Djamel Ait-Boudaoud

An Efficient Feature Based Matching Algorithm for Stereo Images

A novel efficient feature based stereo matching algorithm is presented in this paper. The proposed method links the detected feature points into chains and the matching process is achieved by comparing some of the feature points from different chains. A matching score based on 2 dimensional normalised cross correlation (2D NCC) is used to determine whether feature points are well matched to construct a feature correspondence. This process improves the reliability and the efficiency of the algorithm by concentrating on matching corresponding chains. The proposed method is tested and validated using real scenes and synthetic data images. Experimental results indicate that this novel algorithm is more reliable especially for images in which a number of vertical features are detected. It also compares well with existing methods in terms of speed of execution

Facial expression biometrics using statistical shape models

This paper describes a novel method for representing different facial expressions based on the shape space vector (SSV) of the statistical shape model (SSM) built from 3D facial data. The method relies only on the 3D shape, with texture information not being used in any part of the algorithm, that makes it inherently invariant to changes in the background, illumination, and to some extent viewing angle variations. To evaluate the proposed method, two comprehensive 3D facial data sets have been used for the testing. The experimental results show that the SSV not only controls the shape variations but also captures the expressive characteristic of the faces and can be used as a significant feature for facial expression recognition. Finally the paper suggests improvements of the SSV discriminatory characteristics by using 3D facial sequences rather than 3D stills.

Autonomous Virulence Adaptation Improves Coevolutionary Optimization

A novel approach for the autonomous virulence adaptation (AVA) of competing populations in a coevolutionary optimization framework is presented. Previous work has demonstrated that setting an appropriate virulence, v, of populations accelerates coevolutionary optimization by avoiding detrimental periods of disengagement. However, since the likelihood of disengagement varies both between systems and over time, choosing the ideal value of v is problematic. The AVA technique presented here uses a machine learning approach to continuously tune v as system engagement varies. In a simple, abstract domain, AVA is shown to successfully adapt to the most productive values of v. Further experiments, in more complex domains of sorting networks and maze navigation, demonstrate AVAs efficiency over reduced virulence and the layered Pareto coevolutionary archive.

Low Dimensional Surface Parameterisation with Applications in Biometrics

This paper describes initial results from a novel low dimensional surface parameterisation approach based on a modified iterative closest point (ICP) registration process which uses vertex based principal component analysis (PCA) to incorporate a deformable element into registration process. Using this method a 3D surface is represented by a shape space vector of much smaller dimensionality than the dimensionality of the original data space vector. The proposed method is tested on both simulated 3D faces with different facial expressions and real face data. It is shown that the proposed surface representation can be potentially used as feature space for a facial expression recognition system.

Fast prediction algorithm for multiview video coding

Abstract. The H.264/multiview video coding (MVC) standard has been developed to enable efficient coding for three-dimensional and multiple viewpoint video sequences. The inter-view statistical dependencies are utilized and an inter-view prediction is employed to provide more efficient coding; however, this increases the overall encoding complexity. Motion homogeneity is exploited here to selectively enable inter-view prediction, and to reduce complexity in the motion estimation (ME) and the mode selection processes. This has been accomplished by defining situations that relate macro-blocks’ motion characteristics to the mode selection and the inter-view prediction processes. When comparing the proposed algorithm to the H.264/MVC reference software and other recent work, the experimental results demonstrate a significant reduction in ME time while maintaining similar rate-distortion performance.

Pixel decimation of RD-cost functions in the HEVC encoder

We present and analyse schemes for the improvement of computational complexity in the current HEVC (High Efficiency Video Coding) standard, by a subsampling of the block-matching distortion cost functions used in the encoding process. HEVC improves on prior standards considerably in coding (compression) efficiency, with a large set-back in time complexity for inter and intra prediction processes and mode decisions. We alleviate this by reducing the number of calculations per decision in all modes of prediction, through pixel decimation in the SAD and SSE distortion cost functions. Experimentation with different patterns shows significant encoding time reduction with these schemes, used in tandem with built-in Fast Encoding optimizations in the HEVC reference implementation.

Fast Adaptive Hierarchical Prediction Algorithm for H.264/AVC Scalable Video Coding

The objective of scalable video coding (SVC) is to enable the generation of a unique bitstream that can adapt to various bit-rates, transmission channels and display capabilities. The scalability is categorised in terms of temporal, spatial, and quality. In order to improve encoding efficiency, the SVC scheme incorporates inter-layer prediction mechanisms to complement the H.264/AVC very refined Motion Estimation (ME) and mode decision processes. However, this further increases the overall encoding complexity of the scalable coding standard. In this paper several conditional probabilities are established relating motion estimation characteristics and the mode distribution at different layers of the H.264/SVC. An evaluation of these probabilities is used to structure a low-complexity prediction algorithm for Group of Pictures (GOP) in H.264/SVC, reducing computational complexity whilst maintaining similar RD performance. When compared to the JSVM software, the proposed algorithm achieves a significant reduction of encoding time, with a negligible average PSNR loss and bit-rate increase in temporal, spatial and SNR scalability. Experiments are conducted to provide a comparison between our method and recently developed fast mode selection algorithms. These demonstrate the proposed method achieves appreciable time savings for scalable spatial and scalable quality video coding, while maintaining similar PSNR and bit rate.

Fast mode decision for the H.264/AVC video coding standard based on frequency domain motion estimation

The H.264 video coding standard achieves high performance compression and image quality at the expense of increased encoding complexity. Consequently, several fast mode decision and motion estimation techniques have been developed to reduce the computational cost. These approaches successfully reduce the computational time by reducing the image quality and/or increasing the bitrate. In this paper we propose a novel fast mode decision and motion estimation technique. The algorithm utilizes preprocessing frequency domain motion estimation in order to accurately predict the best mode and the search range. Experimental results show that the proposed algorithm significantly reduces the motion estimation time by up to 97%, while maintaining similar rate distortion performance when compared to the Joint Model software.

Low Complexity Hierarchical Prediction Algorithm for H.264/SVC

In the scalable video coding extension of the H.264/AVC standard, an exhaustive search technique is used to select the best coding mode for each macroblock. This technique achieves the highest possible coding efficiency, but it demands a higher video encoding computational complexity which constrains its use in many practical applications. This paper proposes combined fast sub-pixel motion estimation and a fast mode decision algorithm for inter-frame coding for temporal, spatial, and coarse grain signal-to-noise ratio scalability. It makes use of correlation between the macroblock and its enclosed partitions at different layers. Experimental results show that the scheme reduces the computational complexity significantly with negligible coding loss and bit-rate increases when compared to JSVM 9.15 and recently reported fast mode decision algorithms.

Selective application of sub-pixel motion estimation and Hadamard transform in H.264/AVC

In this paper, we propose an algorithm for selective application of sub-pixel Motion Estimation and Hadamard transform in the H.264/AVC video coding standard. The algorithm exploits the spatial interpolation effect of the reference slices on the best matches of different block sizes in order to increase the computational efficiency of the overall motion estimation process. Experimental results show that the proposed algorithm significantly reduces the CPU cycles in the Fast-Full-Search Motion Estimation Scheme by up to 8.2% with similar RD performance, as compared to the H.264/AVC standard.