CN115082848A - Method, device, equipment, medium and program product for managing wearing of industrial and ground work clothes - Google Patents
Method, device, equipment, medium and program product for managing wearing of industrial and ground work clothes Download PDFInfo
- Publication number
- CN115082848A CN115082848A CN202210551996.XA CN202210551996A CN115082848A CN 115082848 A CN115082848 A CN 115082848A CN 202210551996 A CN202210551996 A CN 202210551996A CN 115082848 A CN115082848 A CN 115082848A
- Authority
- CN
- China
- Prior art keywords
- human body
- picture
- construction site
- work clothes
- work
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/53—Recognition of crowd images, e.g. recognition of crowd congestion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Human Computer Interaction (AREA)
- Alarm Systems (AREA)
Abstract
The embodiment of the invention provides a method, a device, equipment, a medium and a program product for managing wearing of construction site work clothes, wherein the method comprises the following steps: receiving video monitoring data returned by a construction site, and extracting construction site pictures; carrying out human body detection on the site picture of the construction site to mark a human body detection frame; cutting the construction site picture based on the human body detection frame to obtain a human body picture; inputting the human body picture into a classification network to obtain a work clothes identification result of the human body picture; the work clothes identification result comprises a first identification result of whether a person in the human body picture wears the work clothes or not; the classification network is obtained by taking a training sample picture containing a human body as input and taking a labeling result of a person wearing a frock or not wearing the frock in the training sample picture as a label training. The embodiment of the invention can realize the automatic identification of whether workers in a construction site wear a worker's clothes, improve the automation degree of construction site management, improve the construction site management efficiency and reduce the construction site management burden.
Description
Technical Field
The embodiment of the invention relates to a method, a device, equipment, a medium and a program product for managing wearing of construction site work clothes.
Background
Fig. 2 is a schematic flow chart of a method for managing wearing of a work clothes in a home decoration factory in the prior art. As shown in fig. 2, one method is to report the construction site with problems by manual offline inspection, and the manager can make corrections. The offline inspection method is low in efficiency, and the cost consumption of back-and-forth wave among different construction sites is high. The other method is that a common non-wide-angle camera is installed on a construction site, a background binding camera receives video data returned by the camera, operation and maintenance personnel check the live video to judge whether workers wear work clothes or not, the construction site with problems is reported, and the manager carries out rectification. This method still requires manual observation to find the problem site and worker, and cannot realize automatic site management.
Disclosure of Invention
In order to solve the problems in the prior art, embodiments of the present invention provide a method, an apparatus, a device, a medium, and a program product for managing wearing of work site suits.
The embodiment of the invention provides a method for managing wearing of work clothes on a construction site, which comprises the following steps: receiving video monitoring data returned by a construction site, and extracting construction site pictures according to the video monitoring data; carrying out human body detection on the construction site picture by using a human body identification algorithm, and marking a human body detection frame in the construction site picture; cutting the construction site picture based on the human body detection frame to obtain a human body picture; inputting the human body picture into a classification network to obtain a work clothes identification result of the human body picture; wherein the work clothes identification result comprises a first identification result of whether a person in the human body picture wears work clothes or not; the classification network is obtained by taking a training sample picture containing a human body as input and taking a labeling result of the training sample picture with or without a worker's clothes as a label for training.
According to the method for managing the wearing of the industrial and local work clothes, provided by the embodiment of the invention, the work clothes identification result further comprises a second identification result of the work clothes classification under the condition of wearing the work clothes; and for the training sample picture of the work clothes, the marking result comprises the work clothes category information.
According to an embodiment of the invention, a method for managing wearing of a work site and a work site, which receives video monitoring data returned by a work site, includes: and receiving video monitoring data which are transmitted back on site at the construction site and shot by the fisheye camera.
According to the method for managing wearing of the industrial and local work clothes provided by the embodiment of the invention, the method for extracting the pictures of the construction site according to the video monitoring data comprises the following steps: extracting a site picture of the construction site from the video monitoring data according to a preset frame extraction time interval; wherein the frame extraction time interval is used to represent the time between two extractions of the worksite picture from the video surveillance data.
According to the method for managing wearing of the work site work clothes provided by the embodiment of the invention, before the cutting of the picture of the work site based on the human body detection frame, the method further comprises the following steps: and rotating the construction site picture to enable the human body in the human body detection frame to be at a right angle.
According to the method for managing the wearing of the work and ground work clothes provided by the embodiment of the invention, after the work and ground work clothes identification result of the human body picture is obtained, the method further comprises the following steps: responding to the fact that the person in the human body picture belongs to the target worker, and sending a rectification work order to a preset first terminal; in response to determining that the person in the human body picture belongs to other persons permitted to enter a worksite, ending the processing of the human body picture; and responding to the fact that the person in the human body picture does not belong to the target person or other persons allowed to enter the construction site, and sending safety reminding information to the preset first terminal and/or the preset second terminal.
The embodiment of the invention also provides a device for managing the wearing of the industrial and terrestrial work clothes, which comprises: a picture acquisition module to: receiving video monitoring data returned by a construction site, and extracting construction site pictures according to the video monitoring data; a human detection module to: carrying out human body detection on the construction site picture by using a human body identification algorithm, and marking a human body detection frame in the construction site picture; an image processing module to: cutting the construction site picture based on the human body detection frame to obtain a human body picture; a frock identification module for: inputting the human body picture into a classification network to obtain a work clothes identification result of the human body picture; wherein the work clothes identification result comprises a first identification result of whether a person in the human body picture wears work clothes or not; the classification network is obtained by taking a training sample picture containing a human body as input and taking a labeling result of a worker wearing or not wearing the worker clothing in the training sample picture as a label for training.
The embodiment of the invention also provides an electronic device, which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor executes the program to realize the steps of any one of the above methods for managing the wearing of the work clothes on the ground.
Embodiments of the present invention further provide a non-transitory computer readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the method for managing wearing of industrial and industrial suits as described in any one of the above.
An embodiment of the present invention further provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the above method for managing wearing of industrial and terrestrial frock clothes are implemented.
According to the method, the device, the equipment, the medium and the program product for managing the wearing of the work and ground work clothes, provided by the embodiment of the invention, the video monitoring data returned by the site of the construction site are received, the site picture of the construction site is extracted according to the video monitoring data, the human body detection is carried out on the site picture of the construction site by using the human body identification algorithm, the human body detection frame is marked in the site picture of the construction site, the site picture of the construction site is cut based on the human body detection frame to obtain the human body picture, the human body picture is input to the classification network to obtain the work and ground clothes identification result of the human body picture, the automatic identification of whether the work and ground clothes are worn by the site personnel of the construction site can be realized, the automation degree of the construction site management is improved, the construction site management efficiency is improved, and the construction site management burden is lightened.
Drawings
In order to more clearly illustrate the technical solutions of the present invention or the prior art, the drawings needed for the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
Fig. 1 is one of the flow diagrams of a method for managing wearing of industrial and terrestrial work clothes according to an embodiment of the present invention;
FIG. 2 is a flow chart illustrating a method for managing wear of a home decoration worker's ground work clothes in the prior art;
FIG. 3 is a schematic diagram of a scene picture of a construction site taken by a fisheye camera in the method for wearing and managing the work-site clothes according to the embodiment of the invention;
FIG. 4 is a schematic diagram of a human body picture obtained by rotating and cutting the construction site picture of FIG. 3;
FIG. 5 is a second schematic flow chart of a method for managing wearing of industrial and terrestrial garments according to an embodiment of the present invention;
FIG. 6 is a schematic structural diagram of a work and ground work clothing wear management device according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. 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 method, apparatus, device, medium, and program product for wear management of industrial and terrestrial work suits according to embodiments of the present invention are described below with reference to fig. 1 to 7.
Fig. 1 is a schematic flow chart of a method for managing wearing of industrial and terrestrial work clothes according to an embodiment of the present invention. As shown in fig. 1, the method includes:
step 101, receiving video monitoring data returned by a construction site, and extracting construction site pictures according to the video monitoring data.
The worksite may be, for example, a home decoration worksite. The camera array can be arranged on the site of the construction site, so that the shooting range of the camera covers the whole site of the construction site. The camera array is bound with the worker dress management device of the construction site, and shot video monitoring data are transmitted back to the worker dress management device.
The work clothes wearing management device extracts the pictures of the site of the construction site according to the video monitoring data, and the pictures of the site of the construction site can be obtained by extracting partial pictures from the video monitoring data in order to avoid processing excessive redundant data because the video monitoring data is a video file formed by pictures of one frame.
And 102, carrying out human body detection on the construction site picture by using a human body identification algorithm, and marking a human body detection frame in the construction site picture.
The human body recognition algorithm can recognize the position of a human body in the picture, and mark a human body detection frame in the picture, wherein the human body detection frame frames the recognized human body. The human recognition algorithm may be, for example, a RAPiD algorithm. The pictures of the construction site where the human body is not identified can be filtered.
And 103, cutting the construction site picture based on the human body detection frame to obtain a human body picture.
And cutting the construction site picture based on the boundary of the human body detection frame to obtain a human body picture.
Training sample pictures containing human bodies can be obtained in advance, and some of the human bodies in the training sample pictures wear the work clothes, and some of the human bodies do not wear the work clothes. And training by taking a training sample picture containing a human body as input and taking a labeling result of the person wearing the work clothes or not wearing the work clothes in the training sample picture as a label to obtain a classification network. For example, in training, the label of the training sample picture with the work clothes is set to 0, and the label of the training sample picture without the work clothes is set to 1.
The style, color, etc. of the work clothes may be different according to the character, if it is only to identify whether the work clothes are worn, the pictures wearing various work clothes may be covered in the training sample picture wearing the work clothes, but as long as the label of the work clothes is set to 1.
And inputting the human body picture into a classification network to obtain a work clothes identification result of the human body picture. The work clothes identification result comprises a first identification result of whether a person in the human body picture wears the work clothes. The classification network may for example employ a resnet network.
And after the work clothes identification result is obtained, the construction site which does not wear the work clothes is rectified according to the work clothes identification result.
According to the work and ground work clothes wearing management method provided by the embodiment of the invention, the video monitoring data returned from the site of the construction site is received, the site picture of the construction site is extracted according to the video monitoring data, the human body recognition algorithm is utilized to carry out human body detection on the site picture of the construction site, the human body detection frame is marked in the site picture of the construction site, the site picture of the construction site is cut based on the human body detection frame to obtain the human body picture, the human body picture is input into the classification network to obtain the work and ground clothes recognition result of the human body picture, the automatic recognition of whether the site personnel wear the work and ground clothes or not can be realized, the automation degree of the construction site management is improved, the construction site management efficiency is improved, and the construction site management burden is reduced.
According to the method for managing the wearing of the industrial and local work clothes, provided by the embodiment of the invention, the work clothes identification result further comprises a second identification result of the work clothes classification under the condition of wearing the work clothes; and for the training sample picture of the work clothes, the marking result comprises the work clothes category information.
Networks such as Resnet may implement multiple classifications. When the classification network is trained, on the basis that the training sample pictures are divided into the worn work clothes and the unworn work clothes, the work clothes type information can be further added to the labeling result of the training sample of the worn work clothes, and the work clothes type information can be used for representing the roles of workers, such as workers, stewards and the like.
For example, in training, the picture of the training sample of the clothing of the wearer is marked as 1, the picture of the training sample of the clothing of the wearer is marked as 2, the picture of the training sample of the clothing of the housekeeper is marked as 3, and the picture of the training sample of the clothing not worn is marked as 4. In this case, the labeling results 1, 2, and 3 include not only information on the type of work clothes worn by the person in the training sample picture, but also information on the type of work clothes worn. The classification network obtained by training can not only identify whether the person in the picture wears the clothing, but also identify the category of the clothing worn by the person, namely identify the character role.
Therefore, after the human body picture is input into the classification network, a worker clothes recognition result of the human body picture is obtained; the work clothes identification result comprises a first identification result of whether a person in the human body picture wears the work clothes or not and a second identification result of the work clothes classification under the condition of wearing the work clothes.
According to the method for managing the wearing of the industrial and local work clothes, the marking result of the training sample picture of the wearing work clothes comprises the work clothes category information, so that the automatic identification of whether the work clothes are worn or not can be realized, the wearing type of the work clothes can be identified, and the identification level of the work clothes is improved.
According to an embodiment of the invention, a method for managing wearing of a work site and a work site, which receives video monitoring data returned by a work site, includes: and receiving video monitoring data which are transmitted back on site at the construction site and shot by the fisheye camera.
Because the shooting angle of the common camera is limited, and the cost for deploying the camera array is higher, the embodiment of the invention collects the video monitoring data by deploying the fisheye camera on the site of a construction site. A fisheye camera is a lens having a focal length of 16mm or less and an angle of view close to or equal to 180 °, and is an extreme wide-angle lens. The fisheye camera is adopted to shoot in an indoor scene, and shooting without blind areas can be achieved under the condition of no shielding.
In indoor scenes such as home decoration, the camera is deployed at the middle part of a room as much as possible, and then the camera is bound with the construction site work clothes wearing management device.
According to the method for managing the wearing of the work and ground work clothes, the fisheye camera is used for shooting the video monitoring data, more and more complete information than that of a non-wide-angle camera can be collected, meanwhile, the problem of angles under the non-wide-angle camera cannot exist, and the quality of the video monitoring data is guaranteed.
According to the method for managing wearing of the industrial and local work clothes provided by the embodiment of the invention, the method for extracting the pictures of the construction site according to the video monitoring data comprises the following steps: extracting a site picture of the construction site from the video monitoring data according to a preset frame extraction time interval; wherein the frame extraction time interval is used to represent the time between two extractions of the jobsite pictures from the video surveillance data.
The jobsite pictures may be extracted from the video surveillance data at preset frame extraction intervals. And extracting pictures according to the frame extraction time interval, wherein the extracted pictures are regular, and the operation monitoring requirement and the algorithm efficiency requirement can be balanced by setting the specific frame extraction time interval.
The frame-extracting picture interval is used for representing the number of pictures spaced by extracting the scene pictures of the construction site twice from the video monitoring data, and the frame-extracting picture interval is represented as follows:
n＝FPS*HZ
wherein n represents a frame extraction picture interval; FPS represents the number of frames transmitted per second of a picture; HZ denotes a frame extraction interval.
For example, if the interval of FPS is 30 s and one picture is extracted for algorithm identification, the interval of FPS is 30 s, 2s, 60 pictures are required for extraction.
According to the method for managing the wearing of the work and ground work clothes, the pictures of the work site are extracted from the video monitoring data according to the preset frame extraction time interval, the processing of redundant data of the video monitoring data is reduced, and the requirements of reflecting the actual conditions of operation and the processing efficiency are balanced.
According to the method for managing wearing of the work site work clothes provided by the embodiment of the invention, before the cutting of the picture of the work site based on the human body detection frame, the method further comprises the following steps: and rotating the site picture of the construction site to enable the human body in the human body detection frame to be at a right angle.
Because most of the human bodies in the training sample pictures are at the upright angle, if the classification network is trained directly through the original training sample pictures (picture augmentation is not performed through operations such as rotation), in order to improve the recognition performance of the classification network, the construction site picture can be rotated firstly before the construction site picture is cut based on the human body detection frame, so that the human bodies in the human body detection frame are at the upright angle. The rotation of the picture can be realized by affine transformation or the like. Then the human body detection frame with the human body at the upright angle is cut off and input into the classification network.
Fig. 3 is a schematic diagram of a scene picture of a construction site taken by a fisheye camera in the method for wearing and managing the construction site clothing according to the embodiment of the invention. Fig. 4 is a schematic diagram of a human body picture obtained by rotating and cutting the picture of the construction site of fig. 3. As shown in fig. 3 and 4, the angle at which the human body stands upright means an angle at which the human body stands normally. It can be understood that the field worker is in the construction process, does not need to have a standing posture with a straight waist and back, and only needs to rotate to a normal visual angle.
According to the method for managing the wearing of the work and ground work clothes, provided by the embodiment of the invention, the picture of the work and ground work site is rotated before the picture of the work and ground work site is cut based on the human body detection frame, so that the human body in the human body detection frame is in a vertical angle, and the effect of work and ground work clothes identification is favorably improved.
According to the method for managing the wearing of the work and ground work clothes provided by the embodiment of the invention, after the work and ground work clothes identification result of the human body picture is obtained, the method further comprises the following steps: responding to the fact that the person in the human body picture belongs to the target worker, and sending a rectification work order to a preset first terminal; in response to determining that the person in the human body picture belongs to other persons permitted to enter a worksite, ending the processing of the human body picture; and responding to the fact that the person in the human body picture does not belong to the target person or other persons allowed to enter the construction site, and sending safety reminding information to the preset first terminal and/or the preset second terminal.
After the human body picture that does not wear the work clothes is discerned, can carry out personnel's role to the people in the human body picture that does not wear the work clothes through artifical judgement and confirm, the work clothes of building site is worn the management device and can be received the result of confirming of personnel's role and respond according to the difference of personnel's role. For example, a person role confirmation button can be set corresponding to a human body picture without a worker garment, a person role selection list is popped up after trigger information of clicking the person role confirmation button is received, and possible person roles such as a worker, a manager, an owner family, a designer, an unidentified person and the like can be listed in the person role selection list according to management requirements. After checking the corresponding personnel role and confirming, the construction site worker service management device can receive the confirmation result of the personnel role.
And after receiving the confirmation result of the personnel role, the work and place work service management device performs corresponding processing according to the personnel role of the personnel who do not wear the work service, and if the personnel who do not wear the work service are confirmed to belong to the target worker (such as a worker, a worker leader or a manager), the work and place work service management device sends a rectification work order to the preset first terminal. For example, when it is recognized that the worker does not wear the work clothes, the correction work order is sent to a terminal held by a worker leader and a manager, and the correction work order may include site information, worker information, time information, and the like.
If it is confirmed that the person who does not wear the work clothes belongs to other persons who are allowed to enter the work site, such as an owner, a family member of the owner, an independent designer, and the like, the processing of the human body picture is finished.
If the person in the human body picture is confirmed not to belong to the target worker and other persons allowed to enter the construction site, safety reminding information is sent to a preset first terminal and/or a preset second terminal (such as a worker leader, a manager holding terminal and/or an owner holding terminal), and the unknown person is prevented from entering the construction site.
The work site service management apparatus may store in advance information on a person role corresponding to a target worker and a person role corresponding to another person who is permitted to enter the work site. After the confirmation result of the role of the person is received, the person in the human body picture without wearing the work clothes can be known to belong to the target worker or other persons allowed to enter the construction site, or to belong to neither the target worker nor other persons allowed to enter the construction site.
According to the method for managing the wearing of the work and ground work clothes, provided by the embodiment of the invention, the correction work order is sent to the preset first terminal by determining that people in the human body picture belong to the target staff; finishing the processing of the human body picture by determining that the person in the human body picture belongs to other persons allowed to enter the construction site; sending safety reminding information to a preset first terminal and/or a preset second terminal by determining that people in the human body picture belong to neither a target person nor other persons allowed to enter a construction site; the automation level of the construction site management is improved.
Fig. 5 is a second flowchart of a method for managing wearing of industrial and terrestrial work clothes according to an embodiment of the present invention. As shown in fig. 5, taking a home decoration application scenario as an example, the method includes:
step 1: the method comprises the steps of firstly deploying the fisheye camera on a construction site, deploying the camera in the middle of a room as much as possible, and then binding the camera on a background system.
Step 2: the method comprises the steps of performing frame extraction processing on a video to reduce redundant features in a video sequence, wherein a certain frame extraction strategy needs to be set, and the frame extraction strategy is comprehensively considered by combining algorithm processing efficiency on the premise of ensuring that the actual conditions of operation can be reflected.
And 3, step 3: and detecting the human body in the picture. Some extracted pictures in the video do not appear, so that the part of the pictures needs to be filtered. The algorithm adopted by the human body detection is RAPiD, and the algorithm can obtain a detection frame of the human body and the rotation angle of the frame. The RAPiD network is divided into 3 parts, namely backbone, fpn and head, wherein the backbone is used for extracting features, fpn is used for processing a multi-scale feature map generated by the backbone to facilitate better detection of targets with different sizes, the head part is a prediction part of the network, each target obtains a 6-dimensional vector which is respectively a central point x and y of a target frame, a width w and a height h of the frame, a rotation angle theta and a confidence conf, and the values can be used for preparing for subsequent rotation and clipping.
And 4, step 4: and rotating and cutting the picture. And (4) taking the result processed in the step (3) as the input of the step (4), rotating the human body with an angle in the picture to obtain a human body picture with a normal angle, and cutting out the human body detection frame.
And 5, step 5: and classifying and identifying the work clothes. The small picture (human body picture) cut in the step 4 does not have work clothes information, the small picture needs to be classified, only 3 roles, namely workers, workmans and managers, can be concerned about according to the situation of workers possibly appearing on the site of the construction site, and the three roles can trigger the correction of the work order if the work clothes are not worn. The classification algorithm employs a resurent classification network, such as a resurent 50 classification network. The reason why the resnet classification is good is mainly that a structure with residual connection exists.
And 6, step 6: and processing the classification result. And (4) not further processing the pictures of the worn work clothes, and correspondingly processing the pictures of the human body without the work clothes according to the role of the personnel. No requirement is made on whether the owner or the family members wear the industrial clothes. When detecting that someone does not wear the work clothes, judging whether the person does not wear the work clothes or not, if so, sending a correction work order for correction, and establishing a corresponding work order by combining the roles of service personnel based on the identification result, thereby achieving the purposes of quick response and correction of illegal work of the construction site. If the person is not a decoration company and does not wear the service, judging whether the person is an owner, if the person is not the owner, finishing the picture processing flow, if the person is not the owner, contacting the owner (for example, interacting with a terminal held by the owner through an instant message or a telephone, and the like), judging whether the person is a family or other person allowed to enter the construction site, if the person is not the owner, finishing the flow, otherwise, indicating that an unknown person enters, and immediately notifying a manager, an owner or the owner to pay attention to the construction site to prevent safety accidents.
The decoration company carries out worker's clothes discernment based on the data of camera passback, can judge whether the workman wears worker's clothes, sends out the warning when not wearing in real time, and the administrator can look over to the alarm situation fast to judge whether the workman normally dresses, combines corresponding service personnel role, establishes perfect emergency treatment mechanism and strategy. Simultaneously, for the more comprehensive understanding workman's operation condition, provide the visual angle of wider more, adopt the fisheye camera to carry out data acquisition and analysis.
According to the construction site management method based on fisheye camera work clothes identification, whether workers wear work clothes or not is automatically identified through structured video data, meanwhile, a set of complete emergency processing flow and method can be established, offline inspection of construction management personnel can be replaced to a certain extent, the whole process is operated at a corresponding background interface, convenience and rapidness are achieved, efficiency of previous full-data diffuse and purposeless live broadcast inspection can be improved, and online inspection efficiency is greatly improved.
The work site work clothes wearing management device provided by the embodiment of the invention is described below, and the work site work clothes wearing management device described below and the work site work clothes wearing management method described above can be referred to correspondingly.
Fig. 6 is a schematic structural diagram of a work-place frock wearing management device according to an embodiment of the present invention. As shown in fig. 6, the apparatus includes a picture acquiring module 10, a human body detecting module 20, a picture processing module 30 and an employee identification module 40, wherein: the picture taking module 10 is configured to: receiving video monitoring data returned by a construction site, and extracting construction site pictures according to the video monitoring data; the human detection module 20 is configured to: carrying out human body detection on the construction site picture by using a human body identification algorithm, and marking a human body detection frame in the construction site picture; the image processing module 30 is configured to: cutting the construction site picture based on the human body detection frame to obtain a human body picture; the worker-uniform identification module 40 is configured to: inputting the human body picture into a classification network to obtain a work clothes identification result of the human body picture; wherein the work clothes identification result comprises a first identification result of whether a person in the human body picture wears work clothes or not; the classification network is obtained by taking a training sample picture containing a human body as input and taking a labeling result of the training sample picture with or without a worker's clothes as a label for training.
According to the work and ground work clothes wearing management device provided by the embodiment of the invention, the video monitoring data returned from the site of the construction site is received, the site picture of the construction site is extracted according to the video monitoring data, the human body recognition algorithm is utilized to carry out human body detection on the site picture of the construction site, the human body detection frame is marked in the site picture of the construction site, the site picture of the construction site is cut based on the human body detection frame to obtain the human body picture, the human body picture is input into the classification network to obtain the work and ground clothes recognition result of the human body picture, the automatic recognition of whether the site personnel wear the work and ground clothes or not can be realized, the automation degree of the construction site management is improved, the efficiency of the construction site management is improved, and the burden of the construction site management is reduced.
According to the construction site work clothes wearing management device provided by the embodiment of the invention, the work clothes identification result further comprises a second identification result of the work clothes classification under the condition of wearing the work clothes; and for the training sample picture of the work clothes, the marking result comprises the work clothes category information.
According to the work and land work clothes wearing management device provided by the embodiment of the invention, the marking result of the training sample picture of the worn work clothes comprises the work clothes category information, so that the automatic identification of whether the work clothes are worn or not can be realized, the wearing type of the work clothes can be identified, and the work clothes identification level is improved.
According to the construction site work clothes wearing management device provided by the embodiment of the invention, when the picture acquisition module 10 is used for receiving video monitoring data returned from a construction site, the picture acquisition module is specifically used for: and receiving video monitoring data which are transmitted back on site at the construction site and shot by the fisheye camera.
According to the work and land work clothes wearing management device provided by the embodiment of the invention, the fisheye camera is adopted to shoot the video monitoring data, more and more complete information than that of a non-wide-angle camera can be collected, meanwhile, the angle problem under the non-wide-angle camera cannot exist, and the quality of the video monitoring data is ensured.
According to the device for managing wearing of work clothes on a construction site provided by the embodiment of the invention, when the picture acquisition module 10 is used for extracting the picture of the construction site according to the video monitoring data, the picture acquisition module is specifically used for: extracting a site picture of the construction site from the video monitoring data according to a preset frame extraction time interval; wherein the frame extraction time interval is used to represent the time between two extractions of the jobsite pictures from the video surveillance data.
According to the work and ground work clothes wearing management device provided by the embodiment of the invention, the pictures of the work and ground sites are extracted from the video monitoring data according to the preset frame extraction time interval, so that the processing of redundant data of the video monitoring data is reduced, and the requirements of reflecting the actual conditions of operation and the processing efficiency are balanced.
According to the work site clothing management device provided by the embodiment of the invention, the picture processing module 30 is further configured to, before being configured to crop the work site picture based on the human body detection frame: and rotating the site picture of the construction site to enable the human body in the human body detection frame to be at a right angle.
According to the work and land work clothes wearing management device provided by the embodiment of the invention, the work and land work clothes are rotated before the work and land work site picture is cut based on the human body detection frame, so that the human body in the human body detection frame is in a vertical angle, and the work and land work clothes wearing management device is beneficial to improving the work and land work clothes identification effect.
According to an embodiment of the present invention, there is provided a work site frock dress management device, the device further comprises a post-processing module, configured to: responding to the fact that the person in the human body picture belongs to the target worker, and sending a rectification work order to a preset first terminal; in response to determining that the person in the human body picture belongs to other persons permitted to enter a worksite, ending the processing of the human body picture; and responding to the fact that the person in the human body picture does not belong to the target person or other persons allowed to enter the construction site, and sending safety reminding information to the preset first terminal and/or the preset second terminal.
The work and ground work clothes wearing management device provided by the embodiment of the invention sends a rectification work order to a preset first terminal by determining that people in a human body picture belong to a target worker; finishing the processing of the human body picture by determining that the person in the human body picture belongs to other persons allowed to enter the construction site; sending safety reminding information to a preset first terminal and/or a preset second terminal by determining that people in the human body picture belong to neither a target person nor other persons allowed to enter a construction site; the automation level of the construction site management is improved.
Fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, and as shown in fig. 7, the electronic device may include: a processor (processor)710, a communication Interface (Communications Interface)720, a memory (memory)730, and a communication bus 740, wherein the processor 710, the communication Interface 720, and the memory 730 communicate with each other via the communication bus 740. Processor 710 may invoke logic instructions in memory 730 to perform a method of work-place dress management, the method comprising: receiving video monitoring data returned by a construction site, and extracting construction site pictures according to the video monitoring data; carrying out human body detection on the construction site picture by using a human body identification algorithm, and marking a human body detection frame in the construction site picture; cutting the construction site picture based on the human body detection frame to obtain a human body picture; inputting the human body picture into a classification network to obtain a work clothes identification result of the human body picture; wherein the work clothes identification result comprises a first identification result of whether a person in the human body picture wears work clothes or not; the classification network is obtained by taking a training sample picture containing a human body as input and taking a labeling result of a worker wearing or not wearing the worker clothing in the training sample picture as a label for training.
In addition, the logic instructions in the memory 730 can be implemented in the form of software functional units and stored in a computer readable storage medium when the software functional units are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In another aspect, an embodiment of the present invention further provides a computer program product, where the computer program product includes a computer program, the computer program may be stored on a non-transitory computer-readable storage medium, and when the computer program is executed by a processor, a computer is capable of executing the method for managing wearing of industrial and terrestrial garments provided by the above methods, the method includes: receiving video monitoring data returned by a construction site, and extracting construction site pictures according to the video monitoring data; carrying out human body detection on the construction site picture by using a human body identification algorithm, and marking a human body detection frame in the construction site picture; cutting the construction site picture based on the human body detection frame to obtain a human body picture; inputting the human body picture into a classification network to obtain a work clothes identification result of the human body picture; wherein the work clothes identification result comprises a first identification result of whether a person in the human body picture wears work clothes or not; the classification network is obtained by taking a training sample picture containing a human body as input and taking a labeling result of a worker wearing or not wearing the worker clothing in the training sample picture as a label for training.
In yet another aspect, an embodiment of the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored, the computer program being implemented by a processor to perform the method for managing work on the ground service provided by the above methods, the method including: receiving video monitoring data returned by a construction site, and extracting construction site pictures according to the video monitoring data; carrying out human body detection on the construction site picture by using a human body recognition algorithm, and marking a human body detection frame in the construction site picture; cutting the construction site picture based on the human body detection frame to obtain a human body picture; inputting the human body picture into a classification network to obtain a work clothes identification result of the human body picture; wherein the work clothes identification result comprises a first identification result of whether a person in the human body picture wears work clothes or not; the classification network is obtained by taking a training sample picture containing a human body as input and taking a labeling result of a worker wearing or not wearing the worker clothing in the training sample picture as a label for training.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment may be implemented by software plus a necessary general hardware platform, and may also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A method for managing wearing of work clothes on a construction site, which is characterized by comprising the following steps:
receiving video monitoring data returned by a construction site, and extracting construction site pictures according to the video monitoring data;
carrying out human body detection on the construction site picture by using a human body identification algorithm, and marking a human body detection frame in the construction site picture;
cutting the construction site picture based on the human body detection frame to obtain a human body picture;
inputting the human body picture into a classification network to obtain a work clothes identification result of the human body picture; wherein the work clothes identification result comprises a first identification result of whether a person in the human body picture wears work clothes or not; the classification network is obtained by taking a training sample picture containing a human body as input and taking a labeling result of a worker wearing or not wearing the worker clothing in the training sample picture as a label for training.
2. The method for managing wearing of work and ground work clothes according to claim 1, wherein the work clothes recognition result further includes a second recognition result of a work clothes classification in a case of wearing the work clothes; and for the training sample picture of the work clothes, the marking result comprises the work clothes category information.
3. The method for managing wearing of industrial and terrestrial work clothes according to claim 1, wherein the receiving of video monitoring data returned from a site of a construction site comprises:
and receiving video monitoring data which are transmitted back on site at the construction site and shot by the fisheye camera.
4. The method for wearing and managing work clothes of construction site as claimed in claim 1, wherein the extracting of the picture of the work site according to the video monitoring data comprises: extracting a site picture of the construction site from the video monitoring data according to a preset frame extraction time interval; wherein the frame extraction time interval is used to represent the time between two extractions of the jobsite pictures from the video surveillance data.
5. The work-site dress management method according to claim 1, wherein before said cropping the work-site picture based on the human detection box, the method further comprises:
and rotating the site picture of the construction site to enable the human body in the human body detection frame to be at a right angle.
6. The method for managing wearing of work and ground work clothes according to claim 1, wherein after obtaining the result of identifying work and ground work clothes of the human body picture, the method further comprises:
responding to the fact that the person in the human body picture belongs to the target worker, and sending a rectification work order to a preset first terminal;
in response to determining that the person in the human body picture belongs to other persons permitted to enter a worksite, ending the processing of the human body picture;
and responding to the fact that the person in the human body picture does not belong to the target person or other persons allowed to enter the construction site, and sending safety reminding information to the preset first terminal and/or the preset second terminal.
7. A work site clothing wear management device, comprising:
a picture acquisition module to: receiving video monitoring data returned by a construction site, and extracting construction site pictures according to the video monitoring data;
a human detection module to: carrying out human body detection on the construction site picture by using a human body recognition algorithm, and marking a human body detection frame in the construction site picture;
an image processing module to: cutting the construction site picture based on the human body detection frame to obtain a human body picture;
a frock identification module for: inputting the human body picture into a classification network to obtain a work clothes identification result of the human body picture; wherein the work clothes identification result comprises a first identification result of whether a person in the human body picture wears work clothes or not; the classification network is obtained by taking a training sample picture containing a human body as input and taking a labeling result of a worker wearing or not wearing the worker clothing in the training sample picture as a label for training.
8. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program performs the steps of the method of wear management for a work place garment according to any one of claims 1 to 6.
9. A non-transitory computer readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the method for wear management of industrial and terrestrial frock according to any one of claims 1 to 6.
10. A computer program product comprising a computer program, wherein the computer program when executed by a processor implements the steps of the method of wear management for a work place suit according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210551996.XA CN115082848A (en) | 2022-05-18 | 2022-05-18 | Method, device, equipment, medium and program product for managing wearing of industrial and ground work clothes |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210551996.XA CN115082848A (en) | 2022-05-18 | 2022-05-18 | Method, device, equipment, medium and program product for managing wearing of industrial and ground work clothes |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115082848A true CN115082848A (en) | 2022-09-20 |
Family
ID=83249727
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210551996.XA Pending CN115082848A (en) | 2022-05-18 | 2022-05-18 | Method, device, equipment, medium and program product for managing wearing of industrial and ground work clothes |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115082848A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111401314A (en) * | 2020-04-10 | 2020-07-10 | 上海东普信息科技有限公司 | Dressing information detection method, device, equipment and storage medium |
| CN111860471A (en) * | 2020-09-21 | 2020-10-30 | 之江实验室 | Work clothes wearing identification method and system based on feature retrieval |
| WO2021082692A1 (en) * | 2019-10-30 | 2021-05-06 | 平安科技（深圳）有限公司 | Pedestrian picture labeling method and device, storage medium, and intelligent apparatus |
-
2022
- 2022-05-18 CN CN202210551996.XA patent/CN115082848A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021082692A1 (en) * | 2019-10-30 | 2021-05-06 | 平安科技（深圳）有限公司 | Pedestrian picture labeling method and device, storage medium, and intelligent apparatus |
| CN111401314A (en) * | 2020-04-10 | 2020-07-10 | 上海东普信息科技有限公司 | Dressing information detection method, device, equipment and storage medium |
| CN111860471A (en) * | 2020-09-21 | 2020-10-30 | 之江实验室 | Work clothes wearing identification method and system based on feature retrieval |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105979210B (en) | A kind of pedestrian's identifying system based on the more ball video camera arrays of multiple gun | |
| CN109271554B (en) | Intelligent video identification system and application thereof | |
| CN106650671B (en) | Face recognition method, device and system | |
| CN110348348B (en) | Quick identification method and early warning system for entrance identities of participants | |
| CN111310947A (en) | Building facility operation and maintenance method, equipment, storage medium and system based on 5G | |
| CN102663444A (en) | Method for preventing account number from being stolen and system thereof | |
| CN110942580A (en) | Intelligent building visitor management method and system and storage medium | |
| CN113034826A (en) | Video-based abnormal event warning method and system, equipment and storage medium thereof | |
| CN112287823A (en) | Facial mask identification method based on video monitoring | |
| CN111191507A (en) | Safety early warning analysis method and system for smart community | |
| CN113343854A (en) | Fire operation flow compliance detection method based on video monitoring | |
| CN110781735A (en) | Alarm method and system for identifying on-duty state of personnel | |
| CN108460357B (en) | Windowing alarm detection system and method based on image recognition | |
| CN114943841A (en) | Method and device for assisting operation safety control based on image recognition | |
| CN114898443A (en) | Face data acquisition method and device | |
| EP1266525B1 (en) | Image data processing | |
| CN113627321A (en) | Image identification method and device based on artificial intelligence and computer equipment | |
| CN113628172A (en) | Intelligent detection algorithm for personnel handheld weapons and smart city security system | |
| CN212936047U (en) | Personnel safety management and control system | |
| CN115082848A (en) | Method, device, equipment, medium and program product for managing wearing of industrial and ground work clothes | |
| CN111582183A (en) | Mask identification method and system in public place | |
| KR20160003996A (en) | Apparatus and method for video analytics | |
| CN108090473A (en) | The method and device of polyphaser human face identification | |
| CN116886874A (en) | Ecological garden security monitoring and early warning data acquisition method and system | |
| CN112183251A (en) | Monitoring system for weak current security engineering of Internet of things |
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 |