CN113379987B - Design method of nursing electronic fence module - Google Patents
Design method of nursing electronic fence module Download PDFInfo
- Publication number
- CN113379987B CN113379987B CN202010117407.8A CN202010117407A CN113379987B CN 113379987 B CN113379987 B CN 113379987B CN 202010117407 A CN202010117407 A CN 202010117407A CN 113379987 B CN113379987 B CN 113379987B
- Authority
- CN
- China
- Prior art keywords
- frame
- motion
- motion detection
- detection frame
- electronic fence
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
- G08B13/19602—Image analysis to detect motion of the intruder, e.g. by frame subtraction
- G08B13/19613—Recognition of a predetermined image pattern or behaviour pattern indicating theft or intrusion
- G08B13/19615—Recognition of a predetermined image pattern or behaviour pattern indicating theft or intrusion wherein said pattern is defined by the user
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Image Analysis (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The invention provides a design method of a nursing electronic fence module, which comprises the following steps: s1, obtaining a current frame motion detection frame by a self-adaptive motion history processing method; s2, making a mask on the whole frame, and resetting the color value; s3, filling any polygonal area with white color to enable the periphery of an external rectangle of the polygonal area to be black; and S4, solving the intersection of the motion detection frame and the circumscribed rectangle of any polygon, and obtaining whether the occupation ratio is in the interior of the perimeter of any polygon or not by counting the proportion of non-zero values of the intersection part in the whole motion detection frame. The technical scheme of this application can solve the problem that arbitrary irregular polygon perimeter was taken precautions against, easy maintenance, and adaptability is stronger. Meanwhile, the problem that the hollow phenomenon is generated or/and the noise is filtered similarly is solved.
Description
Technical Field
The invention relates to the technical field of perimeter safety precaution, in particular to a design method of a nursing electronic fence module.
Background
With the development of science and technology, especially the development of technologies such as video technology, artificial intelligence, pattern recognition, etc., and the perimeter security protection and perimeter intrusion detection technology, it is also in force to come up. Perimeter protection is very important especially for applications in nursing electronic fences. However, in the conventional perimeter intrusion and protection technologies, most perimeter protection technologies are effective for regular polygons, for example, the size of the intersection of the motion detection frame and the perimeter is directly used to determine whether the boundary is out of range, but the conventional perimeter intrusion and protection technologies fail to work for irregular polygons. Some adopt the motion direction of the object, but the accuracy is affected because the direction calculation itself is inaccurate. In addition, although the moving pixel detection frame of the current frame can be obtained by the frame difference method or the background method, a hollow phenomenon occurs due to the speed of the motion amplitude or noise is filtered.
Disclosure of Invention
In order to solve the above problems, the present invention is directed to: by the technical scheme, the perimeter precaution of any polygon is supported; and (3) a self-adaptive motion history processing method is adopted to self-adaptively process the motion speed and restore the motion history track.
Specifically, the invention provides a design method of a nursing electronic fence module, which comprises the following steps:
s1, obtaining a current frame motion detection frame by a self-adaptive motion history processing method;
s2, making a mask on the whole frame, and resetting the color value;
s3, filling any polygonal area with white color, so that the periphery of an external rectangle is black;
and S4, solving the intersection of the motion detection frame and the circumscribed rectangle of any polygon, and obtaining whether the occupation ratio is in the interior of the perimeter of any polygon or not by counting the proportion of non-zero values of the intersection part in the whole motion detection frame.
The S1 further comprises: and obtaining a motion pixel point of the current frame through the difference of two frames or the difference of three frames, and obtaining a motion detection frame of the current frame through a contour extraction method according to the reserved motion history pixel points.
The contour extraction method is to binarize the image, and 1 can be set as a foreground image and 0 can be set as a background image in the binary image.
If the current frame has moving pixels, the moving speed of the object is pre-judged according to the size of the moving detection frame of the previous frame, if the height and width of the object in the N frames are larger than a threshold value, in order to avoid long trailing, the position of the object is set as a short history reserved value, and if the height and width of the object are smaller than the threshold value, in order to prevent the target from being overlooked or from vertically facing a camera to cause target missing detection, the position of the moving pixel point is set as a long history reserved value;
if the current frame has no motion pixels but has motion history pixels reserved, the corresponding motion history pixels are subtracted by 1.
Thus, the application has the advantages that: the problem of arbitrary irregular polygon perimeter precaution can be solved through the technical scheme of this application. Meanwhile, the problem that the hollow phenomenon is generated or/and the noise is filtered similarly is solved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the principles of the invention.
FIG. 1 is a flow chart of the method of the present invention.
Detailed Description
In order that the technical contents and advantages of the present invention can be more clearly understood, the present invention will now be described in further detail with reference to the accompanying drawings.
Furthermore, technical terms in the prior art include:
a nursing electronic fence: an object approaches the fence from inside to outside or crosses the fence from inside to outside in a small area, an alarm signal is sent out, the situation of baby nursing is suitable, and the small area crossing can be understood that only one small foot protrudes out of the fence.
Short history retention value: the moving pixel points of the current frame are reassigned to a smaller number whose value decreases in the following frame if there is no motion until 0 disappears. It is simply understood that the number of frames reserved for moving pixel points is relatively short.
Long history retention value: the moving pixel points of the current frame are reassigned to a larger number whose value decreases in the following frame if there is no motion until 0 disappears. It is simply understood that the number of frames reserved for a moving pixel point is relatively long.
MASK is a MASK, also called MASK.
The method is completed by the following steps:
and A, obtaining an object motion detection frame by a self-adaptive motion history processing method.
The specific method comprises the following steps:
obtaining a motion pixel point of the current frame through two-frame difference or three-frame difference, and obtaining a motion detection frame of the current frame through a contour extraction method according to the reserved motion history pixel point;
in particular:
if the current frame has moving pixels, the moving speed of the object is pre-judged according to the size of the moving detection frame of the previous frame, if the height and width of the object in the N frame are larger than a threshold value, in order to avoid Long trailing, the position of the object is a Short history reserved value Short _ hst _ val, and if the height and width of the object are smaller than the threshold value, in order to prevent the target from being too small or from missing detection caused by the condition that the target vertically faces the camera, the position of the moving pixel point is a Long history reserved value Long _ hst _ val.
If the current frame has no motion pixels but has motion history pixels reserved, the corresponding motion history pixels are subtracted by 1.
And B, designing the electronic fence.
1, a large MASK is made for the whole frame and is cleared.
And 2, filling any polygonal area with white, so that the periphery of the circumscribed rectangle is black.
And 3, calculating the intersection of the motion detection frame and any polygon, wherein the intersection is in an irregular shape, the intersection part is white, namely 255, and the rest part is black and 0, so that whether the intersection part is in the interior of any perimeter can be obtained by counting the proportion of the number of non-zero points of the intersection part in the whole motion detection frame.
Specifically, as shown in fig. 1, the present invention relates to a design method of a nursing electronic fence module, which comprises the following steps:
s1, obtaining a current frame motion detection frame by a self-adaptive motion history processing method;
s2, making a mask on the whole frame, and resetting the color value;
s3, filling any polygonal area with white color, so that the periphery of an external rectangle is black;
and S4, solving the intersection of the motion detection frame and the circumscribed rectangle of any polygon, and obtaining whether the occupation ratio is in the interior of the perimeter of any polygon or not by counting the proportion of non-zero values of the intersection part in the whole motion detection frame.
Here, the entire frame refers to a mask pattern having the same size as that of the current frame image, for example, the resolution is 640 × 360, and the entire mask pattern is set to an initial value of 0 in the first step. The motion detection needs to perform region detection on a circumscribed rectangle of a plurality of arbitrary polygons on the current frame image, for example, if there are N arbitrary polygons, there are N regions to perform motion detection, and a motion detection frame on the current frame and an arbitrary polygon on the mask image are circumscribed to obtain an intersection.
The S1 further comprises: and obtaining a motion pixel point of the current frame through the difference of two frames or the difference of three frames, and obtaining a motion detection frame of the current frame through a contour extraction method according to the reserved motion history pixel points.
The contour extraction method is to binarize the image, and 1 can be set as foreground and 0 as background in the binary image.
If the current frame has moving pixels, the moving speed of the object is pre-judged according to the size of the moving detection frame of the previous frame, if the current frame is within N frames (for example, N is 3-6), the height and width of the object are larger than a threshold (for example, the threshold 40 and can be adjusted according to sensitivity), in order to avoid long trailing, the position of the object is set as a short history reserved value, and if the height and width of the object are smaller than the threshold, in order to prevent the target from being overlooked or from missing detection caused by the condition that the object vertically faces a camera, the position of a moving pixel point is set as a long history reserved value;
if the current frame has no motion pixels but has a retained motion history pixel, the corresponding motion history pixel is decremented by 1 (e.g., the initial value of the short history retained value is set to 6, and the initial value of the long history retained value is set to 10).
The intersection of the motion detection frame and any polygon is in an irregular shape.
The intersection part is white, and the rest part is black.
The color value of white RGB is 255, and the color value of black RGB is 0.
The proportion of the statistic intersection part in the whole motion detection frame is the proportion of the number of the non-zero points of the statistic intersection part in the whole motion detection frame.
Wherein, a foreground image is obtained by using a three-frame difference method to detect a moving target in a region by way of example:
specifically, an interested image area and a perimeter precaution moving target are established by a real-time video stream captured in an intrusion detection environment, and a foreground image is obtained. The three-frame difference method comprises the following steps:
h1, passing two-frame difference D n (x,y)＝|f n (x,y)-f n-1 (x, y) | and D n+1 (x,y)＝ |f n+1 (x,y)-f n (x, y) | gives rise to adjacent difference images, where f n-1 (x, y) is the (n-1) th frame image, f n (x, y) is the nth frame image, f n+1 (x, y) is the n +1 th frame image, n>1, and n is an integer;
wherein, D is n (x, y) is the nth frame image f n (x, y) and the (n-1) th frame image f n-1 Two frame difference of (x, y), said D n+1 (x, y) is the (n + 1) th frame image f n+1 (x, y) and nth frame image f n Two frame difference of (x, y).
H2, through a preset threshold value, comparing the obtained D n (x, y) and D n+1 (x, y) binarizing to obtain a binary image d n (x, y) and d n+1 (x,y)；
Wherein d is n (x, y) is the difference D between two frames n (x, y) a binary image obtained by binarization, wherein d is n+1 (x, y) is the difference D between two frames n+1 (x, y) binarizing to obtain a binary image.
H3, by formula
For the binary image d obtained above n (x, y) and d n+1 (x, y) AND operation is carried out to obtain a foreground image Mn (x, y).
And after the foreground image is obtained, eliminating the void phenomenon according to a historical motion method to obtain a complete motion target. And obtaining a current frame motion detection frame by a contour extraction method according to the reserved motion history pixel points. And then according to the motion detection frame, design the fence, realize nurse fence module.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the present invention, and various modifications and changes may be made to the embodiment of the present invention by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (5)
1. A method of designing a nursing electronic fence module, the method comprising the steps of:
s1, obtaining a current frame motion detection frame by a self-adaptive motion history processing method; the self-adaptive motion history processing method comprises the steps of obtaining motion pixel points of a current frame through two-frame difference or three-frame difference, and obtaining a motion detection frame of the current frame through a contour extraction method according to the reserved motion history pixel points; the contour extraction method is to binarize an image, wherein 1 in a binary image is set as a foreground image, and 0 in the binary image is set as a background image; if the current frame has moving pixels, the moving speed of the object is pre-judged according to the size of the moving detection frame of the previous frame, if the height and width of the object in the N frames are larger than a threshold value, in order to avoid long trailing, the position of the object is set as a short history reserved value, and if the height and width of the object are smaller than the threshold value, in order to prevent the target from being overlooked or from vertically facing a camera to cause target missing detection, the position of the moving pixel point is set as a long history reserved value; if the current frame has no motion pixel but has a reserved motion history pixel, subtracting 1 from the corresponding motion history pixel;
s2, making a mask on the whole frame, and resetting the color value;
s3, filling any polygonal area with white color to enable the periphery of an external rectangle of the polygonal area to be black;
and S4, solving the intersection of the motion detection frame and the circumscribed rectangle of any polygon, and obtaining whether the occupation ratio is in the interior of the perimeter of any polygon or not by counting the proportion of non-zero values of the intersection part in the whole motion detection frame.
2. A method of designing a nursing electronic fence module as in claim 1,
the intersection of the motion detection frame and any polygon in step S4 is an irregular shape.
3. A method of designing a nursing electronic fence module as in claim 1,
the intersection part is white, and the rest part is black.
4. A method of designing a nursing electronic fence module as in claim 3,
the color value of white RGB is 255, and the color value of black RGB is 0.
5. A method of designing a nursing electronic fence module as in claim 4,
and the proportion of the non-zero value of the statistical intersection part in the whole motion detection frame is the proportion of the number of the non-zero points of the statistical intersection part in the whole motion detection frame.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010117407.8A CN113379987B (en) | 2020-02-25 | 2020-02-25 | Design method of nursing electronic fence module |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010117407.8A CN113379987B (en) | 2020-02-25 | 2020-02-25 | Design method of nursing electronic fence module |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113379987A CN113379987A (en) | 2021-09-10 |
| CN113379987B true CN113379987B (en) | 2022-10-21 |
Family
ID=77569269
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010117407.8A Active CN113379987B (en) | 2020-02-25 | 2020-02-25 | Design method of nursing electronic fence module |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113379987B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO1999059116A1 (en) * | 1998-05-08 | 1999-11-18 | Primary Image Limited | Method and apparatus for detecting motion across a surveillance area |
| KR20130130958A (en) * | 2012-05-23 | 2013-12-03 | 주호걸 | Electric fence system |
| CN105575027A (en) * | 2014-10-09 | 2016-05-11 | 北京君正集成电路股份有限公司 | Invasion and perimeter defense method and invasion and perimeter defense device |
| CN109068099A (en) * | 2018-09-05 | 2018-12-21 | 济南大学 | Virtual electronic fence monitoring method and system based on video monitoring |
| CN109903503A (en) * | 2019-04-16 | 2019-06-18 | 上海天诚比集科技有限公司 | A kind of detection method in video monitoring object intrusion detection region |
| CN110766899A (en) * | 2019-11-11 | 2020-02-07 | 四川航天神坤科技有限公司 | Method and system for enhancing electronic fence monitoring early warning in virtual environment |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU2484531C2 (en) * | 2009-01-22 | 2013-06-10 | Государственное научное учреждение центральный научно-исследовательский и опытно-конструкторский институт робототехники и технической кибернетики (ЦНИИ РТК) | Apparatus for processing video information of security alarm system |
-
2020
- 2020-02-25 CN CN202010117407.8A patent/CN113379987B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO1999059116A1 (en) * | 1998-05-08 | 1999-11-18 | Primary Image Limited | Method and apparatus for detecting motion across a surveillance area |
| KR20130130958A (en) * | 2012-05-23 | 2013-12-03 | 주호걸 | Electric fence system |
| CN105575027A (en) * | 2014-10-09 | 2016-05-11 | 北京君正集成电路股份有限公司 | Invasion and perimeter defense method and invasion and perimeter defense device |
| CN109068099A (en) * | 2018-09-05 | 2018-12-21 | 济南大学 | Virtual electronic fence monitoring method and system based on video monitoring |
| CN109903503A (en) * | 2019-04-16 | 2019-06-18 | 上海天诚比集科技有限公司 | A kind of detection method in video monitoring object intrusion detection region |
| CN110766899A (en) * | 2019-11-11 | 2020-02-07 | 四川航天神坤科技有限公司 | Method and system for enhancing electronic fence monitoring early warning in virtual environment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113379987A (en) | 2021-09-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106067023B (en) | Container number and truck number identification system and method based on image processing | |
| TWI409718B (en) | Method of locating license plate of moving vehicle | |
| US9547800B2 (en) | System and a method for the detection of multiple number-plates of moving cars in a series of 2-D images | |
| JP7122364B2 (en) | Deposit detection device, deposit detection method | |
| Hu et al. | Robust real-time ship detection and tracking for visual surveillance of cage aquaculture | |
| KR101717613B1 (en) | The moving vehicle detection system using an object tracking algorithm based on edge information, and method thereof | |
| JP3228638B2 (en) | Moving object detection method using background difference method | |
| WO2022027931A1 (en) | Video image-based foreground detection method for vehicle in motion | |
| CN110807392B (en) | Encoding control method and related device | |
| CN113379987B (en) | Design method of nursing electronic fence module | |
| CN114511530A (en) | Anabaena cell statistical method based on microscope image | |
| CN113379984B (en) | Electronic nursing fence system | |
| JPS62267889A (en) | Character reading system | |
| CN113379985B (en) | Nursing electronic fence alarm device | |
| US20180285675A1 (en) | System and method for text localization in images | |
| Russell et al. | Vehicle detection based on color analysis | |
| CN114639159A (en) | Moving pedestrian detection method, electronic device and robot | |
| Zhu et al. | Optimization of image processing in video-based traffic monitoring | |
| CN109547777B (en) | Method for rapidly detecting video noise of complex scene | |
| Zheng et al. | An automatic moving object detection algorithm for video surveillance applications | |
| JP2011237931A (en) | Mobile body identification device, computer program and mobile body identification method | |
| JP6591349B2 (en) | Motion detection system and motion detection method | |
| Vinary et al. | Object tracking using background subtraction algorithm | |
| JPH0863549A (en) | Vehicle number recognition device, binarization device and picture processor | |
| Zemčík et al. | Performance evaluation of CNN based pedestrian and cyclist detectors on degraded images |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |