Human activity recognition is one of the intensively studied areas in computer vision. Most existing works do not assume video resolution to be a problem due to general applications of interests. However, with continuous concerns about global security and emerging needs for intelligent video analysis tools, activity recognition from low-resolution and low-quality videos has become a crucial topic for further research. In this dissertation, We present a series of approaches which are developed specifically to address the related issues regarding low-level image preprocessing, single person activity recognition, and human-vehicle interaction reasoning from low-resolution surveillance videos. Human cast shadows are one of the major issues which adversely effect the performance of an activity recognition system. This is because human shadow direction varies depending on the time of the day and the date of the year. To better resolve this problem, we propose a shadow removal technique which effectively eliminates a human shadow cast from a light source of unknown direction. A multi-cue shadow descriptor is employed to characterize the distinctive properties of shadows. Our approach detects, segments, and then removes shadows. We propose two different methods to recognize single person actions and activities from low-resolution surveillance videos. The first approach adopts a joint feature histogram based representation, which is the concatenation of subspace projected gradient and optical flow features in time. However, in this problem, the use of low-resolution, coarse, pixel-level features alone limits the recognition accuracy. Therefore, in the second work, we contributed a novel mid-level descriptor, which converts an activity sequence into simultaneous temporal signals at body parts. With our representation, activities are recognized through both the local video content and the short-time spectral properties of body parts' movements. We draw the analogies between activity and speech recognition and show that our speech-like representation and recognition scheme improves recognition performance in several low-resolution datasets. To complete the research on this subject, we also tackle the challenging problem of recognizing human-vehicle interactions from low-resolution aerial videos. We present a temporal logic based approach which does not require training from event examples. At the low-level, we employ dynamic programming to perform fast model fitting between the tracked vehicle and the rendered 3-D vehicle models. At the semantic-level, given the localized event region of interest (ROI), we verify the time series of human-vehicle spatial relationships with the pre-specified event definitions in a piecewise fashion. Our framework can be generalized to recognize any type of human-vehicle interaction from aerial videos. / text

Dvidešimtajame amžiuje dėl intensyvaus ekonomikos vystymosi ir sparčios mokslo bei technikos pažangos įvyko esminiai pakitimai sąveikaujant visuomenei ir aplinkai. Ūkinės veiklos poveikis aplinkai vertinamas planuojant ūkinę veiklą, nes didžiausia aplinkos teršėjai yra pramonė, energetika, transportas ir žemės ūkis. Ūkinės veiklos interesai turi didelės įtakos aplinkos apsaugos politikos efektyvumui. Dėl griežtų ES reikalavimų ūkinės veiklos poveikio vertinimui, Lietuvoje šiai sričiai skiriamas vis didesnis dėmesys bei prioritetas. Lietuva, įstojusi į Europos Sąjungą, įsipareigoja vykdyti visus ES reikalavimus aplinkosaugos srityje. Nagrinėjant Lietuvos integraciją į ES, magistriniame darbe buvo nustatyta sėkminga jos raida: šiuo metu į Lietuvos teisę perkelti beveik visi vandens, atliekų bei oro apsaugos politiką reglamentuojantys teisės aktai. Keturioms ES direktyvoms yra numatyti pereinamieji laikotarpiai, kurie per ilgesnį laiką leis imti taikyti nustatytas ES normas ir suteiks galimybę visiškai įgyvendinti ES reikalavimus. Atlikus Lietuvos ir ES teisės aktų lyginamąją analizę, nustatytos jų įgyvendinimo spragos, kurios galėtų būti užpildytos stiprinant atsakingų institucijų gebėjimą vykdyti numatytas funkcijas, sukuriant racionalesnę struktūrą, kad darbas būtų mažiau dubliuojamas, bendradarbiaujant su kitomis ES narėmis ir perimant jų patirtį efektyvaus teisės aktų įgyvendinimo srityje. Pasiūlymuose numatyta parengti Lietuvos įmonėms metodikas, leidžiančias įvertinti... [to full text] / In the 20th century due to fast progress of economy and incredible development of science and technologies major influences have been made to our environment. Economy’s impact on the environment may be assessed while planning it, as major environmental polluters are industry, energetics, transport and agricultural sectors. Economy’s interests have an impact on the effectiveness of environmental policy. Due to strict demands from the EU, this subject is exposed to an increasing concern and priority. Having become a part of the EU, Lithuania has committed to implement all of the European Union’s legal claims in the environmental sector. By analyzing Lithuania’s integration into the EU, this thesis establishes its successful development: currently almost all of the EU’s directives on water, air protection and waste management have been harmonized with the Lithuanian law. Four of the EU’s directives have transitional periods assigned, which will allow to employ EU’s norms and fulfill its requirements in the longer run. Having executed a comparative analysis of Lithuanian and European Union legal acts, certain breaches in their implementation were found. These breaches may be emended by strengthening functional performance of responsible institutions, creating a more rational working structure which would prevent redundancy at work while cooperating with EU’s institutions and taking over their experience in effective implementation of legal norms. Suggestions present proposed... [to full text]

Background and Purpose: Physical activity is significantly lower in the end-stage renal disease (ESRD) population compared with age-matched sedentary controls. Self-efficacy is a significant contributing factor to exercise behaviour in the healthy and various chronic disease populations; however, little information is available on self-efficacy and exercise in the ESRD population. The purpose of this study was to examine the relationship between self-efficacy and physical activity levels in individuals with ESRD and to determine factors which may contribute to this relationship. Participants: Patients (127 hemodialysis and 5 peritoneal dialysis) were recruited from the Kingston General Hospital renal units. Methods: Self-efficacy was measured using the Exercise Self-Efficacy Scale (ESES) and the Chronic Disease Self-Efficacy Scale (CDSES). Physical activity was measured using the Human Activity Profile (HAP). Responses on the HAP resulted in 2 scores: the maximum activity score (MAS) and the adjusted activity score (AAS). Contributing factors, such as age, co-morbidities, length on dialysis (vintage), medications, dialysis efficacy (Kt/V), albumin, prealbumin, total protein, protein catabolic rate (PCR) and hemoglobin (HgB) were collected from patient records. Results: The average MAS and AAS scores were 62.5±15.6 and 49.1± 21.0 (SD), respectively, which are substantively lower than those in the healthy population. Serum albumin was the sole contributing factor to physical activity such that AAS in those with lower levels of albumin (24-30g/L, 31-34 g/L) was less than those with higher levels of albumin (p<0.05). Both MAS and AAS were significantly lower in those with diabetes (n=66) compared to those without (n=66), as was the difference between MAS and AAS. Age and self-efficacy explained 51% of the variance in MAS. Age, self-efficacy and serum albumin level explained 59% of variance in AAS. Discussion and Conclusion: Individuals on dialysis have lower functional capability within their maximal energy ability at any age and this difference is more pronounced among those with diabetes. Physical activity was substantially influenced by an individual’s self-efficacy, age and serum albumin level. These findings indicate that self-efficacy must be taken into account and used to promote greater participation in physical activity in the ESRD population. / Thesis (Master, Rehabilitation Science) -- Queen's University, 2010-04-27 09:47:12.764

Αντικείμενο της εργασίας αυτής είναι η μελέτη και κατασκευή εφαρμογής ασύρματου δικτύου με σκοπό την αναγνώριση της ανθρώπινης δραστηριότητας και τον εντοπισμό της πτώσης σε πραγματικό χρόνο, καθώς επίσης και την παρακολούθηση των αποτελεσμάτων από απομακρυσμένη τοποθεσία. Στη συγκεκριμένη εργασία σκοπός είναι η αναγνώριση των τεσσάρων βασικών καταστάσεων της ανθρώπινης φυσικής δραστηριότητας (κάθομαι, ξαπλώνω, στέκομαι, κινούμαι) και ο εντοπισμός της πτώσης με χρήση της των επιταχυνσιομέτρων που προσφέρει η πλατφόρμα SunSpot καθώς και η σύνδεση της διάταξης με το διαδίκτυο για την παροχή πληροφορίας σχετικά με την κατάσταση του κατόχου του συστήματος σε απομακρυσμένη τοποθεσία. Πραγματοποιήθηκε μελέτη σχετικά με διάφορες διατάξεις των αισθητήρων ,την συχνότητα δειγματοληψίας, τους αλγορίθμους κατάταξης καθώς και για τις μεθόδους διάθεσης της πληροφορίας στο διαδίκτυο. Για την αναγνώριση των καταστάσεων και τον εντοπισμό της πτώσης χρησιμοποιήθηκαν δυο πλατφόρμες αισθητήρων SunSPOT, μια στο στήθος (master) και μια στο δεξιό τετρακέφαλο (slave) / A wearable wireless sensor network application performing human activity recognition and fall detection using the Naïve Bayesian Classifier algorithm in the SunSpot Platform accompanied by a web application in the Google App Engine platform to be able to monitor the classification results from a remote location and to automatically notify via e-mail in case of emergency.

L'objectif de cette thèse est de concevoir une approche transparente originale apte à détecter en temps-réel l'occurrence d'une action, dans un flot non segmenté et idéalement le plus tôt possible. Ces travaux s'inscrivent dans une collaboration entre deux équipes de l'IRISA-lnria de Rennes, à savoir lntuidoc et MimeTIC. En profitant de la complémentarité des savoir-faire des deux équipes de recherche, nous proposons de reconsidérer les besoins et les difficultés rencontrées pour modéliser, reconnaître et détecter une action 30 en proposant de nouvelles solutions à la lumière des avancées réalisées en termes de modélisation de gestes manuscrits 20. Les contributions de cette thèse sont regroupées en trois parties principales. Dans la première partie, nous proposons une nouvelle approche pour modéliser et reconnaître une action pré­segmentée. Dans la deuxième partie, nous introduisons une approche permettant de reconnaître une action dans un flot non segmenté. Enfin, dans la troisième partie, nous étendons cette dernière approche pour la caractérisation précoce d'une action avec très peu de d'information. Pour chacune de ces trois problématiques, nous avons identifié explicitement les difficultés à considérer afin d'en effectuer une description complète pour permettre de concevoir des solutions ciblées pour chacune d'elles. Les résultats expérimentaux obtenus sur différents benchmarks d'actions attestent de la validité de notre démarche. En outre, à travers des coopérations ayant eu lieu au cours de la thèse, les approches développées ont été déployées dans trois applications, dont des applications en animation et en reconnaissance de gestes dynamiques de la main. / The objective of this thesis is to design an original transparent approach able to detect in real time the occurrence of an action, in an unsegmented flow and ideally as early as possible. This work is part of a collaboration between two IRISA-lnria teams in Rennes, namely lntuidoc and Mime TIC. By taking advantage of the complementary expertise of the two research teams, we propose to reconsider the needs and difficulties encountered to model, recognize and detect a 30 action by proposing new solutions in the light of the advances made in terms of 20 handwriting modeling. The contributions of this thesis are grouped into three main parts. In the first part, we propose a new approach to model and recognize a pre-segmented action. Indeed, it is first necessary to develop a representation able to characterize as finely as possible a given action to facilitate recognition. In the second part, we introduce an approach to recognize an action in an unsegmented flow. Finally, in the third part, we extend this last approach for the early characterization of an action with very little information. For each of these three issues, we have explicitly identified the difficulties to be considered in order to make a complete description of them so that we can design targeted solutions for each of them. The experimental results obtained on different benchmarks of actions attest to the validity of our approach. In addition, through collaborations that took place during the thesis, the developed approaches were deployed in three applications, including applications in animation and in dynamic hand gestures recognition.

Animais de laboratório estão sujeitos a uma variedade de ruídos diários que podem afetar seu bem estar, havendo estudos que apontam o trabalho humano nas salas de animais como uma importante fonte de ruídos com intensidades e frequências variáveis capazes de causar alterações comportamentais e fisiológicas nesses animais. Este trabalho teve como objetivo analisar os possíveis efeitos dos ruídos gerados durante a atividade humana na gestação de ratas wistar e no crescimento ponderal dos neonatos. Quarenta e quatro ratas wistar de 120 dias de idade, alojadas em sistema de gaiola aberta, oriundas do CREAL/UFRGS, foram acasaladas e submetidas à rotina de trabalho normal (grupo controle) ou expostas a ruídos em duas sessões de 20 minutos/dia com intervalo de 15 segundos entre cada ruído (grupo tratado) durante toda a gestação e na primeira semana de vida dos filhotes. Os ruídos foram previamente selecionados com base no trabalho humano realizado nas salas de animais e registrados por meio do microfone de um medidor de nível de pressão sonora com resposta de frequência 20 Hz-20kHz. As frequências foram avaliadas utilizando-se um software editor de áudio (Audacity® 1.3). Os partos de ambos os grupos (tratado e controle) foram acompanhados e durante os mesmos anotou-se o número de filhotes vivos e natimortos. Para avaliação do peso ponderal dos neonatos pesaram-se os três filhotes maiores de cada ninhada das fêmeas uma vez ao dia entre 14:00 e 16:00 hs. Utilizou-se o teste- T para análise do número de natimortos no qual demonstrou diferença significativa (p= 0,021) entre os grupos. O teste de variância Anova para medidas repetidas e o Tukey-Kramer foram utilizados para comparar o peso médio dos três filhotes maiores, o qual foi observado diferença significativa do peso médio dos três filhotes maiores nos dias 4 (p= 0,0026),5 (p<0,001),6 (p=0,0005) e 7 (p< 0,0001). Este estudo demonstra que ruídos gerados por atividade humana podem gerar filhotes natimortos e interferir no comportamento materno diminuindo o peso do filhote a partir do quarto dia na primeira semana de vida. / Laboratory animals are subjected to a variety of daily noises which can affect their well-being. There are studies that suggest the human work in animal rooms is an important source of noise with varying frequencies and intensities which may cause physiological and behavioral changes in the animals. This work had as its main objective the analysis of the possible effects that the noise generated by professionals while doing their activities may have on pregnancy of Wistar rats, evaluating the natimortality and the weight development of newborns. Fourty-for 120 days old Wistar rats from CREAL/UFRGS accommodated in an open cage system have been paired and have undergone a normal work routine (control group) or have been exposed to noise in two sessions of 20 minutes/day with interval of 15 seconds between each noise (treated group) throughout their pregnancy and in the first week of their offspring’s life. The noises were previously selected on the basis of the human work carried out in animal rooms and recorded through the use of a microphone sound pressure level meter frequency response of 20 Hz-20kHz. The frequencies were evaluated using an audio editor software (Audacity® 1.3). The delivery in both groups (treated and control) were accompanied and during them it was taken note the number of living and stillborn offspring. To evaluate the weight of newborns, the three biggest ones of each litter rats were weighed up once a day between 2:00 and 4:00 p.m. It was used the T-test for examining the number of stillborns which showed a significant difference (p = 0.021) between the groups. The Anova variance test for repeated measures and the Tukey- Kramer test were used to compare the average weight of the three biggest offspring. It was observed significant difference of average weight in the three biggest ones on day 4 (p = 0.0026), 5 (p < 0.001), 6 (p = 0.0005) and 7 (p < 0.0001). This study shows that noise generated by human activity may cause stillborn offspring and interfere with maternal behavior by decreasing the weight of the new born from the fourth day the first week of life.

abstract: The human motion is defined as an amalgamation of several physical traits such as bipedal locomotion, posture and manual dexterity, and mental expectation. In addition to the “positive” body form defined by these traits, casting light on the body produces a “negative” of the body: its shadow. We often interchangeably use with silhouettes in the place of shadow to emphasize indifference to interior features. In a manner of speaking, the shadow is an alter ego that imitates the individual. The principal value of shadow is its non-invasive behaviour of reflecting precisely the actions of the individual it is attached to. Nonetheless we can still think of the body’s shadow not as the body but its alter ego. Based on this premise, my thesis creates an experiential system that extracts the data related to the contour of your human shape and gives it a texture and life of its own, so as to emulate your movements and postures, and to be your extension. In technical terms, my thesis extracts abstraction from a pre-indexed database that could be generated from an offline data set or in real time to complement these actions of a user in front of a low-cost optical motion capture device like the Microsoft Kinect. This notion could be the system’s interpretation of the action which creates modularized art through the abstraction’s ‘similarity’ to the live action. Through my research, I have developed a stable system that tackles various connotations associated with shadows and the need to determine the ideal features that contribute to the relevance of the actions performed. The implication of Factor Oracle [3] pattern interpretation is tested with a feature bin of videos. The system also is flexible towards several methods of Nearest Neighbours searches and a machine learning module to derive the same output. The overall purpose is to establish this in real time and provide a constant feedback to the user. This can be expanded to handle larger dynamic data. In addition to estimating human actions, my thesis best tries to test various Nearest Neighbour search methods in real time depending upon the data stream. This provides a basis to understand varying parameters that complement human activity recognition and feature matching in real time. / Dissertation/Thesis / Masters Thesis Electrical Engineering 2016