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

A video abnormal behavior detection method based on action prediction

A detection method and action prediction technology, which is applied in the direction of instruments, biological neural network models, character and pattern recognition, etc., can solve the problems of low robustness and low applicability, achieve faster processing speed, reduce preprocessing time, increase The effect of robustness

Active Publication Date: 2019-06-21
SOUTH CHINA UNIV OF TECH
View PDF8 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method is more practical for scenes with dense crowds. It is less applicable to scenes where the motion trajectory does not change when anomalies occur. It is less robust when detecting abnormal events caused by behaviors such as running and jumping. defect

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
  • A video abnormal behavior detection method based on action prediction
  • A video abnormal behavior detection method based on action prediction
  • A video abnormal behavior detection method based on action prediction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0040] In this example, if figure 1 Shown is a flow chart of a video abnormal behavior detection method based on motion prediction, and the specific steps include:

[0041] (1) Design an adversarial generative network model, the designed adversarial generative network model includes a generator and a discriminator.

[0042] Such as figure 2As shown, this embodiment adopts the confrontation generative network model to generate the predicted video, and the model includes two parts: a generator and a discriminator, and the generator includes two parts: an encoder and a decoder. The encoder in the generator is used to extract the action features and graphic features of the observed video, and the decoder is used to generate the predicted video based on the action features and graphic features output by the encoder. The discriminator is used to score the generated predicted or real videos. The method of anomaly detection adopts the Raida criterion method to statistically predic...

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 video abnormal behavior detection method based on motion prediction, and the method comprises the specific steps: designing a confrontation generation network model which comprises a generator and a discriminator; Constructing a coding part of the generator; Constructing a decoding part of the generator; Establishing a discriminator; Training a generator and a discriminator of the adversarial generation network model; And detecting an abnormal event occurring in the video according to the obtained optimal generator network. According to the method, a part of videos ofnormal behaviors are used for counting the generation errors, the abnormal detection threshold values are dynamically generated according to different scenes and time changes, the method can be applied to more different scenes, and robustness is improved.

Description

technical field [0001] The invention relates to the field of image and video processing, in particular to a method for detecting abnormal video behavior based on motion prediction. Background technique [0002] Video detection is one of the important applications in the field of computer vision, and video abnormal behavior detection is an indispensable and important part of intelligent video surveillance. Handle unusual behavior. [0003] One of the key issues in abnormal behavior detection methods is to extract relevant features from raw videos in order to classify different types of abnormalities well. Among traditional feature extraction methods, spatial and temporal features are most commonly used to model behavioral patterns. Both spatial and temporal features are proposed based on computer vision, such as histograms of oriented gradients, optical flow histograms, social force models, dense trajectories, and dynamic textures. But artificially designed features requir...

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
IPC IPC(8): G06K9/00G06N3/04
Inventor 黎敏婷余翔宇范子娟
Owner SOUTH CHINA UNIV OF TECH
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