TY - GEN
T1 - Vision-based Fight Detection from Surveillance Cameras
AU - Akti, Seymanur
AU - Tataroglu, Gozde Ayse
AU - Ekenel, Hazim Kemal
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/11
Y1 - 2019/11
N2 - Vision-based action recognition is one of the most challenging research topics of computer vision and pattern recognition. A specific application of it, namely, detecting fights from surveillance cameras in public areas, prisons, etc., is desired to quickly get under control these violent incidents. This paper addresses this research problem and explores LSTM-based approaches to solve it. Moreover, the attention layer is also utilized. Besides, a new dataset is collected, which consists of fight scenes from surveillance camera videos available at YouTube. This dataset is made publicly available 1. From the extensive experiments conducted on Hockey Fight, Peliculas, and the newly collected fight datasets, it is observed that the proposed approach, which integrates Xception model, Bi-LSTM, and attention, improves the state-of-the-art accuracy for fight scene classification.
AB - Vision-based action recognition is one of the most challenging research topics of computer vision and pattern recognition. A specific application of it, namely, detecting fights from surveillance cameras in public areas, prisons, etc., is desired to quickly get under control these violent incidents. This paper addresses this research problem and explores LSTM-based approaches to solve it. Moreover, the attention layer is also utilized. Besides, a new dataset is collected, which consists of fight scenes from surveillance camera videos available at YouTube. This dataset is made publicly available 1. From the extensive experiments conducted on Hockey Fight, Peliculas, and the newly collected fight datasets, it is observed that the proposed approach, which integrates Xception model, Bi-LSTM, and attention, improves the state-of-the-art accuracy for fight scene classification.
KW - Action recognition
KW - Deep learning
KW - Fight detection
UR - http://www.scopus.com/inward/record.url?scp=85077959553&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85077959553&partnerID=8YFLogxK
U2 - 10.1109/IPTA.2019.8936070
DO - 10.1109/IPTA.2019.8936070
M3 - Conference contribution
AN - SCOPUS:85077959553
T3 - 2019 9th International Conference on Image Processing Theory, Tools and Applications, IPTA 2019
BT - 2019 9th International Conference on Image Processing Theory, Tools and Applications, IPTA 2019
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 9th International Conference on Image Processing Theory, Tools and Applications, IPTA 2019
Y2 - 6 November 2019 through 9 November 2019
ER -