CN111191705A - Method, apparatus and computer-readable storage medium for detecting safety equipment of human body - Google Patents

Method, apparatus and computer-readable storage medium for detecting safety equipment of human body Download PDF

Info

Publication number
CN111191705A
CN111191705A CN201911350854.1A CN201911350854A CN111191705A CN 111191705 A CN111191705 A CN 111191705A CN 201911350854 A CN201911350854 A CN 201911350854A CN 111191705 A CN111191705 A CN 111191705A
Authority
CN
China
Prior art keywords
human body
safety equipment
original image
human
detected
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
Application number
CN201911350854.1A
Other languages
Chinese (zh)
Inventor
周康明
丁苗高
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Eye Control Technology Co Ltd
Original Assignee
Shanghai Eye Control Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shanghai Eye Control Technology Co Ltd filed Critical Shanghai Eye Control Technology Co Ltd
Priority to CN201911350854.1A priority Critical patent/CN111191705A/en
Publication of CN111191705A publication Critical patent/CN111191705A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches

Landscapes

  • Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Image Analysis (AREA)

Abstract

The invention provides a method, a device and a computer-readable storage medium for detecting safety equipment of a human body. The method comprises the following steps: acquiring an original image including the human body; detecting the original image by using a human key point detection model to determine the positions of a plurality of human key points; selecting at least two key points from the plurality of human key points based on the safety equipment to be detected; intercepting a sub-graph expected to include the safety equipment to be detected from the original image based on the at least two key points; and inputting the sub-graph into a trained classification model of the safety equipment to determine whether the safety equipment is detected.

Description

Method, apparatus and computer-readable storage medium for detecting safety equipment of human body
Technical Field
The present invention relates to the field of smart detection, and more particularly, to a method for detecting safety equipment of a human body, a device implementing the method, and a computer-readable storage medium.
Background
Nowadays, many special work stations impose the requirement that safety precautions must be taken, including setting up safety facilities and wearing safety equipment. For example, in the building construction industry, construction workers are required to wear safety helmets, and in the hazardous chemical industry, workers are required to wear goggles, protective clothing, and the like. However, due to the lack of effective enough supervision measures, there are still accidents that workers on duty are injured or even killed by not wearing safety equipment such as safety helmets, goggles, protective clothing, antistatic shoes, etc.
Therefore, how to accurately and quickly monitor the safety wearing equipment of the personnel, and simultaneously avoid the defects of high manual inspection cost, easy fatigue of the inspection personnel, easy negligence and errors and the like, which become the technical problems which are urgently needed to be solved at present.
Disclosure of Invention
In order to solve the problems, the invention provides a scheme of safety equipment for detecting a human body, which can quickly and accurately detect whether a person wears certain safety equipment, thereby avoiding safety accidents and ensuring the personal safety of workers.
According to one aspect of the invention, a method is provided for detecting safety equipment of a human body. The method comprises the following steps: acquiring an original image including the human body; detecting the original image by using a human key point detection model to determine the positions of a plurality of human key points; selecting at least two key points from the plurality of human key points based on the safety equipment to be detected; intercepting a sub-graph expected to include the safety equipment to be detected from the original image based on the at least two key points; and inputting the sub-graph into a trained classification model of the safety equipment to determine whether the safety equipment is detected.
According to another aspect of the present invention, there is provided an apparatus for detecting safety equipment of a human body. The apparatus comprises: a memory having computer program code stored thereon; and a processor configured to execute the computer program code to perform the operations of: acquiring an original image including the human body; detecting the original image by using a human key point detection model to determine the positions of a plurality of human key points; selecting at least two key points from the plurality of human key points based on the safety equipment to be detected; intercepting a sub-graph expected to include the safety equipment to be detected from the original image based on the at least two key points; and inputting the sub-graph into a trained classification model of the safety equipment to determine whether the safety equipment is detected.
According to yet another aspect of the present invention, a computer-readable storage medium is provided. The computer readable storage medium has stored thereon a computer program code which, when executed, performs the method as described above.
By utilizing the scheme of the invention, the detection and classification model based on deep learning is jointly used, so that the safety equipment detection scheme is more accurate and timely.
Drawings
FIG. 1 shows a schematic diagram of key points of a human body according to the present invention;
FIG. 2 shows a flow diagram of a method for detecting safety equipment of a human body according to an embodiment of the invention; and
FIG. 3 shows a schematic block diagram of an example device that may be used to implement an embodiment of the invention.
Detailed Description
The embodiments of the present invention will be described in detail below with reference to the accompanying drawings in order to more clearly understand the objects, features and advantages of the present invention. It should be understood that the embodiments shown in the drawings are not intended to limit the scope of the present invention, but are merely intended to illustrate the spirit of the technical solution of the present invention.
In the following description, for the purposes of illustrating various inventive embodiments, certain specific details are set forth in order to provide a thorough understanding of the various inventive embodiments. One skilled in the relevant art will recognize, however, that the embodiments may be practiced without one or more of the specific details. In other instances, well-known devices, structures and techniques associated with this application may not be shown or described in detail to avoid unnecessarily obscuring the description of the embodiments.
Throughout the specification and claims, the word "comprise" and variations thereof, such as "comprises" and "comprising," are to be understood as an open, inclusive meaning, i.e., as being interpreted to mean "including, but not limited to," unless the context requires otherwise.
Reference throughout this specification to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment. Thus, the appearances of the phrases "in one embodiment" or "in an embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
As used in the specification and the appended claims, the singular forms "a", "an", and "the" include plural referents unless the context clearly dictates otherwise. It should be noted that the term "or" is generally employed in its sense including "and/or" unless the context clearly dictates otherwise.
Fig. 1 shows a schematic diagram of key points of a human body 100 according to the present invention. Fig. 2 shows a flow diagram of a method 200 for detecting safety equipment of a human body according to an embodiment of the invention. The method 200 according to the invention will be described in detail below in connection with fig. 1 and 2.
As previously mentioned, the safety equipment herein includes at least one of a safety helmet, a visor, an article of clothing, and a pair of safety shoes. However, it will be appreciated by those skilled in the art that the safety equipment described in the present invention is not limited thereto, but may include other wearing equipment such as a bracelet, a watch, smart glasses, and the like.
In the method 200, first at step 210, an original image including the human body 100 is acquired. In one embodiment, the raw images may be acquired from a video stream at predetermined time intervals. For example, at a construction site, images including the human body 100 may be periodically (e.g., every one minute or several minutes) captured from real-time video frames taken by cameras installed at various locations on the site. Furthermore, a plurality of human bodies 100 as shown in fig. 1 may be included in the intercepted one original image, and the method 200 as described herein may be performed separately for each human body 100.
Next, in step 220, the original image acquired in step 210 is detected using the human keypoint detection model to determine the locations of a plurality of human keypoints.
Currently, there are a variety of human key point detection models, and for different human key point detection models, the human key points that can be detected may be different. In this context, a detection model is utilized that is capable of detecting 25 keypoints. As shown in fig. 1, the detected human key points may include: at least a portion of a left overhead side 101, a right overhead side 102, a left ear 103, a right ear 104, a chin 105, a left shoulder 106, a right shoulder 107, a neck 108, a left elbow 109, a right elbow 110, a left wrist 111, a right wrist 112, a left pelvic end 113, a right pelvic end 114, an abdomen 115, a left knee 116, a right knee 117, a left ankle 118, a right ankle 119, a left toe 120, a right toe 121, a left ball 122, a right ball 123, a left heel 124, a right heel 125. Here, all of the above-mentioned key points or only a part thereof may be detected in step 220, depending on the type of safety equipment to be detected. For example, at a building construction site, if the safety equipment to be detected is a safety helmet, at least the overhead left side 101, the overhead right side 102, the neck 108, and the left shoulder 106 or the right shoulder 107 need to be detected.
In one embodiment, step 220 includes: the original image obtained in step 210 is detected using the above-mentioned human body key point detection model to determine whether a human body gesture is detected. If a human gesture is detected, the desired human keypoints can be detected. Conversely, if no body gesture is detected, it indicates that the desired body keypoint is not detected. In this case, step 210 is repeated to obtain an image subsequent to the current original image (e.g., one or several frames apart) from the video stream as a new original image, and the new original image is detected in step 220 to determine the locations of the key points of the human body.
In one embodiment, the human key point detection model used in step 220 is trained on the safety equipment to be detected. Therefore, prior to step 220, the method 200 further includes a process of training the keypoint target detection deep neural network model to obtain the human keypoint detection model. Specifically, the method 200 further comprises: acquiring different human body area images; respectively marking the coordinates of a plurality of human body key points in each human body area image; and training a key point target detection depth neural network model by using the human body region image marked with the human body key point coordinates to obtain the human body key point detection model.
Next, at step 230, at least two keypoints are selected from the plurality of human keypoints determined in step 220 based on the safety equipment to be detected.
Here, depending on the type of safety equipment to be detected, in some embodiments, the acquired human keypoint detection model may be for all types of safety equipment, which may obtain all human keypoints (e.g., all 25 human keypoints as described above). In other embodiments, the acquired human keypoint detection model may be for some particular type of safety equipment, which may acquire partial human keypoints (e.g., human keypoint overhead left 101, overhead right 102, neck 108, and left shoulder 106 or right shoulder 107 dedicated for helmet detection). In addition, in order to accurately extract a sub-image including the safety equipment to be detected from the original image, at least two human key points need to be selected from the plurality of human key points detected in step 220.
Next, at step 240, a sub-image expected to include the safety equipment to be detected is truncated from the original image based on the at least two keypoints selected at step 230.
In one embodiment, a bounding box (bounding box) may be utilized to intercept the subgraph. Specifically, step 240 may further include: determining two reference points based on the coordinates of the selected at least two keypoints; forming a frame based on the two reference points; and intercepting the subgraph from the original image by using the frame.
In one embodiment, where the safety equipment to be tested is a safety helmet, the at least two key points selected may include overhead left 101, overhead right 102, neck 108, and left shoulder 106 or right shoulder 107. In this case, two reference points p1And p2Can be determined as:
p1＝(xhead left-2d/3,yHead left-d)，
p2＝(xHead right side+3d/5,yHead right side)，
d＝xNeck-xLeft or right shoulder，
Wherein xHead leftAnd yHead leftRespectively, the abscissa and ordinate, x, of the left side 101 of the vertexHead right sideAnd yHead right sideRespectively, the abscissa and ordinate, x, of the parietal right 102NeckDenotes the abscissa, x, of the neck 108Left or right shoulderIndicating the abscissa of the left shoulder 106 or the right shoulder 107.
In this case, the reference point p1(xHead left-2d/3,yHead left-d), reference point p1Projection point (x) on the abscissa axisHead left2d/3,0), reference point p1Projection point (0, y) on the ordinate axisHead left-d) and the origin of coordinates (0,0) constitute a first rectangular frame. Similarly, reference point p2(xHead right side+3d/5,yHead right side) Reference point p2Projection point (x) on abscissaHead right side+3d/5,0), reference point p2Projection point (0, y) on ordinateHead right side) And the origin of coordinates (0,0) constitute a second rectangular frame. The portion where the first rectangular frame and the second rectangular frame overlap constitutes the bounding box. The border may be used to cut out a desired sub-image from the original image that is expected to include the headgear to be detected.
Here, the method of intercepting the sub-figure is described by taking as an example that the safety equipment to be detected is a helmet. However, it will be understood by those skilled in the art that in the case where the safety equipment to be detected is other safety equipment such as goggles, clothes, and shoes, different human key points may be selected to intercept different sub-figures, and the implementation thereof will not be described in detail herein.
The method 200 continues to step 250 where the sub-graph intercepted in step 240 is input into a classification model for the safety equipment to determine whether the safety equipment is detected.
In one embodiment, the classification model used in step 250 is trained on the safety equipment to be detected. Thus, prior to step 250, the method 200 further includes a process of training the neural network model to obtain a deep learning based classification model. Specifically, the method 200 further comprises: different body region images are acquired. In each human body region image, the coordinates of a plurality of human body key points are determined using the human body key point detection model described in step 220. And intercepting an image of the safety equipment to be detected by using the determined coordinates of the plurality of key points of the human body. The image of the security device is tagged with a label that can indicate both the presence and absence of the security device. Gaussian noise is added to an identity mapping layer (identity map) of the ResNet network to construct a ResNet network structure with the Gaussian noise added. The image of the safety equipment marked with the label is input into a ResNet network structure added with Gaussian noise so as to train a classification model of the safety equipment. Finally, a trained classification model for the safety equipment is obtained when the trained loss function converges.
Here, ResNet is a deep learning classification model that introduces residual blocks in the neural network to train to build a deeper neural network. Of course, it will be understood by those skilled in the art that the present invention is not limited to the ResNet classification model, but may be extended to any classification model that is capable of classifying sub-graphs that include safety equipment, and the principles and training processes of these classification models will not be described in detail herein.
As a result of step 250, if the predicted result of the classification model output indicates that the safety equipment was detected, the method 200 may further include highlighting the detected safety equipment in the acquired original image or simply outputting a result representing the detection of the safety equipment, such as "yes". On the other hand, if the prediction output by the classification model indicates that the safety equipment is not detected, the method 200 may further include outputting a reminder or alarm indication, etc. In this way, in the event that no safety equipment is detected, the safety inspector can easily learn of this and take remedial action in time.
FIG. 3 shows a schematic block diagram of an example device 300 that may be used to implement an embodiment of the invention. The device 300 may be, for example, a computer for security inspection, such as a security monitoring device at a construction site, or may be a handheld device of a security inspector. As shown, device 300 may include one or more Central Processing Units (CPUs) 310 (only one shown schematically) that may perform various appropriate actions and processes according to computer program instructions stored in a Read Only Memory (ROM)320 or loaded from a storage unit 380 into a Random Access Memory (RAM) 330. In the RAM 330, various programs and data required for the operation of the device 300 can also be stored. The CPU 310, ROM320, and RAM 330 are connected to each other via a bus 340. An input/output (I/O) interface 350 is also connected to bus 340.
Various components in device 300 are connected to I/O interface 350, including: an input unit 360 such as a keyboard, a mouse, etc.; an output unit 370 such as various types of displays, speakers, and the like; a storage unit 380 such as a magnetic disk, optical disk, or the like; and a communication unit 390 such as a network card, modem, wireless communication transceiver, etc. The communication unit 390 allows the device 300 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.
The method 200 described above may be performed, for example, by the processing unit 310 of the device 300. For example, in some embodiments, method 200 may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 380. In some embodiments, part or all of the computer program may be loaded and/or installed onto device 300 via ROM320 and/or communications unit 390. When the computer program is loaded into RAM 330 and executed by CPU 310, one or more operations of method 200 described above may be performed. Further, the communication unit 390 may support wired or wireless communication functions.
The method 200 and the device 300 for a safety equipment for detecting a human body according to the present invention are described above with reference to the accompanying drawings. However, it will be appreciated by those skilled in the art that the performance of the steps of the method 200 is not limited to the order shown in the figures and described above, but may be performed in any other reasonable order. Further, the device 300 also need not include all of the components shown in fig. 3, it may include only some of the components necessary to perform the functions described in the present invention, and the manner in which these components are connected is not limited to the form shown in the drawings. For example, in the case where the device 300 is a portable device such as a cellular phone, the device 300 may have a different structure than that in fig. 3.
By utilizing the scheme of the invention, the detection and classification model based on deep learning is jointly used, so that the safety equipment detection scheme is more accurate and timely. For example, real-time monitoring, identification and detection are carried out on safety helmets, goggles, work clothes, protective shoes and the like of workers in real time, dangerous behaviors without wearing corresponding safety equipment can be monitored and early warned, and background safety management personnel can timely learn and deal with the dangerous situation, so that safe production informatization management is really achieved, advance prevention is achieved, normal state monitoring in the accident is achieved, and standard management is carried out after the accident.
The present invention may be methods, apparatus, systems and/or computer program products. The computer program product may include a computer-readable storage medium having computer-readable program instructions embodied therein for carrying out aspects of the present invention.
The computer readable storage medium may be a tangible device that can hold and store the instructions for use by the instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic memory device, a magnetic memory device, an optical memory device, an electromagnetic memory device, a semiconductor memory device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a Static Random Access Memory (SRAM), a portable compact disc read-only memory (CD-ROM), a Digital Versatile Disc (DVD), a memory stick, a floppy disk, a mechanical coding device, such as punch cards or in-groove projection structures having instructions stored thereon, and any suitable combination of the foregoing. Computer-readable storage media as used herein is not to be construed as transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission medium (e.g., optical pulses through a fiber optic cable), or electrical signals transmitted through electrical wires.
The computer-readable program instructions described herein may be downloaded from a computer-readable storage medium to a respective computing/processing device, or to an external computer or external storage device via a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers and/or edge servers. The network adapter card or network interface in each computing/processing device receives computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in the respective computing/processing device.
The computer program instructions for carrying out operations of the present invention may be assembler instructions, Instruction Set Architecture (ISA) instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider). In some embodiments, aspects of the present invention are implemented by personalizing an electronic circuit, such as a programmable logic circuit, a Field Programmable Gate Array (FPGA), or a Programmable Logic Array (PLA), with state information of computer-readable program instructions, which can execute the computer-readable program instructions.
Aspects of the present invention are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions.
These computer-readable program instructions may be provided to a processing unit of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processing unit of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer-readable program instructions may also be stored in a computer-readable storage medium that can direct a computer, programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer-readable medium storing the instructions comprises an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.
The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer, other programmable apparatus or other devices implement the functions/acts specified in the flowchart and/or block diagram block or blocks.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
Having described embodiments of the present invention, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terms used herein were chosen in order to best explain the principles of the embodiments, the practical application, or technical improvements to the techniques in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.

Claims (10)

1. A method of safety equipment for detecting a human body, comprising:
acquiring an original image including the human body;
detecting the original image by using a human key point detection model to determine the positions of a plurality of human key points;
selecting at least two keypoints from the plurality of human keypoints based on safety equipment to be detected;
intercepting a sub-graph from the original image that is expected to include the safety equipment to be detected based on the at least two keypoints; and
inputting the sub-graph into a trained classification model of the safety equipment to determine whether the safety equipment is detected.
2. The method of claim 1, wherein the plurality of human keypoints comprises: at least a portion of a left side of the crown, a right side of the crown, a left ear, a right ear, a chin, a left shoulder, a right shoulder, a neck, a left elbow, a right elbow, a left wrist, a right wrist, a left end of a pelvis, a right end of a pelvis, an abdomen, a left knee, a right knee, a left ankle, a right ankle, a left toe, a right toe, a left ball of the foot, a right ball of the foot, a left heel, and a right heel.
3. The method of claim 1, wherein acquiring an original image including the human body comprises:
the original image is acquired from a video stream at predetermined time intervals.
4. The method of claim 3, wherein detecting the original image with a human keypoint detection model to determine the locations of a plurality of human keypoints comprises:
detecting the original image by using the human body key point detection model to determine whether a human body posture is detected; and
and if the human body posture is not detected, acquiring an image behind the original image from the video stream as the original image.
5. The method of claim 1, wherein prior to detecting the original image with a human keypoint detection model to determine the location of a plurality of human keypoints, the method further comprises:
acquiring different human body area images;
respectively marking the coordinates of the plurality of human body key points in each human body area image;
and training a key point target detection depth neural network model by using the human body region image marked with the human body key point coordinates to obtain the human body key point detection model.
6. The method of claim 1, wherein truncating a sub-graph from the original image that is expected to include the safety equipment to be detected based on the at least two keypoints further comprises:
determining two reference points based on the coordinates of the at least two keypoints;
forming a frame based on the two reference points; and
and intercepting the subgraph from the original image by using the frame.
7. The method of claim 6, wherein the safety equipment comprises a safety helmet, the at least two key points comprise an overhead left side, an overhead right side, a neck, and a left or right shoulder,
two reference points p1And p2Respectively determining as follows:
p1＝(xhead left-2d/3,yHead left-d)，
p2＝(xHead right side+3d/5,yHead right side)，
d＝xNeck-xLeft or right shoulder，
Wherein xHead leftAnd yHead leftRespectively representing the abscissa and ordinate, x, of the left side of the vertexHead right sideAnd yHead right sideRespectively representing the abscissa and ordinate, x, of the top and right of the headNeckDenotes the abscissa, x, of the neckLeft or right shoulderThe abscissa representing the left or right shoulder.
8. The method of claim 1, wherein prior to inputting the sub-graph into the trained classification model of the safety equipment to determine whether the safety equipment is detected, the method further comprises:
acquiring different human body area images;
determining coordinates of the plurality of human body key points in each human body region image by using the human body key point detection model;
intercepting an image of the safety equipment by using the coordinates of the plurality of human body key points;
marking an image of the security apparatus with a label, the label indicating both presence and absence of the security apparatus;
adding Gaussian noise to an identity mapping layer of the ResNet network to construct a ResNet network structure added with the Gaussian noise;
inputting the image of the safety equipment marked with the label into the ResNet network structure added with Gaussian noise to train a classification model of the safety equipment; and
obtaining a trained classification model of the safety equipment when the trained loss function converges.
9. An apparatus for detecting safety equipment of a human body, comprising:
a memory having computer program code stored thereon; and
a processor configured to execute the computer program code to perform the method of any of claims 1 to 8.
10. A computer readable storage medium having stored thereon computer program code which, when executed, performs the method of any of claims 1 to 8.
CN201911350854.1A 2019-12-24 2019-12-24 Method, apparatus and computer-readable storage medium for detecting safety equipment of human body Pending CN111191705A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911350854.1A CN111191705A (en) 2019-12-24 2019-12-24 Method, apparatus and computer-readable storage medium for detecting safety equipment of human body

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911350854.1A CN111191705A (en) 2019-12-24 2019-12-24 Method, apparatus and computer-readable storage medium for detecting safety equipment of human body

Publications (1)

Publication Number Publication Date
CN111191705A true CN111191705A (en) 2020-05-22

Family

ID=70710543

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911350854.1A Pending CN111191705A (en) 2019-12-24 2019-12-24 Method, apparatus and computer-readable storage medium for detecting safety equipment of human body

Country Status (1)

Country Link
CN (1) CN111191705A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2022213552A1 (en) * 2021-04-07 2022-10-13 Zhejiang Dahua Technology Co., Ltd. Systems and methods for helmet detection

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108416258A (en) * 2018-01-23 2018-08-17 华侨大学 A kind of multi-human body tracking method based on human body model
CN110533076A (en) * 2019-08-01 2019-12-03 江苏濠汉信息技术有限公司 The detection method and device of construction personnel's seatbelt wearing of view-based access control model analysis

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108416258A (en) * 2018-01-23 2018-08-17 华侨大学 A kind of multi-human body tracking method based on human body model
CN110533076A (en) * 2019-08-01 2019-12-03 江苏濠汉信息技术有限公司 The detection method and device of construction personnel's seatbelt wearing of view-based access control model analysis

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
H. ZHAO等: ""Spindle Net: Person Re-identification with Human Body Region Guided Feature Decomposition and Fusion"" *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2022213552A1 (en) * 2021-04-07 2022-10-13 Zhejiang Dahua Technology Co., Ltd. Systems and methods for helmet detection

Similar Documents

Publication Publication Date Title
CN106372662B (en) Detection method and device for wearing of safety helmet, camera and server
Park et al. Hardhat-wearing detection for enhancing on-site safety of construction workers
US20210216773A1 (en) Personal protective equipment system with augmented reality for safety event detection and visualization
EP2653772B1 (en) Image recognition for personal protective equipment compliance enforcement in work areas
CN109271881B (en) Safety management and control method and device for personnel in transformer substation and server
US11030464B2 (en) Privacy processing based on person region depth
US20210343182A1 (en) Virtual-reality-based personal protective equipment training system
US20160232758A1 (en) Safety equipment criteria verification
CN111695549A (en) Safety helmet wearing detection and identification method based on edge calculation and alarm system
CN111062303A (en) Image processing method, system and computer storage medium
CN109800715B (en) Park entrance and exit monitoring method and system based on Internet of things
CN110070155A (en) A kind of comprehensive Activity recognition method and system of the inmate based on wearable device
CN110751809A (en) Construction safety monitoring method and related product
CN116206255B (en) Dangerous area personnel monitoring method and device based on machine vision
CN112163497B (en) Construction site accident prediction method and device based on image recognition
CN115294533A (en) Building construction state monitoring method based on data processing
CN112906441B (en) Image recognition system and method for exploration and maintenance in communication industry
CN113591751A (en) Transformer substation abnormal condition warning method and device, computer equipment and storage medium
Jeelani et al. Improving safety performance in construction using eye-tracking, visual data analytics, and virtual reality
CN111191705A (en) Method, apparatus and computer-readable storage medium for detecting safety equipment of human body
CN111091104A (en) Target object protection detection method, device, equipment and storage medium
KR20160108740A (en) Method and apparatus for recognizing worker in working site image data
Huang et al. Skeleton-based automatic assessment and prediction of intrusion risk in construction hazardous areas
Chang et al. Safety risk assessment of electric power operation site based on variable precision rough set
CN111274888B (en) Helmet and work clothes intelligent identification method based on wearable mobile glasses

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