CN117635937A - Method, system and medium for judging shielding alarm of patrol robot camera - Google Patents
Method, system and medium for judging shielding alarm of patrol robot camera Download PDFInfo
- Publication number
- CN117635937A CN117635937A CN202311594095.XA CN202311594095A CN117635937A CN 117635937 A CN117635937 A CN 117635937A CN 202311594095 A CN202311594095 A CN 202311594095A CN 117635937 A CN117635937 A CN 117635937A
- Authority
- CN
- China
- Prior art keywords
- patrol
- texture
- images
- image
- value
- 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
- 238000000034 method Methods 0.000 title claims abstract description 28
- 230000001960 triggered effect Effects 0.000 abstract description 5
- 238000012544 monitoring process Methods 0.000 description 6
- 238000009434 installation Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Image Processing (AREA)
Abstract
According to the method, the system and the medium for judging the shielding alarm of the patrol robot camera, similar textures in patrol images of different time nodes are judged, if the similar texture area value is larger than the preset first alarm threshold value, alarm suspicion information is triggered, high-definition images and infrared images of a plurality of angles are obtained through a plurality of preset positions, secondary judgment is carried out according to the change values of texture pixel points of the high-definition images and the infrared images at the same position in an image overlapping area, false alarm is reduced, and alarm reliability is improved.
Description
Technical Field
The invention relates to the technical field of patrol robots, in particular to a method, a system and a medium for judging shielding alarm of a patrol robot camera.
Background
As patrol robots are increasingly commercially applied, the robots walk on the roads to perform patrol tasks, abnormal conditions are monitored and captured through the camera of the robot holder, and when the situation that someone deliberately shields the camera with foreign matters occurs, the patrol effect of the robots is greatly reduced. The prior art basically judges whether the frame fusion image has image texture missing aiming at the shielding detection area or not through the image pixels of a plurality of frame images of a camera visual picture; if the frame fusion image has image texture missing, the camera is determined to form shielding in a shielding detection area, and then an alarm is generated. At present, only a high-definition camera image of visible light is used as a judging basis, and more false alarm alarms can be generated when a robot form reaches a background environment with the same color.
Accordingly, there is a need for improvement in the art.
Disclosure of Invention
In view of the above problems, the present invention aims to provide a method, a system and a medium for judging whether a patrol robot camera shields an alarm, which can reduce false alarm and improve the reliability of the alarm.
The first aspect of the invention provides a method for judging shielding alarm of a patrol robot camera, which comprises the following steps:
based on automatic patrol of the robot, patrol image information of different time nodes is obtained;
extracting textures in the patrol images, and carrying out contrast analysis on the textures in the patrol images of adjacent time nodes to obtain texture similarity region values;
judging whether the texture similar area value is larger than a preset first alarm threshold value, if so, adjusting the direction of the camera based on a preset holder preset position, and acquiring high definition and infrared images in different directions;
extracting textures of the high-definition image and textures of the infrared image in the same direction;
judging whether the textures of the high-definition image and the infrared image in the same direction are the same or not, if so, generating camera shielding alarm information; if not, re-judging according to the change values of the texture pixel points of the infrared image and the high-definition image;
And sending the camera shielding alarm information to a preset management end for prompting.
In this scheme, the step of comparing and analyzing textures in patrol images of adjacent time nodes to obtain texture similarity region values specifically includes:
comparing and analyzing textures in patrol images of adjacent time nodes to obtain texture similarity values in the patrol images of the adjacent time nodes;
judging whether the texture similarity value is larger than a preset similarity threshold value, if so, extracting texture positions corresponding to the texture similarity value, and obtaining an area value occupied by the corresponding texture positions;
and accumulating the area values occupied by the texture positions to obtain corresponding texture similar area values.
In this scheme, the step of comparing and analyzing textures in patrol images of adjacent time nodes to obtain texture similarity values in patrol images of adjacent time nodes specifically includes:
binarizing textures in patrol images of adjacent time nodes to obtain texture pixel point gray values of patrol gray images of the adjacent time nodes at the same position;
extracting the minimum gray value and the maximum gray value in the gray values of texture pixel points of the patrol gray images of adjacent time nodes at the same position;
Dividing the minimum gray value in the gray values of the texture pixel points at the same position by the maximum gray value to obtain a similar value of the texture pixel points at the corresponding position;
and calculating the average value of the similarity values of the texture pixel points at different positions to obtain the texture similarity values in patrol images corresponding to the adjacent time nodes.
In this scheme, still include:
acquiring Gao Qingdi an image set and infrared first image set information before the robot automatically patrols;
constructing a high-definition image coordinate system according to the Gao Qingdi image set; constructing an infrared image coordinate system according to the infrared first image set;
comparing and analyzing the Gao Qingdi image and the infrared first image of the same time node to obtain an image overlapping area of the corresponding time node;
and judging whether the image overlapping areas of different time nodes are the same, if so, fixing the corresponding high-definition camera and the infrared camera normally, and marking the image overlapping areas.
In this solution, after marking the image overlapping area, the method further includes:
setting a plurality of coordinate reference points in an image overlapping area, and acquiring coordinates of the coordinate reference points in a high-definition image coordinate system to be set as a first coordinate;
Acquiring coordinates of the coordinate point reference points in an infrared image coordinate system, and setting the coordinates as second coordinates;
and forming a multi-element primary equation set by the first coordinates and the second coordinates of the coordinate points, and obtaining the coordinate relation coefficient of the corresponding high-definition image and the infrared image in the image overlapping area according to the multi-element primary equation set.
In this scheme, if not, the step of determining again according to the change values of the texture pixel points of the infrared image and the high-definition image specifically includes:
numbering the high-definition images and the infrared images in different directions according to time sequence to obtain high-definition images and infrared images of different time nodes;
performing difference value calculation on the texture pixel points of the high-definition images of different time nodes to obtain the variation value of the texture pixel points of the high-definition images;
performing difference value calculation on the texture pixel points of the infrared images of different time nodes to obtain the variation value of the texture pixel points of the infrared images;
based on the coordinate relation coefficient in the image overlapping area, judging whether the change value of the texture pixel point of the high-definition image at the same position is the same as the change value of the texture pixel point of the infrared image;
if yes, obtaining information that the camera is not shielded; if not, obtaining the shielding alarm information of one camera head.
The invention provides a system for judging the shielding alarm of a patrol robot camera, which comprises a memory and a processor, wherein a method program for judging the shielding alarm of the patrol robot camera is stored in the memory, and the method program for judging the shielding alarm of the patrol robot camera is executed by the processor and comprises the following steps:
based on automatic patrol of the robot, patrol image information of different time nodes is obtained;
extracting textures in the patrol images, and carrying out contrast analysis on the textures in the patrol images of adjacent time nodes to obtain texture similarity region values;
judging whether the texture similar area value is larger than a preset first alarm threshold value, if so, adjusting the direction of the camera based on a preset holder preset position, and acquiring high definition and infrared images in different directions;
extracting textures of the high-definition image and textures of the infrared image in the same direction;
judging whether the textures of the high-definition image and the infrared image in the same direction are the same or not, if so, generating camera shielding alarm information; if not, re-judging according to the change values of the texture pixel points of the infrared image and the high-definition image;
And sending the camera shielding alarm information to a preset management end for prompting.
In this scheme, the step of comparing and analyzing textures in patrol images of adjacent time nodes to obtain texture similarity region values specifically includes:
comparing and analyzing textures in patrol images of adjacent time nodes to obtain texture similarity values in the patrol images of the adjacent time nodes;
judging whether the texture similarity value is larger than a preset similarity threshold value, if so, extracting texture positions corresponding to the texture similarity value, and obtaining an area value occupied by the corresponding texture positions;
and accumulating the area values occupied by the texture positions to obtain corresponding texture similar area values.
In this scheme, the step of comparing and analyzing textures in patrol images of adjacent time nodes to obtain texture similarity values in patrol images of adjacent time nodes specifically includes:
binarizing textures in patrol images of adjacent time nodes to obtain texture pixel point gray values of patrol gray images of the adjacent time nodes at the same position;
extracting the minimum gray value and the maximum gray value in the gray values of texture pixel points of the patrol gray images of adjacent time nodes at the same position;
Dividing the minimum gray value in the gray values of the texture pixel points at the same position by the maximum gray value to obtain a similar value of the texture pixel points at the corresponding position;
and calculating the average value of the similarity values of the texture pixel points at different positions to obtain the texture similarity values in patrol images corresponding to the adjacent time nodes.
In this scheme, still include:
acquiring Gao Qingdi an image set and infrared first image set information before the robot automatically patrols;
constructing a high-definition image coordinate system according to the Gao Qingdi image set; constructing an infrared image coordinate system according to the infrared first image set;
comparing and analyzing the Gao Qingdi image and the infrared first image of the same time node to obtain an image overlapping area of the corresponding time node;
and judging whether the image overlapping areas of different time nodes are the same, if so, fixing the corresponding high-definition camera and the infrared camera normally, and marking the image overlapping areas.
In this solution, after marking the image overlapping area, the method further includes:
setting a plurality of coordinate reference points in an image overlapping area, and acquiring coordinates of the coordinate reference points in a high-definition image coordinate system to be set as a first coordinate;
Acquiring coordinates of the coordinate point reference points in an infrared image coordinate system, and setting the coordinates as second coordinates;
and forming a multi-element primary equation set by the first coordinates and the second coordinates of the coordinate points, and obtaining the coordinate relation coefficient of the corresponding high-definition image and the infrared image in the image overlapping area according to the multi-element primary equation set.
In this scheme, if not, the step of determining again according to the change values of the texture pixel points of the infrared image and the high-definition image specifically includes:
numbering the high-definition images and the infrared images in different directions according to time sequence to obtain high-definition images and infrared images of different time nodes;
performing difference value calculation on the texture pixel points of the high-definition images of different time nodes to obtain the variation value of the texture pixel points of the high-definition images;
performing difference value calculation on the texture pixel points of the infrared images of different time nodes to obtain the variation value of the texture pixel points of the infrared images;
based on the coordinate relation coefficient in the image overlapping area, judging whether the change value of the texture pixel point of the high-definition image at the same position is the same as the change value of the texture pixel point of the infrared image;
if yes, obtaining information that the camera is not shielded; if not, obtaining the shielding alarm information of one camera head.
A third aspect of the present invention provides a computer readable storage medium, in which a method program for determining a patrol robot camera occlusion alarm is stored, where the method program for determining a patrol robot camera occlusion alarm is executed by a processor, to implement the steps of a method for determining a patrol robot camera occlusion alarm as described in any one of the above.
According to the method, the system and the medium for judging the shielding alarm of the patrol robot camera, similar textures in patrol images of different time nodes are judged, if the similar texture area value is larger than the preset first alarm threshold value, alarm suspicion information is triggered, high-definition images and infrared images of a plurality of angles are obtained through a plurality of preset positions, secondary judgment is carried out according to the change values of texture pixel points of the high-definition images and the infrared images at the same position in an image overlapping area, false alarm is reduced, and alarm reliability is improved.
Drawings
FIG. 1 is a flow chart of a method for determining a patrol robot camera occlusion alarm according to the present invention;
FIG. 2 shows a block diagram of a system for determining a patrol robot camera occlusion alarm of the present invention.
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, in the case of no conflict, the embodiments of the present application and the features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those described herein, and therefore the scope of the present invention is not limited to the specific embodiments disclosed below.
Fig. 1 shows a flowchart of a method for judging a patrol robot camera shielding alarm according to the present invention.
As shown in fig. 1, the invention discloses a method for judging shielding alarm of a patrol robot camera, which comprises the following steps:
s101, based on automatic patrol of a robot, patrol image information of different time nodes is obtained;
s102, extracting textures in patrol images, and carrying out contrast analysis on textures in patrol images of adjacent time nodes to obtain texture similarity region values;
s103, judging whether the texture similarity region value is larger than a preset first alarm threshold value, if so, adjusting the direction of the camera based on a preset holder preset position, and acquiring high definition and infrared images in different directions;
S104, extracting textures of the high-definition image and textures of the infrared image in the same direction;
s105, judging whether the textures of the high-definition image and the infrared image in the same direction are the same, if so, generating camera shielding alarm information; if not, re-judging according to the change values of the texture pixel points of the infrared image and the high-definition image;
s106, sending the camera shielding alarm information to a preset management end for prompting.
According to the embodiment of the invention, when the robot executes an automatic patrol task, a high-definition camera is used for acquiring a monitoring video in real time, extracting a frame image in the monitoring video, setting the monitoring video frame image as a patrol pattern, and numbering according to the time sequence of video frames to obtain patrol images of different time nodes; the camera comprises a high-definition camera and an infrared camera, the rotation direction of the camera is controlled by presetting a holder preset position, the camera is judged by the texture of a high-definition image and the texture of an infrared image in the same direction, and if the high-definition image and the texture of the infrared image are the same, the corresponding infrared camera and the high-definition camera are shielded.
According to an embodiment of the present invention, the step of comparing and analyzing textures in patrol images of adjacent time nodes to obtain texture similarity region values specifically includes:
Comparing and analyzing textures in patrol images of adjacent time nodes to obtain texture similarity values in the patrol images of the adjacent time nodes;
judging whether the texture similarity value is larger than a preset similarity threshold value, if so, extracting texture positions corresponding to the texture similarity value, and obtaining an area value occupied by the corresponding texture positions;
and accumulating the area values occupied by the texture positions to obtain corresponding texture similar area values.
It should be noted that, for example, if the preset similarity threshold is 90%, when the texture similarity value is greater than 90%, the textures in the patrol images of the adjacent time nodes corresponding to the texture similarity value are set to be the same texture, the corresponding texture positions and the area values occupied by the corresponding texture positions are extracted, and the texture similarity area values are accumulated values of the area values occupied by the texture positions.
According to an embodiment of the present invention, the step of comparing and analyzing textures in patrol images of adjacent time nodes to obtain texture similarity values in patrol images of adjacent time nodes specifically includes:
binarizing textures in patrol images of adjacent time nodes to obtain texture pixel point gray values of patrol gray images of the adjacent time nodes at the same position;
Extracting the minimum gray value and the maximum gray value in the gray values of texture pixel points of the patrol gray images of adjacent time nodes at the same position;
dividing the minimum gray value in the gray values of the texture pixel points at the same position by the maximum gray value to obtain a similar value of the texture pixel points at the corresponding position;
and calculating the average value of the similarity values of the texture pixel points at different positions to obtain the texture similarity values in patrol images corresponding to the adjacent time nodes.
When the gray values of the texture pixels of the patrol images of the adjacent time nodes at the same position are the same, the corresponding minimum gray value and the maximum gray value are equal, the similarity value of the texture pixels of the corresponding position is 100%, and the average value calculation is performed on the similarity values of all the texture pixels in the patrol images of the adjacent time nodes, so as to obtain the texture similarity value in the patrol images of the corresponding adjacent time nodes.
According to an embodiment of the present invention, further comprising:
acquiring Gao Qingdi an image set and infrared first image set information before the robot automatically patrols;
constructing a high-definition image coordinate system according to the Gao Qingdi image set; constructing an infrared image coordinate system according to the infrared first image set;
Comparing and analyzing the Gao Qingdi image and the infrared first image of the same time node to obtain an image overlapping area of the corresponding time node;
and judging whether the image overlapping areas of different time nodes are the same, if so, fixing the corresponding high-definition camera and the infrared camera normally, and marking the image overlapping areas.
It should be noted that, the high-definition image coordinate system and the infrared image coordinate system are two-position coordinate systems, because the relative positions of the high-definition camera and the infrared camera are fixed, the image overlapping areas corresponding to the infrared image and the high-definition image are fixed, the Gao Qingdi image set comprises a plurality of Gao Qingdi images, the infrared first image set comprises a plurality of infrared first images, the images are identified by shooting time nodes, the Gao Qingdi image of the same time node and the infrared first images are compared with similar values, when the similar values are 100%, the corresponding positions are the image overlapping positions, all the image overlapping positions are accumulated to obtain the overlapping areas in the corresponding images, if the image overlapping areas of different time nodes are different, the high-definition camera or the infrared camera is not fixed, installation prompt information is triggered, and the corresponding installation prompt information is sent to a preset management end for display.
According to an embodiment of the present invention, after the marking the image overlapping area, the method further includes:
setting a plurality of coordinate reference points in an image overlapping area, and acquiring coordinates of the coordinate reference points in a high-definition image coordinate system to be set as a first coordinate;
acquiring coordinates of the coordinate point reference points in an infrared image coordinate system, and setting the coordinates as second coordinates;
and forming a multi-element primary equation set by the first coordinates and the second coordinates of the coordinate points, and obtaining the coordinate relation coefficient of the corresponding high-definition image and the infrared image in the image overlapping area according to the multi-element primary equation set.
It should be noted that the number of coordinate reference points of the image overlapping region is not less than 2, for example, a is set as n Where n represents the number of the coordinate reference point, such as 1,2, …; setting the first coordinate of the corresponding coordinate reference point as (x) an-1 ，y an-1 ) The second coordinate of the corresponding coordinate reference point is set as (x an-2 ，y an-2 ) Then there is a system of equationsBy bringing not less than 2 reference points into the system of equations, two binary sets of primary equations are reconstructed, e.g. there are two reference points, a respectively 1 And a 2 The corresponding first coordinate is (x a1-1 ，y a1-1 )、(x a2-1 ，y a2-1 ) The corresponding second coordinate is (x a1-2 ，y a1-2 )、(x a2-2 ，y a2-2 ) There is a system of equations- > Can calculate k 1 、k 2 、b 1 And b 2 Four coordinate relationship coefficients.
According to the embodiment of the invention, if not, the step of re-judging according to the change values of the texture pixel points of the infrared image and the high-definition image specifically comprises the following steps:
numbering the high-definition images and the infrared images in different directions according to time sequence to obtain high-definition images and infrared images of different time nodes;
performing difference value calculation on the texture pixel points of the high-definition images of different time nodes to obtain the variation value of the texture pixel points of the high-definition images;
performing difference value calculation on the texture pixel points of the infrared images of different time nodes to obtain the variation value of the texture pixel points of the infrared images;
based on the coordinate relation coefficient in the image overlapping area, judging whether the change value of the texture pixel point of the high-definition image at the same position is the same as the change value of the texture pixel point of the infrared image;
if yes, obtaining information that the camera is not shielded; if not, obtaining the shielding alarm information of one camera head.
It should be noted that, according to the coordinate relation coefficient in the image overlapping area, the same position of the infrared image and the high-definition image is found, and the change value of the texture pixel point of the high-definition image at the same position is determined, wherein when the change values are the same, the corresponding camera is indicated to be not shielded, and when the change values are different, the camera is indicated to be shielded, and one camera is indicated to be shielded, and the camera is shielded for the camera which does not change.
According to an embodiment of the present invention, further comprising:
when the texture similar area value is smaller than or equal to a preset first alarm threshold value and the corresponding texture similar area value is larger than 0, extracting the number value of the corresponding time nodes;
judging whether the number value of the corresponding time node is larger than a preset first number threshold value, if so, generating stain information on the camera;
and sending the information of the stain existing on the camera to a preset management end for prompting.
It should be noted that, when the corresponding texture similarity region value is greater than 0 and less than or equal to the preset first alarm threshold, the adjacent time node is recorded, and one is added to the corresponding time node number, such as t 1 Time node and t 2 Recording pairs if texture similar area values in patrol images of time nodes are larger than 0 and smaller than or equal to a preset first alarm threshold valueThe number of nodes to be time is increased by one, if t 2 Time node and t 3 And when the number value of the corresponding time node is greater than the preset first number threshold, indicating that stains and the like exist on the corresponding camera, such as water drops, stain points and the like.
According to an embodiment of the present invention, further comprising:
before the robot automatically patrol, panoramic image information of a patrol area is acquired;
extracting features in the panoramic image of the patrol area and corresponding feature quantity;
judging whether the quantity in the panoramic image of the patrol area is smaller than a preset second quantity threshold value, if so, generating patrol area similar warning information;
and sending the patrol area similar warning information to a preset management end for prompting.
It should be noted that, before the robot automatically patrols, the panorama of the patrol area is shot by the camera to obtain the panorama image of the corresponding patrol area, wherein when the characteristics in the panorama image of the patrol area are single or small (the number in the panorama image of the patrol area is smaller than the preset second number threshold), the layout of the corresponding patrol area is similar, the patrol effect is relatively large, so that similar warning information of the patrol area is generated, and the preset management end can increase the distinction of the patrol image by increasing the reference points of the patrol area at intervals.
FIG. 2 shows a block diagram of a system for determining a patrol robot camera occlusion alarm of the present invention.
As shown in fig. 2, a second aspect of the present invention provides a system 2 for determining a patrol robot camera occlusion alarm, including a memory 21 and a processor 22, where the memory stores a method program for determining a patrol robot camera occlusion alarm, and the method program for determining a patrol robot camera occlusion alarm when executed by the processor implements the following steps:
based on automatic patrol of the robot, patrol image information of different time nodes is obtained;
extracting textures in the patrol images, and carrying out contrast analysis on the textures in the patrol images of adjacent time nodes to obtain texture similarity region values;
judging whether the texture similar area value is larger than a preset first alarm threshold value, if so, adjusting the direction of the camera based on a preset holder preset position, and acquiring high definition and infrared images in different directions;
extracting textures of the high-definition image and textures of the infrared image in the same direction;
judging whether the textures of the high-definition image and the infrared image in the same direction are the same or not, if so, generating camera shielding alarm information; if not, re-judging according to the change values of the texture pixel points of the infrared image and the high-definition image;
And sending the camera shielding alarm information to a preset management end for prompting.
According to the embodiment of the invention, when the robot executes an automatic patrol task, a high-definition camera is used for acquiring a monitoring video in real time, extracting a frame image in the monitoring video, setting the monitoring video frame image as a patrol pattern, and numbering according to the time sequence of video frames to obtain patrol images of different time nodes; the camera comprises a high-definition camera and an infrared camera, the rotation direction of the camera is controlled by presetting a holder preset position, the camera is judged by the texture of a high-definition image and the texture of an infrared image in the same direction, and if the high-definition image and the texture of the infrared image are the same, the corresponding infrared camera and the high-definition camera are shielded.
According to an embodiment of the present invention, the step of comparing and analyzing textures in patrol images of adjacent time nodes to obtain texture similarity region values specifically includes:
comparing and analyzing textures in patrol images of adjacent time nodes to obtain texture similarity values in the patrol images of the adjacent time nodes;
judging whether the texture similarity value is larger than a preset similarity threshold value, if so, extracting texture positions corresponding to the texture similarity value, and obtaining an area value occupied by the corresponding texture positions;
And accumulating the area values occupied by the texture positions to obtain corresponding texture similar area values.
It should be noted that, for example, if the preset similarity threshold is 90%, when the texture similarity value is greater than 90%, the textures in the patrol images of the adjacent time nodes corresponding to the texture similarity value are set to be the same texture, the corresponding texture positions and the area values occupied by the corresponding texture positions are extracted, and the texture similarity area values are accumulated values of the area values occupied by the texture positions.
According to an embodiment of the present invention, the step of comparing and analyzing textures in patrol images of adjacent time nodes to obtain texture similarity values in patrol images of adjacent time nodes specifically includes:
binarizing textures in patrol images of adjacent time nodes to obtain texture pixel point gray values of patrol gray images of the adjacent time nodes at the same position;
extracting the minimum gray value and the maximum gray value in the gray values of texture pixel points of the patrol gray images of adjacent time nodes at the same position;
dividing the minimum gray value in the gray values of the texture pixel points at the same position by the maximum gray value to obtain a similar value of the texture pixel points at the corresponding position;
And calculating the average value of the similarity values of the texture pixel points at different positions to obtain the texture similarity values in patrol images corresponding to the adjacent time nodes.
When the gray values of the texture pixels of the patrol images of the adjacent time nodes at the same position are the same, the corresponding minimum gray value and the maximum gray value are equal, the similarity value of the texture pixels of the corresponding position is 100%, and the average value calculation is performed on the similarity values of all the texture pixels in the patrol images of the adjacent time nodes, so as to obtain the texture similarity value in the patrol images of the corresponding adjacent time nodes.
According to an embodiment of the present invention, further comprising:
acquiring Gao Qingdi an image set and infrared first image set information before the robot automatically patrols;
constructing a high-definition image coordinate system according to the Gao Qingdi image set; constructing an infrared image coordinate system according to the infrared first image set;
comparing and analyzing the Gao Qingdi image and the infrared first image of the same time node to obtain an image overlapping area of the corresponding time node;
and judging whether the image overlapping areas of different time nodes are the same, if so, fixing the corresponding high-definition camera and the infrared camera normally, and marking the image overlapping areas.
It should be noted that, the high-definition image coordinate system and the infrared image coordinate system are two-position coordinate systems, because the relative positions of the high-definition camera and the infrared camera are fixed, the image overlapping areas corresponding to the infrared image and the high-definition image are fixed, the Gao Qingdi image set comprises a plurality of Gao Qingdi images, the infrared first image set comprises a plurality of infrared first images, the images are identified by shooting time nodes, the Gao Qingdi image of the same time node and the infrared first images are compared with similar values, when the similar values are 100%, the corresponding positions are the image overlapping positions, all the image overlapping positions are accumulated to obtain the overlapping areas in the corresponding images, if the image overlapping areas of different time nodes are different, the high-definition camera or the infrared camera is not fixed, installation prompt information is triggered, and the corresponding installation prompt information is sent to a preset management end for display.
According to an embodiment of the present invention, after the marking the image overlapping area, the method further includes:
setting a plurality of coordinate reference points in an image overlapping area, and acquiring coordinates of the coordinate reference points in a high-definition image coordinate system to be set as a first coordinate;
Acquiring coordinates of the coordinate point reference points in an infrared image coordinate system, and setting the coordinates as second coordinates;
and forming a multi-element primary equation set by the first coordinates and the second coordinates of the coordinate points, and obtaining the coordinate relation coefficient of the corresponding high-definition image and the infrared image in the image overlapping area according to the multi-element primary equation set.
It should be noted that the number of coordinate reference points of the image overlapping region is not less than 2, for example, a is set as n Where n represents the number of the coordinate reference point, such as 1,2, …; setting the first coordinate of the corresponding coordinate reference point as (x) an-1 ，y an-1 ) The second coordinate of the corresponding coordinate reference point is set as (x an-2 ，y an-2 ) Then there is a system of equationsBy bringing not less than 2 reference points into the system of equations, two binary sets of primary equations are reconstructed, e.g. there are two reference points, a respectively 1 And a 2 The corresponding first coordinate is (x a1-1 ，y a1-1 )、(x a2-1 ，y a2-1 ) The corresponding second coordinate is (x a1-2 ，y a1-2 )、(x a2-2 ，y a2-2 ) There is a system of equations-> Can calculate k 1 、k 2 、b 1 And b 2 Four coordinate relationship coefficients.
According to the embodiment of the invention, if not, the step of re-judging according to the change values of the texture pixel points of the infrared image and the high-definition image specifically comprises the following steps:
numbering the high-definition images and the infrared images in different directions according to time sequence to obtain high-definition images and infrared images of different time nodes;
Performing difference value calculation on the texture pixel points of the high-definition images of different time nodes to obtain the variation value of the texture pixel points of the high-definition images;
performing difference value calculation on the texture pixel points of the infrared images of different time nodes to obtain the variation value of the texture pixel points of the infrared images;
based on the coordinate relation coefficient in the image overlapping area, judging whether the change value of the texture pixel point of the high-definition image at the same position is the same as the change value of the texture pixel point of the infrared image;
if yes, obtaining information that the camera is not shielded; if not, obtaining the shielding alarm information of one camera head.
It should be noted that, according to the coordinate relation coefficient in the image overlapping area, the same position of the infrared image and the high-definition image is found, and the change value of the texture pixel point of the high-definition image at the same position is determined, wherein when the change values are the same, the corresponding camera is indicated to be not shielded, and when the change values are different, the camera is indicated to be shielded, and one camera is indicated to be shielded, and the camera is shielded for the camera which does not change.
According to an embodiment of the present invention, further comprising:
when the texture similar area value is smaller than or equal to a preset first alarm threshold value and the corresponding texture similar area value is larger than 0, extracting the number value of the corresponding time nodes;
Judging whether the number value of the corresponding time node is larger than a preset first number threshold value, if so, generating stain information on the camera;
and sending the information of the stain existing on the camera to a preset management end for prompting.
It should be noted that, when the corresponding texture similarity region value is greater than 0 and less than or equal to the preset first alarm threshold, the adjacent time node is recorded, and one is added to the corresponding time node number, such as t 1 Time node and t 2 If the texture similarity area value in the patrol image of the time node is greater than 0 and smaller than or equal to a preset first alarm threshold value, the number value of the corresponding time node is recorded to be increased by one, and if t 2 Time node and t 3 If the texture similarity area value in the patrol image of the time node is greater than 0 and smaller than or equal to a preset first alarm threshold value, recording the number value of the corresponding time nodeAnd continuing to add one, when the number value of the corresponding time nodes is larger than the preset first number threshold value, indicating that stains and the like exist on the corresponding cameras, such as water drops, stain points and the like.
According to an embodiment of the present invention, further comprising:
before the robot automatically patrol, panoramic image information of a patrol area is acquired;
extracting features in the panoramic image of the patrol area and corresponding feature quantity;
Judging whether the quantity in the panoramic image of the patrol area is smaller than a preset second quantity threshold value, if so, generating patrol area similar warning information;
and sending the patrol area similar warning information to a preset management end for prompting.
It should be noted that, before the robot automatically patrols, the panorama of the patrol area is shot by the camera to obtain the panorama image of the corresponding patrol area, wherein when the characteristics in the panorama image of the patrol area are single or small (the number in the panorama image of the patrol area is smaller than the preset second number threshold), the layout of the corresponding patrol area is similar, the patrol effect is relatively large, so that similar warning information of the patrol area is generated, and the preset management end can increase the distinction of the patrol image by increasing the reference points of the patrol area at intervals.
A third aspect of the present invention provides a computer readable storage medium, in which a method program for determining a patrol robot camera occlusion alarm is stored, where the method program for determining a patrol robot camera occlusion alarm is executed by a processor, to implement the steps of a method for determining a patrol robot camera occlusion alarm as described in any one of the above.
According to the method, the system and the medium for judging the shielding alarm of the patrol robot camera, similar textures in patrol images of different time nodes are judged, if the similar texture area value is larger than the preset first alarm threshold value, alarm suspicion information is triggered, high-definition images and infrared images of a plurality of angles are obtained through a plurality of preset positions, secondary judgment is carried out according to the change values of texture pixel points of the high-definition images and the infrared images at the same position in an image overlapping area, false alarm is reduced, and alarm reliability is improved.
In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above described device embodiments are only illustrative, e.g. the division of the units is only one logical function division, and there may be other divisions in practice, such as: multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. In addition, the various components shown or discussed may be coupled or directly coupled or communicatively coupled to each other via some interface, whether indirectly coupled or communicatively coupled to devices or units, whether electrically, mechanically, or otherwise.
The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units; can be located in one place or distributed to a plurality of network units; some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present invention may be integrated in one processing unit, or each unit may be separately used as one unit, or two or more units may be integrated in one unit; the integrated units may be implemented in hardware or in hardware plus software functional units.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk or an optical disk, or the like, which can store program codes.
Alternatively, the above-described integrated units of the present invention may be stored in a computer-readable storage medium if implemented in the form of software functional modules and sold or used as separate products. Based on such understanding, the technical solutions of the embodiments of the present invention may be embodied in essence or a part contributing to the prior art in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, ROM, RAM, magnetic or optical disk, or other medium capable of storing program code.
Claims (10)
1. The method for judging the shielding alarm of the patrol robot camera is characterized by comprising the following steps:
based on automatic patrol of the robot, patrol image information of different time nodes is obtained;
extracting textures in the patrol images, and carrying out contrast analysis on the textures in the patrol images of adjacent time nodes to obtain texture similarity region values;
judging whether the texture similar area value is larger than a preset first alarm threshold value, if so, adjusting the direction of the camera based on a preset holder preset position, and acquiring high definition and infrared images in different directions;
Extracting textures of the high-definition image and textures of the infrared image in the same direction;
judging whether the textures of the high-definition image and the infrared image in the same direction are the same or not, if so, generating camera shielding alarm information; if not, re-judging according to the change values of the texture pixel points of the infrared image and the high-definition image;
and sending the camera shielding alarm information to a preset management end for prompting.
2. The method for judging the shielding alarm of the patrol robot camera according to claim 1, wherein the step of comparing and analyzing textures in patrol images of adjacent time nodes to obtain texture similarity region values specifically comprises:
comparing and analyzing textures in patrol images of adjacent time nodes to obtain texture similarity values in the patrol images of the adjacent time nodes;
judging whether the texture similarity value is larger than a preset similarity threshold value, if so, extracting texture positions corresponding to the texture similarity value, and obtaining an area value occupied by the corresponding texture positions;
and accumulating the area values occupied by the texture positions to obtain corresponding texture similar area values.
3. The method for judging the shielding alarm of the patrol robot camera according to claim 2, wherein the step of comparing and analyzing textures in patrol images of adjacent time nodes to obtain texture similarity values in patrol images of adjacent time nodes specifically comprises:
Binarizing textures in patrol images of adjacent time nodes to obtain texture pixel point gray values of patrol gray images of the adjacent time nodes at the same position;
extracting the minimum gray value and the maximum gray value in the gray values of texture pixel points of the patrol gray images of adjacent time nodes at the same position;
dividing the minimum gray value in the gray values of the texture pixel points at the same position by the maximum gray value to obtain a similar value of the texture pixel points at the corresponding position;
and calculating the average value of the similarity values of the texture pixel points at different positions to obtain the texture similarity values in patrol images corresponding to the adjacent time nodes.
4. The method for judging a patrol robot camera occlusion alarm of claim 1, further comprising:
acquiring Gao Qingdi an image set and infrared first image set information before the robot automatically patrols;
constructing a high-definition image coordinate system according to the Gao Qingdi image set; constructing an infrared image coordinate system according to the infrared first image set;
comparing and analyzing the Gao Qingdi image and the infrared first image of the same time node to obtain an image overlapping area of the corresponding time node;
And judging whether the image overlapping areas of different time nodes are the same, if so, fixing the corresponding high-definition camera and the infrared camera normally, and marking the image overlapping areas.
5. The method for determining a patrol robot camera occlusion alarm of claim 4, wherein after marking the image overlapping area, further comprising:
setting a plurality of coordinate reference points in an image overlapping area, and acquiring coordinates of the coordinate reference points in a high-definition image coordinate system to be set as a first coordinate;
acquiring coordinates of the coordinate point reference points in an infrared image coordinate system, and setting the coordinates as second coordinates;
and forming a multi-element primary equation set by the first coordinates and the second coordinates of the coordinate points, and obtaining the coordinate relation coefficient of the corresponding high-definition image and the infrared image in the image overlapping area according to the multi-element primary equation set.
6. The method for determining a camera shielding alarm of a patrol robot according to claim 1, wherein if not, the step of re-determining according to the change values of the texture pixel points of the infrared image and the high-definition image specifically comprises:
numbering the high-definition images and the infrared images in different directions according to time sequence to obtain high-definition images and infrared images of different time nodes;
Performing difference value calculation on the texture pixel points of the high-definition images of different time nodes to obtain the variation value of the texture pixel points of the high-definition images;
performing difference value calculation on the texture pixel points of the infrared images of different time nodes to obtain the variation value of the texture pixel points of the infrared images;
based on the coordinate relation coefficient in the image overlapping area, judging whether the change value of the texture pixel point of the high-definition image at the same position is the same as the change value of the texture pixel point of the infrared image;
if yes, obtaining information that the camera is not shielded; if not, obtaining the shielding alarm information of one camera head.
7. The system for judging the patrol robot camera shielding alarm is characterized by comprising a memory and a processor, wherein a method program for judging the patrol robot camera shielding alarm is stored in the memory, and the method program for judging the patrol robot camera shielding alarm is implemented when being executed by the processor and comprises the following steps:
based on automatic patrol of the robot, patrol image information of different time nodes is obtained;
extracting textures in the patrol images, and carrying out contrast analysis on the textures in the patrol images of adjacent time nodes to obtain texture similarity region values;
Judging whether the texture similar area value is larger than a preset first alarm threshold value, if so, adjusting the direction of the camera based on a preset holder preset position, and acquiring high definition and infrared images in different directions;
extracting textures of the high-definition image and textures of the infrared image in the same direction;
judging whether the textures of the high-definition image and the infrared image in the same direction are the same or not, if so, generating camera shielding alarm information; if not, re-judging according to the change values of the texture pixel points of the infrared image and the high-definition image;
and sending the camera shielding alarm information to a preset management end for prompting.
8. The system for determining a patrol robot camera shielding alarm according to claim 7, wherein the step of comparing textures in patrol images of adjacent time nodes to obtain texture similarity region values comprises:
comparing and analyzing textures in patrol images of adjacent time nodes to obtain texture similarity values in the patrol images of the adjacent time nodes;
judging whether the texture similarity value is larger than a preset similarity threshold value, if so, extracting texture positions corresponding to the texture similarity value, and obtaining an area value occupied by the corresponding texture positions;
And accumulating the area values occupied by the texture positions to obtain corresponding texture similar area values.
9. The system for judging the shielding alarm of the patrol robot camera according to claim 8, wherein the step of comparing and analyzing textures in patrol images of adjacent time nodes to obtain texture similarity values in patrol images of adjacent time nodes comprises:
binarizing textures in patrol images of adjacent time nodes to obtain texture pixel point gray values of patrol gray images of the adjacent time nodes at the same position;
extracting the minimum gray value and the maximum gray value in the gray values of texture pixel points of the patrol gray images of adjacent time nodes at the same position;
dividing the minimum gray value in the gray values of the texture pixel points at the same position by the maximum gray value to obtain a similar value of the texture pixel points at the corresponding position;
and calculating the average value of the similarity values of the texture pixel points at different positions to obtain the texture similarity values in patrol images corresponding to the adjacent time nodes.
10. A computer readable storage medium, wherein a method program for judging the shielding alarm of the patrol robot camera is stored in the computer readable storage medium, and when the method program for judging the shielding alarm of the patrol robot camera is executed by a processor, the steps of the method for judging the shielding alarm of the patrol robot camera as claimed in any one of claims 1 to 6 are realized.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311594095.XA CN117635937A (en) | 2023-11-27 | 2023-11-27 | Method, system and medium for judging shielding alarm of patrol robot camera |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311594095.XA CN117635937A (en) | 2023-11-27 | 2023-11-27 | Method, system and medium for judging shielding alarm of patrol robot camera |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117635937A true CN117635937A (en) | 2024-03-01 |
Family
ID=90035072
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311594095.XA Pending CN117635937A (en) | 2023-11-27 | 2023-11-27 | Method, system and medium for judging shielding alarm of patrol robot camera |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117635937A (en) |
-
2023
- 2023-11-27 CN CN202311594095.XA patent/CN117635937A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP2549738B1 (en) | Method and camera for determining an image adjustment parameter | |
| US7982774B2 (en) | Image processing apparatus and image processing method | |
| CN111898581B (en) | Animal detection method, apparatus, electronic device, and readable storage medium | |
| US10692225B2 (en) | System and method for detecting moving object in an image | |
| CN109685062B (en) | Target detection method, device, equipment and storage medium | |
| JP3486229B2 (en) | Image change detection device | |
| CN108710837A (en) | Cigarette smoking recognition methods, device, computer equipment and storage medium | |
| CN112800846A (en) | High-altitude parabolic monitoring method and device, electronic equipment and storage medium | |
| CN116402852A (en) | Dynamic high-speed target tracking method and device based on event camera | |
| JP2009545223A (en) | Event detection method and video surveillance system using the method | |
| CN112422909B (en) | Video behavior analysis management system based on artificial intelligence | |
| CN117635937A (en) | Method, system and medium for judging shielding alarm of patrol robot camera | |
| JP4756357B2 (en) | Video surveillance device | |
| CN113936242B (en) | Video image interference detection method, system, device and medium | |
| Maalouf et al. | Offline quality monitoring for legal evidence images in video-surveillance applications | |
| CN111325073A (en) | Monitoring video abnormal behavior detection method based on motion information clustering | |
| CN114897766A (en) | Code stream anomaly detection method and device and computer readable storage medium | |
| CN114699702A (en) | Fire fighting equipment detection method and related device | |
| CN115035543A (en) | Big data-based movement track prediction system | |
| CN114359183A (en) | Image quality evaluation method and device, and lens occlusion determination method | |
| CN114170090A (en) | Method and system for reconstructing high-resolution image from fuzzy monitoring video | |
| CN114004876A (en) | Dimension calibration method, dimension calibration device and computer readable storage medium | |
| CN112819738A (en) | Infrared image fusion method and device, computer equipment and storage medium | |
| CN111860326A (en) | Building site article movement detection method, device, equipment and storage medium | |
| CN114820692B (en) | State analysis method, device, storage medium and terminal for tracking target |
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 |