Activity recognition from videos

• Grant number: 15/03156-7
• Support Opportunities: Scholarships in Brazil - Doctorate
• Start date: August 01, 2015
• End date: May 31, 2018
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Agreement: Coordination of Improvement of Higher Education Personnel (CAPES)
• Principal Investigator: Hélio Pedrini
• Grantee: Thierry Pinheiro Moreira
• Host Institution: Instituto de Computação (IC). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil
• Associated research grant: 11/22749-8 - Challenges in exploratory visualization of multidimensional data: paradigms, scalability and applications, AP.TEM

Abstract

Activity recognition is a growing area and has wide applications, including monitoring, people aiding and human-computer interface. The literature in the field is mainly composed by works that aim to obtain information from different sources and categories, and perform learning by joining them. Activity context is thereby obtained. Many works focus on very specific applications, using techniques that can not be employed in other situations. Other methods add little context information, leaving little or no room to add new data sources. This project proposes the creation of an activity recognition system, flexible to the context, that is based on an action recognition system and information on interaction between people and objects, scenarios and other people. Information fusion will be made by a probabilistic/statistic, graphic or learning system. The method evaluation will be made through tests in public bases by analyzing accuracy rate values and response time. These quantitative indicators will be compared with other state-of-the-art methods. (AU)

Scientific publications

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

MOREIRA, THIERRY PINHEIRO; MENOTTI, DAVID; PEDRINI, HELIO. Video action recognition based on visual rhythm representation. JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, v. 71, p. 14-pg., 2020-08-01. (17/12646-3, 14/12236-1, 15/03156-7)

DE LIMA, VITOR; MOREIRA, THIERRY; PEDRINI, HELIO; SCHWARTZ, WILLIAM ROBSON; IMAI, F; TREMEAU, A; BRAZ, J. Fast Scalable Coding based on a 3D Low Bit Rate Fractal Video Encoder. PROCEEDINGS OF THE 12TH INTERNATIONAL JOINT CONFERENCE ON COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS (VISIGRAPP 2017), VOL 4, v. N/A, p. 10-pg., 2017-01-01. (15/12228-1, 15/03156-7)

MOREIRA, THIERRY PINHEIRO; MENOTTI, DAVID; PEDRINI, HELIO; IEEE. FIRST-PERSON ACTION RECOGNITION THROUGH VISUAL RHYTHM TEXTURE DESCRIPTION. 2017 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), v. N/A, p. 5-pg., 2017-01-01. (15/03156-7, 15/12228-1)

Academic Publications

(References retrieved automatically from State of São Paulo Research Institutions)

MOREIRA, Thierry Pinheiro. Reconhecimento de ações em vídeos baseado na fusão de representações de ritmos visuais. 2018. Doctoral Thesis - Universidade Estadual de Campinas (UNICAMP). Instituto de Computação Campinas, SP.