Skip to main content

Multi-Scale Background Suppression Anomaly Detection In Surveillance Videos

Zhen Yang, Yuanfang Guo, Jinjie Wei, Xiuguo Bao, Di Huang

  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00
    Length: 00:09:43
20 Sep 2021

Video anomaly detection has been widely applied in various surveillance systems for public security. However, the existing weakly supervised video anomaly detection methods tend to ignore the interference of the background frames and possess limited ability to extract effective temporal information among the video snippets. In this paper, a multi-scale background suppression based anomaly detection (MS-BSAD) method is proposed to suppress the interference of the background frames. We propose a multi-scale temporal convolution module to effectively extracts more temporal information among the video snippets for the anomaly events with different durations. A modified hinge loss is constructed in the suppression branch to help our model to better differentiate the abnormal samples from the confusing samples. Experiments on UCF Crime demonstrate the superiority of our MS-BSAD method in the video anomaly detection task.

Value-Added Bundle(s) Including this Product

More Like This

  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00
  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00