A survey on compressed domain video analysis techniques

Image and video analysis requires rich features that can characterize various aspects of visual information. These rich features are typically extracted from the pixel values of the images and videos, which require huge amount of computation and seldom useful for real-time analysis. On the contrary, the compressed domain analysis offers relevant information pertaining to the visual content in the form of transform coefficients, motion vectors, quantization steps, coded block patterns with minimal computational burden. The quantum of work done in compressed domain is relatively much less compared to pixel domain. This paper aims to survey various video analysis efforts published during the last decade across the spectrum of video compression standards. In this survey, we have included only the analysis part, excluding the processing aspect of compressed domain. This analysis spans through various computer vision applications such as moving object segmentation, human action recognition, indexing, retrieval, face detection, video classification and object tracking in compressed videos.

EXACT INTERNAL CONTROLLABILITY FOR THE WAVE EQUATION IN A DOMAIN WITH OSCILLATING BOUNDARY WITH NEUMANN BOUNDARY CONDITION

In this paper, we study the exact controllability of a second order linear evolution equation in a domain with highly oscillating boundary with homogeneous Neumann boundary condition on the oscillating part of boundary. Our aim is to obtain the exact controllability for the homogenized equation. The limit problem with Neumann condition on the oscillating boundary is different and hence we need to study the exact controllability of this new type of problem. In the process of homogenization, we also study the asymptotic analysis of evolution equation in two setups, namely solution by standard weak formulation and solution by transposition method.

Archeal lectins: An identification through a genomic search

Forty-six lectin domains which have homologues among well established eukaryotic and bacterial lectins of known three-dimensional structure, have been identified through a search of 165 archeal genomes using a multipronged approach involving domain recognition, sequence search and analysis of binding sites. Twenty-one of them have the 7-bladed -propeller lectin fold while 16 have the -trefoil fold and 7 the legume lectin fold. The remainder assumes the C-type lectin, the -prism I and the tachylectin folds. Acceptable models of almost all of them could be generated using the appropriate lectins of known three-dimensional structure as templates, with binding sites at one or more expected locations. The work represents the first comprehensive bioinformatic study of archeal lectins. The presence of lectins with the same fold in all domains of life indicates their ancient origin well before the divergence of the three branches. Further work is necessary to identify archeal lectins which have no homologues among eukaryotic and bacterial species. Proteins 2016; 84:21-30. (c) 2015 Wiley Periodicals, Inc.

A coupled discriminative dictionary and transformation learning approach with applications to cross domain matching

Cross domain and cross-modal matching has many applications in the field of computer vision and pattern recognition. A few examples are heterogeneous face recognition, cross view action recognition, etc. This is a very challenging task since the data in two domains can differ significantly. In this work, we propose a coupled dictionary and transformation learning approach that models the relationship between the data in both domains. The approach learns a pair of transformation matrices that map the data in the two domains in such a manner that they share common sparse representations with respect to their own dictionaries in the transformed space. The dictionaries for the two domains are learnt in a coupled manner with an additional discriminative term to ensure improved recognition performance. The dictionaries and the transformation matrices are jointly updated in an iterative manner. The applicability of the proposed approach is illustrated by evaluating its performance on different challenging tasks: face recognition across pose, illumination and resolution, heterogeneous face recognition and cross view action recognition. Extensive experiments on five datasets namely, CMU-PIE, Multi-PIE, ChokePoint, HFB and IXMAS datasets and comparisons with several state-of-the-art approaches show the effectiveness of the proposed approach. (C) 2015 Elsevier B.V. All rights reserved.

A coupled discriminative dictionary and transformation learning approach with applications to cross domain matching

Cross domain and cross-modal matching has many applications in the field of computer vision and pattern recognition. A few examples are heterogeneous face recognition, cross view action recognition, etc. This is a very challenging task since the data in two domains can differ significantly. In this work, we propose a coupled dictionary and transformation learning approach that models the relationship between the data in both domains. The approach learns a pair of transformation matrices that map the data in the two domains in such a manner that they share common sparse representations with respect to their own dictionaries in the transformed space. The dictionaries for the two domains are learnt in a coupled manner with an additional discriminative term to ensure improved recognition performance. The dictionaries and the transformation matrices are jointly updated in an iterative manner. The applicability of the proposed approach is illustrated by evaluating its performance on different challenging tasks: face recognition across pose, illumination and resolution, heterogeneous face recognition and cross view action recognition. Extensive experiments on five datasets namely, CMU-PIE, Multi-PIE, ChokePoint, HFB and IXMAS datasets and comparisons with several state-of-the-art approaches show the effectiveness of the proposed approach. (C) 2015 Elsevier B.V. All rights reserved.

Physiological role of FolD (methylenetetrahydrofolate dehydrogenase), FchA (methenyltetrahydrofolate cyclohydrolase) and Fhs (formyltetrahydrofolate synthetase) from Clostridium perfringens in a heterologous model of Escherichia coli

Most organisms possess bifunctional FolD 5,10-methylenetetrahydrofolate (5,10-CH2-THF) dehydrogenase-cyclohydrolase] to generate NADPH and 10-formyltetrandrofolate (10-CHO-THF) required in various metabolic steps. In addition, some organisms including Clostridium perfringens possess another protein, Fhs (formyltetrahydrofolate synthetase), to synthesize 10-CHO-THF. Here, we show that unlike the bifunctional FolD of Escherichia coli (Eco FolD), and contrary to its annotated bifunctional nature, C. perfringens FolD (Cpe FoID) is a monofunctional 5,10-CH2-THF dehydrogenase. The dehydrogenase activity of Cpe FoID is about five times more efficient than that of Eco FolD. The 5,10-methenyltetrahydrofolate (5,10-CH+-THF) cyclohydrolase activity in C. perfringens is provided by another protein, FchA (5,10-CH+-THF cyclohydrolase), whose cyclohydrolase activity is similar to 10 times more efficient than that of Eco FolD. Kinetic parameters for Cpe Fhs were also determined for utilization of all of its substrates. Both Cpe FoID and Cpe FchA are required to substitute for the single bifunctional FolD in E. coli. The simultaneous presence of Cpe FoID and Cpe FchA is also necessary to rescue an E coli folD deletion strain (harbouring Cpe Fhs support) for its formate and glycine auxotrophies, and to alleviate its susceptibility to trimethoprim (an antifolate drug) or UV light. The presence of the three clostridial proteins (FolD, FchA and Fhs) is required to maintain folate homeostasis in the cell.

Anomalous reduction in domain wall displacement at the morphotropic phase boundary of the piezoelectric alloy system PbTiO3-BiScO3

A comparative study of field-induced domain switching and lattice strain was carried out by in situ electric-field-dependent high-energy synchrotron x-ray diffraction on a morphotropic phase boundary (MPB) and a near-MPB rhombohedral/pseudomonoclinic composition of a high-performance piezoelectric alloy (1-x) PbTiO3-(x)BiScO3. It is demonstrated that the MPB composition showing large d(33) similar to 425 pC/N exhibits significantly reduced propensity of field-induced domain switching as compared to the non-MPB rhombohedral composition (d(33) similar to 260 pC/N). These experimental observations contradict the basic premise of the martensitic-theory-based explanation which emphasizes on enhanced domain wall motion as the primary factor for the anomalous piezoelectric response in MPB piezoelectrics. Our results favor field-induced structural transformation to be the primary mechanism contributing to the large piezoresponse of the critical MPB composition of this system.

CROWD FLOW SEGMENTATION IN COMPRESSED DOMAIN USING CRF

Crowd flow segmentation is an important step in many video surveillance tasks. In this work, we propose an algorithm for segmenting flows in H.264 compressed videos in a completely unsupervised manner. Our algorithm works on motion vectors which can be obtained by partially decoding the compressed video without extracting any additional features. Our approach is based on modelling the motion vector field as a Conditional Random Field (CRF) and obtaining oriented motion segments by finding the optimal labelling which minimises the global energy of CRF. These oriented motion segments are recursively merged based on gradient across their boundaries to obtain the final flow segments. This work in compressed domain can be easily extended to pixel domain by substituting motion vectors with motion based features like optical flow. The proposed algorithm is experimentally evaluated on a standard crowd flow dataset and its superior performance in both accuracy and computational time are demonstrated through quantitative results.

ON THE UTILITY OF CANONICAL CORRELATION ANALYSIS FOR DOMAIN ADAPTATION IN MULTI-VIEW HEADPOSE ESTIMATION

The utility of canonical correlation analysis (CCA) for domain adaptation (DA) in the context of multi-view head pose estimation is examined in this work. We consider the three problems studied in 1], where different DA approaches are explored to transfer head pose-related knowledge from an extensively labeled source dataset to a sparsely labeled target set, whose attributes are vastly different from the source. CCA is found to benefit DA for all the three problems, and the use of a covariance profile-based diagonality score (DS) also improves classification performance with respect to a nearest neighbor (NN) classifier.