Active visual attention monitoring video significant event intelligent detection and early warning method

A technology of active vision and surveillance video, applied in computer parts, instruments, characters and pattern recognition, etc., can solve the problems of difficult numerical change rules, many weights, difficult to approach the optimal solution, etc., to achieve active and accurate positioning Effect

Active Publication Date: 2017-07-14
重庆警察学院
View PDF8 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In practical applications, there are many weights that need to be optimized, and the numerical change law of weights is difficult to accurately describe with mathematical models
If the weight is determined by manual trial and error method or grid search method, the amount of calculation will be very large, and it is difficult to approach the optimal solution

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
  • Active visual attention monitoring video significant event intelligent detection and early warning method
  • Active visual attention monitoring video significant event intelligent detection and early warning method
  • Active visual attention monitoring video significant event intelligent detection and early warning method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0065] The present invention will be described in further detail below.

[0066] Active visual attention intelligent detection and early warning method for surveillance video salient events. In the active dynamic target detection method, the visual saliency calculation model is based on the bottom-up visual saliency attention detection model proposed by Itti. In the underlying feature extraction, the brightness feature and motion The feature replaces the original grayscale (I), color (C), and direction (O) visual features. In the construction of the feature multi-scale space, the convolution efficiency, tight support and good local control of the cubic B-spline are used. Features, to realize the stable multi-resolution representation of features at different scales, construct the B-spline feature scale space, and use the DOB scale space to realize the rapid extraction of video salient attention regions. Through experimental training on a large number of videos, the fusion of ea...

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 relates to an active visual attention monitoring video significant event intelligent detection and early warning method. The method includes the steps of establishing a quick extracting method of visual attention primary information from bottom to top, and constructing an active detection module of a dynamic target; then actively tracking a significant target by particle swarm optimization, and meanwhile, establishing an active early warning model for a significant event in a monitoring video and thus realizing a monitoring video significant event intelligent detection and early warning system based on a visual attention model. The experiment shows that the method of the invention is high in operating efficiency and has good robustness in terms of altitude and shape change, partial shielding, quick movement and illumination change.

Description

technical field [0001] The invention relates to a method for intelligent detection and early warning of significant events in monitoring video with active visual attention. Background technique [0002] The wide popularization and application of target detection and tracking in intelligent robots, video surveillance, medical diagnosis, intelligent human-computer interaction, military and other fields has made the research on dynamic target detection and tracking a hot and difficult topic in machine vision. Automatic detection and tracking of dynamic targets within the monitoring field of view is the basis for the analysis and judgment of video data, intelligent identification, automatic early warning and other tasks, and is the technical core of various video application systems. [0003] Dynamic target detection can be divided into static target detection and moving target detection according to its application scope. Static target detection mostly refers to target detecti...

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): G06K9/00
CPCG06V20/44G06V20/48G06V20/52
Inventor 李博冯欣葛永新
Owner 重庆警察学院
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap