Bacharelado em Ciência da Computação (Sede)
URI permanente desta comunidadehttps://arandu.ufrpe.br/handle/123456789/6
Siglas das Coleções:
APP - Artigo Publicado em Periódico
TAE - Trabalho Apresentado em Evento
TCC - Trabalho de Conclusão de Curso
Navegar
2 resultados
Resultados da Pesquisa
Item Semantic segmentation for people detection on beach images(2021-03-01) Monte, Leonardo de Araujo; Macário Filho, Valmir; http://lattes.cnpq.br/4346898674852080; http://lattes.cnpq.br/0547792731866043Cameras monitoring are increasingly aided by computer vision systems that identify risk situations. This work is part of an automatic track system to monitor beaches in the metropolitan area of Recife in order to prevent bathers to trespass the boundaries of the safe region for swimming. Semantic segmentation has gained strength in several computer vision tasks. Usually, the metaarchitecture of a semantic segmentation network consists of two modules: encoder (backbone) and decoder. This work does a study combining a set of semantic segmentation networks, Unet, Xnet, LinkNet and Unet++ with the pretrained backbones VGG16 and VGG19, to detect swimmners in beach images. We have used our own dataset, made by several images taken at the Boa Viagem beach, RecifeBrazil. The algorithms are evaluated with MIoU metric regarding the entire image scene and just in the water area. The best MIoU regarding all image was 80.87best MIoU in detecting swimmers at the beach was 85.56obtained by the LinkNet algorithm with both VGG16 and VGG19 backbones.Item Detecção de mãos através da combinação de técnicas de detecção de tom de pele e movimento para background complexo(2018-08-18) Sá, Vinícius Cavalcanti Nogueira de; Macário Filho, Valmir; http://lattes.cnpq.br/4346898674852080; http://lattes.cnpq.br/1197232523837982Technology has a social function to facilitate the life of its users, with its evolution, and with the emergence of globalization, the access to information and communication in general have become much more accessible for the general population. Nevertheless, groups with special needs still suffer from the lack of products and systems that can meet their needs. This work will make use of pre-existing technologies that can be used to make life easier for these users, especially deaf users. We live in a world where we are faced with an immensity of devices with cameras, or of equipment that can be connected to one, the computer vision becomes very important or otherwise, essential from this reality. Many areas use images to automate or assist their activities within their segments, whether they are for entertainment, industry or others. Thus, it is possible to realize the importance of image processing as a solution of problems in different areas. In this work it was used image processing to elaborate a possible solution in the hand recognition area, the use of the hand as a way of communication is evident. We can see it as a main character not only in everyday communication through gestures, but we can also use it in the control of computational interfaces, in the aid of immersion in virtual reality, in the manipulation of virtual objects in augmented reality or even as facilitator in the accessibility from the communication by signals, being this last example the key point of this work, that aims to facilitate the communication between deaf and possible users interested in the sign language through a new approach. Hand recognition was performed through a hybrid approach involving skin tone segmentation and movement, this approach was chosen to overcome the difficulties that each type of segmentation brings. The best hit rate we had with this approach was 76.4% indoors and 45.15% in outdoor environment.