Detection versus false alarm characterisation of a vision-based airborne dim-target collision detection system

This paper presents a preliminary flight test based detection range versus false alarm performance characterisation of a morphological-hidden Markov model filtering approach to vision-based airborne dim-target collision detection. On the basis of compelling in-flight collision scenario data, we calculate system operating characteristic (SOC) curves that concisely illustrate the detection range versus false alarm rate performance design trade-offs. These preliminary SOC curves provide a more complete dim-target detection performance description than previous studies (due to the experimental difficulties involved, previous studies have been limited to very short flight data sample sets and hence have not been able to quantify false alarm behaviour). The preliminary investigation here is based on data collected from 4 controlled collision encounters and supporting non-target flight data. This study suggests head-on detection ranges of approximately 2.22 km under blue sky background conditions (1.26 km in cluttered background conditions), whilst experiencing false alarms at a rate less than 1.7 false alarms/hour (ie. less than once every 36 minutes). Further data collection is currently in progress.

Fat and thin adaptive HMM filters for vision based detection of moving targets

Computer vision is an attractive solution for uninhabited aerial vehicle (UAV) collision avoidance, due to the low weight, size and power requirements of hardware. A two-stage paradigm has emerged in the literature for detection and tracking of dim targets in images, comprising of spatial preprocessing, followed by temporal filtering. In this paper, we investigate a hidden Markov model (HMM) based temporal filtering approach. Specifically, we propose an adaptive HMM filter, in which the variance of model parameters is refined as the quality of the target estimate improves. Filters with high variance (fat filters) are used for target acquisition, and filters with low variance (thin filters) are used for target tracking. The adaptive filter is tested in simulation and with real data (video of a collision-course aircraft). Our test results demonstrate that our adaptive filtering approach has improved tracking performance, and provides an estimate of target heading not present in previous HMM filtering approaches.

Bayesian mixtures for modelling complex medical data : a case study in Parkinson’s disease

Mixture models are a flexible tool for unsupervised clustering that have found popularity in a vast array of research areas. In studies of medicine, the use of mixtures holds the potential to greatly enhance our understanding of patient responses through the identification of clinically meaningful clusters that, given the complexity of many data sources, may otherwise by intangible. Furthermore, when developed in the Bayesian framework, mixture models provide a natural means for capturing and propagating uncertainty in different aspects of a clustering solution, arguably resulting in richer analyses of the population under study. This thesis aims to investigate the use of Bayesian mixture models in analysing varied and detailed sources of patient information collected in the study of complex disease. The first aim of this thesis is to showcase the flexibility of mixture models in modelling markedly different types of data. In particular, we examine three common variants on the mixture model, namely, finite mixtures, Dirichlet Process mixtures and hidden Markov models. Beyond the development and application of these models to different sources of data, this thesis also focuses on modelling different aspects relating to uncertainty in clustering. Examples of clustering uncertainty considered are uncertainty in a patient’s true cluster membership and accounting for uncertainty in the true number of clusters present. Finally, this thesis aims to address and propose solutions to the task of comparing clustering solutions, whether this be comparing patients or observations assigned to different subgroups or comparing clustering solutions over multiple datasets. To address these aims, we consider a case study in Parkinson’s disease (PD), a complex and commonly diagnosed neurodegenerative disorder. In particular, two commonly collected sources of patient information are considered. The first source of data are on symptoms associated with PD, recorded using the Unified Parkinson’s Disease Rating Scale (UPDRS) and constitutes the first half of this thesis. The second half of this thesis is dedicated to the analysis of microelectrode recordings collected during Deep Brain Stimulation (DBS), a popular palliative treatment for advanced PD. Analysis of this second source of data centers on the problems of unsupervised detection and sorting of action potentials or "spikes" in recordings of multiple cell activity, providing valuable information on real time neural activity in the brain.

HMM triangle relative entropy concepts in sequential change detection applied to vision-based dim target manoeuvre detection

The quick detection of abrupt (unknown) parameter changes in an observed hidden Markov model (HMM) is important in several applications. Motivated by the recent application of relative entropy concepts in the robust sequential change detection problem (and the related model selection problem), this paper proposes a sequential unknown change detection algorithm based on a relative entropy based HMM parameter estimator. Our proposed approach is able to overcome the lack of knowledge of post-change parameters, and is illustrated to have similar performance to the popular cumulative sum (CUSUM) algorithm (which requires knowledge of the post-change parameter values) when examined, on both simulated and real data, in a vision-based aircraft manoeuvre detection problem.

Multiple cameras for audio-visual speech recognition in an automotive environment

Audio-visualspeechrecognition, or the combination of visual lip-reading with traditional acoustic speechrecognition, has been previously shown to provide a considerable improvement over acoustic-only approaches in noisy environments, such as that present in an automotive cabin. The research presented in this paper will extend upon the established audio-visualspeechrecognition literature to show that further improvements in speechrecognition accuracy can be obtained when multiple frontal or near-frontal views of a speaker's face are available. A series of visualspeechrecognition experiments using a four-stream visual synchronous hidden Markov model (SHMM) are conducted on the four-camera AVICAR automotiveaudio-visualspeech database. We study the relative contribution between the side and central orientated cameras in improving visualspeechrecognition accuracy. Finally combination of the four visual streams with a single audio stream in a five-stream SHMM demonstrates a relative improvement of over 56% in word recognition accuracy when compared to the acoustic-only approach in the noisiest conditions of the AVICAR database.

Characterization of sky-region morphological-temporal airborne collision detection

Automated airborne collision-detection systems are a key enabling technology for facilitat- ing the integration of unmanned aerial vehicles (UAVs) into the national airspace. These safety-critical systems must be sensitive enough to provide timely warnings of genuine air- borne collision threats, but not so sensitive as to cause excessive false-alarms. Hence, an accurate characterisation of detection and false alarm sensitivity is essential for understand- ing performance trade-offs, and system designers can exploit this characterisation to help achieve a desired balance in system performance. In this paper we experimentally evaluate a sky-region, image based, aircraft collision detection system that is based on morphologi- cal and temporal processing techniques. (Note that the examined detection approaches are not suitable for the detection of potential collision threats against a ground clutter back- ground). A novel collection methodology for collecting realistic airborne collision-course target footage in both head-on and tail-chase engagement geometries is described. Under (hazy) blue sky conditions, our proposed system achieved detection ranges greater than 1540m in 3 flight test cases with no false alarm events in 14.14 hours of non-target data (under cloudy conditions, the system achieved detection ranges greater than 1170m in 4 flight test cases with no false alarm events in 6.63 hours of non-target data). Importantly, this paper is the first documented presentation of detection range versus false alarm curves generated from airborne target and non-target image data.

High-resolution loss of heterozygosity screening implicates PTPRJ as a potential tumor suppressor gene that affects susceptibility to non-Hodgkin's Lymphoma

We employed a Hidden-Markov-Model (HMM) algorithm in loss of heterozygosity (LOH) analysis of high-density single nucleotide polymorphism (SNP) array data from Non-Hodgkin’s lymphoma (NHL) entities, follicular lymphoma (FL), and diffuse large B-cell lymphoma (DLBCL). This revealed a high frequency of LOH over the chromosomal region 11p11.2, containing the gene encoding the protein tyrosine phosphatase receptor type J (PTPRJ). Although PTPRJ regulates components of key survival pathways in B-cells (i.e., BCR, MAPK, and PI3K signaling), its role in B-cell development is poorly understood. LOH of PTPRJ has been described in several types of cancer but not in any hematological malignancy. Interestingly, FL cases with LOH exhibited down-regulation of PTPRJ, in contrast no significant variation of expression was shown in DLBCLs. In addition, sequence screening in Exons 5 and 13 of PTPRJ identified the G973A (rs2270993), T1054C (rs2270992), A1182C (rs1566734), and G2971C (rs4752904) coding SNPs (cSNPs). The A1182 allele was significantly more frequent in FLs and in NHLs with LOH. Significant over-representation of the C1054 (rs2270992) and the C2971 (rs4752904) alleles were also observed in LOH cases. A haplotype analysis also revealed a significant lower frequency of haplotype GTCG in NHL cases, but it was only detected in cases with retention. Conversely, haplotype GCAC was over-representated in cases with LOH. Altogether, these results indicate that the inactivation of PTPRJ may be a common lymphomagenic mechanism in these NHL subtypes and that haplotypes in PTPRJ gene may play a role in susceptibility to NHL, by affecting activation of PTPRJ in these B-cell lymphomas.

A new method to detect loss of heterozygosity using cohort heterozygosity comparisons

Background Loss of heterozygosity (LOH) is an important marker for one of the 'two-hits' required for tumor suppressor gene inactivation. Traditional methods for mapping LOH regions require the comparison of both tumor and patient-matched normal DNA samples. However, for many archival samples, patient-matched normal DNA is not available leading to the under-utilization of this important resource in LOH studies. Here we describe a new method for LOH analysis that relies on the genome-wide comparison of heterozygosity of single nucleotide polymorphisms (SNPs) between cohorts of cases and un-matched healthy control samples. Regions of LOH are defined by consistent decreases in heterozygosity across a genetic region in the case cohort compared to the control cohort. Methods DNA was collected from 20 Follicular Lymphoma (FL) tumor samples, 20 Diffuse Large B-cell Lymphoma (DLBCL) tumor samples, neoplastic B-cells of 10 B-cell Chronic Lymphocytic Leukemia (B-CLL) patients and Buccal cell samples matched to 4 of these B-CLL patients. The cohort heterozygosity comparison method was developed and validated using LOH derived in a small cohort of B-CLL by traditional comparisons of tumor and normal DNA samples, and compared to the only alternative method for LOH analysis without patient matched controls. LOH candidate regions were then generated for enlarged cohorts of B-CLL, FL and DLBCL samples using our cohort heterozygosity comparison method in order to evaluate potential LOH candidate regions in these non-Hodgkin's lymphoma tumor subtypes. Results Using a small cohort of B-CLL samples with patient-matched normal DNA we have validated the utility of this method and shown that it displays more accuracy and sensitivity in detecting LOH candidate regions compared to the only alternative method, the Hidden Markov Model (HMM) method. Subsequently, using B-CLL, FL and DLBCL tumor samples we have utilised cohort heterozygosity comparisons to localise LOH candidate regions in these subtypes of non-Hodgkin's lymphoma. Detected LOH regions included both previously described regions of LOH as well as novel genomic candidate regions. Conclusions We have proven the efficacy of the use of cohort heterozygosity comparisons for genome-wide mapping of LOH and shown it to be in many ways superior to the HMM method. Additionally, the use of this method to analyse SNP microarray data from 3 common forms of non-Hodgkin's lymphoma yielded interesting tumor suppressor gene candidates, including the ETV3 gene that was highlighted in both B-CLL and FL.

Detecting anomalous events at railway level crossings

Collisions between pedestrians and vehicles continue to be a major problem throughout the world. Pedestrians trying to cross roads and railway tracks without any caution are often highly susceptible to collisions with vehicles and trains. Continuous financial, human and other losses have prompted transport related organizations to come up with various solutions addressing this issue. However, the quest for new and significant improvements in this area is still ongoing. This work addresses this issue by building a general framework using computer vision techniques to automatically monitor pedestrian movements in such high-risk areas to enable better analysis of activity, and the creation of future alerting strategies. As a result of rapid development in the electronics and semi-conductor industry there is extensive deployment of CCTV cameras in public places to capture video footage. This footage can then be used to analyse crowd activities in those particular places. This work seeks to identify the abnormal behaviour of individuals in video footage. In this work we propose using a Semi-2D Hidden Markov Model (HMM), Full-2D HMM and Spatial HMM to model the normal activities of people. The outliers of the model (i.e. those observations with insufficient likelihood) are identified as abnormal activities. Location features, flow features and optical flow textures are used as the features for the model. The proposed approaches are evaluated using the publicly available UCSD datasets, and we demonstrate improved performance using a Semi-2D Hidden Markov Model compared to other state of the art methods. Further we illustrate how our proposed methods can be applied to detect anomalous events at rail level crossings.

Sequential decision fusion of multibiometrics applied to text-dependent speaker verification for controlled errors

Reliability of the performance of biometric identity verification systems remains a significant challenge. Individual biometric samples of the same person (identity class) are not identical at each presentation and performance degradation arises from intra-class variability and inter-class similarity. These limitations lead to false accepts and false rejects that are dependent. It is therefore difficult to reduce the rate of one type of error without increasing the other. The focus of this dissertation is to investigate a method based on classifier fusion techniques to better control the trade-off between the verification errors using text-dependent speaker verification as the test platform. A sequential classifier fusion architecture that integrates multi-instance and multisample fusion schemes is proposed. This fusion method enables a controlled trade-off between false alarms and false rejects. For statistically independent classifier decisions, analytical expressions for each type of verification error are derived using base classifier performances. As this assumption may not be always valid, these expressions are modified to incorporate the correlation between statistically dependent decisions from clients and impostors. The architecture is empirically evaluated by applying the proposed architecture for text dependent speaker verification using the Hidden Markov Model based digit dependent speaker models in each stage with multiple attempts for each digit utterance. The trade-off between the verification errors is controlled using the parameters, number of decision stages (instances) and the number of attempts at each decision stage (samples), fine-tuned on evaluation/tune set. The statistical validation of the derived expressions for error estimates is evaluated on test data. The performance of the sequential method is further demonstrated to depend on the order of the combination of digits (instances) and the nature of repetitive attempts (samples). The false rejection and false acceptance rates for proposed fusion are estimated using the base classifier performances, the variance in correlation between classifier decisions and the sequence of classifiers with favourable dependence selected using the 'Sequential Error Ratio' criteria. The error rates are better estimated by incorporating user-dependent (such as speaker-dependent thresholds and speaker-specific digit combinations) and class-dependent (such as clientimpostor dependent favourable combinations and class-error based threshold estimation) information. The proposed architecture is desirable in most of the speaker verification applications such as remote authentication, telephone and internet shopping applications. The tuning of parameters - the number of instances and samples - serve both the security and user convenience requirements of speaker-specific verification. The architecture investigated here is applicable to verification using other biometric modalities such as handwriting, fingerprints and key strokes.

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.

HMM relative entropy rate concepts for vision-based aircraft manoeuvre detection

Machine vision is emerging as a viable sensing approach for mid-air collision avoidance (particularly for small to medium aircraft such as unmanned aerial vehicles). In this paper, using relative entropy rate concepts, we propose and investigate a new change detection approach that uses hidden Markov model filters to sequentially detect aircraft manoeuvres from morphologically processed image sequences. Experiments using simulated and airborne image sequences illustrate the performance of our proposed algorithm in comparison to other sequential change detection approaches applied to this application.

Consistent HMM parameter estimation using Kerridge inaccuracy rates

In this paper, we propose a novel online hidden Markov model (HMM) parameter estimator based on Kerridge inaccuracy rate (KIR) concepts. Under mild identifiability conditions, we prove that our online KIR-based estimator is strongly consistent. In simulation studies, we illustrate the convergence behaviour of our proposed online KIR-based estimator and provide a counter-example illustrating the local convergence properties of the well known recursive maximum likelihood estimator (arguably the best existing solution).

Resilient Navigation through Probabilistic Modality Reconfiguration

This paper proposes an approach to achieve resilient navigation for indoor mobile robots. Resilient navigation seeks to mitigate the impact of control, localisation, or map errors on the safety of the platform while enforcing the robot’s ability to achieve its goal. We show that resilience to unpredictable errors can be achieved by combining the benefits of independent and complementary algorithmic approaches to navigation, or modalities, each tuned to a particular type of environment or situation. In this paper, the modalities comprise a path planning method and a reactive motion strategy. While the robot navigates, a Hidden Markov Model continually estimates the most appropriate modality based on two types of information: context (information known a priori) and monitoring (evaluating unpredictable aspects of the current situation). The robot then uses the recommended modality, switching between one and another dynamically. Experimental validation with a SegwayRMP- based platform in an office environment shows that our approach enables failure mitigation while maintaining the safety of the platform. The robot is shown to reach its goal in the presence of: 1) unpredicted control errors, 2) unexpected map errors and 3) a large injected localisation fault.

Enhanced locomotion control for a planetary rover

This article presents an approach to improve and monitor the behavior of a skid-steering rover on rough terrains. An adaptive locomotion control generates speeds references to avoid slipping situations. An enhanced odometry provides a better estimation of the distance travelled. A probabilistic classification procedure provides an evaluation of the locomotion efficiency on-line, with a detection of locomotion faults. Results obtained with a Marsokhod rover are presented throughout the paper