Doutorado em Engenharia Elétrica

URI Permanente para esta coleção

http://repositorio.ufes.br/handle/10/17618

Nível: Doutorado
Ano de início:
Conceito atual na CAPES:
Ato normativo:
Periodicidade de seleção:
Área(s) de concentração:
Url do curso:

Navegar

Navegando Doutorado em Engenharia Elétrica por Autor "Almonfrey, Douglas"

Agora exibindo 1 - 2 de 2
  • Nenhuma Miniatura disponível
    Item
    Serviço Flexível de Detecção de Seres Humanos para Espaços Inteligentes Baseados em Redes de Câmeras
    (Universidade Federal do Espírito Santo, 2018-07-26) Almonfrey, Douglas; Salles, Evandro Ottoni Teatini; Vassallo, Raquel Frizera; Santos-Victor, José Alberto; Salomão, João Marques; Rauber, Thomas Walter; Ciarelli, Patrick Marques
    The topic of intelligent spaces has experienced increasing attention in the last decade. As aninstance of the ubiquitous computing paradigm, the general idea is to extract information fromthe ambient and use it to interact and provide services to the actors present in the environment.The sensory analysis is mandatory in this area and humans are usually the principal actorsinvolved. In this sense, we propose a human detector to be used in an intelligent space based ona multi-camera network. Our human detector is implemented using concepts of cloud computingand service-oriented architecture (SOA). As the main contribution of the present work, thehuman detector is designed to be a service that is scalable, reliable and parallelizable. It isalso a concern of our service to be flexible, decoupled from specific processing nodes of theinfrastructure and less structured as possible, attending different intelligent space applicationsand services. Since it can be easily found already installed in many different environments,a multi-camera system is used to overcome some difficulties traditionally faced by existinghuman detection methods that are based in only one camera. To validate our approach, weimplement three different applications that are proof of concept (PoC) of many day-to-day realtasks. Two of these applications are related to robot navigation and demand the knowledge aboutthe tridimensional localization of the humans present in the environment. With respect to timeand detection performance requirements, our human detection service has proved to be suitablefor interacting with the other services of our Intelligent Space, in order to successfully completethe tasks of each application. As an additional contribution, a feature extraction procedure basedon the independent component analysis (ICA) theory is proposed as part of a detector andevaluated in public datasets. The pedestrian detection area is used as a playground to developthe human detector since it is the most mature research area of the human detection literature.The resulted detector is also used in the pipeline of the proposed human detection service, thus,being also applied in real-time applications in the intelligent space used as our testbed.
  • Nenhuma Miniatura disponível
    Item
    Sistema de reconhecimento de gestos e ações em tempo real baseado em visão computacional
    (Universidade Federal do Espírito Santo, 2020-12-17) Santos, Clebeson Canuto dos; Vassallo, Raquel Frizera; https://orcid.org/0000000247623219; http://lattes.cnpq.br/9572903915280374; https://orcid.org/0000000273141934; http://lattes.cnpq.br/7754166023347003 ; Ciarelli, Patrick Marques; https://orcid.org/0000000331774028; http://lattes.cnpq.br/1267950518719423; Almonfrey, Douglas; https://orcid.org/0000-0002-0547-3494; http://lattes.cnpq.br/1291322166628469; Montalvão Filho, Jugurta Rosa; https://orcid.org/0000-0002-6659-6439; http://lattes.cnpq.br/4582408199121884; Bernardino, Alexandre José Malheiro; https://orcid.org/0000-0003-3991-1269
    This thesis aims to investigate and propose mechanisms for recognizing and anticipating dynamic gestures and actions based only on computer vision. Three proposals are focused on gesture recognition: Star RGB- a representation that condenses the montion contained in the frames of a video into only one RGB image; Star iRGB- an iterative version of Star RGB that can be used by learning models of sequential nature; and Star iRGBhand- an iterative model for recognizing gestures that uses the shape of the hands as context. For action anticipation, bayesian models based on recurrent neural networks were presented, which uses context information to reduce the ambiguity between similar movements in addition to a threshold on the estimated epistemic uncertainty to decide when an action should be anticipaded. In this context, two models have been proposed to recognize and anticipate gestures online. All proposals were validated through several experiments whose results were compared to several baselines. In this sense, three main datasets were used: Montalbano, for gestures captured by only one camera; IS-Gesture, for gestures captured in a multi-camera environment; and Acticipate, for action anticipation. The results achieved with the gesture recognition models were the best for the Montalbano set when considering works that use only RGB images. Even when compared to multimodal models, based on CNN 3D, the results are among the best, just slightly behind (less than 1%) two multimodal proposals. In the task of anticipating actions, the accuracy of recognition and anticipation obtained when using the dataset Acticipate were the best ones achieved so far. Finally, considering the models that aim to recognize and anticipate gestures online, the proposed model that works with only one camera has also achieved results among the best in literature for the Montalbano dataset. In relation to IS-Gesture, which represents the most complex challenge due to the multi-camera environment, the average accuracy of recognition and anticipation of gestures was considered satisfactory, with clear indications of where improvements should be made to achieve better results. Regarding the execution time, the proposed models were all able to provide information for an application that requires a frame rate of up to 10 FPS. Thus, it is possible to use such models in an interactive application in real time, in an environment with one or several cameras. In summary, all the proposals have shown to be very promising, obtaining results that go beyond the main related works that address the previously mentioned datasets.