2019-11-202019-09-27SOARES, I. M. Uma abordagem bottom-up completa para reconhecimento de atividades humanas em imagens através da pose estimada com redes convolucionais. 2019. 127 f. Dissertação (Mestrado em Engenharia Elétrica e da Computação) - Universidade Federal de Goiás, Goiânia, 2019.http://repositorio.bc.ufg.br/tede/handle/tede/10191In the last few years, significant improvements in the computer vision were made, making it possible to obtain important information from images. Some of the challenges for a better understanding of a scene are the detection of people and the recognition of the activities they are performing. This work propose a single end-to-end model able to detect people, estimate their pose, and recognize each one of their activities by their pose. The experiments show that the model has reached the state of the art in the tasks of person detection and pose estimation on MSCOCO Dataset 2017, and can recognize walking, running, sitting, and standing activities with an F1 score of 0.7344. The model is real-time with an inference rate of approximately 20 frames/sec.application/pdfAcesso AbertoEstimação de poseReconhecimento de atividadesDetecção de pessoasRedes neurais convolucionaisMulti-person pose estimationHuman activity recognitionPerson detectionConvolutional neural networksENGENHARIAS::ENGENHARIA ELETRICADissertação