CN111667419A - Moving target ghost eliminating method and system based on Vibe algorithm - Google Patents
Moving target ghost eliminating method and system based on Vibe algorithm Download PDFInfo
- Publication number
- CN111667419A CN111667419A CN202010411962.1A CN202010411962A CN111667419A CN 111667419 A CN111667419 A CN 111667419A CN 202010411962 A CN202010411962 A CN 202010411962A CN 111667419 A CN111667419 A CN 111667419A
- Authority
- CN
- China
- Prior art keywords
- pixel
- background
- point
- moving target
- points
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 61
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000001514 detection method Methods 0.000 claims abstract description 37
- 239000003245 coal Substances 0.000 claims abstract description 10
- 230000008030 elimination Effects 0.000 claims description 7
- 238000003379 elimination reaction Methods 0.000 claims description 7
- 238000013507 mapping Methods 0.000 claims description 7
- 230000000694 effects Effects 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 9
- 238000004590 computer program Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 4
- 230000006399 behavior Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/73—Deblurring; Sharpening
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/215—Motion-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to a moving target ghost eliminating method and a moving target ghost eliminating system based on a Vibe algorithm. The invention can effectively eliminate ghost areas in the detection process, improves the detection effect and provides technical support for the accuracy of the detection of underground personnel in the coal mine.
Description
Technical Field
The application belongs to the technical field of image detection, and particularly relates to a moving target ghost eliminating method and system based on a Vibe algorithm.
Background
Along with increasing attention to coal mine safety and increasing control means, in recent years, coal mine safety work has achieved remarkable results, but safety accidents are still not thoroughly avoided, and certain blind areas and weak links also exist in safety management. Particularly, accidents are caused by the fact that people do not identify the danger source in place and the people do not safe behaviors.
The behavior analysis and abnormal condition detection and identification of the underground personnel in the coal mine are the understanding and identification of the semantic layer of human body movement after the visual semantic detection and analysis. The premise of analyzing the behavior of the personnel and detecting the abnormity is to correctly identify the personnel and separate the moving target from the complex scene. Moving object detection may in turn become moving object segmentation. At present, the mature algorithms applied to the detection of moving objects include an optical flow algorithm, a background difference method, an inter-frame difference method and a Vibe algorithm. The Vibe algorithm has the characteristics of easy understanding, simple implementation, small operation complexity and the like, and is widely applied to various scenes.
The Vibe algorithm is taken as a mainstream moving target detection algorithm at present, and has the characteristics of easiness in understanding, simplicity in implementation, small operation complexity, real-time detection and the like, but the current Vibe algorithm also has some disadvantages when being applied to a coal mine scene, wherein a Ghost area, which is a problem often called a Ghost area, is easily generated in a detection process.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the problem that a ghost area is easily generated when a Vibe algorithm is adopted to detect the moving target in the prior art is solved.
In order to solve the technical problems, the invention provides a moving target ghost elimination method and system based on a Vibe algorithm.
The technical scheme adopted by the invention for solving the technical problems is as follows:
the first aspect of the invention provides a moving target ghost eliminating method based on a Vibe algorithm, which adopts the Vibe algorithm to carry out background model initialization, foreground detection and background model updating on an input original image, detects a moving target, and further comprises the step of ghost area detection if the detected moving target has a ghost:
extracting minimum circumscribed rectangles corresponding to all moving target images detected according to a Vibe algorithm;
mapping the minimum circumscribed rectangular area in the image detected by the Vibe algorithm to the corresponding position of the original image of the current frame;
in the current frame original image, subtracting a moving target area from the minimum circumscribed rectangular area to obtain a difference image area;
selecting a group of pixel points in the difference image region as pixel sample points to form a pixel sample set;
calculating the difference value between the pixel value of the corresponding pixel point in the moving target area and the pixel value of each pixel sample point, and counting the number of the pixel sample points of which the absolute value of the difference value is smaller than a set pixel threshold value;
and if the counted number of the pixel sample points is larger than a first set threshold, judging that the corresponding pixel points are the points of the ghost area, and updating the background model so as to eliminate the ghost area.
The invention provides a moving target ghost eliminating system based on a Vibe algorithm, which comprises a Vibe algorithm module, a foreground detection module and a background model updating module, wherein the Vibe algorithm module is used for carrying out background model initialization, foreground detection and background model updating on an input original image by adopting the Vibe algorithm to detect a moving target;
further comprising a ghost area detection module configured to:
extracting minimum circumscribed rectangles corresponding to all moving target images detected according to a Vibe algorithm;
mapping the minimum circumscribed rectangular area in the image detected by the Vibe algorithm to the corresponding position of the original image of the current frame;
in the current frame original image, subtracting a moving target area from the minimum circumscribed rectangular area to obtain a difference image area;
selecting a group of pixel points in the difference image region as pixel sample points to form a pixel sample set;
calculating the difference value between the pixel value of the corresponding pixel point in the moving target area and the pixel value of each pixel sample point, and counting the number of the pixel sample points of which the absolute value of the difference value is smaller than a set pixel threshold value;
and if the counted number of the pixel sample points is larger than a first set threshold, judging that the corresponding pixel points are the points of the ghost area, and updating the background model so as to eliminate the ghost area.
The third aspect of the invention provides a method for detecting underground coal mine personnel, which comprises the method for eliminating the ghost of the moving target in the first aspect of the invention.
The invention has the beneficial effects that: according to the invention, the step of detecting the ghost area is added in the traditional Vibe algorithm, so that the occurrence of the ghost area in the detection process can be effectively inhibited, the detection effect is improved, and technical support is provided for the accuracy of the detection of underground personnel of a coal mine.
Drawings
The technical solution of the present application is further explained below with reference to the drawings and the embodiments.
FIG. 1 is a flow chart of a method of an embodiment of the present application;
FIG. 2 is a schematic diagram of a moving object detection image including ghosting according to an embodiment of the present disclosure.
Detailed Description
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
The technical solutions of the present application will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
Example 1
The present embodiment provides a method for removing a ghost of a moving target based on a Vibe algorithm, as shown in fig. 1, the method for detecting a moving target by performing background model initialization, foreground detection, and background model update on an input original image by using the Vibe algorithm further includes:
s1, extracting the minimum circumscribed rectangles corresponding to all the moving target images detected according to the Vibe algorithm;
s2, mapping the minimum circumscribed rectangular area in the image detected by the Vibe algorithm to the corresponding position of the original image of the current frame;
s3, in the current frame original image, subtracting the moving target area from the minimum circumscribed rectangle area to obtain a difference image area;
s4, selecting a group of pixel points in the difference image area as pixel sample points to form a pixel sample set;
s5, calculating the difference value between the pixel value of the corresponding pixel point in the moving target area and the pixel value of each pixel sample point, and counting the number of the pixel sample points of which the absolute value of the difference value is less than a set pixel threshold value;
and S6, if the counted number of the pixel sample points is larger than a first set threshold, judging that the corresponding pixel points are the points of the ghost area, and updating the background model so as to eliminate the ghost area.
Because the Vibe algorithm selects a sample set around a pixel point from a first frame image to generate a background model, if a moving target to be detected appears in the first frame, the moving target to be detected is easily used as a background when the background model is initialized, so that the background image cannot be updated in the subsequent detection process, and a 'ghost' is formed.
As shown in fig. 2, the moving object detection image is obtained by using the Vibe algorithm, and there are only three moving objects to be detected in the original image, but there are 6 moving objects in the detection image of the Vibe algorithm, and 3 of them belong to the "ghost".
In this case, the present embodiment adds steps S1 to S6 of detecting a ghost region to the Vibe algorithm, identifies the ghost region, and finally eliminates "ghost".
Optionally, in this embodiment, a spindle method is used to extract the minimum circumscribed rectangle corresponding to all moving target images detected according to the Vibe algorithm.
The advantage of extracting the minimum circumscribed rectangle by adopting the spindle method is that the operation speed is high and is almost 4 times of that of the existing algorithms. The method for extracting the minimum bounding rectangle belongs to the conventional technical means in the field, and is not described herein again.
And after extracting the minimum circumscribed rectangle, mapping the minimum circumscribed rectangle to the corresponding position of the current frame original image, and subtracting the moving target area determined by the Vibe algorithm from the minimum circumscribed rectangle area to obtain a difference image area in the minimum circumscribed rectangle area.
The minimum circumscribed rectangle corresponding to each moving target extracted in this embodiment is shown in fig. 2, in the drawing, a white rectangle frame is the minimum circumscribed rectangle corresponding to the moving target, a region in the minimum circumscribed rectangle is denoted as R, and a white region in the minimum circumscribed rectangle is a moving target region detected by the Vibe algorithm and denoted as R1The black area in the minimum bounding rectangle is the difference image area, denoted as R2Wherein R is2=R-R1。
In this embodiment, the mode of determining the "ghost" is to map the minimum circumscribed rectangular region corresponding to the image detected by the Vibe algorithm to the corresponding position of the current frame original image, and in the current frame original image, first, a group of pixel points m in the difference image region is selected1、m2、m3、……、mkForm a sample set of pixels, i.e. M ═ M1、m2、m3、……、mk}。
And then, calculating the difference value between the pixel value of the corresponding pixel point in the moving target area and the pixel value of each pixel sample point in the pixel sample set.
Setting a pixel value corresponding to a pixel point x in a moving target area as fxCalculating the pixel value and f of each pixel sample point in the pixel sample set M one by onexThe absolute value of the difference obtained by the statistical calculation is smaller than the number of pixel sample points of the set pixel threshold, optionally, the specific statistical method of this embodiment may be:
setting a counter to count the number of the pixel sample points, namely:
wherein T (x) represents the statistical value of the number of pixel sample points, f1Pixel value f representing the pixel point determined by the Vibe algorithm as the corresponding pixel point of the moving target area2Representing pixel values of corresponding pixel sample points in a pixel sample setAnd f denotes a set pixel threshold.
And finally, if the counted pixel sample point number T (x) is larger than a first set threshold T1, judging that the pixel point x belongs to the ghost area, updating the background model obtained by the Vibe algorithm, namely changing the update factor phi, and updating the pixel point x judged as the ghost area into the background model to realize the quick elimination of the ghost area.
Of course, as another possible embodiment, the determination of the ghost area can also be implemented by:
by calculating difference image regions R2And the moving target region R1And comparing the absolute value of the difference with a set pixel threshold, and if the absolute value of the difference is less than the set pixel threshold, determining the corresponding moving target region R1Belonging to ghost regions and are eliminated in the subsequent image processing.
Further, the steps of performing background model initialization, foreground detection and background model update on the input original image by using the Vibe algorithm in the embodiment specifically include:
initializing a background model: acquiring a first frame image of an original image, establishing a background model for each pixel point in the first frame image, and acquiring N pixel points from pixels in the neighborhood of a current pixel point to form a background sample set Q ═ Q1,q2,...qNAnd Q, the background sample set Q is a background model of the current pixel point, Q1,q2,...qNN background sample points for the current pixel point.
And (3) foreground detection: comparing each pixel point of the current frame image with a pre-stored background sample set, calculating the Euclidean distance between the pixel point of the current frame image and each background sample point in the corresponding background sample set, obtaining the number of the background sample points of which the Euclidean distance corresponding to the corresponding pixel point is smaller than a set distance threshold, and when the number of the background sample points is larger than a second set threshold, judging the corresponding pixel point as the background point.
The similarity between the jth pixel point q (x, y) and the background sample point in the corresponding background sample set is represented by the Euclidean distance between the jth pixel point q (x, y) and the background sample point, and the similarity can be represented by a binary method, namely:
djrepresenting the Euclidean distance between the jth pixel point of the current frame image and the background sample point in the corresponding background sample set, R representing a set distance threshold value, PjRepresenting the similarity of the jth pixel point to the background sample point in the corresponding background sample set.
Setting a second threshold T2, and determining whether the current frame pixel is background according to the following:
in the formula, Σ pjRepresenting the number of the jth pixel point of the current frame image and the number of the Euclidean distances smaller than R of the corresponding background sample set, T2For the second setting of the threshold value, fj(x, y) represents the gray value of the jth pixel point, fj(x, y) — 0 denotes a background point, fj(x, y) — 255 denotes a foreground point.
Updating a background model: if the pixel point is determined as the background point, the probability of 1/phi of the pixel point is updated to the background model, and phi is an updating factor; and if the foreground point is determined, the background model is not updated.
According to the embodiment of the invention, the step of detecting the ghost area is added in the traditional Vibe algorithm, so that the occurrence of the ghost area in the detection process can be effectively inhibited, the detection effect is improved, and the technical support is provided for the accuracy of the detection of the underground personnel of the coal mine.
Example 2:
the embodiment provides a moving target ghost eliminating system based on a Vibe algorithm, which comprises a Vibe algorithm module, a foreground detection module and a background model updating module, wherein the Vibe algorithm module is used for carrying out background model initialization, foreground detection and background model updating on an input original image by adopting the Vibe algorithm to detect a moving target;
further comprising a ghost area detection module configured to:
extracting minimum circumscribed rectangles corresponding to all moving target images detected according to a Vibe algorithm;
mapping the minimum circumscribed rectangular area in the image detected by the Vibe algorithm to the corresponding position of the original image of the current frame;
in the current frame original image, subtracting a moving target area from the minimum circumscribed rectangular area to obtain a difference image area;
selecting a group of pixel points in the difference image region as pixel sample points to form a pixel sample set;
calculating the difference value between the pixel value of the corresponding pixel point in the moving target area and the pixel value of each pixel sample point, and counting the number of the pixel sample points of which the absolute value of the difference value is smaller than a set pixel threshold value;
and if the number of the pixel sample points is larger than a first set threshold, judging that the corresponding pixel points are the points of the ghost area, and updating the background model so as to eliminate the ghost area.
Please refer to embodiment 1 for a specific implementation process of ghost elimination in this embodiment, which is not described herein again.
Further, the Vibe algorithm module comprises:
the background model initialization unit is used for acquiring a first frame image of an original image, establishing a background model for each pixel point in the first frame image, and acquiring N pixel points from pixels in the neighborhood of the current pixel point to form a background sample set Q ═ Q1, Q2.. qN }, wherein the background sample set Q is the background model of the current pixel point, and Q1, Q2.. qN are N background sample points of the current pixel point;
the foreground detection unit is used for comparing each pixel point of the current frame image with a pre-stored background sample set, calculating the Euclidean distance between the pixel point of the current frame image and each background sample point in the corresponding background sample set, obtaining the number of the background sample points of which the Euclidean distance corresponding to the corresponding pixel point is smaller than a set distance threshold, and judging the corresponding pixel point as the background point when the number of the background sample points is larger than a second set threshold;
the background model updating unit is used for updating the probability of the pixel point to the background model as an updating factor if the pixel point is judged as the background point; and if the foreground point is determined, the background model is not updated.
Please refer to embodiment 1 for a specific implementation of the Vibe algorithm module in this embodiment.
Example 3:
the embodiment provides a method for detecting underground coal mine personnel, which comprises the moving target ghost eliminating method in the embodiment 1 of the invention.
In light of the foregoing description of the preferred embodiments according to the present application, it is to be understood that various changes and modifications may be made without departing from the spirit and scope of the invention. The technical scope of the present application is not limited to the contents of the specification, and must be determined according to the scope of the claims.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Claims (10)
1. A moving target ghost eliminating method based on a Vibe algorithm adopts the Vibe algorithm to carry out background model initialization, foreground detection and background model updating on an input original image, and detects a moving target, and is characterized in that if the detected moving target has a ghost, the method further comprises the step of detecting a ghost area:
extracting minimum circumscribed rectangles corresponding to all moving target images detected according to a Vibe algorithm;
mapping the minimum circumscribed rectangular area in the image detected by the Vibe algorithm to the corresponding position of the original image of the current frame;
in the current frame original image, subtracting a moving target area from the minimum circumscribed rectangular area to obtain a difference image area;
selecting a group of pixel points in the difference image region as pixel sample points to form a pixel sample set;
calculating the difference value between the pixel value of the corresponding pixel point in the moving target area and the pixel value of each pixel sample point, and counting the number of the pixel sample points of which the absolute value of the difference value is smaller than a set pixel threshold value;
and if the counted number of the pixel sample points is larger than a first set threshold, judging that the corresponding pixel points are the points of the ghost area, updating the background model, and eliminating the ghost area.
2. The method according to claim 1, wherein the background model initialization step comprises:
acquiring a first frame image of an original image, establishing a background model for each pixel point in the first frame image, and acquiring N pixel points from pixels in the neighborhood of a current pixel point to form a background sample set Q ═ Q1,q2,...qNAnd Q, the background sample set Q is a background model of the current pixel point, Q1,q2,...qNN background sample points for the current pixel point.
3. The moving-target ghost elimination method according to claim 2, wherein the foreground detection step comprises:
comparing each pixel point of the current frame image with a pre-stored background sample set, calculating the Euclidean distance between the pixel point of the current frame image and each background sample point in the corresponding background sample set, obtaining the number of the background sample points of which the Euclidean distance corresponding to the corresponding pixel point is smaller than a set distance threshold, and when the number of the background sample points is larger than a second set threshold, judging the corresponding pixel point as the background point.
4. The moving-target ghosting elimination method of claim 3, wherein the background model updating step comprises:
if the pixel point is determined as the background point, the probability of 1/phi of the pixel point is updated to the background model, and phi is an updating factor; and if the foreground point is determined, the background model is not updated.
5. The method of claim 3, wherein the determination of whether the current frame pixel is background is based on:
wherein, ∑ pjThe number T of the Euclidean distance between the jth pixel point of the current frame image and the corresponding background sample set smaller than the set distance threshold2For the second setting of the threshold value, fj(x, y) represents the gray value of the jth pixel point of the current frame image, fj(x, y) — 0 denotes a background point, fj(x, y) — 255 denotes a foreground point.
6. The method of claim 1, wherein a counter is set to count the number of pixel sample points, that is:
wherein T (x) represents the statistical value of the number of pixel sample points, f1Pixel value f representing the pixel point determined by the Vibe algorithm as the moving target2Indicating the pixel value of the corresponding pixel sample point in the pixel sample set, and f indicates the set pixel threshold.
7. The moving-target ghosting elimination method of claim 1, wherein a principal axis method is adopted to extract the minimum bounding rectangles corresponding to all the moving-target images detected according to the Vibe algorithm.
8. A moving target ghost eliminating system based on a Vibe algorithm comprises a Vibe algorithm module, and is used for carrying out background model initialization, foreground detection and background model updating on an input original image by adopting the Vibe algorithm, and detecting a moving target, and is characterized in that:
further comprising a ghost area detection module configured to:
extracting minimum circumscribed rectangles corresponding to all moving target images detected according to a Vibe algorithm;
mapping the minimum circumscribed rectangular area in the image detected by the Vibe algorithm to the corresponding position of the original image of the current frame;
in the current frame original image, subtracting a moving target area from the minimum circumscribed rectangular area to obtain a difference image area;
selecting a group of pixel points in the difference image region as pixel sample points to form a pixel sample set;
calculating the difference value between the pixel value of the corresponding pixel point in the moving target area and the pixel value of each pixel sample point, and counting the number of the pixel sample points of which the absolute value of the difference value is smaller than a set pixel threshold value;
and if the number of the pixel sample points is larger than a first set threshold, judging that the corresponding pixel points are the points of the ghost area, and updating the background model so as to eliminate the ghost area.
9. The moving object ghosting elimination system of claim 8, wherein the Vibe algorithm module comprises:
a background model initialization unit, configured to obtain a first frame image of an original image, establish a background model for each pixel in the first frame image, collect N pixels from neighboring pixels of a current pixel, and form a background sample set Q ═ Q1,q2,...qNAnd Q, the background sample set Q is a background model of the current pixel point, Q1,q2,...qNN background sample points of the current pixel point;
the foreground detection unit is used for comparing each pixel point of the current frame image with a pre-stored background sample set, calculating the Euclidean distance between the pixel point of the current frame image and each background sample point in the corresponding background sample set, obtaining the number of the background sample points of which the Euclidean distance corresponding to the corresponding pixel point is smaller than a set distance threshold, and judging the corresponding pixel point as the background point when the number of the background sample points is larger than a second set threshold;
the background model updating unit is used for updating the probability of 1/phi of the pixel point to the background model if the pixel point is judged to be the background point, and phi is an updating factor; and if the foreground point is determined, the background model is not updated.
10. A method for detecting personnel in a coal mine well, which is characterized by comprising the method for eliminating the ghost of the moving target according to any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010411962.1A CN111667419A (en) | 2020-05-15 | 2020-05-15 | Moving target ghost eliminating method and system based on Vibe algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010411962.1A CN111667419A (en) | 2020-05-15 | 2020-05-15 | Moving target ghost eliminating method and system based on Vibe algorithm |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111667419A true CN111667419A (en) | 2020-09-15 |
Family
ID=72383680
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010411962.1A Pending CN111667419A (en) | 2020-05-15 | 2020-05-15 | Moving target ghost eliminating method and system based on Vibe algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111667419A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112819854A (en) * | 2021-02-02 | 2021-05-18 | 歌尔光学科技有限公司 | Ghost detection method, ghost detection apparatus, and readable storage medium |
CN116683986A (en) * | 2023-08-04 | 2023-09-01 | 武汉孚晟科技有限公司 | Ghost image identification method, system and medium of optical time domain reflectometer |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20060062454A1 (en) * | 2004-09-23 | 2006-03-23 | Jian Fan | Segmenting pixels in an image based on orientation-dependent adaptive thresholds |
CN104166983A (en) * | 2014-06-30 | 2014-11-26 | 中国传媒大学 | Motion object real time extraction method of Vibe improvement algorithm based on combination of graph cut |
US9213904B1 (en) * | 2013-03-15 | 2015-12-15 | PureTech Systems Inc. | Autonomous lock-on target tracking with geospatial-aware PTZ cameras |
CN105868708A (en) * | 2016-03-28 | 2016-08-17 | 锐捷网络股份有限公司 | Image object identifying method and apparatus |
CN110599523A (en) * | 2019-09-10 | 2019-12-20 | 江南大学 | ViBe ghost suppression method fused with interframe difference method |
-
2020
- 2020-05-15 CN CN202010411962.1A patent/CN111667419A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20060062454A1 (en) * | 2004-09-23 | 2006-03-23 | Jian Fan | Segmenting pixels in an image based on orientation-dependent adaptive thresholds |
US9213904B1 (en) * | 2013-03-15 | 2015-12-15 | PureTech Systems Inc. | Autonomous lock-on target tracking with geospatial-aware PTZ cameras |
CN104166983A (en) * | 2014-06-30 | 2014-11-26 | 中国传媒大学 | Motion object real time extraction method of Vibe improvement algorithm based on combination of graph cut |
CN105868708A (en) * | 2016-03-28 | 2016-08-17 | 锐捷网络股份有限公司 | Image object identifying method and apparatus |
CN110599523A (en) * | 2019-09-10 | 2019-12-20 | 江南大学 | ViBe ghost suppression method fused with interframe difference method |
Non-Patent Citations (1)
Title |
---|
惠开发 等: "基于改进ViBe 算法的视频浓缩", 山东大学学报( 工学版) * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112819854A (en) * | 2021-02-02 | 2021-05-18 | 歌尔光学科技有限公司 | Ghost detection method, ghost detection apparatus, and readable storage medium |
CN112819854B (en) * | 2021-02-02 | 2023-06-13 | 歌尔光学科技有限公司 | Ghost detection method, ghost detection device, and readable storage medium |
CN116683986A (en) * | 2023-08-04 | 2023-09-01 | 武汉孚晟科技有限公司 | Ghost image identification method, system and medium of optical time domain reflectometer |
CN116683986B (en) * | 2023-08-04 | 2023-10-27 | 武汉孚晟科技有限公司 | Ghost image identification method, system and medium of optical time domain reflectometer |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN115082683B (en) | Injection molding defect detection method based on image processing | |
EP1683105B1 (en) | Object detection in images | |
WO2020215552A1 (en) | Multi-target tracking method, apparatus, computer device, and storage medium | |
US20150178568A1 (en) | Method for improving tracking using dynamic background compensation with centroid compensation | |
CN111062974B (en) | Method and system for extracting foreground target by removing ghost | |
US20150248592A1 (en) | Method and device for identifying target object in image | |
CN109271848B (en) | Face detection method, face detection device and storage medium | |
CN109697725B (en) | Background filtering method and device and computer readable storage medium | |
CN103729858A (en) | Method for detecting article left over in video monitoring system | |
CN111783665A (en) | Action recognition method and device, storage medium and electronic equipment | |
Huerta et al. | Chromatic shadow detection and tracking for moving foreground segmentation | |
EP3340075A1 (en) | Video abstract using signed foreground extraction and fusion | |
CN111325773A (en) | Method, device and equipment for detecting moving target and readable storage medium | |
CN111667419A (en) | Moving target ghost eliminating method and system based on Vibe algorithm | |
EP3156972A1 (en) | Counting apparatus and method for moving objects | |
CN113485615B (en) | Method and system for manufacturing typical application intelligent image-text course based on computer vision | |
Cavallaro et al. | Accurate video object segmentation through change detection | |
CN115049954A (en) | Target identification method, device, electronic equipment and medium | |
US10115028B2 (en) | Method and device for classifying an object in an image | |
KR101690050B1 (en) | Intelligent video security system | |
CN107832732B (en) | Lane line detection method based on treble traversal | |
CN111401102A (en) | Deep learning model training method and device, electronic equipment and storage medium | |
CN113052019A (en) | Target tracking method and device, intelligent equipment and computer storage medium | |
WO2012081969A1 (en) | A system and method to detect intrusion event | |
EP3018626A9 (en) | Apparatus and method for image segmentation |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |