Unlock instant, AI-driven research and patent intelligence for your innovation.

Anomaly detection method based on multi-scale video

An anomaly detection and multi-scale technology, applied in the direction of neural learning methods, instruments, biological neural network models, etc., can solve the problems of inability to detect local anomalies, insensitivity of local anomalies, etc., to improve regional prediction capabilities, enhance local difference samples, The effect of speeding up training

Active Publication Date: 2021-08-27
广东众聚人工智能科技有限公司
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

We found that anomalies often occur in a certain area of ​​the video frame. If we simply calculate the peak signal-to-noise ratio score directly between the generated frame and the real frame, it will not be sensitive to local anomalies and cannot perform good detection on local anomalies. detection

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Anomaly detection method based on multi-scale video

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments, wherein the schematic embodiments and descriptions are only used to explain the present invention, but are not intended to limit the present invention.

[0023] Video anomaly detection is a challenging task, and it is quite difficult to collect all types of anomalous events, which makes traditional binary classification methods unsuitable. Furthermore, it is difficult to clearly define abnormal situations. Given that outliers are usually context-dependent, abnormal events in one scene can be treated as normal events in another scene.

[0024] In the prior art, when performing anomaly detection, the anomaly type is directly found in the binary method through the training of the anomaly type, and the normal frames are input into the deep neural network during the training process of the model, and these frames are attempted to be reconstructed wi...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The present invention relates to a multi-scale video anomaly detection method. The method includes: step S1: acquire video sample data, and make multi-scale changes to the video sample; step S2: build an anomaly detection model and perform model training; step S3: carry out Testing of Multiscale Anomaly Detection Models. The invention improves the monitoring sensitivity of local anomalies by dividing predicted frames and real frames into blocks on different scales.

Description

technical field [0001] The invention belongs to the field of security technology, and in particular relates to a multi-scale video anomaly detection method. Background technique [0002] Video anomaly detection refers to the detection of abnormal behaviors that occur in videos. With the increasing popularity of surveillance video, it becomes more and more necessary to automatically identify abnormal events in the video, because manual inspection may cause a lot of waste of resources (e.g., labor force). However, video anomaly detection is a challenging task due to the rarity and diversity of anomalous events. More specifically, anomalous events occur rarely and may be events that have never been seen before. Therefore, it is quite difficult to collect all types of anomalous events, which makes traditional binary classification methods unsuitable. Furthermore, it is difficult to clearly define abnormal situations. Given that outliers are usually context-dependent, abnorma...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V20/41G06N3/045G06F18/214
Inventor 房体品韩忠义杨光远张凯
Owner 广东众聚人工智能科技有限公司