User-driven saliency maps for evaluating Region-of-Interest detection

Detection of Region of Interest (ROI) in a video leads to more efficient utilization of bandwidth. This is because any ROIs in a given frame can be encoded in higher quality than the rest of that frame, with little or no degradation of quality from the perception of the viewers. Consequently, it is not necessary to uniformly encode the whole video in high quality. One approach to determine ROIs is to use saliency detectors to locate salient regions. This paper proposes a methodology for obtaining ground truth saliency maps to measure the effectiveness of ROI detection by considering the role of user experience during the labelling process of such maps. User perceptions can be captured and incorporated into the definition of salience in a particular video, taking advantage of human visual recall within a given context. Experiments with two state-of-the-art saliency detectors validate the effectiveness of this approach to validating visual saliency in video. This paper will provide the relevant datasets associated with the experiments.

Robust suspicious behaviour detection for smart surveillance systems

Video surveillance technology, based on Closed Circuit Television (CCTV) cameras, is one of the fastest growing markets in the field of security technologies. However, the existing video surveillance systems are still not at a stage where they can be used for crime prevention. The systems rely heavily on human observers and are therefore limited by factors such as fatigue and monitoring capabilities over long periods of time. To overcome this limitation, it is necessary to have “intelligent” processes which are able to highlight the salient data and filter out normal conditions that do not pose a threat to security. In order to create such intelligent systems, an understanding of human behaviour, specifically, suspicious behaviour is required. One of the challenges in achieving this is that human behaviour can only be understood correctly in the context in which it appears. Although context has been exploited in the general computer vision domain, it has not been widely used in the automatic suspicious behaviour detection domain. So, it is essential that context has to be formulated, stored and used by the system in order to understand human behaviour. Finally, since surveillance systems could be modeled as largescale data stream systems, it is difficult to have a complete knowledge base. In this case, the systems need to not only continuously update their knowledge but also be able to retrieve the extracted information which is related to the given context. To address these issues, a context-based approach for detecting suspicious behaviour is proposed. In this approach, contextual information is exploited in order to make a better detection. The proposed approach utilises a data stream clustering algorithm in order to discover the behaviour classes and their frequency of occurrences from the incoming behaviour instances. Contextual information is then used in addition to the above information to detect suspicious behaviour. The proposed approach is able to detect observed, unobserved and contextual suspicious behaviour. Two case studies using video feeds taken from CAVIAR dataset and Z-block building, Queensland University of Technology are presented in order to test the proposed approach. From these experiments, it is shown that by using information about context, the proposed system is able to make a more accurate detection, especially those behaviours which are only suspicious in some contexts while being normal in the others. Moreover, this information give critical feedback to the system designers to refine the system. Finally, the proposed modified Clustream algorithm enables the system to both continuously update the system’s knowledge and to effectively retrieve the information learned in a given context. The outcomes from this research are: (a) A context-based framework for automatic detecting suspicious behaviour which can be used by an intelligent video surveillance in making decisions; (b) A modified Clustream data stream clustering algorithm which continuously updates the system knowledge and is able to retrieve contextually related information effectively; and (c) An update-describe approach which extends the capability of the existing human local motion features called interest points based features to the data stream environment.

Comparison of koala LPCoLN and human strains of Chlamydia pneumoniae highlights extended genetic diversity in the species

Background Chlamydia pneumoniae is a widespread pathogen causing upper and lower respiratory tract infections in addition to a range of other diseases in humans and animals. Previous whole genome analyses have focused on four essentially clonal (> 99% identity) C. pneumoniae human genomes (AR39, CWL029, J138 and TW183), providing relatively little insight into strain diversity and evolution of this species. Results We performed individual gene-by-gene comparisons of the recently sequenced C. pneumoniae koala genome and four C. pneumoniae human genomes to identify species-specific genes, and more importantly, to gain an insight into the genetic diversity and evolution of the species. We selected genes dispersed throughout the chromosome, representing genes that were specific to C. pneumoniae, genes with a demonstrated role in chlamydial biology and/or pathogenicity (n = 49), genes encoding nucleotide salvage or amino acid biosynthesis proteins (n = 6), and extrachromosomal elements (9 plasmid and 2 bacteriophage genes). Conclusions We have identified strain-specific differences and targets for detection of C. pneumoniae isolates from both human and animal origin. Such characterisation is necessary for an improved understanding of disease transmission and intervention.

Visual voice activity detection using frontal versus profile views

Visual activity detection of lip movements can be used to overcome the poor performance of voice activity detection based solely in the audio domain, particularly in noisy acoustic conditions. However, most of the research conducted in visual voice activity detection (VVAD) has neglected addressing variabilities in the visual domain such as viewpoint variation. In this paper we investigate the effectiveness of the visual information from the speaker’s frontal and profile views (i.e left and right side views) for the task of VVAD. As far as we are aware, our work constitutes the first real attempt to study this problem. We describe our visual front end approach and the Gaussian mixture model (GMM) based VVAD framework, and report the experimental results using the freely available CUAVE database. The experimental results show that VVAD is indeed possible from profile views and we give a quantitative comparison of VVAD based on frontal and profile views The results presented are useful in the development of multi-modal Human Machine Interaction (HMI) using a single camera, where the speaker’s face may not always be frontal.

Neural differentiation potential of human bone marrow-derived mesenchymal stromal cells: misleading marker gene expression

Background In contrast to pluripotent embryonic stem cells, adult stem cells have been considered to be multipotent, being somewhat more restricted in their differentiation capacity and only giving rise to cell types related to their tissue of origin. Several studies, however, have reported that bone marrow-derived mesenchymal stromal cells (MSCs) are capable of transdifferentiating to neural cell types, effectively crossing normal lineage restriction boundaries. Such reports have been based on the detection of neural-related proteins by the differentiated MSCs. In order to assess the potential of human adult MSCs to undergo true differentiation to a neural lineage and to determine the degree of homogeneity between donor samples, we have used RT-PCR and immunocytochemistry to investigate the basal expression of a range of neural related mRNAs and proteins in populations of non-differentiated MSCs obtained from 4 donors. Results The expression analysis revealed that several of the commonly used marker genes from other studies like nestin, Enolase2 and microtubule associated protein 1b (MAP1b) are already expressed by undifferentiated human MSCs. Furthermore, mRNA for some of the neural-related transcription factors, e.g. Engrailed-1 and Nurr1 were also strongly expressed. However, several other neural-related mRNAs (e.g. DRD2, enolase2, NFL and MBP) could be identified, but not in all donor samples. Similarly, synaptic vesicle-related mRNA, STX1A could only be detected in 2 of the 4 undifferentiated donor hMSC samples. More significantly, each donor sample revealed a unique expression pattern, demonstrating a significant variation of marker expression. Conclusion The present study highlights the existence of an inter-donor variability of expression of neural-related markers in human MSC samples that has not previously been described. This donor-related heterogeneity might influence the reproducibility of transdifferentiation protocols as well as contributing to the ongoing controversy about differentiation capacities of MSCs. Therefore, further studies need to consider the differences between donor samples prior to any treatment as well as the possibility of harvesting donor cells that may be inappropriate for transplantation strategies.

A suspicious behaviour detection using a context space model for smart surveillance systems

Video surveillance systems using Closed Circuit Television (CCTV) cameras, is one of the fastest growing areas in the field of security technologies. However, the existing video surveillance systems are still not at a stage where they can be used for crime prevention. The systems rely heavily on human observers and are therefore limited by factors such as fatigue and monitoring capabilities over long periods of time. This work attempts to address these problems by proposing an automatic suspicious behaviour detection which utilises contextual information. The utilisation of contextual information is done via three main components: a context space model, a data stream clustering algorithm, and an inference algorithm. The utilisation of contextual information is still limited in the domain of suspicious behaviour detection. Furthermore, it is nearly impossible to correctly understand human behaviour without considering the context where it is observed. This work presents experiments using video feeds taken from CAVIAR dataset and a camera mounted on one of the buildings Z-Block) at the Queensland University of Technology, Australia. From these experiments, it is shown that by exploiting contextual information, the proposed system is able to make more accurate detections, especially of those behaviours which are only suspicious in some contexts while being normal in the others. Moreover, this information gives critical feedback to the system designers to refine the system.

Detection of tissue plasminogen activator (t-PA) and plasminogen activator inhibitor 2(PAI-2) in gingival crevicular fluid from healthy, gingivitis and periodontitis patients

Background: The regulation of plasminogen activation is a key element in controlling proteolytic events in the extracellular matrix. Our previous studies had demonstrated that in inflamed gingival tissues, tissue-type plasminogen activator (t-PA) is significantly increased in the extracellular matrix of the connective tissue and that interleukin 1β (IL-1β) can up regulate the level of t-PA and plasminogen activator inhibitor-2 (PAI-2) synthesis by human gingival fibroblasts. Method: In the present study, the levels of t-PA and PAI-2 in gingival crevicular fluid (GCF) were measured from healthy, gingivitis and periodontitis sites and compared before and after periodontal treatment. Crevicular fluid from106 periodontal sites in 33 patients were collected. 24 sites from 11 periodontitis patients received periodontal treatment after the first sample collection and post-treatment samples were collected 14 days after treatment. All samples were analyzed by enzyme-linked immunosorbent assay (ELISA) for t-PA and PAI-2. Results: The results showed that significantly high levels of t-PA and PAI-2 in GCF were found in the gingivitis and periodontitis sites. Periodontal treatment led to significant decreases of PAI-2, but not t-PA, after 14 days. A significant positive linear correlation was found between t-PA and PAI-2 in GCF (r=0.80, p<0.01). In the healthy group, different sites from within the same subject showed little variation of t-PA and PAI-2 in GCF. However, the gingivitis and periodontitis sites showed large variation. These results suggest a good correlation between t-PA and PAI-2 with the severity of periodontal conditions. Conclusion: This study indicates that t-PA and PAI-2 may play a significant rôle in the periodontal tissue destruction and tissue remodeling and that t-PA and PAI-2 in GCF may be used as clinical markers to evaluate the periodontal diseases and assess treatment.

Automatic region-of-interest detection and prioritisation for visually optimised coding of low bit rate videos

The increasing popularity of video consumption from mobile devices requires an effective video coding strategy. To overcome diverse communication networks, video services often need to maintain sustainable quality when the available bandwidth is limited. One of the strategy for a visually-optimised video adaptation is by implementing a region-of-interest (ROI) based scalability, whereby important regions can be encoded at a higher quality while maintaining sufficient quality for the rest of the frame. The result is an improved perceived quality at the same bit rate as normal encoding, which is particularly obvious at the range of lower bit rate. However, because of the difficulties of predicting region-of-interest (ROI) accurately, there is a limited research and development of ROI-based video coding for general videos. In this paper, the phase spectrum quaternion of Fourier Transform (PQFT) method is adopted to determine the ROI. To improve the results of ROI detection, the saliency map from the PQFT is augmented with maps created from high level knowledge of factors that are known to attract human attention. Hence, maps that locate faces and emphasise the centre of the screen are used in combination with the saliency map to determine the ROI. The contribution of this paper lies on the automatic ROI detection technique for coding a low bit rate videos which include the ROI prioritisation technique to give different level of encoding qualities for multiple ROIs, and the evaluation of the proposed automatic ROI detection that is shown to have a close performance to human ROI, based on the eye fixation data.

Determining the detection capabilities of existing real time measurement techniques for different engineered nanoparticles

The application of nanotechnology products has increased significantly in recent years. With their broad range of applications, including electronics, food and agriculture, power and energy, scientific instruments, clothing, cosmetics, buildings, biomedical and health, etc (Catanzariti, 2008), nanomaterials are an indispensible part of human life.

Next-generation sequencing of cervical DNA detects human papillomavirus types not detected by commercial kits

Background Human papillomavirus (HPV) is the aetiological agent for cervical cancer and genital warts. Concurrent HPV and HIV infection in the South African population is high. HIV positive (+) women are often infected with multiple, rare and undetermined HPV types. Data on HPV incidence and genotype distribution are based on commercial HPV detection kits, but these kits may not detect all HPV types in HIV + women. The objectives of this study were to (i) identify the HPV types not detected by commercial genotyping kits present in a cervical specimen from an HIV positive South African woman using next generation sequencing, and (ii) determine if these types were prevalent in a cohort of HIV-infected South African women. Methods Total DNA was isolated from 109 cervical specimens from South African HIV + women. A specimen within this cohort representing a complex multiple HPV infection, with 12 HPV genotypes detected by the Roche Linear Array HPV genotyping (LA) kit, was selected for next generation sequencing analysis. All HPV types present in this cervical specimen were identified by Illumina sequencing of the extracted DNA following rolling circle amplification. The prevalence of the HPV types identified by sequencing, but not included in the Roche LA, was then determined in the 109 HIV positive South African women by type-specific PCR. Results Illumina sequencing identified a total of 16 HPV genotypes in the selected specimen, with four genotypes (HPV-30, 74, 86 and 90) not included in the commercial kit. The prevalence's of HPV-30, 74, 86 and 90 in 109 HIV positive South African women were found to be 14.6 %, 12.8 %, 4.6 % and 8.3 % respectively. Conclusions Our results indicate that there are HPV types, with substantial prevalence, in HIV positive women not being detected in molecular epidemiology studies using commercial kits. The significance of these types in relation to cervical disease remains to be investigated.

Anomalous event detection using a semi-two dimensional hidden Markov model

The rapid increase in the deployment of CCTV systems has led to a greater demand for algorithms that are able to process incoming video feeds. These algorithms are designed to extract information of interest for human operators. During the past several years, there has been a large effort to detect abnormal activities through computer vision techniques. Typically, the problem is formulated as a novelty detection task where the system is trained on normal data and is required to detect events which do not fit the learned `normal' model. Many researchers have tried various sets of features to train different learning models to detect abnormal behaviour in video footage. In this work we propose using a Semi-2D Hidden Markov Model (HMM) to model the normal activities of people. The outliers of the model with insufficient likelihood are identified as abnormal activities. Our Semi-2D HMM is designed to model both the temporal and spatial causalities of the crowd behaviour by assuming the current state of the Hidden Markov Model depends not only on the previous state in the temporal direction, but also on the previous states of the adjacent spatial locations. Two different HMMs are trained to model both the vertical and horizontal spatial causal information. Location features, flow features and optical flow textures are used as the features for the model. The proposed approach is evaluated using the publicly available UCSD datasets and we demonstrate improved performance compared to other state of the art methods.

Power of QTL detection using association tests with family controls

The power of testing for a population-wide association between a biallelic quantitative trait locus and a linked biallelic marker locus is predicted both empirically and deterministically for several tests. The tests were based on the analysis of variance (ANOVA) and on a number of transmission disequilibrium tests (TDT). Deterministic power predictions made use of family information, and were functions of population parameters including linkage disequilibrium, allele frequencies, and recombination rate. Deterministic power predictions were very close to the empirical power from simulations in all scenarios considered in this study. The different TDTs had very similar power, intermediate between one-way and nested ANOVAs. One-way ANOVA was the only test that was not robust against spurious disequilibrium. Our general framework for predicting power deterministically can be used to predict power in other association tests. Deterministic power calculations are a powerful tool for researchers to plan and evaluate experiments and obviate the need for elaborate simulation studies.

Ultra-trace detection of diagnostically important biomarkers using functionalised-Surface Enhanced Raman Spectroscopy (SERS)

Here we report an ultrasensitive method for detecting bio-active compounds in biological samples by means of functionalised nanoparticles interrogated by surface enhanced Raman spectroscopy (SERS). This method is applicable to the recovery and detection of many diagnostically important peptidyl analytes such as insulin, human growth hormone, growth factors (IGFs) and erythropoietin (EPO), as well as many small molecule analytes and metabolites. Our method, developed to detect EPO, demonstrates its utility in a complex yet well defined biological system. Recombinant human EPO (rhEPO) and EPO analogues have successfully been used to treat anaemia in end-stage renal failure, chronic disorders and infections, cancer and AIDS. Current methods for EPO testing are lengthy, laborious and relatively insensitive to low concentrations. In our rapid screening methodology, gold nanoparticles were functionalised with anti-EPO antibodies to provide very high selectivity towards the EPO protein in urine. These “smart sensor” nanoparticles interact with and trap EPO. Subsequent SERS screening allows for the detection and quantisation of ultra trace amounts (<<10-15 M) of EPO in urine samples with minimal sample preparation. We present data showing that the SERS spectrum differentiates between human endogenous EPO and rhEPO in unpurified urine, and potentially distinguishes between purified EPO isoforms. The elimination of sample preparation and direct screening in biological fluids significantly reduces the time required by current methods. Antibody recognition against a variety of biological targets and the availability of portable commercial SERS analysers for rapid onsite testing suggest broad diagnostic applicability in a flexible analytical platform.

Detection of a novel mutation in the CACNA1A gene

Familial hemiplegic migraine (FHM) is a rare autosomal dominant subtype of migraine with aura. It is divided into three subtypes FHM1, FHM2 and FHM3, which are caused by mutations in the CACNA1A, ATP1A2 and SCN1A genes respectively. As part of a regular diagnostic service, we investigated 168 patients with FHM symptoms. Samples were tested for mutations contained within the CACNA1A gene. Some tested samples (4.43%) showed an FHM1 mutation, with five of the mutations found in exon 5, one mutation in exon 16 and one in exon 17. Four polymorphisms were also detected, one of which occurred in a large percentage of samples (14.88%). The exon 16 2094G>A polymorphism, however, has been found to occur in healthy Caucasian control populations up to a frequency of 16% and is not considered to be significantly associated with FHM. A finding of significance, found in a single patient, was the detection of a novel mutation in exon 5 that results in a P225H change. The affected individual was an 8-year-old female. The exact phenotypic effect of this mutation is unknown, and further studies are needed to understand the pathophysiology of this mutation in FHM1. New information will allow for diagnostic procedures to be constantly updated, thus improving accuracy of diagnosis. It is possible that new information will also aid the development of new therapeutic agents for the treatment of FHM.

An evaluation of different features and learning models for anomalous event detection

The huge amount of CCTV footage available makes it very burdensome to process these videos manually through human operators. This has made automated processing of video footage through computer vision technologies necessary. During the past several years, there has been a large effort to detect abnormal activities through computer vision techniques. Typically, the problem is formulated as a novelty detection task where the system is trained on normal data and is required to detect events which do not fit the learned ‘normal’ model. There is no precise and exact definition for an abnormal activity; it is dependent on the context of the scene. Hence there is a requirement for different feature sets to detect different kinds of abnormal activities. In this work we evaluate the performance of different state of the art features to detect the presence of the abnormal objects in the scene. These include optical flow vectors to detect motion related anomalies, textures of optical flow and image textures to detect the presence of abnormal objects. These extracted features in different combinations are modeled using different state of the art models such as Gaussian mixture model(GMM) and Semi- 2D Hidden Markov model(HMM) to analyse the performances. Further we apply perspective normalization to the extracted features to compensate for perspective distortion due to the distance between the camera and objects of consideration. The proposed approach is evaluated using the publicly available UCSD datasets and we demonstrate improved performance compared to other state of the art methods.