Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Learning a distance function with a Siamese network to localize anomalies in videos

About

This work introduces a new approach to localize anomalies in surveillance video. The main novelty is the idea of using a Siamese convolutional neural network (CNN) to learn a distance function between a pair of video patches (spatio-temporal regions of video). The learned distance function, which is not specific to the target video, is used to measure the distance between each video patch in the testing video and the video patches found in normal training video. If a testing video patch is not similar to any normal video patch then it must be anomalous. We compare our approach to previously published algorithms using 4 evaluation measures and 3 challenging target benchmark datasets. Experiments show that our approach either surpasses or performs comparably to current state-of-the-art methods.

Bharathkumar Ramachandra, Michael J. Jones, Ranga Raju Vatsavai• 2020

Related benchmarks

TaskDatasetResultRank
Video Anomaly DetectionCUHK Avenue (Ave) (test)
AUC87.2
203
Abnormal Event DetectionUCSD Ped2 (test)
AUC94
146
Abnormal Event DetectionUCSD Ped2
AUC94
132
Video Anomaly DetectionAvenue (test)
AUC (Micro)87.2
85
Video Anomaly DetectionCUHK Avenue
Frame AUC87.2
65
Abnormal Event DetectionAvenue (test)
RBDC41.2
37
Abnormal Event DetectionUCSD Ped1 (test)--
33
Abnormal Event DetectionUCSD Ped1--
28
Showing 8 of 8 rows

Other info

Follow for update