CN110288630B - Moving target ghost suppression method for background modeling - Google Patents

Abstract

The invention discloses a moving target ghost suppression method for background modeling, which comprises the following steps: step 1: extracting a segmented binary image mask generated by a ViBe algorithm, a corresponding video frame and a gray image gray of the frame, wherein the frame is an RGB image, the gray is a gray image, and the mask, the frame and the gray are all width multiplied by height; step 2: frame segmentation, step 3: the mask foreground points are restrained, and the method has the advantages that: the invention can better overcome the ghost problem of the ViBe algorithm on the premise of uncomplicated background in the video sequence.

Description

Moving target ghost suppression method for background modeling

Technical Field

The invention relates to the technical field of automatic detection of video sequences, in particular to a moving target ghost suppression method for background modeling.

Background

With the development of the world, the number of cameras available worldwide has increased dramatically. This growth has resulted in a large increase in data, which means that video data cannot be stored or manually processed.

Moving object detection is an important research direction in the field of computer vision, is the basis of various subsequent advanced processes such as object classification, behavior understanding and the like, and has wide application in the fields of safety monitoring, intelligent transportation and the like. In the fields of computer vision monitoring by an intelligent video screen and the like, background modeling is a key technology and is the basis for realizing the detection and tracking of moving targets. Therefore, the method has important significance for the research of the visual screen background modeling.

Background modeling is fundamental work of sequence image analysis and is a hot problem for researchers at home and abroad at present. The modeling result has important influence on the subsequent processing of video image such as motion detection, moving target classification, tracking and behavior understanding. But due to the difference of practical application environments and the diversity of backgrounds, it is difficult to establish a good background sample. Therefore, in practical application, the design scheme needs to be optimized through different algorithms to obtain a better result.

Since 2011 publication of a paper of the ViBe algorithm, the ViBe algorithm is applied to moving target detection of a visual screen sequence, but the technique has a ghost problem (a detected moving object does not correspond to any real moving object). Ghost problems can lead to false positives by downstream technologies.

Disclosure of Invention

In order to overcome the ghost problem of the ViBe algorithm, the invention provides a ghost detection method.

The technical scheme of the invention is as follows:

a method for suppressing ghost of a moving object of background modeling comprises the following steps:

step 1: extracting a segmented binary image mask generated by a ViBe algorithm, a corresponding video frame and a gray image gray of the frame, wherein the frame is an RGB image, the gray is a gray image, and the mask, the frame and the gray are all width multiplied by height;

step 2: dividing the frame;

and step 3: mask foreground spots are suppressed.

The method for suppressing the ghosting of the moving object modeled by the background is characterized in that the step 2 specifically comprises the following steps:

step 2.1: detecting a gray edge by using an edge detection algorithm to obtain an edge image gray edge;

step 2.2: dividing the frame into N partitions by a watershed algorithm according to the gray edge, wherein each partition has M_iEach pixel point, the coordinate in each partition is recorded in A_i＝{(r_ij,c_ij)|j∈[0,M_i-1]}，i∈[0,N-1]Wherein r is not less than 0_ij＜height，0≤c_ij＜width；

The method for suppressing the ghosting of the moving object modeled by the background is characterized in that the step 3 specifically comprises the following steps:

step 3.1: calculating the occupation ratio d of the foreground pixels of the partition according to the formulas (1) and (2)_i：

Wherein, I (·) represents an illustrative function, if the parameter is true, 1 is returned, otherwise 0 is returned; mask (r)_ij,c_ij) Representing the binary image mask in coordinates (r)_ij,c_ij) The gray value of (d);

step 3.2: for all the subareas A_iI is 0,1, …, N-1, and is processed as follows: if d is_iIf < D, the coordinate in the mask is (r)_ij,c_ij) Is set to 0, (r)_ij,c_ij)∈A_i(ii) a Wherein D is a threshold value.

The invention has the beneficial effects that: the invention can better overcome the problems of ghost and smear of the ViBe algorithm on the premise of uncomplicated background in the video sequence, and can extract the target area which obviously changes or moves in the video sequence.

Detailed Description

The following examples are given to illustrate specific embodiments of the present invention.

Step 1: and extracting a segmented binary image mask generated by the ViBe algorithm, a corresponding video frame and a gray image gray of the frame, wherein the frame is an RGB image, the gray is a gray image, and the mask, the frame and the gray are all width multiplied by height.

Step 2: the frame is segmented, and the specific steps are as follows:

step 2.1: detecting the gray edge by using an edge detection algorithm (such as Canny and sobel), and obtaining an edge image gray edge;

step 2.2: dividing the frame into N partitions by a watershed algorithm according to the gray edge, wherein each partition has M_iEach pixel point, the coordinate in each partition is recorded in A_i＝{(r_ij,c_ij)|j∈[0,M_i-1]}，i∈[0,N-1]Wherein r is not less than 0_ij＜height，0≤c_ij< width; wherein A is_iDenotes the ith partition, A_iIs a set containing all points within the partition; (r)_ij,c_ij) And indicating the jth pixel point in the ith partition.

And step 3: inhibiting mask foreground spots, and specifically comprising the following steps:

step 3.1: calculating the occupation ratio d of the foreground pixels of the partition according to the formulas (1) and (2)_i：

Wherein, I (·) represents an illustrative function, if the parameter is true, 1 is returned, otherwise 0 is returned; mask (r)_ij,c_ij) Representing the binary image mask in coordinates (r)_ij,c_ij) The gray value of (d);

step 3.2: for all the subareas A_iI is 0,1, …, N-1, and is processed as follows: if d is_iIf < D, the coordinate in the mask is (r)_ij,c_ij) Is set to 0, (r)_ij,c_ij)∈A_i(ii) a Where D is the threshold, in this example, D is 0.2.

The embodiments described in this specification are merely illustrative of implementations of the inventive concept and the scope of the present invention should not be considered limited to the specific forms set forth in the embodiments but rather by the equivalents thereof as may occur to those skilled in the art upon consideration of the present inventive concept.

Claims (1)

1. A method for suppressing ghost of a moving object of background modeling is characterized by comprising the following steps:

step 1: extracting a segmented binary image mask generated by a ViBe algorithm, a corresponding video frame and a gray image gray of the frame, wherein the frame is an RGB image, the gray is a gray image, and the mask, the frame and the gray are all width multiplied by height;

step 2: dividing the frame;

the step 2 comprises the following specific steps:

step 2.1: detecting a gray edge by using an edge detection algorithm to obtain an edge image gray edge;

step 2.2: dividing the frame into N partitions by a watershed algorithm according to the gray edge, wherein each partition has M_iEach pixel point, the coordinate in each partition is recorded in A_i＝{(r_ij,c_ij)|j∈[0,M_i-1]}，i∈[0,N-1]Wherein r is not less than 0_ij＜height，0≤c_ij< width; wherein A is_iDenotes the ith partition, A_iIs a set containing all points within the partition; (r)_ij,c_ij) Representing the jth pixel point in the ith partition;

and step 3: inhibiting mask foreground spots;

the step 3 comprises the following specific steps:

step 3.1: calculating the occupation ratio d of the foreground pixels of the partition according to the formulas (1) and (2)_i：

Wherein, I (·) represents an illustrative function, if the parameter is true, 1 is returned, otherwise 0 is returned; mask (r)_ij,c_ij) Representing the binary image mask in coordinates (r)_ij,c_ij) The gray value of (d);

step 3.2: for all the subareas A_iI is 0,1, …, N-1, and is processed as follows: if d is_iIf < D, the coordinate in the mask is (r)_ij,c_ij) Is set to 0, (r)_ij,c_ij)∈A_i(ii) a Wherein D is a threshold value.