Human Behaviour Recognition based on Trajectory Analysis using Neural Networks

Automated human behaviour analysis has been, and still remains, a challenging problem. It has been dealt from different points of views: from primitive actions to human interaction recognition. This paper is focused on trajectory analysis which allows a simple high level understanding of complex human behaviour. It is proposed a novel representation method of trajectory data, called Activity Description Vector (ADV) based on the number of occurrences of a person is in a specific point of the scenario and the local movements that perform in it. The ADV is calculated for each cell of the scenario in which it is spatially sampled obtaining a cue for different clustering methods. The ADV representation has been tested as the input of several classic classifiers and compared to other approaches using CAVIAR dataset sequences obtaining great accuracy in the recognition of the behaviour of people in a Shopping Centre.

A survey of human motion analysis using depth imagery

Analysis of human behaviour through visual information has been a highly active research topic in the computer vision community. This was previously achieved via images from a conventional camera, but recently depth sensors have made a new type of data available. This survey starts by explaining the advantages of depth imagery, then describes the new sensors that are available to obtain it. In particular, the Microsoft Kinect has made high-resolution real-time depth cheaply available. The main published research on the use of depth imagery for analysing human activity is reviewed. Much of the existing work focuses on body part detection and pose estimation. A growing research area addresses the recognition of human actions. The publicly available datasets that include depth imagery are listed, as are the software libraries that can acquire it from a sensor. This survey concludes by summarising the current state of work on this topic, and pointing out promising future research directions.

Human behaviour modelled as a statistico-deterministic turing machine

'Free will' and its corollary, the concept of individual responsibility are keystones of the justice system. This paper shows that if we accept a physics that disallows time reversal, the concept of 'free will' is undermined by an integrated understanding of the influence of genetics and environment on human behavioural responses. Analysis is undertaken by modelling life as a novel statistico-deterministic version of a Turing machine, i.e. as a series of transitions between states at successive instants of time. Using this model it is proven by induction that the entire course of life is independent of the action of free will. Although determined by prior state, the probability of transitions between states in response to a standard environmental stimulus is not equal to 1 and the transitions may differ quantitatively at the molecular level and qualitatively at the level of the whole organism. Transitions between states correspond to behaviours. It is shown that the behaviour of identical twins (or clones), although determined, would be incompletely predictable and non-identical, creating an illusion of the operation of 'free will'. 'Free will' is a convenient construct for current judicial systems and social control because it allows rationalization of punishment for those whose behaviour falls outside socially defined norms. Indeed, it is conceivable that maintenance of ideas of free will has co-evolved with community morality to reinforce its operation. If the concept is free will is to be maintained it would require revision of our current physical theories.

Human behaviour recognition in data-scarce domains

This paper presents the novel theory for performing multi-agent activity recognition without requiring large training corpora. The reduced need for data means that robust probabilistic recognition can be performed within domains where annotated datasets are traditionally unavailable. Complex human activities are composed from sequences of underlying primitive activities. We do not assume that the exact temporal ordering of primitives is necessary, so can represent complex activity using an unordered bag. Our three-tier architecture comprises low-level video tracking, event analysis and high-level inference. High-level inference is performed using a new, cascading extension of the Rao–Blackwellised Particle Filter. Simulated annealing is used to identify pairs of agents involved in multi-agent activity. We validate our framework using the benchmarked PETS 2006 video surveillance dataset and our own sequences, and achieve a mean recognition F-Score of 0.82. Our approach achieves a mean improvement of 17% over a Hidden Markov Model baseline.

Hierarchical Task Network Planning with Common-Sense Reasoning for Multiple-People Behaviour Analysis

Safety on public transport is a major concern for the relevant authorities. We
address this issue by proposing an automated surveillance platform which combines data from video, infrared and pressure sensors. Data homogenisation and integration is achieved by a distributed architecture based on communication middleware that resolves interconnection issues, thereby enabling data modelling. A common-sense knowledge base models and encodes knowledge about public-transport platforms and the actions and activities of passengers. Trajectory data from passengers is modelled as a time-series of human activities. Common-sense knowledge and rules are then applied to detect inconsistencies or errors in the data interpretation. Lastly, the rationality that characterises human behaviour is also captured here through a bottom-up Hierarchical Task Network planner that, along with common-sense, corrects misinterpretations to explain passenger behaviour. The system is validated using a simulated bus saloon scenario as a case-study. Eighteen video sequences were recorded with up to six passengers. Four metrics were used to evaluate performance. The system, with an accuracy greater than 90% for each of the four metrics, was found to outperform a rule-base system and a system containing planning alone.

Modelling human behaviour and event detection from videos

Automatic analysis of human behaviour in large collections of videos is gaining interest, even more so with the advent of file sharing sites such as YouTube. However, challenges still exist owing to several factors such as inter- and intra-class variations, cluttered backgrounds, occlusion, camera motion, scale, view and illumination changes. This research focuses on modelling human behaviour for action recognition in videos. The developed techniques are validated on large scale benchmark datasets and applied on real-world scenarios such as soccer videos. Three major contributions are made. The first contribution is in the area of proper choice of a feature representation for videos. This involved a study of state-of-the-art techniques for action recognition, feature extraction processing and dimensional reduction techniques so as to yield the best performance with optimal computational requirements. Secondly, temporal modelling of human behaviour is performed. This involved frequency analysis and temporal integration of local information in the video frames to yield a temporal feature vector. Current practices mostly average the frame information over an entire video and neglect the temporal order. Lastly, the proposed framework is applied and further adapted to real-world scenario such as soccer videos. A dataset consisting of video sequences depicting events of players falling is created from actual match data to this end and used to experimentally evaluate the proposed framework.

Cancer culture: Epidemics, human behaviour and the dubious search for new risk factors

The rise of melanoma and the almost complete decline of stomach cancer clearly reflect disturbances of human culture during the 20th century. Environmental factors play a dominant role in the epidemiology of melanoma and many other malignancies.

Mechanical behaviour analysis of polyester polymer mortars modified with recycled GFRP waste materials

In this study the effect of incorporation of recycled glass-fibre reinforced polymer (GFRP) waste materials, obtained by means of milling processes, on mechanical behaviour of polyester polymer mortars was assessed. For this purpose, different contents of recycled GFRP waste powder and fibres, with distinct size gradings, were incorporated into polyester based mortars as sand aggregates and filler replacements. Flexural and compressive loading capacities were evaluated and found better than unmodified polymer mortars. GFRP modified polyester based mortars also show a less brittle behaviour, with retention of some loading capacity after peak load. Obtained results highlight the high potential of recycled GFRP waste materials as efficient and sustainable reinforcement and admixture for polymer concrete and mortars composites, constituting an emergent waste management solution.

Semantic and fuzzy modelling for human behaviour recognition in smart spaces : a case study on ambient assisted living.

Human activity recognition in everyday environments is a critical, but challenging task in Ambient Intelligence applications to achieve proper Ambient Assisted Living, and key challenges still remain to be dealt with to realize robust methods. One of the major limitations of the Ambient Intelligence systems today is the lack of semantic models of those activities on the environment, so that the system can recognize the speci c activity being performed by the user(s) and act accordingly. In this context, this thesis addresses the general problem of knowledge representation in Smart Spaces. The main objective is to develop knowledge-based models, equipped with semantics to learn, infer and monitor human behaviours in Smart Spaces. Moreover, it is easy to recognize that some aspects of this problem have a high degree of uncertainty, and therefore, the developed models must be equipped with mechanisms to manage this type of information. A fuzzy ontology and a semantic hybrid system are presented to allow modelling and recognition of a set of complex real-life scenarios where vagueness and uncertainty are inherent to the human nature of the users that perform it. The handling of uncertain, incomplete and vague data (i.e., missing sensor readings and activity execution variations, since human behaviour is non-deterministic) is approached for the rst time through a fuzzy ontology validated on real-time settings within a hybrid data-driven and knowledgebased architecture. The semantics of activities, sub-activities and real-time object interaction are taken into consideration. The proposed framework consists of two main modules: the low-level sub-activity recognizer and the high-level activity recognizer. The rst module detects sub-activities (i.e., actions or basic activities) that take input data directly from a depth sensor (Kinect). The main contribution of this thesis tackles the second component of the hybrid system, which lays on top of the previous one, in a superior level of abstraction, and acquires the input data from the rst module's output, and executes ontological inference to provide users, activities and their in uence in the environment, with semantics. This component is thus knowledge-based, and a fuzzy ontology was designed to model the high-level activities. Since activity recognition requires context-awareness and the ability to discriminate among activities in di erent environments, the semantic framework allows for modelling common-sense knowledge in the form of a rule-based system that supports expressions close to natural language in the form of fuzzy linguistic labels. The framework advantages have been evaluated with a challenging and new public dataset, CAD-120, achieving an accuracy of 90.1% and 91.1% respectively for low and high-level activities. This entails an improvement over both, entirely data-driven approaches, and merely ontology-based approaches. As an added value, for the system to be su ciently simple and exible to be managed by non-expert users, and thus, facilitate the transfer of research to industry, a development framework composed by a programming toolbox, a hybrid crisp and fuzzy architecture, and graphical models to represent and con gure human behaviour in Smart Spaces, were developed in order to provide the framework with more usability in the nal application. As a result, human behaviour recognition can help assisting people with special needs such as in healthcare, independent elderly living, in remote rehabilitation monitoring, industrial process guideline control, and many other cases. This thesis shows use cases in these areas.

"I might be a duck, but I'm human" : an analysis of clothing in Disney cartoons

Mickey Mouse, one of the world's most recognizable cartoon characters, did not wear a shirt in his earliest incarnation in theatrical shorts and, for many years, Donald Duck did not wear pants and still rarely does so. Especially when one considers the era in which these figures were first created by the Walt Disney Studio, in the 1920s and 1930s, why are they portrayed without full clothing? The obvious answer, of course, is that they are animals, and animals do not wear clothes. But these are no ordinary animals: in most cases, they do wear clothing - some clothing, at least - and they walk on two legs, talk in a more or less intelligible fashion, and display a number of other anthropomorphic traits. If they are essentially animals, why do they wear clothing at all? On the other hand, if these characters are more human than animal, as suggested by other behavioral traits - they walk, talk, work, read, and so on - why are they not more often fully clothed? To answer these questions I undertook three major research strategies used to gather evidence: interpretive textual analysis of 321 cartoons; secondary analysis of interviews conducted with the animators who created the Disney characters; and historical and archival research on the Disney Company and on the times and context in which it functioned. I was able to identify five themes that played a large part in what kind of clothing a character wore; first, the character's gender and/or sexuality; second, what species or "race" the character was; third, the character's socio-economic status; fourth, the degree to which the character was anthropomorphized; and, fifth, the context in which the character and its clothing appeared in a particular scene or narrative. I concluded that all of these factors played a part in determining, to some extent, the clothing worn by particular characters at particular times. However, certain patterns emerged from the analysis that could not be explained by these factors alone or in combination. Therefore, my analysis also investigates the individual and collective attitudes and desires of the men in the Disney studio who were responsible for creating these characters and the cultural conditions under which they were created. Drawing on literature from the psychoanalytic approach to film studies, I argue that the clothing choices spoke to an idealized fantasy world to which the animators (most importantly, Walt Disney himself), and possibly wider society, wanted to return.

Effectiveness of Self-Instructional Mediator Training in Applied Behaviour Analysis

Interventions using applied behaviour analysis (ABA) are widely used with children with autism spectrum disorders (ASD). Individuals who work with this population are important to target for ABA education. This study evaluated the efficacy of a self-directed program in increasing parent and student ABA knowledge and skills, self-efficacy, and new skill development in children with ASD. Study 1 was a pilot study of the newly developed evaluation materials. Study 2 tested the self-instructional package with three parents of children with ASD, three university students, and eight children diagnosed with ASD. Parents and students were given the Simple Steps ABA training package to use independently and were measured using a multiple baseline across participants and/or skills design. After training, ABA knowledge scores and self-efficacy showed variable improvement as did children’s appropriate behaviours. These results suggest that more research is needed to determine the efficacy of a self-instructional ABA package.

An Introduction to Behaviour Analysis

Behaviour Analysis is a distinct philospophy of science. Individuals new to the approach often find difficulty in understanding the basic principles involved. This presentation, aimed at Final Year undergraduates, is designed to provide an introduction to the principles of operant conditioning (e.g., reinforcement, punishment, and extinction), making clear that these words describe functional, rather than structural, relations.