Search

Wedding is one of the most important ceremonies in our lives. It symbolizes the birth and creation of a new family. In this paper, we present a system for automatically segmenting a wedding ceremony video into a sequence of recognizable wedding events, e.g., the couple's wedding kiss. Our goal is to develop an automatic tool that helps users to efficiently organize, search, and retrieve his/her treasured wedding memories. Furthermore, the obtained event descriptions could benefit and complement the current research in semantic video understanding. Based on the knowledge of wedding customs, a set of audiovisual features, relating to the wedding contexts of speech/music types, applause activities, picture-taking activities, and leading roles, are exploited to build statistical models for each wedding event. Thirteen wedding events are then recognized by a hidden Markov model, which takes into account both the fitness of observed features and the temporal rationality of event ordering to improve the segmentation accuracy. We conducted experiments on a collection of wedding videos and the promising results demonstrate the effectiveness of our approach. Comparisons with conditional random fields show that the proposed approach is more effective in this application domain. Index Terms--Event detection, home videos, semantic content analysis, video segmentation, wedding ceremonies.

This paper addresses the optimization problem of minimizing the number of memory access subject to a rate constraint for any Huffman decoding of various standard codecs. We propose a Lagrangian multiplier based penalty-resource metric to be the targeting cost function. To the best of our knowledge, there is few related discussion, in the literature, on providing a criterion to judge the approaches of entropy decoding under resource constraint. The existing approaches which dealt with the decoding of the single-side growing Huffman tree may not be memory-efficient for arbitrary-side growing Huffman trees adopted in current codecs. By grouping the common prefix part of a Huffman tree, in stead of the commonly used single-side growing Huffman tree, we provide a memory efficient hierarchical lookup table to speed up the Huffman decoding. Simulation results show that the proposed hierarchical table outperforms previous methods. A Viterbi-like algorithm is also proposed to efficiently find the optimal hierarchical table. More importantly, the Viterbi-like algorithm obtains the same results as that of the brute-force search algorithm. Index Terms--Audio/video decoding, Huffman decoding, tree data structure.

In this paper, Huffman-code based reversible variable length code (RVLC) construction algorithms are studied. We use graph models to represent the prefix, suffix and Hamming distance relationships among RVLC candidate codewords. The properties of the so-obtained graphs are investigated in detail, based on which we present two efficient RVLC construction algorithms: Algorithm 1 aims at minimizing the average codeword length while Algorithm 2 jointly minimizes the average codeword length and maximizes the error detection probability at the same time. Index Terms--Error detection coding, error synchronization, variable length codes.

Frame rate up-conversion is a postprocessing tool to convert the frame rate from a lower number to a higher one. It is a useful technique for a lot of practical applications, such as display format conversion, low bit rate video coding and slow motion playback. Unlike traditional approaches, such as frame repetition or linear frame interpolation, motion-compensated frame interpolation (MCFI) technique is more efficient since it takes block motion into account. In this paper, by considering the deficiencies of previous works, new criteria and coding schemes for improving motion derivation and interpolation processes are proposed. Next, for video coding applications, adaptive frame skip is executed at the encoder side to maximize the power of MCFI so that the quality of interpolated frames is guaranteed. Experimental results show that our proposal effectively enhances the overall quality of the frame rate up-converted video sequence, both subjectively and objectively. Index Terms--Adaptive frame skip, frame rate up-conversion (FRUC), motion-compensated frame interpolation (MCFI).

An efficient matrix-based discrete cosine transform splitter/merger for realizing MPEG-2 to AVC/H.264 transform kernel conversion is presented in this paper. Due to its matrix-based nature, the proposed transform kernel converter can be readily implemented by specific multimedia instruction set available today. Both the computational complexity and numerical error behavior of the proposed approach are shown to be superior to that of the straightforward (full decoding + reencoding) one. In other words, the effectiveness of the proposed algorithm can be justified by examining both the execution speed and the reproduced image quality. Index Terms--Discrete cosine transform (DCT), DCT splitter/ merger, MPEG-2-to-AVC/H.264 transform Kernel conversion.

The browsing of quality videos on small hand-held devices is a common scenario in pervasive media environments. In this paper, we propose a novel framework for video adaptation based on content recomposition. Our objective is to provide effective small size videos which emphasize the important aspects of a scene while faithfully retaining the background context. That is achieved by explicitly separating the manipulation of different video objects. A generic video attention model is developed to extract user-interest objects, in which a high-level combination strategy is proposed for fusing the adopted three types of visual attention features: intensity, color, and motion. Based on the knowledge of media aesthetics, a set of aesthetic criteria is presented. Accordingly, these objects are well reintegrated with the direct-resized background to optimally match the specific screen sizes. Experimental results demonstrate the efficiency and effectiveness of our approach. Index Terms--Content recomposition, media aesthetics, region of interest, video adaptation, visual attention model.

Foveation is one of the nonuniform resolution properties of the human visual system. Recently, different foveation models are proposed and utilized for image and video coding, for the sake of bit-rate saving with no or minor perceptual quality distortion. In the first part of this paper, we propose an efficient and practical DCT-domain foveation model, which is deduced from existing experimental results. In the second part, we present a foveation-based rate-shaping mechanism for MPEG bitstreams, as an application example of the proposed foveation model. The rate shaper is based on eliminating DCT coefficients embedded in MPEG bitstreams. An efficient rate-shaping mechanism is developed to meet various bit-rate requirements. Our simulation confirmed that the proposed foveation model and the rate-shaping mechanism are practical for real-world usage. Index Terms--Foveated image processing, foveation model, human visual system (HVS), MPEG, rate shaping.

Power consumption is an important design issue of current multimedia embedded systems. Data caches consume a significant portion of total processor power for multimedia applications because they are data intensive. In an integrated multimedia system, the cache architecture cannot be tuned specifically for an application. Therefore, a significant amount of cache energy is actually wasted. In this paper, we propose the software-controlled cache architecture that improves the energy efficiency of the shared cache in an integrated multimedia system on an application-specific base. Data types in an application are allocated to different cache regions. On each access, only the allocated cache regions need to be activated. We test the effectiveness of the software-controlled cache of the MPEG-2 software decoder. The results show up to 40 % of cache energy reduction on an ARM-like cache architecture without sacrificing performance. Index Terms--Dynamic power dissipation, energy consumption, MPEG-2, multimedia applications, software-controlled cache.

Reversible variablel length codes (RVLCs) are not only prefix-free but also suffix-free codes. Due to the additional suffix-free condition, RVLCs are usually nonexhaustive codes. When a bit error occurs in a sentence from a nonexhaustive RVLC, it is possible that the corrupted sentence is not decodable. The error is said to be detected in this case. We present a model for analyzing the error detection and error synchronization characteristics of nonexhaustive VLCs. Six indices, the error detection probability, the mean and the variance of forward error detection delay length, the error synchronization probability, the mean and the variance of forward error synchronization delay length are formulated based on this model. When applying the proposed model to the case of nonexhaustive RVLCs, these formulations can be further simplified. Since RVLCs can be decoded in backward direction, the mean and the variance of backward error detection delay length, the mean and the variance of backward error synchronization delay length are also introduced as measures to examine the error detection and error synchronization characteristics of RVLCs. In addition, we found that error synchronization probabilities of RVLCs with minimum block distance greater than 1 are 0. Index Terms--Error detection, error synchronization, reversible variable-length codes (RVLCs).

Fine granularity scalability (FGS) is the latest video-coding tool provided in Amendment 2 of the MPEG-4 standard. By taking advantage of bitplane coding of DCT residues, the compressed bitstream can be truncated at any location to support the finest rate scalability in the enhancement layer. However, both frame buffer scanning several times in bitplane decoding and frame duplication simultaneously for base and enhancement layer decoding make FGS difficult in its implementation. In this paper, we propose a corresponding pair of efficient streaming schedule and pipeline decoding architecture to deal with the prescribed problems. The design may be applied to the case of streaming stored FGS videos and benefit FGS-related applications. Index Terms--Bitplane coding, fine granularity scalability, pipeline processing, scheduling, timing.

INTRODUCTION The effective protection of intellectual property rights is of priority concern in the light of the accelerated growth of digital media. Digital watermarking has been increasingly recognized as a […], Digital watermarking has been increasingly recognized as a highly effective means of protecting the intellectual property rights associated with multimedia data. Based on the multiresolution structures of wavelet decomposition, both on a real field and on binary field, we propose a multiresolution watermarking technique. In this work, we embed each decomposed layer of a binary watermark into the corresponding decomposed layer of a host image. Therefore, in case of attacks or progressive transmission, the coarser approximation of a watermark will be preserved in the coarser version of an image, but not be corrupted entirely. In the application of progressive transmission, adding higher frequency components, allows us to obtain higher resolution image, and, correspondingly, extract a higher resolution watermark. Experimental results demonstrate the robustness and validity of the watermarking process proposed herein.

A fast two-dimensional discrete cosine transform algorithm based on index permutation is described. Discrete cosine transform is used in a wide range of digital signal processing applications, and the proposed algorithm enhances the efficiency of this approach by minimizing any measure of computational complexity. Numerical results show that the N x N two-dimensional discrete cosine transform, where N = 2(super m), can be calculated using only N one-dimensional discrete cosine transforms and some post additions.

In this paper, a multiresolution-based technique for embedding digital 'watermarks' into images is proposed. The watermarking technique has been proposed as a method by hiding secret information into the images so as to discourage unauthorized copying or attesting the origin of the images. In our method, we take advantage of multiresolution signal decomposition. Both the watermark and the host image are composed of multiresolution representations with different structures and then the decomposed watermarks of different resolution are embedded into the corresponding resolution of the decomposed images. In case of image quality degradation, the low-resolution rendition of the watermark will still be preserved within the corresponding low-resolution components of the image. The experimental results show that the proposed watermarking technique results in an almost invisible difference between the watermarked image and the original image, and is robust to common image processing operations and JPEG lossy compression.

In this paper, a lightweight genetic search algorithm (LGSA) is proposed. Different evolution schemes are investigated, such that the control overheads are largely reduced. It is also shown that the proposed LGSA can be viewed as a novel expansion of the three-step search algorithm (TSS). It can be seen from the simulation results that the performance of LGSA is very similar to that of FSA, and the computational complexity is much lower than that of FSA and other previously proposed genetic motion estimation algorithms. Index Terms - Block matching, genetic algorithm, video coding.

The statistical analysis of space-varying (SV) morphological openings shows that different structure elements (SE) for each spatial position in SV operations results in better signal smoothing and noise filtering than space invariant (SI) openings. The analysis utilizes rectangular sampling grids and flat SE's to compare the SV and SI openings for a step edge model. The mean curves of filtering in a noisy step edge model exhibit better edge-preserving capabilities of SV openings, while maintaining the sharpness of the edge.

We will define a new class of real-number linear block codes using the discrete cosine transform (DCT). We will also show that a subclass with a BCH-like structure can be defined and, therefore, encoding/decoding algorithms for BCH cedes can be applied. A (16, 10) DCT code is given as an example.

A novel algorithm for deriving the discrete Fourier transform (DFT) and the discrete Hartley transform of an N-point sequence is introduced. Built via a basis-vector decomposition of the transform's core matrix into add/subtract preprocessing and block diagonal postprocessing matrices, it has the same computational complexity as the split-radix fast Fourier transformation. A discussion on its correlations with other familiar DFT algorithms is also included.

A decimation in frequency (DIF) vector split-radix algorithm for the decomposition of an N *N 2-D DHT into one (N/2) * (N/2) DHT and 12 (N/4) * (N/4) DHTs is presented. The proposed algorithm consists of a very regular computational structure that eliminates the use of matrix transposition. Numerical analysis shows that the algorithm outperforms all existing nonseparable 2-D DHTs in the computation of the power spectrum and correlation.

Research describing an output pruning algorithm is presented. The algorithm eliminates the need for unnecessary operations for computing a discrete cosine transform.

The relationship between the discrete Hartley transform and the discrete Fourier transform (DFT) described by Hong et al. (1994) from the perspectives of field extension and projection is extended to obtain the discrete cosine transform (DCT). DCT is an important discrete orthogonal transform in data compression, from the normal bases expansion of the DFT. A novel interpretation of the forward and the inverse DCT transforms has been developed to facilitate the easy derivation of a fully recursive fast DCT algorithm.

In this letter, we propose a generic and efficient algorithm that can construct both asymmetrical and symmetrical reversible variable-length codes (RVLCs). Starting from a given Huffman code, the construction is based on two developed code-word selection mechanisms, for the symmetrical case and the asymmetrical case, respectively; it is shown that the two mechanisms possess simple features and can generate efficient RVLCs easily. In addition, two new asymmetrical RVLCs are constructe and shown to be very efficient for further reducing the coding overheads in MPEG-4 when operating in the reversible decoding mode. Index Terms--H.263, Huffman codes, MPEG-4, reversible variable-length codes.

Reversible variable length codes (RVLCs) have been adopted in emerging video coding standards--H.263+ and MPEG-4--to enhance their error-resilience capabilities (which are important and essential) in error-prone environments. This study proposes an efficient algorithm to construct a symmetrical RVLC from a given Huffman code. In addition, theoretical bounds on the maximum codeword length for fixed-length Huffman codes, and on the optimal average codeword lengths for sources with exponential distribution are provided. Index Terms--Error resilience, Huffman Codes, MPEG-4., reversible variable length codes (RVLCs).

Genetic algorithms for automatic facial feature extraction were formulated. These proposed algorithms are composed of two main stages, namely, the face region estimation and the feature extraction stage. Evaluation of their application indicates that they can automatically and exactly extract facial features with limited computational complexity. Hence, they can be useful in very low bit-rate video coding and human face recognition.

An image authentication technique that uses digital watermarks is presented. The method works by selectively modifying the middle frequency parts of the image during the embedding of digital watermarks. Experiments using watermarks with visually recognizable patterns show that the technique can withstand the cropping of an image, image enhancement and the Joint Photographic Experts Group lossy compression.