Minicurso: “Percepção Ambiental a partir de Características de Baixo Nível e Fusão de Dados”
Trilha de PD&I
Local: Laboratório de Graduação 1 do ICOMP
Público alvo: Alunos de graduação finalistas, pós-graduação ou profissionais das áreas de engenharia, computação e afins. É importante ter algum conhecimento sobre arquitetura, sensores, visão e imagem digital.
Resumo: At the core of a several tasks such as object recognition, tridimensional reconstruction and alignment resides the critical problem of extracting features. Due to the ambiguity in our world and the presence of noise in the data acquisition process, computing high quality features, i.e. discriminative and invariant features, is one of the most challenging tasks in robotics and computer vision. The past decade has witnessed the explosion of approaches on extracting visual features and geometrical features and most recently there is a great effort to design new methods that use the best information of both worlds (visual and geometrical) in an efficient and low cost way. In this course we will present the most used image and geometrical descriptors to extract information and to perceive the environment and how to fuse visual and geometrical features to improve the results in tasks such as object recognition, superresolusion and mapping.
Carga horária: 10 h
Vagas: 40
IMPORTANTE! Conflita com a oficina de UAV CTR da trilha de PD&I e com as Oficinas 1 e 2 da trilha de educação.