Modeling abnormal spatiotemporal events is challenging since data belonging to abnormal activities are less in the course of a surveillance stream. We solve this issue using a normality modeling approach, where abnormalities are detected as deviations from the normal patterns. To this end, we propose a residual spatiotemporal autoencoder, which is trainable end-to-end to carry out the anomaly detection task in surveillance videos. Irregularities are detected using the reconstruction loss, where normal frames are reconstructed well with a low reconstruction cost, and the converse is identified as abnormal frames. We evaluate the effect of residual connections in the STAE architecture and presented good practices to train an autoencoder for video anomaly detection using benchmark datasets, namely CUHK-Avenue, UCSD-Ped2, and Live Videos. Comparisons with the existing approaches prove that the effectiveness of residual blocks is incremental than going deeper with additional layers to train a spatiotemporal autoencoder with good generalization across datasets.

中文翻译：

---

用于无监督视频异常检测的残差时空自编码器

对异常时空事件进行建模具有挑战性，因为在监视流的过程中属于异常活动的数据较少。我们使用正态性建模方法来解决这个问题，其中异常被检测为与正常模式的偏差。为此，我们提出了一种残差时空自编码器，它是可端到端训练的，用于执行监控视频中的异常检测任务。使用重建损失检测不规则，其中正常帧以较低的重建成本被很好地重建，反之则被识别为异常帧。我们评估了 STAE 架构中残差连接的效果，并提出了使用基准数据集（即 CUHK-Avenue、UCSD-Ped2 和 Live Videos）训练用于视频异常检测的自动编码器的良好实践。