288 resultados para Person Recognition
Resumo:
Robust facial expression recognition (FER) under occluded face conditions is challenging. It requires robust algorithms of feature extraction and investigations into the effects of different types of occlusion on the recognition performance to gain insight. Previous FER studies in this area have been limited. They have spanned recovery strategies for loss of local texture information and testing limited to only a few types of occlusion and predominantly a matched train-test strategy. This paper proposes a robust approach that employs a Monte Carlo algorithm to extract a set of Gabor based part-face templates from gallery images and converts these templates into template match distance features. The resulting feature vectors are robust to occlusion because occluded parts are covered by some but not all of the random templates. The method is evaluated using facial images with occluded regions around the eyes and the mouth, randomly placed occlusion patches of different sizes, and near-realistic occlusion of eyes with clear and solid glasses. Both matched and mis-matched train and test strategies are adopted to analyze the effects of such occlusion. Overall recognition performance and the performance for each facial expression are investigated. Experimental results on the Cohn-Kanade and JAFFE databases demonstrate the high robustness and fast processing speed of our approach, and provide useful insight into the effects of occlusion on FER. The results on the parameter sensitivity demonstrate a certain level of robustness of the approach to changes in the orientation and scale of Gabor filters, the size of templates, and occlusions ratios. Performance comparisons with previous approaches show that the proposed method is more robust to occlusion with lower reductions in accuracy from occlusion of eyes or mouth.
Resumo:
Faunal vocalisations are vital indicators for environmental change and faunal vocalisation analysis can provide information for answering ecological questions. Therefore, automated species recognition in environmental recordings has become a critical research area. This thesis presents an automated species recognition approach named Timed and Probabilistic Automata. A small lexicon for describing animal calls is defined, six algorithms for acoustic component detection are developed, and a series of species recognisers are built and evaluated.The presented automated species recognition approach yields significant improvement on the analysis performance over a real world dataset, and may be transferred to commercial software in the future.
Resumo:
Recent advances suggest that encoding images through Symmetric Positive Definite (SPD) matrices and then interpreting such matrices as points on Riemannian manifolds can lead to increased classification performance. Taking into account manifold geometry is typically done via (1) embedding the manifolds in tangent spaces, or (2) embedding into Reproducing Kernel Hilbert Spaces (RKHS). While embedding into tangent spaces allows the use of existing Euclidean-based learning algorithms, manifold shape is only approximated which can cause loss of discriminatory information. The RKHS approach retains more of the manifold structure, but may require non-trivial effort to kernelise Euclidean-based learning algorithms. In contrast to the above approaches, in this paper we offer a novel solution that allows SPD matrices to be used with unmodified Euclidean-based learning algorithms, with the true manifold shape well-preserved. Specifically, we propose to project SPD matrices using a set of random projection hyperplanes over RKHS into a random projection space, which leads to representing each matrix as a vector of projection coefficients. Experiments on face recognition, person re-identification and texture classification show that the proposed approach outperforms several recent methods, such as Tensor Sparse Coding, Histogram Plus Epitome, Riemannian Locality Preserving Projection and Relational Divergence Classification.
Resumo:
Accurate and detailed measurement of an individual's physical activity is a key requirement for helping researchers understand the relationship between physical activity and health. Accelerometers have become the method of choice for measuring physical activity due to their small size, low cost, convenience and their ability to provide objective information about physical activity. However, interpreting accelerometer data once it has been collected can be challenging. In this work, we applied machine learning algorithms to the task of physical activity recognition from triaxial accelerometer data. We employed a simple but effective approach of dividing the accelerometer data into short non-overlapping windows, converting each window into a feature vector, and treating each feature vector as an i.i.d training instance for a supervised learning algorithm. In addition, we improved on this simple approach with a multi-scale ensemble method that did not need to commit to a single window size and was able to leverage the fact that physical activities produced time series with repetitive patterns and discriminative features for physical activity occurred at different temporal scales.
Resumo:
Facial expression recognition (FER) has been dramatically developed in recent years, thanks to the advancements in related fields, especially machine learning, image processing and human recognition. Accordingly, the impact and potential usage of automatic FER have been growing in a wide range of applications, including human-computer interaction, robot control and driver state surveillance. However, to date, robust recognition of facial expressions from images and videos is still a challenging task due to the difficulty in accurately extracting the useful emotional features. These features are often represented in different forms, such as static, dynamic, point-based geometric or region-based appearance. Facial movement features, which include feature position and shape changes, are generally caused by the movements of facial elements and muscles during the course of emotional expression. The facial elements, especially key elements, will constantly change their positions when subjects are expressing emotions. As a consequence, the same feature in different images usually has different positions. In some cases, the shape of the feature may also be distorted due to the subtle facial muscle movements. Therefore, for any feature representing a certain emotion, the geometric-based position and appearance-based shape normally changes from one image to another image in image databases, as well as in videos. This kind of movement features represents a rich pool of both static and dynamic characteristics of expressions, which playa critical role for FER. The vast majority of the past work on FER does not take the dynamics of facial expressions into account. Some efforts have been made on capturing and utilizing facial movement features, and almost all of them are static based. These efforts try to adopt either geometric features of the tracked facial points, or appearance difference between holistic facial regions in consequent frames or texture and motion changes in loca- facial regions. Although achieved promising results, these approaches often require accurate location and tracking of facial points, which remains problematic.
Resumo:
This paper presents Sequence Matching Across Route Traversals (SMART); a generally applicable sequence-based place recognition algorithm. SMART provides invariance to changes in illumination and vehicle speed while also providing moderate pose invariance and robustness to environmental aliasing. We evaluate SMART on vehicles travelling at highly variable speeds in two challenging environments; firstly, on an all-terrain vehicle in an off-road, forest track and secondly, using a passenger car traversing an urban environment across day and night. We provide comparative results to the current state-of-the-art SeqSLAM algorithm and investigate the effects of altering SMART’s image matching parameters. Additionally, we conduct an extensive study of the relationship between image sequence length and SMART’s matching performance. Our results show viable place recognition performance in both environments with short 10-metre sequences, and up to 96% recall at 100% precision across extreme day-night cycles when longer image sequences are used.
Resumo:
Recognising that charitable behaviour can be motivated by public recognition and emotional satisfaction, not-for-profit organisations have developed strategies that leverage self-interest over altruism by facilitating individuals to donate conspicuously. Initially developed as novel marketing programs to increase donation income, such conspicuous tokens of recognition are being recognised as important value propositions to nurture donor relationships. Despite this, there is little empirical evidence that identifies when donations can be increased through conspicuous recognition. Furthermore, social media’s growing popularity for self-expression, as well as the increasing use of technology in donor relationship management strategies, makes an examination of virtual conspicuous tokens of recognition in relation to what value donors seek particularly insightful. Therefore, this research examined the impact of experiential donor value and virtual conspicuous tokens of recognition on blood donor intentions. Using online survey data from 186 Australian blood donors, results show that in fact emotional value is a stronger predictor of intentions to donate blood than altruistic value, while social value is the strongest predictor of intentions if provided with recognition. Clear linkages between dimensions of donor value (altruistic, emotional and social) and conspicuous donation behaviour (CDB) were identified. The findings provide valuable insights into the use of conspicuous donation tokens of recognition on social media, and contribute to our understanding into the under-researched areas of donor value and CDB.
Resumo:
The location of previously unseen and unregistered individuals in complex camera networks from semantic descriptions is a time consuming and often inaccurate process carried out by human operators, or security staff on the ground. To promote the development and evaluation of automated semantic description based localisation systems, we present a new, publicly available, unconstrained 110 sequence database, collected from 6 stationary cameras. Each sequence contains detailed semantic information for a single search subject who appears in the clip (gender, age, height, build, hair and skin colour, clothing type, texture and colour), and between 21 and 290 frames for each clip are annotated with the target subject location (over 11,000 frames are annotated in total). A novel approach for localising a person given a semantic query is also proposed and demonstrated on this database. The proposed approach incorporates clothing colour and type (for clothing worn below the waist), as well as height and build to detect people. A method to assess the quality of candidate regions, as well as a symmetry driven approach to aid in modelling clothing on the lower half of the body, is proposed within this approach. An evaluation on the proposed dataset shows that a relative improvement in localisation accuracy of up to 21 is achieved over the baseline technique.
Resumo:
This paper presents a novel place recognition algorithm inspired by the recent discovery of overlapping and multi-scale spatial maps in the rodent brain. We mimic this hierarchical framework by training arrays of Support Vector Machines to recognize places at multiple spatial scales. Place match hypotheses are then cross-validated across all spatial scales, a process which combines the spatial specificity of the finest spatial map with the consensus provided by broader mapping scales. Experiments on three real-world datasets including a large robotics benchmark demonstrate that mapping over multiple scales uniformly improves place recognition performance over a single scale approach without sacrificing localization accuracy. We present analysis that illustrates how matching over multiple scales leads to better place recognition performance and discuss several promising areas for future investigation.
Resumo:
To identify and categorize complex stimuli such as familiar objects or speech, the human brain integrates information that is abstracted at multiple levels from its sensory inputs. Using cross-modal priming for spoken words and sounds, this functional magnetic resonance imaging study identified 3 distinct classes of visuoauditory incongruency effects: visuoauditory incongruency effects were selective for 1) spoken words in the left superior temporal sulcus (STS), 2) environmental sounds in the left angular gyrus (AG), and 3) both words and sounds in the lateral and medial prefrontal cortices (IFS/mPFC). From a cognitive perspective, these incongruency effects suggest that prior visual information influences the neural processes underlying speech and sound recognition at multiple levels, with the STS being involved in phonological, AG in semantic, and mPFC/IFS in higher conceptual processing. In terms of neural mechanisms, effective connectivity analyses (dynamic causal modeling) suggest that these incongruency effects may emerge via greater bottom-up effects from early auditory regions to intermediate multisensory integration areas (i.e., STS and AG). This is consistent with a predictive coding perspective on hierarchical Bayesian inference in the cortex where the domain of the prediction error (phonological vs. semantic) determines its regional expression (middle temporal gyrus/STS vs. AG/intraparietal sulcus).
Resumo:
RNA polymerase II (pol II) transcription termination requires co‐transcriptional recognition of a functional polyadenylation signal, but the molecular mechanisms that transduce this signal to pol II remain unclear. We show that Yhh1p/Cft1p, the yeast homologue of the mammalian AAUAAA interacting protein CPSF 160, is an RNA‐binding protein and provide evidence that it participates in poly(A) site recognition. Interestingly, RNA binding is mediated by a central domain composed of predicted β‐propeller‐forming repeats, which occurs in proteins of diverse cellular functions. We also found that Yhh1p/Cft1p bound specifically to the phosphorylated C‐terminal domain (CTD) of pol II in vitro and in a two‐hybrid test in vivo. Furthermore, transcriptional run‐on analysis demonstrated that yhh1 mutants were defective in transcription termination, suggesting that Yhh1p/Cft1p functions in the coupling of transcription and 3′‐end formation. We propose that direct interactions of Yhh1p/Cft1p with both the RNA transcript and the CTD are required to communicate poly(A) site recognition to elongating pol II to initiate transcription termination.
Resumo:
Organizational change is a typical phenomenon within public sector agencies in OECD countries. An increasing number of studies in the literature examine the implementation of change and its resulting impact on the work attitudes of public sector employees; however, little is known about the extent to which change management processes impact on employees’ work attitudes. This study aims to address this issue by developing a path model underpinned by change management and public service motivation literature. The path model was tested on a sample of 308 managerial and non-managerial public sector employees from the U.S. The results provide further empirical evidence on the types of change initiatives on nursing work and change management processes being implemented. Public sector agencies in the sample implemented a variety of change initiatives such as downsizing, delayering and empowerment. Employees reported two change management processes: the provision of change-related information and participation in change decision making. While the results indicate that change produces change-induced stressors, change information tends to reduce stressors and, subsequently, role stress. The results also indicate that change management processes are associated with higher levels of public service motivation, which is in turn connected to higher levels of person–organization fit. Person–organization fit was found to partially mediate the relationship between public service motivation and job satisfaction in the context of change.
Resumo:
There is substantial evidence for facial emotion recognition (FER) deficits in autism spectrum disorder (ASD). The extent of this impairment, however, remains unclear, and there is some suggestion that clinical groups might benefit from the use of dynamic rather than static images. High-functioning individuals with ASD (n = 36) and typically developing controls (n = 36) completed a computerised FER task involving static and dynamic expressions of the six basic emotions. The ASD group showed poorer overall performance in identifying anger and disgust and were disadvantaged by dynamic (relative to static) stimuli when presented with sad expressions. Among both groups, however, dynamic stimuli appeared to improve recognition of anger. This research provides further evidence of specific impairment in the recognition of negative emotions in ASD, but argues against any broad advantages associated with the use of dynamic displays.
Resumo:
The solutions proposed in this thesis contribute to improve gait recognition performance in practical scenarios that further enable the adoption of gait recognition into real world security and forensic applications that require identifying humans at a distance. Pioneering work has been conducted on frontal gait recognition using depth images to allow gait to be integrated with biometric walkthrough portals. The effects of gait challenging conditions including clothing, carrying goods, and viewpoint have been explored. Enhanced approaches are proposed on segmentation, feature extraction, feature optimisation and classification elements, and state-of-the-art recognition performance has been achieved. A frontal depth gait database has been developed and made available to the research community for further investigation. Solutions are explored in 2D and 3D domains using multiple images sources, and both domain-specific and independent modality gait features are proposed.
Resumo:
Background Maintenance of communication is important for people with dementia living in long-term care. The purpose of this study was to assess the feasibility of using “Giraff”, a telepresence robot to enhance engagement between family and a person with dementia living in long-term care. Methods A mixed-methods approach involving semi-structured interviews, call records and video observational data was used. Five people with dementia and their family member participated in a discussion via the Giraff robot for a minimum of six times over a six-week period. A feasibility framework was used to assess feasibility and included video analysis of emotional response and engagement. Results Twenty-six calls with an average duration of 23 mins took place. Residents showed a general state of positive emotions across the calls with a high level of engagement and a minimal level of negative emotions. Participants enjoyed the experience and families reported that the Giraff robot offered the opportunity to reduce social isolation. A number of software and hardware challenges were encountered. Conclusions Participants perceived this novel approach to engage families and people with dementia as a feasible option. Participants were observed and also reported to enjoy the experience. The technical challenges identified have been improved in a newer version of the robot. Future research should include a feasibility trial of longer duration, with a larger sample and a cost analysis.