Human action recognition using a fast learning fully complex-valued classifier

In this paper, we use optical flow based complex-valued features extracted from video sequences to recognize human actions. The optical flow features between two image planes can be appropriately represented in the Complex plane. Therefore, we argue that motion information that is used to model the human actions should be represented as complex-valued features and propose a fast learning fully complex-valued neural classifier to solve the action recognition task. The classifier, termed as, ``fast learning fully complex-valued neural (FLFCN) classifier'' is a single hidden layer fully complex-valued neural network. The neurons in the hidden layer employ the fully complex-valued activation function of the type of a hyperbolic secant function. The parameters of the hidden layer are chosen randomly and the output weights are estimated as the minimum norm least square solution to a set of linear equations. The results indicate the superior performance of FLFCN classifier in recognizing the actions compared to real-valued support vector machines and other existing results in the literature. Complex valued representation of 2D motion and orthogonal decision boundaries boost the classification performance of FLFCN classifier. (c) 2012 Elsevier B.V. All rights reserved.

Fully complex-valued ELM classifiers for human action recognition

In this paper, we present a fast learning neural network classifier for human action recognition. The proposed classifier is a fully complex-valued neural network with a single hidden layer. The neurons in the hidden layer employ the fully complex-valued hyperbolic secant as an activation function. The parameters of the hidden layer are chosen randomly and the output weights are estimated analytically as a minimum norm least square solution to a set of linear equations. The fast leaning fully complex-valued neural classifier is used for recognizing human actions accurately. Optical flow-based features extracted from the video sequences are utilized to recognize 10 different human actions. The feature vectors are computationally simple first order statistics of the optical flow vectors, obtained from coarse to fine rectangular patches centered around the object. The results indicate the superior performance of the complex-valued neural classifier for action recognition. The superior performance of the complex neural network for action recognition stems from the fact that motion, by nature, consists of two components, one along each of the axes.

Robust tracking with interest points: A sparse representation approach

Visual tracking is an important task in various computer vision applications including visual surveillance, human computer interaction, event detection, video indexing and retrieval. Recent state of the art sparse representation (SR) based trackers show better robustness than many of the other existing trackers. One of the issues with these SR trackers is low execution speed. The particle filter framework is one of the major aspects responsible for slow execution, and is common to most of the existing SR trackers. In this paper,(1) we propose a robust interest point based tracker in l(1) minimization framework that runs at real-time with performance comparable to the state of the art trackers. In the proposed tracker, the target dictionary is obtained from the patches around target interest points. Next, the interest points from the candidate window of the current frame are obtained. The correspondence between target and candidate points is obtained via solving the proposed l(1) minimization problem. In order to prune the noisy matches, a robust matching criterion is proposed, where only the reliable candidate points that mutually match with target and candidate dictionary elements are considered for tracking. The object is localized by measuring the displacement of these interest points. The reliable candidate patches are used for updating the target dictionary. The performance and accuracy of the proposed tracker is benchmarked with several complex video sequences. The tracker is found to be considerably fast as compared to the reported state of the art trackers. The proposed tracker is further evaluated for various local patch sizes, number of interest points and regularization parameters. The performance of the tracker for various challenges including illumination change, occlusion, and background clutter has been quantified with a benchmark dataset containing 50 videos. (C) 2014 Elsevier B.V. All rights reserved.

An adaptive decomposition method for video

Scalable video coding (SVC) is an emerging standard built on the success of advanced video coding standard (H.264/AVC) by the Joint video team (JVT). Motion compensated temporal filtering (MCTF) and Closed loop hierarchical B pictures (CHBP) are two important coding methods proposed during initial stages of standardization. Either of the coding methods, MCTF/CHBP performs better depending upon noise content and characteristics of the sequence. This work identifies other characteristics of the sequences for which performance of MCTF is superior to that of CHBP and presents a method to adaptively select either of MCTF and CHBP coding methods at the GOP level. This method, referred as "Adaptive Decomposition" is shown to provide better R-D performance than of that by using MCTF or CRBP only. Further this method is extended to non-scalable coders.

Memory Bandwidth and Power Reduction Using Lossy Reference Frame Compression in Video Encoding

Large external memory bandwidth requirement leads to increased system power dissipation and cost in video coding application. Majority of the external memory traffic in video encoder is due to reference data accesses. We describe a lossy reference frame compression technique that can be used in video coding with minimal impact on quality while significantly reducing power and bandwidth requirement. The low cost transformless compression technique uses lossy reference for motion estimation to reduce memory traffic, and lossless reference for motion compensation (MC) to avoid drift. Thus, it is compatible with all existing video standards. We calculate the quantization error bound and show that by storing quantization error separately, bandwidth overhead due to MC can be reduced significantly. The technique meets key requirements specific to the video encode application. 24-39% reduction in peak bandwidth and 23-31% reduction in total average power consumption are observed for IBBP sequences.

SPSA Based Feature Relevance Estimation For Video Retrieval

With the availability of a huge amount of video data on various sources, efficient video retrieval tools are increasingly in demand. Video being a multi-modal data, the perceptions of ``relevance'' between the user provided query video (in case of Query-By-Example type of video search) and retrieved video clips are subjective in nature. We present an efficient video retrieval method that takes user's feedback on the relevance of retrieved videos and iteratively reformulates the input query feature vectors (QFV) for improved video retrieval. The QFV reformulation is done by a simple, but powerful feature weight optimization method based on Simultaneous Perturbation Stochastic Approximation (SPSA) technique. A video retrieval system with video indexing, searching and relevance feedback (RF) phases is built for demonstrating the performance of the proposed method. The query and database videos are indexed using the conventional video features like color, texture, etc. However, we use the comprehensive and novel methods of feature representations, and a spatio-temporal distance measure to retrieve the top M videos that are similar to the query. In feedback phase, the user activated iterative on the previously retrieved videos is used to reformulate the QFV weights (measure of importance) that reflect the user's preference, automatically. It is our observation that a few iterations of such feedback are generally sufficient for retrieving the desired video clips. The novel application of SPSA based RF for user-oriented feature weights optimization makes the proposed method to be distinct from the existing ones. The experimental results show that the proposed RF based video retrieval exhibit good performance.

x-ray studies on crystalline complexes involving amino-acids and peptides .10. head-to-tail sequences in the crystal-structure of l-lysine acetate

l-Lysine acetate crystallises in the monoclinic space group P21 with a = 5.411 (1), b = 7.562(1), c= l2.635(2) Å and β = 91.7(1). The crystal structure was solved by direct methods and refined to an R value of 0.049 using the full matrix least squares method. The conformation and the aggregation of lysine molecules in the structure are similar to those found in the crystal structure of l-lysine l-aspartate. A conspicuous similarity between the crystal structures of l-arginine acetate and l-lysine acetate is that in both cases the strongly basic side chain, although having the largest pK value, interacts with the weakly acidic acetate group leaving the α-amino and the α-carboxylate groups to take part in head-to-tail sequences. These structures thus indicate that electrostatic effects are strongly modulated by other factors so as to give rise to head-to-tail sequences which have earlier been shown to be an almost universal feature of amino acid aggregation in the solid state.

Solution conformations of penta and heptapeptides containing repetitive α-aminoisobutyryl-Image -alanyl and α -aminoisobutyryl-Image -valyl sequences

The presence of folded solution conformations in the peptides Boc-Ala-(Aib-Ala)2-OMe, Boc-Val-(Aib-Val) 2-OMe, Boc-Ala-(Aib-Ala)3-OMe and Boc-Val-(Aib-Val)3-OMe has been established by 270MHz 1H NMR. Intramolecularly H-bonded NH groups have been identified using temperature and solvent dependence of NH chemical shifts and paramagnetic radical induced broadening of NH resonances. Both pentapeptides adopt 310 helical conformations possessing 3 intramolecular H-bonds in CDCl3 and (CD3)2SO. The heptapeptides favour helical structures with 5 H-bonds in CDCl3. In (CD3)2SO only 4 H-bonds are readily detected.

Effects Of 5' Flanking Sequences And Changes In The 5' Internal Control Region On The Transcription Of Rice Transfer-Rna Gcc Cly Gene

A stretch of 71 nucleotides in a 1.2 kilobase pair Pst I fragment of rice DNA was identified as tRNA~ gene by hybridization and nucleotide sequence analyses. The hybridization of genomic DNA with the tRNA gene showed that there are about 10 glycine tRNA genes per diploid rice genome. The 3' and 5' internal control regions, where RNA polymerase III and transcription factors bind, were found to be present in the coding sequence. The gene was transcribed into a 4S product in an yeast cell-free extract. The substitution of 5' internal control region with analogous sequences from either M13mpl9 or M13mpl8 DNA did not affect the transcription of the gene in vitro. The changes in three highly conserved nucleotides in the consensus 5' internal control region (RGYNNARYGG; R = purine, Y = pyrimidine, N = any nucleotide) did not affect transcription showing that these nucleotides are not essential for promotion of transcription. There were two 16 base pair repeats, 'TGTTTGTTTCAGCTTA' at - 130 and - 375 positions upstream from the start of the gene. Deletion of 5' flanking sequences including the 16 base pair repeat at - 375 showed increased transcription indicating that these sequences negatively modulate the expression of the gene.

Bi-criteria single machine scheduling problem with a learning effect: Aneja-Nair method to obtain the set of optimal sequences

In this paper, we consider the bi-criteria single machine scheduling problem of n jobs with a learning effect. The two objectives considered are the total completion time (TC) and total absolute differences in completion times (TADC). The objective is to find a sequence that performs well with respect to both the objectives: the total completion time and the total absolute differences in completion times. In an earlier study, a method of solving bi-criteria transportation problem is presented. In this paper, we use the methodology of solvin bi-criteria transportation problem, to our bi-criteria single machine scheduling problem with a learning effect, and obtain the set of optimal sequences,. Numerical examples are presented for illustrating the applicability and ease of understanding.

Sequences that adopt non-B-DNA conformation in form V DNA as probed by enzymic methylation

pBR322 form V DNA is a highly torsionally strained molecule with a linking number of zero. We have used sequence- specific DNA methylases as probes for B-DNA in this molecule, exploiting the inability of methylases to methylate single-stranded DNA and Z-DNA, both of which are known to occur in form V DNA. Some sequences in form V DNA were shown to be totally in the B-form, others were totally in an altered, unmethylatable conformation, while still other sites appeared to exist partly in altered and partly in normal B-conformation. Some potential Z-forming sequences (alternating pyrimidine/purine) of less than seven base-pairs were not in the Z conformation in form V DNA, whereas others did adopt an altered structure, indicating a modulating influence of flanking sequences. Furthermore, regions of imperfect alternating pyrimidine/purine structure were sometimes capable of adopting an altered structure. In addition, some regions of altered structure had no apparent Z-forming sequences, nor were they in polypurine stretches, which have also been proposed to form left-handed DNA. These non-B-DNA conformations may represent novel left-handed helical structures or sequences that become single stranded under torsional strain. Long regions of either altered (unmethylatable) DNA or B-DNA were not always observed. In fact, one region showed three transitions between B-like DNA and altered structure within 26 base-pairs.

X-Pro peptides. A theoretical study of the hydrogen bonded conformations of (alpha-aminoisobutyryl-L -prolyl)n sequences

Intramolecularly hydrogen bonded conformations of (Aib-Pro)n sequences have been analysed theoretically. Both 4-1 (C10 and 3-1 (C7 hydrogen bonded regular structures are shown to be stereochemically feasible. Conformational energies for the helical structures have been estimated using classical potential energy methods. Both C10 and C7 conformations have very similar energies. Pyrrolidine ring puckering has a pronounced effect on the energies, and only Cv-endo puckered Pro residues can be accommodated. The theoretical calculations using spectroscopic data suggest that the recently proposed novel 310 helical conformation for benzyloxycarbonyl(Aib-Pro)4-methyl ester is in solution, is indeed energetically and stereochemically favourable.

X-Pro peptides. A theoretical study of the hydrogen bonded conformations of (a-aminoisobutyryl-L -prolyl)n sequences

Intramolecularly hydrogen bonded conformations of (Aib-Pro)n sequences have been analysed theoretically. Both 4�1 (C10 and 3�1 (C7 hydrogen bonded regular structures are shown to be stereochemically feasible. Conformational energies for the helical structures have been estimated using classical potential energy methods. Both C10 and C7 conformations have very similar energies. Pyrrolidine ring puckering has a pronounced effect on the energies, and only Cγ-endo puckered Pro residues can be accommodated. The theoretical calculations using spectroscopic data suggest that the recently proposed novel 310 helical conformation for benzyloxycarbonyl(Aib-Pro)4-methyl ester is in solution, is indeed energetically and stereochemically favourable.

Optical Barker sequences and self-orthogonal convolutional codes

The relation between optical Barker codes and self-orthogonal convolutional codes is pointed out. It is then used to update the results in earlier publication.

Multilevel aperiodic Huffman sequences

Certain sequences that have zero aperiodic autocorrelation except for zero and the maximum shifts are described. They are useful in radar pulse compression.