Unlock instant, AI-driven research and patent intelligence for your innovation.

Moving target detection method based on Lab color space and ViBe improvement

A color space and moving target technology, applied in image data processing, instruments, calculations, etc., can solve the problems of unsolved shadows on foreground detection, ViBe algorithm prone to ghosting and other problems, to reduce the impact, improve accuracy, eliminate ghost effect

Active Publication Date: 2018-07-06
XIDIAN UNIV
View PDF6 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the ViBe algorithm also has many shortcomings. First, the ViBe algorithm does not solve the impact of shadows on foreground detection. Second, the ViBe algorithm is prone to ghosting

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
  • Moving target detection method based on Lab color space and ViBe improvement
  • Moving target detection method based on Lab color space and ViBe improvement
  • Moving target detection method based on Lab color space and ViBe improvement

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The present invention is further described below in conjunction with accompanying drawing.

[0037] Such as figure 1 As shown, a moving target detection method based on Lab color space and ViBe improvement includes the following steps:

[0038] 1) Color space conversion

[0039] Convert video frame sequence from RGB color space to Lab color space. For each pixel (x', y') of the image, the Lab value of the pixel is I (x′,y′) =(L (x′,y′) ,a (x′,y′) ,b (x′,y′) ).

[0040] 2) Background model initialization

[0041] Use the first frame of video image to initialize the background model. For each pixel point (x', y') in the image, the background model is initialized as B(x', y')={b 1 ,b 2 ,...,b N},

[0042] where x i and y i by a two-dimensional Gaussian distribution Randomly generated, σ is a given threshold. In this example, the value of σ is 2, and the value of N is 20.

[0043] 3) Foreground detection

[0044] m (x′,y′) Indicates the detection value...

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 moving target detection method based on Lab color space and ViBe improvement includes: using two-dimensional Gaussian distribution to randomly initialize a ViBe background model; detecting a foreground in the Lab color space; introducing posterior probability of background in conjunction with two-dimensional Gaussian model to randomly update the background model. The moving target detection method based on Lab color space and ViBe improvement has the advantages that moving target detection is more accurate, shadow areas and shadows in motion are removed accurately and effectively, and foreground detection accuracy is improved.

Description

technical field [0001] The invention belongs to the related field of image processing and video processing technology, and in particular relates to a moving target detection method based on Lab color space and ViBe improvement. Background technique [0002] Moving object detection is a key technology in image processing and video processing. Its essence is to reduce redundant information in time and space through computer vision methods, and extract moving targets very effectively. It is the most critical issue in intelligent video surveillance and provides basic functions for subsequent links. [0003] At present, the main methods of moving target detection are: frame difference method, background difference method and optical flow method. The frame difference algorithm is simple, fast, and less sensitive to light, but it cannot extract complete objects. The optical flow method can calculate the motion information and three-dimensional structure information of the object...

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): G06T7/246
CPCG06T7/251G06T2207/10016
Inventor 杨刚赵德亮张佳豪
Owner XIDIAN UNIV