNR for Rayleigh channels) over popular JSCC schemes which are based on compressed, entropy-coded, and appropriately unequal error-protected (UEP) source representations.