CN111709360B - Safety rope wearing identification method and system - Google Patents
Safety rope wearing identification method and system Download PDFInfo
- Publication number
- CN111709360B CN111709360B CN202010546834.8A CN202010546834A CN111709360B CN 111709360 B CN111709360 B CN 111709360B CN 202010546834 A CN202010546834 A CN 202010546834A CN 111709360 B CN111709360 B CN 111709360B
- Authority
- CN
- China
- Prior art keywords
- safety rope
- determining
- safety
- human body
- prediction area
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/103—Static body considered as a whole, e.g. static pedestrian or occupant recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
- G06V10/443—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
Abstract
The invention discloses a safety rope wearing identification method and system. The method comprises the following steps: determining the position and radiation range of a human body; determining a safety rope prediction area according to the position of a human body, and determining the outline of the safety rope in the prediction area by a safety rope color identification method; determining a minimum circumscribed rectangle of the outline of the safety rope, and determining coordinates of four corner points of the minimum circumscribed rectangle according to the position of the minimum circumscribed rectangle on the picture to be recognized; determining the length-width ratio of the minimum circumscribed rectangle according to the coordinates of the four corner points, and determining whether a safety rope exists according to the comparison result of the length-width ratio and a preset ratio; if the safety rope exists, the coordinates of the four angular points and the distance between the original points are respectively compared with the radius, the number of the distances smaller than the radius is determined, and the wearing identification of the safety rope is carried out according to the number. By adopting the method and the system, whether the person wears the safety rope can be identified by identifying the position relation between the safety rope and the person through the image, and the method and the system have the advantages of low cost, rapid detection and convenient operation.
Description
Technical Field
The invention relates to the technical field of image recognition, in particular to a safety rope wearing recognition method and system.
Background
The existing wearing detection research on the safety rope mainly adopts two modes: one is that the pressure that utilizes the safety rope to produce in the wearing process through the sensor, passes through signal transmission after the pressure that detects the safety rope production through pressure sensor, transmits to the computer, and whether the constructor wears the safety rope is discerned through the signal that acquires to the computer. If the safety rope is not pulled or stressed, the sensor cannot generate a signal due to incapability of being stressed and cannot transmit the signal to the computer, and the computer cannot judge whether the safety rope is worn or not because the computer does not acquire the signal of the sensor. However, a safety rope needs a plurality of sensors, and a wired or wireless network is required to be used as a carrier for signal transmission, so that the cost for wearing and detecting by a large number of construction personnel is more expensive. The second method is to perform model training on the safety rope in a model training mode, and recognize the safety rope in the image in the model training mode, but the mode of model training has many misjudgment situations, and many similar objects similar to the safety rope can be recognized, such as water pipes, steel bars and the like. Meanwhile, a large amount of basic data training sets are needed for model training, the quality of the model is directly influenced by the acquired quality, manpower and material resources are consumed for obtaining the training sets of the basic data, the time cost of model training is very high, and the situation that one model is in one scene may exist. For time-demanding and complex environments, the detection period will be very long. And the detection of the safety rope is only the detection of the safety rope, and whether the constructor wears the safety rope really or not cannot be judged.
Disclosure of Invention
The invention aims to provide a safety rope wearing identification method and a safety rope wearing identification system, which can identify whether to wear a safety rope or not by identifying the position relation between the safety rope and constructors through images and have the advantages of low cost, rapid detection and convenient operation.
In order to achieve the purpose, the invention provides the following scheme:
a safety line wear identification method, comprising:
acquiring a picture to be identified;
determining the position and the radiation range of the human body by adopting a human body detection algorithm according to the picture to be identified; the outline shape of the radiation range is circular, the origin is the center point of the human body, and the radius is N times of the distance from the center point of the human body to the top of the head of the human body;
determining a safety rope prediction area according to the position of the human body;
determining the safety rope outline in the safety rope prediction area by adopting a safety rope color identification method;
determining a minimum circumscribed rectangle of the safety rope outline, and determining coordinates of four corner points of the minimum circumscribed rectangle according to the position of the minimum circumscribed rectangle on the picture to be identified;
determining the length-width ratio of the minimum circumscribed rectangle according to the coordinates of the four corner points, comparing the length-width ratio with a preset ratio, and determining whether a safety rope exists according to a comparison result;
if the safety rope exists, comparing the coordinates of the four angular points and the distances between the original points with the radius respectively, and determining the number of the distances smaller than the radius;
and carrying out safety rope wearing identification according to the number.
Optionally, the determining the safety rope prediction area according to the position of the human body specifically includes:
forming a rectangle by taking the coordinate position of the center of the human body as the center point of the rectangle, and determining the rectangle as a safety rope prediction area; the length and width of the rectangle are both 3 times the radius.
Optionally, the determining the safety rope profile in the safety rope prediction area by using a safety rope color identification method specifically includes:
carrying out color space conversion on the safety rope prediction area to obtain an HSV color space;
extracting the color of the safety rope in the HSV color space, and removing the colors except the color of the safety rope to obtain a prediction area after color filtration;
filtering the prediction region after color filtering to obtain a prediction region after filtering;
carrying out binarization processing on the prediction region after the filtering processing to obtain a prediction region after the binarization processing;
determining safety rope edge information of the prediction area after the binarization processing by adopting an edge detection method;
and searching the safety rope wheel outline according to the safety rope edge information to obtain the safety rope outline.
Optionally, the identifying of wearing the safety rope according to the number specifically includes:
acquiring a preset number;
judging whether the number of the distances smaller than the radius is larger than or equal to the preset number or not; if yes, identifying to obtain a wearing safety rope; if not, identifying to obtain that the safety rope is not worn.
Optionally, the method further includes, after the safety rope wearing identification is performed according to the number:
when the safety rope is identified and not worn, the corresponding safety rope information is removed; and when the safety rope is worn through identification, carrying out safety marking on the corresponding safety rope and personnel, and displaying a safety marking result.
The invention also provides a safety rope wearing identification system, comprising:
the image acquisition module is used for acquiring an image to be identified;
the human body detection module is used for determining the position and the radiation range of a human body by adopting a human body detection algorithm according to the picture to be identified; the outline shape of the radiation range is circular, the origin is the center point of the human body, and the radius is N times of the distance from the center point of the human body to the top of the head of the human body;
the safety rope prediction area determining module is used for determining a safety rope prediction area according to the position of the human body;
the safety rope outline determining module is used for determining the safety rope outline in the safety rope prediction area by adopting a safety rope color identification method;
the minimum circumscribed rectangle determining module is used for determining a minimum circumscribed rectangle of the safety rope outline and determining coordinates of four corner points of the minimum circumscribed rectangle according to the position of the minimum circumscribed rectangle on the picture to be identified;
the safety rope existence judging module is used for determining the length-width ratio of the minimum external rectangle according to the coordinates of the four corner points, comparing the length-width ratio with a preset ratio and determining whether a safety rope exists according to a comparison result;
the comparison module is used for comparing the coordinates of the four corner points and the distances between the origin points with the radius respectively when the safety rope exists, and determining the number of the distances smaller than the radius;
and the safety rope wearing identification module is used for carrying out safety rope wearing identification according to the number.
Optionally, the safety rope prediction area determining module specifically includes:
the safety rope prediction area determining unit is used for forming a rectangle by taking the central coordinate position of the human body as a central point of the rectangle and determining the rectangle as a safety rope prediction area; the length and width of the rectangle are both 3 times the radius.
Optionally, the safety rope profile determining module specifically includes:
the color space conversion unit is used for carrying out color space conversion on the safety rope prediction area to obtain an HSV color space;
the filtering processing unit is used for extracting the color of the safety rope in the HSV color space and removing the colors except the color of the safety rope to obtain a prediction area after color filtering;
the filtering processing unit is used for carrying out filtering processing on the prediction region after the color filtering to obtain a prediction region after the filtering processing;
a binarization processing unit, configured to perform binarization processing on the prediction region after the filtering processing to obtain a prediction region after the binarization processing;
an edge detection unit, configured to determine safety rope edge information of the prediction region after the binarization processing by using an edge detection method;
and the safety rope contour determining unit is used for searching the safety rope contour according to the safety rope edge information to obtain the safety rope contour.
Optionally, the safety rope wearing identification module specifically includes:
the number acquisition unit is used for acquiring a preset number;
the judging unit is used for judging whether the number of the distances smaller than the radius is larger than or equal to the preset number; if yes, identifying to obtain a wearing safety rope; if not, identifying to obtain that the safety rope is not worn.
Optionally, the system further includes:
the identification result display module is used for eliminating the corresponding safety rope information when the safety rope is identified to be worn; and when the safety rope is worn through identification, carrying out safety marking on the corresponding safety rope and personnel, and displaying a safety marking result.
Compared with the prior art, the invention has the beneficial effects that:
the invention provides a safety rope wearing identification method and a safety rope wearing identification system.A human body position and a radiation range are determined by adopting a human body detection algorithm according to a picture to be identified, the outline shape of the radiation range is circular, the original point is a human body central point, and the radius is N times of the distance from the human body central point to the top of the head of the human body; determining a safety rope prediction area according to the position of a human body, wherein the area is rectangular, and determining the outline of the safety rope in the prediction area by a safety rope color identification method; determining a minimum circumscribed rectangle of the outline of the safety rope, and determining coordinates of four corner points of the minimum circumscribed rectangle according to the position of the minimum circumscribed rectangle on the picture to be recognized; determining the length-width ratio of the minimum circumscribed rectangle according to the coordinates of the four corner points, comparing the length-width ratio with a preset ratio, and determining whether a safety rope exists according to a comparison result; if the safety rope exists, the coordinates of the four angular points and the distance between the original points are respectively compared with the radius, the number of the distances smaller than the radius is determined, and the wearing identification of the safety rope is carried out according to the number. The invention can identify whether the person wears the safety rope or not by identifying the position relation between the safety rope and the person through the image, and has the advantages of low cost, rapid detection and convenient operation.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a flow chart of a safety line wearing identification method in an embodiment of the invention;
fig. 2 is a block diagram of a safety line wearing identification system according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention aims to provide a safety rope wearing identification method and a safety rope wearing identification system, which can identify whether to wear a safety rope or not by identifying the position relation between the safety rope and constructors through images and have the advantages of low cost, rapid detection and convenient operation.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
Examples
Fig. 1 is a flowchart of a safety rope wearing identification method in an embodiment of the present invention, and as shown in fig. 1, a safety rope wearing identification method includes:
step 101: and acquiring a picture to be identified.
A user obtains monitored image information, namely an image of the site operation of a constructor, through self-shooting or through shooting equipment such as an unmanned aerial vehicle; and after the user acquires the image to be detected, storing the image into a specified folder. After a user opens the program, the program can automatically load the images in the folder, if the loading is not successful, the existing file information cannot be displayed, and whether the storage is correct or not and whether the format is wrong or not need to be checked. And after the image is loaded successfully, image selection is carried out, all loaded images can be seen by selecting the image pulldown box, and the detected image is selected. After the selected image is confirmed, the detection program is triggered by clicking the detection. And acquiring the name information of the image file transmitted and entering, and recording the name information of the image file into a memory for calling during detection.
Step 102: determining the position and the radiation range of a human body by adopting a human body detection algorithm according to the picture to be identified; the outline shape of the radiation range is circular, the origin is the central point of the upper half of the human body, the radius is N times of the distance from the origin to the top of the head of the human body, wherein N =1.5.
And (3) adopting a deep neural network based on a YOLO3 model, obtaining a human body model through model training, detecting an area with characteristics conforming to the human body model in the image through the human body model, and recording characteristic parameter information and carrying out marking processing in the image if the area is detected.
Step 103: and determining a safety rope prediction area according to the position of the human body.
Forming a rectangle by taking the coordinate position of the center of the human body as the center point of the rectangle, and determining the rectangle as a safety rope prediction area; the length and width of the rectangle are both 3 times the radius of the radiating range.
Step 104: and determining the safety rope outline in the safety rope prediction area by adopting a safety rope color identification method.
1) Carrying out color space conversion on the prediction area to obtain an HSV color space; i.e. conversion of RGB and HSV color spaces.
2) And extracting the color of the safety rope in the HSV color space, and removing the colors except the color of the safety rope to obtain the prediction region after color filtration.
3) And carrying out filtering processing on the prediction area after color filtering to obtain the prediction area after filtering processing. Useless image noise is removed through filtering.
4) And carrying out binarization processing on the prediction region after the filtering processing to obtain the prediction region after the binarization processing.
5) And determining safety rope edge information of the prediction area after binarization processing by adopting an edge detection method, and then processing useless information by morphological processing.
6) And searching the safety rope wheel outline according to the safety rope edge information to obtain the safety rope outline.
And finally, filtering the reserved information based on the morphological characteristics of the safety rope when the safety rope is worn, and acquiring the characteristic parameters of the safety rope.
Step 105: and determining the minimum circumscribed rectangle of the outline of the safety rope, and determining the coordinates of four corner points of the minimum circumscribed rectangle according to the position of the minimum circumscribed rectangle on the picture to be recognized.
Step 106: and determining the length-width ratio of the minimum circumscribed rectangle according to the coordinates of the four corner points, comparing the length-width ratio with a preset ratio, and determining whether the safety rope exists according to the comparison result.
Specifically, the method comprises the following steps:
comparing the length-width ratio with a preset ratio, and if the length-width ratio is greater than the preset ratio, a safety rope exists; otherwise, no safety cord is present. Wherein the predetermined ratio is 5.
Step 107: if the safety rope exists, the distances between the coordinates of the four angular points and the original point are respectively compared with the radius, and the number of the distances smaller than the radius is determined.
Step 108: and carrying out safety rope wearing identification according to the number. Namely, the incidence relation between the safety rope and the constructor is judged, and whether the safety rope is worn by the constructor or is judged.
acquiring a preset number;
judging whether the number of the distances smaller than the radius is larger than or equal to a preset number or not; if yes, identifying to obtain a wearing safety rope; if not, identifying to obtain that the safety rope is not worn.
Step 109: when the safety rope which is not worn is identified, the corresponding safety rope information is removed (namely the safety rope which is not worn is deleted); and when the safety rope is worn through identification, carrying out safety marking on the corresponding safety rope and personnel, and displaying a safety marking result.
According to the method, the characteristic information of the safety rope and the characteristic information of the human body are obtained, the characteristic that the safety rope is worn by the human body is combined to carry out association judgment of the safety rope and the characteristic information of the human body, if the safety rope is not associated with the human body, the safety rope information at the position is removed, if the safety rope is associated with the human body, the safety rope information is reserved, under the condition that a plurality of human bodies exist, each human body carries out association polling judgment of the safety rope, and only the safety rope associated with the human body is reserved and marked after polling. For constructors who wear the safety rope, marking 'safe', namely, indicating safety, and for constructors who do not wear the safety rope, marking 'no _ safe', namely, indicating unsafe. The display is on the interface, a user can check the detection result through the display area, one displayed image is an original image, the other displayed image is a detected image, the judgment can be better carried out through the comparison of the original image and the detected image, and meanwhile, the detection accuracy can be further verified through manual work. And storing the detected image.
The invention improves the detection speed, reduces the investment of equipment and resources, expands the use scene range of each construction site, saves the cost, can quickly adapt to the detection of each scene through the adjustment of partial parameters, does not need to do a large amount of preparation work before the detection, can directly configure background parameters according to each scene, and achieves high efficiency and rapidness.
Fig. 2 is a block diagram of a safety line wearing identification system according to an embodiment of the present invention. As shown in fig. 2, a safety line wearing identification system includes:
the image obtaining module 201 is configured to obtain an image to be identified.
The human body detection module 202 is used for determining the position and the radiation range of a human body by adopting a human body detection algorithm according to the picture to be identified; the outline shape of the radiation range is circular, the origin point is the center point of the human body, and the radius is N times of the distance from the center point of the human body to the top of the head of the human body.
And the safety rope prediction area determining module 203 is used for determining the safety rope prediction area according to the position of the human body.
The safety rope prediction area determining module 203 specifically includes:
the safety rope prediction area determining unit is used for forming a rectangle by taking the central coordinate position of the human body as a central point of the rectangle and determining the rectangle as a safety rope prediction area; the rectangle is 3 times the radius in both length and width.
And the safety rope outline determining module 204 is used for determining the safety rope outline in the safety rope prediction area by adopting a safety rope color identification method.
The safety rope profile determining module 204 specifically includes:
the color space conversion unit is used for performing color space conversion on the safety rope prediction area to obtain an HSV color space;
the filtering processing unit is used for extracting the color of the safety rope in the HSV color space and removing the colors except the color of the safety rope to obtain a prediction area after color filtering;
the filtering processing unit is used for carrying out filtering processing on the prediction area after color filtering to obtain the prediction area after filtering processing;
a binarization processing unit, configured to perform binarization processing on the prediction region after the filtering processing to obtain a prediction region after the binarization processing;
the edge detection unit is used for determining safety rope edge information of the prediction area after binarization processing by adopting an edge detection method;
and the safety rope profile determining unit is used for searching the safety rope wheel profile according to the safety rope edge information to obtain the safety rope profile.
And the minimum circumscribed rectangle determining module 205 is configured to determine a minimum circumscribed rectangle of the outline of the safety rope, and determine coordinates of four corner points of the minimum circumscribed rectangle according to the position of the minimum circumscribed rectangle on the picture to be recognized.
And the safety rope existence judging module 206 is configured to determine the length-width ratio of the minimum external rectangle according to the coordinates of the four corner points, compare the length-width ratio with a preset ratio, and determine whether the safety rope exists according to a comparison result.
And the comparison module 207 is used for comparing the distances between the coordinates of the four corner points and the original point with the radius respectively when the safety rope exists, and determining the number of the distances smaller than the radius.
And the safety rope wearing identification module 208 is used for carrying out safety rope wearing identification according to the number.
The safety rope wearing identification module 208 specifically includes:
the number acquisition unit is used for acquiring a preset number;
the judging unit is used for judging whether the number of the distances smaller than the radius is larger than or equal to the preset number; if yes, identifying to obtain a wearing safety rope; if not, identifying that the safety rope is not worn.
The identification result display module 209 is used for removing the corresponding safety rope information when the safety rope is identified and not worn; when the safety rope is worn through identification, safety marking is carried out on the corresponding safety rope and the corresponding personnel, and a safety marking result is displayed.
The safety rope wearing identification system also comprises a storage module, and the storage module is used for storing the detection result image (marked image) into a specific folder for the user to use as a storage file.
For the system disclosed by the embodiment, the description is relatively simple because the system corresponds to the method disclosed by the embodiment, and the relevant points can be referred to the description of the method part.
The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, this summary should not be construed as limiting the invention.
Claims (10)
1. A safety rope wearing identification method is characterized by comprising the following steps:
acquiring a picture to be identified;
determining the position and the radiation range of the human body by adopting a human body detection algorithm according to the picture to be identified; the outline shape of the radiation range is circular, the origin is the center point of the human body, and the radius is N times of the distance from the center point of the human body to the top of the head of the human body;
determining a safety rope prediction area according to the position of the human body;
determining the safety rope outline in the safety rope prediction area by adopting a safety rope color identification method;
determining a minimum circumscribed rectangle of the safety rope outline, and determining coordinates of four corner points of the minimum circumscribed rectangle according to the position of the minimum circumscribed rectangle on the picture to be identified;
determining the length-width ratio of the minimum circumscribed rectangle according to the coordinates of the four corner points, comparing the length-width ratio with a preset ratio, and determining whether a safety rope exists according to a comparison result;
if the safety rope exists, comparing the coordinates of the four angular points and the distances between the original points with the radius respectively, and determining the number of the distances smaller than the radius;
and carrying out safety rope wearing identification according to the number.
2. The safety rope wearing identification method according to claim 1, wherein the determining a safety rope prediction area according to the position of the human body specifically comprises:
forming a rectangle by taking the coordinate position of the center of the human body as the center point of the rectangle, and determining the rectangle as a safety rope prediction area; the length and width of the rectangle are both 3 times the radius.
3. The safety rope wearing identification method according to claim 1, wherein the determining of the safety rope profile in the safety rope prediction region by using a safety rope color identification method specifically comprises:
carrying out color space conversion on the safety rope prediction area to obtain an HSV color space;
extracting the color of the safety rope in the HSV color space, and removing the colors except the color of the safety rope to obtain a prediction region after color filtration;
filtering the prediction area after color filtering to obtain a prediction area after filtering;
carrying out binarization processing on the prediction area after the filtering processing to obtain a prediction area after the binarization processing;
determining safety rope edge information of the prediction area after binarization processing by adopting an edge detection method;
and searching the safety rope wheel outline according to the safety rope edge information to obtain the safety rope outline.
4. The safety rope wearing identification method according to claim 1, wherein the safety rope wearing identification according to the number specifically includes:
acquiring a preset number;
judging whether the number of the distances smaller than the radius is larger than or equal to the preset number or not; if yes, identifying to obtain a wearing safety rope; if not, identifying to obtain that the safety rope is not worn.
5. The safety rope wearing identification method according to claim 4, wherein the method further comprises, after the safety rope wearing identification is performed according to the number:
when the safety rope is identified and not worn, the corresponding safety rope information is removed; and when the safety rope is worn through identification, carrying out safety marking on the corresponding safety rope and personnel, and displaying a safety marking result.
6. A safety line wear identification system, comprising:
the image acquisition module is used for acquiring an image to be identified;
the human body detection module is used for determining the position and the radiation range of a human body by adopting a human body detection algorithm according to the picture to be identified; the outline shape of the radiation range is circular, the origin is the center point of the human body, and the radius is N times of the distance from the center point of the human body to the top of the head of the human body;
the safety rope prediction area determining module is used for determining a safety rope prediction area according to the position of the human body;
the safety rope outline determining module is used for determining the safety rope outline in the safety rope prediction area by adopting a safety rope color identification method;
the minimum circumscribed rectangle determining module is used for determining a minimum circumscribed rectangle of the outline of the safety rope and determining coordinates of four corner points of the minimum circumscribed rectangle according to the position of the minimum circumscribed rectangle on the picture to be identified;
the safety rope existence judging module is used for determining the length-width ratio of the minimum circumscribed rectangle according to the coordinates of the four corner points, comparing the length-width ratio with a preset ratio and determining whether a safety rope exists according to a comparison result;
the comparison module is used for comparing the coordinates of the four corner points and the distances between the origin points with the radius respectively when the safety rope exists, and determining the number of the distances smaller than the radius;
and the safety rope wearing identification module is used for carrying out safety rope wearing identification according to the number.
7. The safety line wear identification system of claim 6, wherein the safety line prediction region determination module specifically comprises:
the safety rope prediction area determining unit is used for forming a rectangle by taking the central coordinate position of the human body as a central point of the rectangle and determining the rectangle as a safety rope prediction area; the length and width of the rectangle are both 3 times the radius.
8. The safety line wear identification system of claim 6, wherein the safety line profile determination module specifically comprises:
the color space conversion unit is used for carrying out color space conversion on the safety rope prediction area to obtain an HSV color space;
the filtering processing unit is used for extracting the color of the safety rope in the HSV color space and removing the colors except the color of the safety rope to obtain a prediction area after color filtering;
the filtering processing unit is used for carrying out filtering processing on the prediction region after the color filtering to obtain a prediction region after the filtering processing;
a binarization processing unit, configured to perform binarization processing on the prediction region after the filtering processing to obtain a prediction region after the binarization processing;
an edge detection unit, configured to determine safety rope edge information of the prediction area after the binarization processing by using an edge detection method;
and the safety rope contour determining unit is used for searching the safety rope pulley contour according to the safety rope edge information to obtain the safety rope contour.
9. The safety rope wearing identification system according to claim 6, wherein the safety rope wearing identification module specifically comprises:
the number acquisition unit is used for acquiring a preset number;
the judging unit is used for judging whether the number of the distances smaller than the radius is larger than or equal to the preset number; if yes, identifying to obtain a wearing safety rope; if not, identifying to obtain that the safety rope is not worn.
10. The safety line wear identification system of claim 9, further comprising:
the identification result display module is used for eliminating the corresponding safety rope information when the safety rope is identified and not worn; and when the safety rope is worn through identification, carrying out safety marking on the corresponding safety rope and personnel, and displaying a safety marking result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010546834.8A CN111709360B (en) | 2020-06-16 | 2020-06-16 | Safety rope wearing identification method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010546834.8A CN111709360B (en) | 2020-06-16 | 2020-06-16 | Safety rope wearing identification method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111709360A CN111709360A (en) | 2020-09-25 |
| CN111709360B true CN111709360B (en) | 2023-04-07 |
Family
ID=72540231
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010546834.8A Active CN111709360B (en) | 2020-06-16 | 2020-06-16 | Safety rope wearing identification method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111709360B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114155492A (en) * | 2021-12-09 | 2022-03-08 | 华电宁夏灵武发电有限公司 | High-altitude operation safety belt hanging rope high-hanging low-hanging use identification method and device and electronic equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017084204A1 (en) * | 2015-11-19 | 2017-05-26 | 广州新节奏智能科技有限公司 | Method and system for tracking human body skeleton point in two-dimensional video stream |
| CN108537256A (en) * | 2018-03-26 | 2018-09-14 | 北京智芯原动科技有限公司 | A kind of safety cap wears recognition methods and device |
| CN109117827A (en) * | 2018-09-05 | 2019-01-01 | 武汉市蓝领英才科技有限公司 | Work clothes work hat wearing state automatic identifying method and alarm system based on video |
-
2020
- 2020-06-16 CN CN202010546834.8A patent/CN111709360B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017084204A1 (en) * | 2015-11-19 | 2017-05-26 | 广州新节奏智能科技有限公司 | Method and system for tracking human body skeleton point in two-dimensional video stream |
| CN108537256A (en) * | 2018-03-26 | 2018-09-14 | 北京智芯原动科技有限公司 | A kind of safety cap wears recognition methods and device |
| CN109117827A (en) * | 2018-09-05 | 2019-01-01 | 武汉市蓝领英才科技有限公司 | Work clothes work hat wearing state automatic identifying method and alarm system based on video |
Non-Patent Citations (2)
| Title |
|---|
| 朱明，余彧，庄悦，戴玥，郭旭雷，陆小锋."基于DSP的广告智能推送系统".《数据采集与处理》.2012,第27卷(第S2期),第267-271页. * |
| 钱国权，李可中，周健华."钢丝绳检测对电力安全施工的保障作用".《华东电力》.2006,第34卷(第12期),第83-85页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111709360A (en) | 2020-09-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109670441B (en) | Method, system, terminal and computer readable storage medium for realizing wearing recognition of safety helmet | |
| CN107578012B (en) | Driving assistance system for selecting sensitive area based on clustering algorithm | |
| CN108182383B (en) | Vehicle window detection method and device | |
| CN111639629B (en) | Pig weight measurement method and device based on image processing and storage medium | |
| CN102708691B (en) | False license plate identification method based on matching between license plate and automobile type | |
| CN112784821A (en) | Building site behavior safety detection and identification method and system based on YOLOv5 | |
| CN111709360B (en) | Safety rope wearing identification method and system | |
| CN111506011A (en) | Construction safety monitoring method and device | |
| CN110428579B (en) | Indoor monitoring system, method and device based on image recognition | |
| CN110728212B (en) | Road well lid monitoring device and monitoring method based on computer vision | |
| KR101236234B1 (en) | Detection system of road line using both laser sensor and camera | |
| CN110874572A (en) | Information detection method and device and storage medium | |
| CN111332306A (en) | Traffic road perception auxiliary driving early warning device based on machine vision | |
| CN113808087A (en) | Defect management and control method and device for surface of steel plate and computer readable storage medium | |
| CN113657201A (en) | Method, device, equipment and storage medium for monitoring and analyzing behavior of crew | |
| CN112749735A (en) | Converter tapping steel flow identification method, system, medium and terminal based on deep learning | |
| CN112966618A (en) | Dressing identification method, device, equipment and computer readable medium | |
| CN111127494A (en) | Expressway truck weight limit identification method based on image processing | |
| CN114694073B (en) | Intelligent detection method, device, storage medium and equipment for wearing condition of safety belt | |
| CN115953815A (en) | Monitoring method and device for infrastructure site | |
| CN115810161A (en) | Transformer substation fire identification method and system | |
| CN111107139B (en) | Information pushing method, device, equipment and storage medium | |
| CN209946948U (en) | Intelligent reinspection equipment of PC component | |
| US20230230344A1 (en) | Signal color determination device and signal color determination method | |
| CN109241798A (en) | A kind of intelligent identifying system in driving |
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 |