Detection method of moving target on a real-time basis

A technology for real-time detection and moving targets, applied in image analysis, instrumentation, computing, etc.

Inactive Publication Date: 2009-06-03
HUAZHONG UNIV OF SCI & TECH
View PDF0 Cites 42 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention proposes a real-time detection method for moving targets, which solves the shortcomings of existing background modeling methods in the detection of moving targets in terms of background update, background disturbance, false target judgment and shadow suppression, and makes target detection more stable and practical , for moving object detection in complex surveillance scenes

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
  • Detection method of moving target on a real-time basis
  • Detection method of moving target on a real-time basis
  • Detection method of moving target on a real-time basis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0096] figure 1 It is a schematic flow chart of the present invention.

[0097] The present invention will be further described below in conjunction with a specific example.

[0098] (1) Build a model

[0099] Read a frame from a shadow scene video with a resolution of 320×240 such as Figure 3A and Figure 4A In the original image shown, each pixel of the frame image is mixed with Gaussian modeling in the YUV color space, and four Gaussian models are used to characterize the characteristics of each pixel in the image. Let X i,j,t is the pixel Q at the position (i, j) (1≤i≤320, 1≤j≤240) in the t-th frame image i,j,t A vector of pixel values ​​with values ​​{Y i,j,t , U i,j,t , V i,j,t} T , its probability density function P(X i,j,t ) can be written as a linear combination of four Gaussian models:

[0100] P ( X i , j , ...

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

A detection method of a moving target on a real-time basis belongs to a method for processing image data, and is characterized in that the shortages of a background modeling method in the aspects such as background updating, background perturbation, false target judgment, shadow suppression and the like in the prior moving target detection are overcome; the target detection is stable and practical; and the method is used for processing the moving target detection in a complex monitor scene. The method comprises the following stops: the model creating step, the model initialization step, the target detection and model updating step, the false target processing step, the shadow detection step, after-treating step, the target region determining step, the background integral updating step and the outputting step. The method has the advantages that the accuracy, the robustness and the integrity of the moving target in moving target detection are improved; and the moving target is detected more effectively, thereby laying the foundation for target assorting, tracking and event detecting.

Description

technical field [0001] The invention belongs to a processing method of image data, and in particular relates to a real-time detection method of a moving target, which is used for automatically detecting the moving target from various monitoring scenes. Background technique [0002] Video surveillance systems are widely used in various occasions such as banks, supermarkets, parking lots, and residential quarters. However, on the one hand, traditional surveillance systems require manual continuous observation of multiple surveillance screens, which not only consumes a lot of manpower and material resources, but also often causes leakage Real-time and effective monitoring cannot be achieved due to alarms and false alarms; on the other hand, the non-selective storage of monitoring data requires a large amount of storage space, and the massive amount of data makes it extremely difficult to retrieve specific monitoring content. With the development of computer software and hardwar...

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): G06T7/20G06K9/00
Inventor 谭毅华呼志刚孙爱蓉田金文
Owner HUAZHONG UNIV OF SCI & TECH
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