Vision-based Fight Detection from Surveillance Cameras
It addresses a specific application for public safety in areas like prisons, but is incremental in method.
The paper tackles the problem of detecting fights from surveillance camera videos using an LSTM-based approach with attention, and reports improved state-of-the-art accuracy on datasets including a newly collected one.
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. 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.