… a novel statistical feature descriptor to detect violent human activities in real-world surveillance
videos. … In this work, a statistical feature descriptor to represent the violent activities in …

… statistical distance for anomaly detection. In contrast to previous methods which were based
on either handcrafted or deep features, … vision features, we applied this statistical distance to …

… low-level features, such as texture and statistical features of the … with these features is lower
than that without these features. … and LHOF features could capture the texture and statistical …

… In this paper, we adopt a two-level statistical aggregation technique to generate the feature
… motion statistics according to the classified types in the video to generate the feature set for …

… Non-parametric background models consider the statistical behaviour of image features to
segment the foreground from the background. In [13], a non-parametric model is proposed for …

… video surveillance, the extracted features should capture the difference between the nominal
and anomalous events within a video… the optical flow statistics for the first test video of the …

… we call it temporal feature set. The spatial feature set is composed by one feature, which is
the … In the temporal feature set, the features have been designed upon three temporal basic …

… With more expressive features and more complicated model, our framework can accurately
… in surveillance video. We carried out extensive experiments on several benchmark video …

… statistical theory, we introduce Boltzmann Entropy to capture the chaos degree of crowd
behavior for video surveillance. … nature of crowd motion in surveillance videos. This accounts for …

… On the other hand, the GMDs are commonly used in surveillance applications to detect …
features that highlight and summarize motion. For example, 3d spatio temporal Haar features …