Utilize este identificador para referenciar este registo:
https://hdl.handle.net/10316/27816
Título: | Trajectory-based human action segmentation | Autor: | Santos, Luís Khoshhal, Kamrad Dias, Jorge |
Palavras-chave: | Motion segmentation; Classification framework; Signal processing; Motion variability; Adaptive sliding window | Data: | Fev-2015 | Editora: | Elsevier | Citação: | SANTOS, Luís; KHOSHHAL, Kamrad; DIAS, Jorge - Trajectory-based human action segmentation. "Pattern Recognition". ISSN 0031-3203. Vol. 48 Nº. 2 (2015) p. 568–579 | Título da revista, periódico, livro ou evento: | Pattern Recognition | Volume: | 48 | Número: | 2 | Resumo: | This paper proposes a sliding window approach, whose length and time shift are dynamically adaptable in order to improve model confidence, speed and segmentation accuracy in human action sequences. Activity recognition is the process of inferring an action class from a set of observations acquired by sensors. We address the temporal segmentation problem of body part trajectories in Cartesian Space in which features are generated using Discrete Fast Fourier Transform (DFFT) and Power Spectrum (PS). We pose this as an entropy minimization problem. Using entropy from the classifier output as a feedback parameter, we continuously adjust the two key parameters in a sliding window approach, to maximize the model confidence at every step. The proposed classifier is a Dynamic Bayesian Network (DBN) model where classes are estimated using Bayesian inference. We compare our approach with our previously developed fixed window method. Experiments show that our method accurately recognizes and segments activities, with improved model confidence and faster convergence times, exhibiting anticipatory capabilities. Our work demonstrates that entropy feedback mitigates variability problems, and our method is applicable in research areas where action segmentation and classification is used. A working demo source code is provided online for academical dissemination purposes, by requesting the authors. | URI: | https://hdl.handle.net/10316/27816 | ISSN: | 0031-3203 | DOI: | 10.1016/j.patcog.2014.08.015 | Direitos: | openAccess |
Aparece nas coleções: | I&D ISR - Artigos em Revistas Internacionais FCTUC Eng.Electrotécnica - Artigos em Revistas Internacionais |
Ficheiros deste registo:
Ficheiro | Descrição | Tamanho | Formato | |
---|---|---|---|---|
Trajectory-based human action segmentation.pdf | 6.89 MB | Adobe PDF | Ver/Abrir |
Citações SCOPUSTM
34
Visto em 15/abr/2024
Citações WEB OF SCIENCETM
5
27
Visto em 2/abr/2024
Visualizações de página 5
1.619
Visto em 23/abr/2024
Downloads 50
790
Visto em 23/abr/2024
Google ScholarTM
Verificar
Altmetric
Altmetric
Todos os registos no repositório estão protegidos por leis de copyright, com todos os direitos reservados.