FIRST-PERSON ACTION RECOGNITION THROUGH VISUAL RHYTHM TEXTURE DESCRIPTION

Autor(es)

Moreira, Thierry Pinheiro ; Menotti, David ; Pedrini, Helio ; IEEE

• Tipo de documento: Artigo Científico
• Fonte: 2017 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP); v. N/A, p. 5-pg., 2017-01-01.

Resumo

First-person action recognition is a recent problem in computer vision, where an observer wears body cameras to understand and recognize actions from the captured video sequences. Technological advances have made it possible to offer small wearable cameras that can be attached onto bike helmets, belts, animal halters, among other accessories. Examples of potential applications include sports, security, healthcare, visual life logging, among others. In this paper, we propose a novel approach to first-person action recognition that consists in encoding video appearance, shape and motion information as visual rhythms and describing them through texture analysis. Experiments are conducted on the Dog Centric Activity and JPL First-Person Interaction datasets, showing accuracy improvement over the baselines. (AU)

• Processo FAPESP: 15/03156-7 - Reconhecimento de atividades em vídeos
• Beneficiário: Thierry Pinheiro Moreira
• Modalidade de apoio: Bolsas no Brasil - Doutorado
• Processo FAPESP: 15/12228-1 - Detecção e reconhecimento de eventos complexos em vídeos
• Beneficiário: Hélio Pedrini
• Modalidade de apoio: Bolsas no Exterior - Pesquisa