Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Multi-mode two-stage unsupervised video anomaly detection method

An anomaly detection and unsupervised technology, applied in neural learning methods, biological neural network models, image analysis, etc., can solve the problems of high missed detection rate and insufficient robustness, achieve enhanced accuracy, reduce missed detection probability, Enhanced Robustness Effects

Pending Publication Date: 2022-04-12
SHANGHAI JIAO TONG UNIV
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This algorithm solves the problems of high missed detection rate and insufficient robustness in the current deep autoencoder algorithm for video anomaly 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
  • Multi-mode two-stage unsupervised video anomaly detection method
  • Multi-mode two-stage unsupervised video anomaly detection method
  • Multi-mode two-stage unsupervised video anomaly detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] Embodiments of the present invention are described below through specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific implementation modes, and various modifications or changes can be made to the details in this specification based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that, in the case of no conflict, the following embodiments and features in the embodiments can be combined with each other.

[0040] Such as figure 1 As shown, the embodiment of the present invention includes a multimodal two-stage unsupervised abnormal video detection method. In the first stage, a multi-scale memory-enhanced autoencoder network is designed, and the network is used to learn the image features and op...

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 invention discloses a multi-mode two-stage unsupervised abnormal video detection method. According to the method, video optical flow information and a memory network module are fully utilized, and the end-to-end unsupervised video anomaly detection method is realized. In the two stages, firstly, a multi-scale memory enhanced auto-encoder network module is used for respectively inputting an image sequence and an optical flow sequence of a video for reconstruction, and then the reconstructed image sequence, the reconstructed optical flow sequence and memory network feature information of optical flow are input into an optical flow feature fusion auto-encoder network module. And outputting the predicted video image, and detecting the video abnormality according to the error between the predicted image and the real image and the error between the reconstructed optical flow and the real optical flow. According to the method, the common problems of high omission ratio, insufficient robustness and the like of a depth auto-encoder method for video anomaly detection at present are solved.

Description

technical field [0001] The invention relates to the field of machine vision, in particular to a multimodal two-stage unsupervised video anomaly detection method. Background technique [0002] In modern video surveillance systems, the detection of abnormal video activities can be divided into real-time judgment and video query after abnormal events occur. The real-time judgment mainly relies on the monitoring personnel to operate multiple cameras in the control room in real time and be on duty around the clock. This has high requirements on the attention of the monitoring personnel, and observing the screen for a long time will seriously damage the human visual system. Video query after an abnormal event occurs requires manual retrieval of stored video recordings, which takes a long time and often fails to obtain abnormal event clips in time. [0003] In response to these disadvantages, the intelligent monitoring system based on computer vision technology has attracted more...

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 Applications(China)
IPC IPC(8): G06T7/00G06T7/269G06V10/80G06N3/04G06N3/08
Inventor 田野施晓华卢宏涛
Owner SHANGHAI JIAO TONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com