Search

This paper proposes an intermediate fused network with multiple timescales to predict future video segments for video anomaly detection. Video prediction technique for anomaly detection requires to derive an anomaly-distinguishable future frame from normal distributions provided by training data. Then by measuring the difference between generated frames and reference frames, the model can tell which frames represent anomalous events in certain video sequence. In order to synthesize more distinctive future frames, we propose to boost image predictions by integrating several input video segments in multiple timescales. Specifically, the diversity in timescales means the diversity in sampling frequencies of video frames. In addition, we introduce a novel intermediate fusion strategy by concatenating feature maps from intermediate layers to better preserve different characteristics from different timescales. We evaluate the proposed method on some public video surveillance datasets and achieve competitive results with respect to the state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

In this paper, we present a novel deep learning based method for video anomaly detection and localization. The key idea of our approach is that the latent space representations of normal samples are trained to accord with a specific prior distribution by the proposed deep neural network - Multivariate Gaussian Fully Convolution Adversarial Autoencoder (MGFC-AAE), while the latent representations of anomalies do not. In order to extract deep features from input samples as latent representations, a convolutional neural network (CNN) is employed for the encoder of the deep network. Based on the probability that the test sample is associated with the prior distribution, an energy-based method is applied to obtain its anomaly score. A two-stream framework is utilized to integrate the appearance and motion cues to achieve more comprehensive detection results, taking the gradient and optical flow patches as inputs for each stream. Besides, a multi-scale patch structure is put forward to handle the perspective of some video scenes. Experiments are conducted on three public datasets, results verify that our framework can accurately detect and locate abnormal objects in various video scenes, achieving competitive performance when compared with other state-of-the-art works. [ABSTRACT FROM AUTHOR]