Intrusion detection method applied to intelligent video surveillance of long-distance track lines

A technology of intelligent video monitoring and intrusion detection, which is applied in closed-circuit television systems, instruments, anti-theft alarms, etc., can solve the problems of increasing the overall investment of the system, and achieve the effect of reducing false alarms

Active Publication Date: 2015-08-19
无锡厉鲨人工智能科技有限公司
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this approach significantly increases the overall system investment

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
  • Intrusion detection method applied to intelligent video surveillance of long-distance track lines
  • Intrusion detection method applied to intelligent video surveillance of long-distance track lines
  • Intrusion detection method applied to intelligent video surveillance of long-distance track lines

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0011] As mentioned above, the specific embodiment of the present invention includes an initialization phase and an intrusion detection phase, wherein the initialization phase only needs to be executed at the first run. Combine below figure 1 The specific embodiment of the present invention will be further elaborated.

[0012] 1. Initialization

[0013] In the initialization phase, it consists of two parallel steps, perspective modeling and background learning.

[0014] 1. The idea of ​​perspective modeling is: according to the dual-track parallel principle of rail transit construction, the double-track spacing of each row of pixels in the video frame actually represents the same double-track spacing, so the proportional relationship between the changes in the double-track spacing can be used. The moving target whose position breaks in is restored to a uniform scale, thereby eliminating the influence of the perspective phenomenon.

[0015] The purpose of perspective modelin...

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 intrusion detection method applied in the intelligent video monitoring of long-distance railway lines, which belongs to the field of video monitoring. The method is implemented by the following steps: (1) initialization: by a perspective modeling step and a background leaning step which are parallel, perspective zooming factors corresponding to the different positions of a railway line in video frames and relatively stable monitoring field background images are obtained, and if the perspective zooming factors and the monitoring field background images are already obtained by initialization, then initialization does not need to be repeated; (2) intrusion detection: intrusion detection includes a detection alarm step and a background updating step which are parallel, wherein detection alarm is composed of four substeps, i.e. foreground detection, form correction, perspective restoration and threshold determination, and the perspective restoration can restore moving objects intruding at different positions on the railway line into a unified scale, so that the affection of the perspective phenomenon is eliminated. Compared with the prior art, the intrusion detection method can eliminate the affection of the perspective phenomenon, so that all the moving objects appearing at different positions on the railway line can submit to the constraint of a unified threshold range, consequently, false alarm and missing alarm caused by the perspective phenomenon can be greatly reduced, and thereby the long-distance railway line can be effectively protected.

Description

technical field [0001] The invention belongs to the field of video monitoring, in particular to an intrusion detection method applied to intelligent video monitoring of long-distance track lines. Background technique [0002] With the wide application of video surveillance systems, video surveillance has become an important technical means of security protection for state organs, enterprises and institutions, and residential buildings. Traditional video surveillance mainly relies on manual monitoring, and it is difficult to avoid false alarms or missed alarms caused by fatigue or off-duty personnel on duty. With the improvement of computer performance and the development of image processing technology, intelligent video surveillance shows outstanding advantages such as strong alarm initiative and long-term work, which has gradually become a development trend. [0003] The core application of intelligent video surveillance is intrusion detection. Its function is to detect in...

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): G08B13/196H04N7/18
Inventor 李正浩李伟红付仕清仲建华龚卫国杨利平胡舟陈凯
Owner 无锡厉鲨人工智能科技有限公司
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