Integrated Multiscale Appearance Features and Motion Information Prediction Network for Anomaly Detection

Figure 6

Frame-level evaluation results on Avenue 7th test video. (a) Ground truth of the 465th frame (A) and 593rd frame (B) labelled as abnormal. (b) Difference between the ground truth and the corresponding predicted frame. (c) Relationship between the test video frames and the regular score.

(a)

(b)

(c)