Robust polynomial classifier using <Emphasis Type="Italic">L</Emphasis><Superscript>1</Superscript>-<Emphasis Type="Italic">norm</Emphasis> minimization

In this paper we present a robust polynomial classifier based on L ¹-norm minimization. We do so by reformulating the classifier training process as a linear programming problem. Due to the inherent insensitivity of the L ¹-norm to influential observations, class models obtained via L ¹-norm minimization are much more robust than their counterparts obtained by the classical least squares minimization (L ²-norm). For validation purposes, we apply this method to two recognition problems: character recognition and sign language recognition. Both are examined under different signal to noise ratio (SNR) values of the test data. Results show that L ¹-norm minimization provides superior recognition rates over L ²-norm minimization when the training data contains influential observations especially if the test dataset is noisy.     

Embedded SNR multilayer video transcoding with MPEG-2 compliancy

Proposed are various codec architectures for encoding the quantisation error of MPEG-2 base layer transcoders using embedded bitstreams technologies. An existing solution based on fine granular scalability is reviewed and amended resulting in drift-free picture decoding. Likewise, two new approaches to MPEG-2 SNR scalability based on JPEG2000 (J2k) coding technology are proposed. It is shown that no modifications are required for MPEG-2-compliant single-layer decoders whilst replacing the static (not adaptable) MPEG-2 SNR video layers with embedded bitstreams.     

Hybrid M-JPEG/MPEG-2 video streams using MPEG-2 compliant spatial scalability

The MPEG-2 video content has become very popular. In an attempt to make this widely available content flexible in terms of meeting the constraints of an assortment of networks and end-systems, the bitstream syntax of MPEG-2 spatial scalability is utilised to generate a hybrid embedded motion-JPEG/MPEG-2 video stream from prerecorded contents. A report is made on the proposed codec architecture and the experimental results are elaborated     

Spatio-temporal feature-extraction techniques for isolated gesture recognition in Arabic sign language.

This paper presents various spatio-temporal feature-extraction techniques with applications to online and offline recognitions of isolated Arabic Sign Language gestures. The temporal features of a video-based gesture are extracted through forward, backward, and bidirectional predictions. The prediction errors are thresholded and accumulated into one image that represents the motion of the sequence. The motion representation is then followed by spatial-domain feature extractions. As such, the temporal dependencies are eliminated and the whole video sequence is represented by a few coefficients. The linear separability of the extracted features is assessed, and its suitability for both parametric and nonparametric classification techniques is elaborated upon. The proposed feature-extraction scheme was complemented by simple classification techniques, namely, K nearest neighbor (KNN) and Bayesian, i.e., likelihood ratio, classifiers. Experimental results showed classification performance ranging from 97% to 100% recognition rates. To validate our proposed technique, we have conducted a series of experiments using the classical way of classifying data with temporal dependencies, namely, hidden Markov models (HMMs). Experimental results revealed that the proposed feature-extraction scheme combined with simple KNN or Bayesian classification yields comparable results to the classical HMM-based scheme. Moreover, since the proposed scheme compresses the motion information of an image sequence into a single image, it allows for using simple classification techniques where the temporal dimension is eliminated. This is actually advantageous for both computational and storage requirements of the classifier.     

Multilayer transcoding with format portability for multicasting of single-layered video

This paper proposes a novel multilayer video transcoding approach for multicasting pre-encoded video to heterogeneous end-systems via diverse grouping of networks. Multilayer transcoding is first addressed by means of multiquality or SNR scalability of the MPEG-2 standard. Frequency domain transcoding and drift-compensated transcoding are derived from the closed-loop and multiloop SNR scalabilities, respectively. The proposed transcoding architectures are verified in terms of eliminating picture drift whilst preserving compatibility with the MPEG-2 SNR decoder. Multilayer transcoding is then addressed by means of multiresolution or spatial scalability of the MPEG-2 standard that supports different video formats. The transcoder retains the full resolution of the incoming video stream in its enhancement layer while generating a low spatio-temporal resolution base-layer compatible with the H.263 video format. Hence providing both multilayer transcoding and video format portability. The resultant video layers are shown to be free from drift with PSNR results comparable to those of the respective scalable encoders.     

Heterogeneous video transcoding to lower spatio-temporalresolutions and different encoding formats

In this work, transcoding of pre-encoded MPEG-1, 2 video into lower bit rates is realized through altering the coding algorithm into H.261/H.263 standards with lower spatio-temporal resolutions. For this heterogeneous transcoding, we extract and compose a set of candidate motion vectors, from the incoming bit stream, to comply with the encoding format of the output bit stream. For the spatial resolution reduction we generate one motion vector out of a set of input motion vectors operating on the higher spatial resolution image. Finally, for the temporal resolution reduction we compose new motion vectors from the dropped frames motion vectors. Throughout the paper, we discuss the impact of motion estimation refinement on the new motion vectors and show that for all cases a simple half-pixel refinement is sufficient for near-optimum results     

Generalized first-order kinetic model for biosolids decomposition and oxidation during hydrothermal treatment

The main objective of this study was to develop generalized first-order kinetic models to represent hydrothermal decomposition and oxidation of biosolids within a wide range of temperatures (200-450 degrees C). A lumping approach was used in which oxidation of the various organic ingredients was characterized by the chemical oxygen demand (COD), and decomposition was characterized by the particulate (i.e., nonfilterable) chemical oxygen demand (PCOD). Using the Arrhenius equation (k = k(o)e(-Ea/RT)), activation energy (Ea) levels were derived from 42 continuous-flow hydrothermal treatment experiments conducted at temperatures in the range of 200-450 degrees C. Using predetermined values for k(o) in the Arrhenius equation, the activation energies of the various organic ingredients were separated into 42 values for oxidation and a similar number for decomposition. The activation energy values were then classified into levels representing the relative ease at which the organic ingredients of the biosolids were oxidized or decomposed. The resulting simple first-order kinetic models adequately represented, within the experimental data range, hydrothermal decomposition of the organic particles as measured by PCOD and oxidation of the organic content as measured by COD. The modeling approach presented in the paper provide a simple and general framework suitable for assessing the relative reaction rates of the various organic ingredients of biosolids.     

Saliency detection in MPEG and HEVC video using intra-frame and inter-frame distances

This paper proposes a video saliency detection model for MPEG and HEVC coded videos. The model extracts features from MPEG macroblocks and HEVC coding units. The feature variables are based on syntax elements and statistics of prediction error. The suitability of the selected features is verified through the use of stepwise regression. Three saliency maps are generated based on intra-frame distances, inter-frame distances and global distances. The proposed model is tested using the eye-1 dataset compiled by Laurent Itti Lab in the University of Southern California. The accuracy of the model is quantified by comparing saliency values at human saccade locations against saliency values at random locations. The comparison is performed in terms of Kullback–Leibler distances and receiver operator curves. The proposed solution is compared against existing work using similar experimental setup. Experimental results revealed that a Kullback–Leibler distance of 2.14 and area under the receiver operator curve of 0.936 are achieved.     

Matrix encoding for data hiding using multilayer video coding and transcoding solutions

This paper proposes a multitier data hiding solution in MPEG video using matrix encoding. In the first tier of the proposed solution, raw video is encoded into two layers using multilayer Signal to Noise Ratio (SNR) encoding. During the multilayer encoding process, the quantization scales and coding parameters are stored. In the second tier, message bits are embedded in the stored quantization scales using matrix encoding. In the third and last tier, the raw video is encoded again into two layers using the modulated quantization scales and coding parameters of the first encoder. The proposed multitier solution is extended by replacing the multilayer encoder with a multilayer transcoder to accommodate situations in which the video exists in pre-coded format only. By the use of multilayer encoder or transcoding, we show that the message payload can be doubled without adversely affecting the coding quality or bitrate of the host video. We also show that message embedding using matrix encoding can be extended to modulate motion vectors. The paper also proposes two solutions for motion vector modulation based on the availability of the raw video. In comparison to existing work, the proposed solutions have higher message payloads, lower degradation in video quality and result in reduced excessive bitrate.