Utilize este identificador para referenciar este registo:
https://hdl.handle.net/1822/62744
Título: | A machine learning approach to detect violent behaviour from video |
Autor(es): | Nova, David Ferreira, André Leite Cortez, Paulo |
Palavras-chave: | Action recognition Machine learning Pose estimation Support Vector Machine Video analysis |
Data: | 2019 |
Editora: | Springer Verlag |
Revista: | Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering (LNICST) |
Resumo(s): | The automatic classification of violent actions performed by two or more persons is an important task for both societal and scientific purposes. In this paper, we propose a machine learning approach, based a Support Vector Machine (SVM), to detect if a human action, captured on a video, is or not violent. Using a pose estimation algorithm, we focus mostly on feature engineering, to generate the SVM inputs. In particular, we hand-engineered a set of input features based on keypoints (angles, velocity and contact detection) and used them, under distinct combinations, to study their effect on violent behavior recognition from video. Overall, an excellent classification was achieved by the best performing SVM model, which used keypoints, angles and contact features computed over a 60 frame image input range. |
Tipo: | Artigo em ata de conferência |
URI: | https://hdl.handle.net/1822/62744 |
ISBN: | 9783030164461 |
DOI: | 10.1007/978-3-030-16447-8_9 |
ISSN: | 1867-8211 |
Versão da editora: | https://link.springer.com/chapter/10.1007%2F978-3-030-16447-8_9 |
Arbitragem científica: | yes |
Acesso: | Acesso aberto |
Aparece nas coleções: |
Ficheiros deste registo:
Ficheiro | Descrição | Tamanho | Formato | |
---|---|---|---|---|
Article_Intetain.pdf | Author's Accepted Manuscript | 2,06 MB | Adobe PDF | Ver/Abrir |