CN115100595A - Potential safety hazard detection method and system, computer equipment and storage medium - Google Patents
Potential safety hazard detection method and system, computer equipment and storage medium Download PDFInfo
- Publication number
- CN115100595A CN115100595A CN202210733600.3A CN202210733600A CN115100595A CN 115100595 A CN115100595 A CN 115100595A CN 202210733600 A CN202210733600 A CN 202210733600A CN 115100595 A CN115100595 A CN 115100595A
- Authority
- CN
- China
- Prior art keywords
- image
- image frame
- image data
- position information
- potential safety
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 36
- 238000000034 method Methods 0.000 claims abstract description 26
- 238000012545 processing Methods 0.000 claims abstract description 15
- 238000004590 computer program Methods 0.000 claims description 17
- 238000000605 extraction Methods 0.000 claims description 8
- 230000008859 change Effects 0.000 claims description 7
- 230000005540 biological transmission Effects 0.000 claims description 5
- 238000004891 communication Methods 0.000 claims description 5
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 230000000717 retained effect Effects 0.000 claims description 3
- 238000004806 packaging method and process Methods 0.000 claims description 2
- 238000012544 monitoring process Methods 0.000 description 9
- 238000010276 construction Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 230000000007 visual effect Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 2
- 125000004435 hydrogen atom Chemical group [H]* 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 239000004566 building material Substances 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 231100001267 hazard identification Toxicity 0.000 description 1
- 231100001261 hazardous Toxicity 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 210000001503 joint Anatomy 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000001681 protective effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/44—Event detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Alarm Systems (AREA)
Abstract
The invention is suitable for the technical field of computers, and provides a potential safety hazard detection method, a system, computer equipment and a storage medium, wherein the method comprises the following steps: acquiring continuous image data packets, wherein the image data packets comprise image frame sequences and relative position relations among image frames; processing the image data packet to obtain an object in an image frame and position information of the object in a world coordinate system; the method comprises the steps of carrying out identification and early warning on potential safety hazards according to position information of objects in a world coordinate system and a preset safety standard position relative relation table, wherein the safety standard position relative relation table is used for representing spatial position relations among the objects and relations between the objects and safety.
Description
Technical Field
The invention belongs to the technical field of computers, and particularly relates to a potential safety hazard detection method, a potential safety hazard detection system, computer equipment and a storage medium.
Background
Safety is an important requirement in the construction industry. In a construction site, once the potential safety hazard cannot be timely and accurately detected, casualty accidents can be caused, and the consequences are unimaginable, so that the accuracy of the potential safety hazard detection in a complex environment of a construction site is extremely high. Because the problems that light rays of a construction site are not uniform, dust is excessive, a danger source is possibly shielded by other obstacles and the like, the potential safety hazard detection with high efficiency and high precision of the construction site is always an industry difficulty. The traditional construction site safety monitoring is a method mainly based on monitoring, the emphasis is placed on 'seeing the whole', collected video data are not fully utilized, and the method is too passive; the video stored in mass is difficult to call, is not intelligent and flexible enough, and is not enough to provide the best security; the method wastes time and labor in video calling and playback, and is easy to make mistakes due to lack of strength caused by manual participation.
In recent years, with the rise of artificial intelligence technology, AI-assisted monitoring has gradually become a new trend. At the rear end of the security inspection camera, algorithms such as object identification, potential safety hazard identification and the like are usually connected in a butt joint mode, and potential safety hazard alarm of a real-time scene is achieved. For example, by fixing a camera, it is monitored whether a worker wears a helmet in a designated area, enters a dangerous area in violation, and the like. However, most of the currently applied schemes mainly use fixed camera monitoring, single image recognition and customized recognition of designated potential safety hazards, and a large space is provided for improving the monitoring range and the universality of the method.
Based on this, the application provides a potential safety hazard detection method, a potential safety hazard detection system, computer equipment and a storage medium.
Disclosure of Invention
Embodiments of the present invention provide a method, a system, a computer device, and a storage medium for detecting a potential safety hazard, which are intended to solve technical problems in the prior art determined in the background art.
The embodiment of the invention is realized in such a way that a potential safety hazard detection method comprises the following steps:
acquiring continuous image data packets, wherein the image data packets comprise image frame sequences and relative position relations among image frames;
processing the image data packet to obtain an object in an image frame and position information of the object in a world coordinate system;
and identifying and early warning the potential safety hazard according to the position information of the object in the world coordinate system and a preset safety regulation position relative relation table, wherein the safety regulation position relative relation table is used for representing the spatial position relation between the objects and the relation between the spatial position relation and the safety.
Another object of an embodiment of the present invention is to provide a system for detecting a potential safety hazard, including:
the image data packet generating module is used for generating continuous image data packets and sending the continuous image data packets to the image sequence semantic extracting module through a communication relay;
the image sequence semantic extraction module is used for acquiring continuous image data packets and processing the image data packets to obtain an object in an image frame and position information of the object in a world coordinate system;
and the potential safety hazard detection and identification module is used for identifying and early warning the potential safety hazard according to the position information of the object in the world coordinate system and a preset safety standard position relative relation table.
It is another object of an embodiment of the present invention to provide a computer device, which includes a memory and a processor, where the memory stores a computer program, and the computer program, when executed by the processor, causes the processor to execute the steps of the safety hazard detection method.
It is another object of an embodiment of the present invention to provide a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the processor is enabled to execute the steps of the safety hazard detection method.
The potential safety hazard detection method provided by the embodiment of the invention provides mobile monitoring based on the safety helmet shooting image aiming at the problem of building site safety monitoring, greatly expands the visual angle limitation problem of the traditional fixed monitoring, and can obtain a larger visual monitoring range.
Drawings
Fig. 1 is an application environment diagram of a potential safety hazard detection method according to an embodiment of the present invention;
fig. 2 is a flowchart of a method for detecting a potential safety hazard according to an embodiment of the present invention;
FIG. 3 is a flowchart of acquiring consecutive image data packets according to an embodiment of the present invention;
FIG. 4 is a flowchart of acquiring an object in an image frame and position information of the object in a world coordinate system according to an embodiment of the present invention;
fig. 5 is a flowchart of identifying and early warning a potential safety hazard according to an embodiment of the present invention;
fig. 6 is a block diagram of a potential safety hazard detection system according to an embodiment of the present invention;
fig. 7 is a block diagram of an internal configuration of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
It will be understood that, as used herein, the terms "first," "second," and the like may be used herein to describe various elements, but these elements are not limited by these terms unless otherwise specified. These terms are only used to distinguish one element from another. For example, a first xx script may be referred to as a second xx script, and similarly, a second xx script may be referred to as a first xx script, without departing from the scope of the present application.
Fig. 1 is an application environment diagram of a method for detecting a potential safety hazard according to an embodiment of the present invention, as shown in fig. 1, in the application environment, a terminal 110 and a computer device 120 are included.
The computer device 120 may be an independent physical server or terminal, may also be a server cluster formed by a plurality of physical servers, and may be a cloud server providing basic cloud computing services such as a cloud server, a cloud database, a cloud storage, and a CDN.
The terminal 110 may be a camera with an image capturing function, in the embodiment of the present invention, it is preferably a movable camera device, and more specifically, it may be an intelligent helmet, the intelligent helmet is at least provided with a power supply, a sound receiving and releasing unit, a positioning unit, a camera, a wireless transmission unit, and a control circuit board, where the sound receiving and releasing unit may be a microphone and a speaker, the wireless transmission unit is mainly used to implement communication transmission, the positioning unit mainly aims to obtain a position and a posture of the intelligent helmet, and the control circuit board is mainly used to implement a control function, and preferably, the terminal 110 may also be an unmanned aerial vehicle or the like with data transmission, image capturing, and positioning functions. The terminal 110 and the computer device 120 may be connected to each other through a communication relay, and the present invention is not limited thereto.
As shown in fig. 2, in an embodiment, a method for detecting a potential safety hazard is provided, and this embodiment is mainly illustrated by applying the method to the terminal 110 (or the server 120) in fig. 1. A potential safety hazard detection method specifically comprises the following steps:
step S100, acquiring continuous image data packets, wherein the image data packets contain image frame sequences and relative position relations among image frames.
In the embodiment of the present invention, the image frame sequence refers to image frames arranged according to a time sequence, the relative position relationship between the image frames refers to a position conversion relationship between a current image frame and a previous image frame, and the terminal 110 has a function of acquiring a position and a posture of the terminal, so that the relative position relationship between the image frames can be acquired.
Step S200, processing the image data packet to obtain the object in the image frame and the position information of the object in the world coordinate system.
And S300, identifying and early warning potential safety hazards according to the position information of the objects in the world coordinate system and a preset safety regulation position relative relation table, wherein the safety regulation position relative relation table is used for representing the spatial position relation between the objects and the safety.
The occurrence of potential safety hazards at a construction site, simple events such as damage of a protective net and non-closing of a distribution box can be identified by a single image detection method, but with the increase of the types of the potential safety hazards, each potential safety hazard is identified by a single image training method, a system becomes too complex, and failure is caused by the influence of a camera view angle. The great class of potential safety hazards is that the position relationship between key objects does not meet the requirements. For example, people and helmets (helmets not on top of a person); a person enters a non-safety area; building materials are not neatly stacked, etc., which may be embodied in some form of inter-object positional relationship.
In the embodiment of the invention, the safety standard position relative relation table comprises related objects, the space position relation among the objects and the relation between the space position relation and the safety. For example, in actual use, objects in a worksite environment are subject to attribute classification. The person alone may be classified into class 1, and other objects may be classified into an operable object, a general object, a dangerous area, an alert area, and the like.
Taking the example of a person wearing the safety helmet as an example, the distance between the position of the head feature point of the person and the center of the intelligent safety helmet must be less than a threshold value, which is expressed as:
D＝|p head with a rotatable shaft -p Cap (hat) |＜T h1
Wherein p is Head with a rotatable shaft Representing the human head jointPosition of the point, p Cap (hat) Center position, T, representing the closest helmet feature point to the head h1 Is a set threshold value;
taking the example of a person walking into a dangerous area, note p Human being Is the center position of all the characteristic points of a person, p Danger(s) For certain dangerous areas, e.g. central positions of distribution boxes, T h2 For the set threshold, the following two-layer relationship can be established for judgment:
if p Human being -p Danger of |＜T h2 If the alarm is not in the warning area, the alarm is not in the warning area;
after entering the warning area, continuously judging:
if | p 1 -p 2 |＜T h3 And then alarming and reminding. Wherein p is 1 And p 2 Respectively representing points of closest mutual distance, T, on the person and the hazardous area h3 The size of the danger zone and the warning threshold value.
The distance between the objects, the set threshold value and the like are recorded or contained in the safety regulation position relative relation table, so that after the position information of the objects in the image frame and the positions of the objects in the world coordinate system is acquired, the potential safety hazards can be rapidly identified and early warned.
In an embodiment, as shown in fig. 3, step S100 may specifically include the following steps:
step S101, acquiring position and posture data of a shooting point and an image frame at the current moment, and aligning the position and posture data and the image frame at the current moment in time.
In the embodiment of the present invention, also taking the foregoing smart helmet as an example, the smart helmet may simultaneously acquire position and orientation data P of its own current time and a captured image frame I, and temporally align consecutive P and I.
Preferably, the positioning unit in the intelligent safety helmet for acquiring the position and posture data P at the current moment of the intelligent safety helmet can be an Intel realsense T265 visual odometer sensor, and after the sensor is started, the visual odometer data at the adjacent moment, namely the position and posture data P can be directly and continuously output based on the fusion matching of the built-in image sensor and the imu sensor data.
Step S102, acquiring the position change relation of the position and posture data corresponding to the image frame at the current moment relative to the position and posture data corresponding to the image frame at the last moment.
In the embodiment of the invention, because the position relationship between the camera and the positioning unit on the intelligent safety helmet is known, and the position posture data P corresponding to the current image frame is also known, the position change relationship or the position conversion relationship between the current image frame and the position posture data corresponding to the image frame at the last moment can be obtained for the continuous image frames, namely (R, T).
And step S103, packaging the image frame at the current moment and the position change relation to obtain continuous image data packets.
In practical application of the embodiment of the present invention, the consecutive image data packets can be represented as (I) 0 ,(0,0))，(I 1 ,(R 1 ,T 1 ))，…，(I n ,(R n ,T n )). Wherein (O, O) represents the initial position, the position attitude is 0, and (R) n ,T n ) Indicates that the camera is I n Camera position P of time n Relative to shooting to n-1 Camera position P of time n-1 Change of position and attitude therebetween, I n Representing an image frame.
In an embodiment, as shown in fig. 4, step S200 may specifically include the following steps:
step S201, performing identification processing on each image frame to identify an object therein and position information of the object in the image frame.
In the embodiment of the present invention, before the step starts, the consecutive image frames may be preprocessed, for example, images of a certain period of time or a certain number of frames are captured, in the embodiment of the present invention, the consecutive images of 5 seconds or the consecutive images of 150 frames are taken, and the images or the data packets may be buffered and then processed.
For the intercepted data, it can be expressed as { (I) n ,(R n ,T n ) In which I is n Representing an image frame, (R) n ,T n ) Indicates that the subject is shot to n Camera position P of time n Relative to shooting to n-1 Camera position P of time n-1 Change of position and attitude therebetween, I n Representing an image frame. Here, the first image frame of the captured data is (R) 1 ,T 1 ) Set to 0 indicates that the image combination starts from here.
For each image frame in the image frame, a deep learning object detection and recognition algorithm, such as YOLO (a kind of object detection algorithm), may be used to detect a recognition object (e.g., a person, a safety helmet, a gate bolt, a vehicle, a machine equipment), and directly extract their image areas, that is, perform recognition processing on each image frame to identify an object in the image frame and an image area where the object is located; further, feature points inside the corresponding object are extracted through an image feature extraction algorithm, such as an ORB (ordered Brief, corner detection and feature description algorithm); for a special object such as a human body, deep learning processing can be directly applied to extract the image position of the corresponding skeleton point, and the image position of the feature point in the object region can be obtained, namely the feature point in the image region where the object is located and the position information of the feature point in the image frame are extracted, wherein the number of the feature points is multiple.
For a certain image frame, { (W) can be obtained n ,(f i ,px i ) In which W is a radical of a hydrogen atom) n Representing an object containing a plurality of feature points, wherein the description of the ith feature point is f i Corresponding to a position px within the current image frame i 。
Step S202, according to the relative position relation between the image frames and the position information of the object and the object in the image frames, the world coordinate system is converted, and the object and the position information of the object in the image frames in the world coordinate system are obtained.
In the embodiment of the invention, for adjacent image frames, because the adjacent image frames have overlapped observation areas and overlapped objects, based on the relative position relationship between the image frames and the position information of the feature points in the image frames, the object in the image frames and the position information of the object in the world coordinate system can be obtained under the condition of combining a plurality of pieces of image frame information according to the conversion relationship between the camera and the world coordinate system.
In one embodiment, as shown in fig. 3, for the same object, the number of feature points in the object is not consistent in different image frames, in the embodiment of the present invention, for the same object, feature points of the object that are present in adjacent image frames and have matching positions are retained, and the position average of all feature points of the object is used as the position information of the object in the world coordinate system.
In the embodiment of the invention, for the same object, the feature points of the object which are present in the adjacent image frames and have matched positions are retained, the feature points which can not be matched are discarded, and the spatial positions of a certain feature point in the continuous adjacent image frames can be obtained for multiple times, so that the position mean value of all the feature points of the object is finally used as output to obtain { (W) n ,(f i ,p i ) In which W is a radical of a hydrogen atom) n Representing an object in which the description of the ith feature point is f i ，f i Is at spatial position px i . In actual application, of course, the position of the feature point may also be determined and optimized by using a multi-frame optimization method such as ba (bundle adjustment), but considering that the required accuracy requirement of the embodiment of the present invention is not high and the calculation pressure thereof is large, the embodiment of the present invention does not use such a method.
In one embodiment, as shown in fig. 5, step S300 may specifically include the following steps:
step S301, according to the identified object, sequentially inquiring security rule items related to the object in a security standard position relative relation table.
In the embodiment of the present invention, since the safety regulation position relative relationship table includes the related objects, and the spatial position relationship between the objects and the safety, for the identified object, firstly, the safety rule item related to the object is queried, for example, the identified object is a human body (a certain worker), and it is assumed that the safety rule item related to the identified object is preset in the safety regulation position relative relationship table as follows: the safety helmet wearing rule and the dangerous area approaching rule can be checked out at the moment.
And S302, for each safety rule item, identifying and early warning potential safety hazards according to a safety standard position relative relation table and position information of the object in a world coordinate system, and outputting the potential safety hazards outwards.
In the embodiment of the invention, the two searched rules are sequentially judged according to the identified human body.
(1) Checking helmet wearing rules
Searching a plurality of safety helmets closest to the human body in the image frame, if the safety helmets are not found, the worker does not wear the safety helmets, and the violation can be directly judged;
if the safety helmet is found, the position of the characteristic point of the human head and the central position of the safety helmet are extracted, and whether the safety helmet meets the rules or not is judged according to the safety relation in the table.
(2) Danger zone proximity rule
Searching all dangerous areas in the image frame, sequentially judging the warning area and further judging the alarm reminding, which is already illustrated in the foregoing embodiment, and the embodiment of the present invention is not described herein in more detail.
After the judgment of compliance or non-compliance is carried out, early warning or alarm information and the like can be output outwards according to the judgment result.
As shown in fig. 6, in an embodiment, a security risk detection system is provided, which may be integrated in the computer device 120, and specifically may include an image data packet generation module 100, an image sequence semantic extraction module 200, and a security risk detection identification module 300, wherein,
an image data packet generating module 100, configured to generate consecutive image data packets and send the consecutive image data packets to the image sequence semantic extracting module 200 through a communication relay;
an image sequence semantic extraction module 200, configured to acquire continuous image data packets, and process the image data packets to obtain an object in an image frame and position information of the object in a world coordinate system;
and the potential safety hazard detection and identification module 300 is configured to identify and early warn a potential safety hazard according to the position information of the object in the world coordinate system and a preset safety standard position relative relationship table.
In the embodiment of the present invention, the image data packet generating module 100 is preferably an intelligent helmet as described in the foregoing embodiment, and of course, the image sequence semantic extracting module 200 and the potential safety hazard detecting and identifying module 300 may also be integrated on the intelligent helmet if the conditions allow.
Preferably, after the determination of compliance is made, the embodiment of the present invention outputs an early warning or an alarm message to the outside, and the like may be broadcasted to the intelligent helmet through voice, or may be stored in the computer device 120 for a person to check, and the embodiment of the present invention is not specifically illustrated.
FIG. 7 is a diagram illustrating an internal structure of a computer device in one embodiment. The computer device may specifically be the terminal 110 (or the server 120) in fig. 1. As shown in fig. 7, the computer apparatus includes a processor, a memory, a network interface, an input device, and a display screen connected through a system bus. The memory comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system and also stores a computer program, and when the computer program is executed by a processor, the computer program can enable the processor to realize the potential safety hazard detection method. The internal memory may also store a computer program, and the computer program, when executed by the processor, may cause the processor to perform the method for detecting a security risk. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
Those skilled in the art will appreciate that the architecture shown in fig. 7 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, the security risk detection system provided by the present application may be implemented in the form of a computer program that is executable on a computer device as shown in fig. 7. The memory of the computer device may store various program modules constituting the safety hazard detection system, such as the image data packet generation module 100, the image sequence semantic extraction module 200, and the safety hazard detection identification module 300 shown in fig. 6. The computer program constituted by the program modules causes the processor to execute the steps in the security risk detection method according to the embodiments of the present application described in the present specification.
For example, the computer device shown in fig. 7 may execute step S100 through the image data packet generation module 100 module in the security risk detection system shown in fig. 7. The computer device may perform step S200 through the image sequence semantic extraction module 200. The computer device may perform step S300 through the potential safety hazard detection and discrimination module 300.
In one embodiment, a computer device is proposed, the computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program:
step S100, acquiring continuous image data packets, wherein the image data packets comprise image frame sequences and relative position relations between image frames
Step S200, processing the image data packet to obtain the object in the image frame and the position information of the object in the world coordinate system
Step S300, identifying and early warning potential safety hazards according to position information of the objects in the world coordinate system and a preset safety regulation position relative relation table, wherein the safety regulation position relative relation table is used for representing the space position relation between the objects and the relation between the space position relation and the safety
In one embodiment, a computer readable storage medium is provided, having a computer program stored thereon, which, when executed by a processor, causes the processor to perform the steps of:
step S100, acquiring continuous image data packets, wherein the image data packets comprise image frame sequences and relative position relations among image frames
Step S200, processing the image data packet to obtain the object in the image frame and the position information of the object in the world coordinate system
And S300, identifying and early warning potential safety hazards according to the position information of the objects in the world coordinate system and a preset safety regulation position relative relation table, wherein the safety regulation position relative relation table is used for representing the spatial position relation between the objects and the safety.
It should be understood that, although the steps in the flowcharts of the embodiments of the present invention are shown in sequence as indicated by the arrows, the steps are not necessarily performed in sequence as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a portion of steps in various embodiments may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed alternately or alternatingly with other steps or at least a portion of sub-steps or stages of other steps.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above may be implemented by a computer program, which may be stored in a non-volatile computer readable storage medium, and when executed, may include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include non-volatile and/or volatile memory. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present invention. It should be noted that various changes and modifications can be made by those skilled in the art without departing from the spirit of the invention, and these changes and modifications are all within the scope of the invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (10)
1. A potential safety hazard detection method is characterized by comprising the following steps:
acquiring continuous image data packets, wherein the image data packets comprise image frame sequences and relative position relations among image frames;
processing the image data packet to obtain an object in an image frame and position information of the object in a world coordinate system;
and identifying and early warning the potential safety hazard according to the position information of the object in the world coordinate system and a preset safety regulation position relative relation table, wherein the safety regulation position relative relation table is used for representing the spatial position relation between the objects and the relation between the spatial position relation and the safety.
2. The method according to claim 1, wherein the step of obtaining consecutive image data packets, the image data packets including a sequence of image frames and a relative positional relationship between the image frames, specifically comprises:
acquiring position and attitude data of a shooting point and an image frame at the current moment, and aligning the position and attitude data with the image frame at the current moment in time;
acquiring the position change relation of position and attitude data corresponding to the image frame at the current moment relative to the position and attitude data corresponding to the image frame at the previous moment;
and packaging the image frame at the current moment and the position change relation to obtain continuous image data packets.
3. The method according to claim 1, wherein the step of processing the image data packet to obtain the object in the image frame and the position information of the object in the world coordinate system specifically comprises:
performing identification processing on each image frame to identify an object therein and position information of the object in the image frame;
and performing world coordinate system conversion according to the relative position relation between the image frames and the position information of the object and the object in the image frames, so as to obtain the object and the position information of the object in the image frames in the world coordinate system.
4. The method according to claim 3, wherein the step of performing identification processing on each image frame to identify an object therein and position information of the object in the image frame specifically comprises:
carrying out identification processing on each image frame, and identifying an object in the image frame and an image area where the object is located;
extracting feature points in an image area where the object is located and position information of the feature points in the image frame, wherein the number of the feature points is multiple.
5. The method of claim 4, wherein for the same object, the feature points of the object that are present in the adjacent image frames and have matching positions are retained, and the position average of all the feature points of the object is used as the position information of the object in the world coordinate system.
6. The method according to claim 1, wherein the steps of identifying and early warning the potential safety hazard according to the position information of the object in the world coordinate system and a preset safety specification position relative relationship table specifically comprise:
according to the identified object, sequentially inquiring security rule items related to the object in a security standard position relative relation table;
and for each safety rule item, identifying and early warning potential safety hazards according to a safety standard position relative relation table and position information of the object in a world coordinate system, and outputting the potential safety hazards outwards.
7. The method according to claim 1, wherein the image data packet is generated and transmitted by an intelligent helmet, and the intelligent helmet is provided with at least a power supply, a sound receiving and emitting unit, a positioning unit, a camera, a wireless transmission unit and a control circuit board.
8. A potential safety hazard detection system, comprising:
the image data packet generating module is used for generating continuous image data packets and sending the continuous image data packets to the image sequence semantic extraction module through the communication relay;
the image sequence semantic extraction module is used for acquiring continuous image data packets and processing the image data packets to obtain an object in an image frame and position information of the object in a world coordinate system;
and the potential safety hazard detection and identification module is used for identifying and early warning the potential safety hazard according to the position information of the object in the world coordinate system and a preset safety standard position relative relation table.
9. A computer arrangement, characterized by a memory and a processor, the memory having stored therein a computer program, which, when executed by the processor, causes the processor to carry out the steps of the safety hazard detection method of any one of claims 1 to 7.
10. A computer-readable storage medium, having a computer program stored thereon, which, when executed by a processor, causes the processor to perform the steps of the safety hazard detection method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210733600.3A CN115100595A (en) | 2022-06-27 | 2022-06-27 | Potential safety hazard detection method and system, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210733600.3A CN115100595A (en) | 2022-06-27 | 2022-06-27 | Potential safety hazard detection method and system, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115100595A true CN115100595A (en) | 2022-09-23 |
Family
ID=83292588
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210733600.3A Pending CN115100595A (en) | 2022-06-27 | 2022-06-27 | Potential safety hazard detection method and system, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115100595A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117204639A (en) * | 2023-09-18 | 2023-12-12 | 山东矿机华能装备制造有限公司 | Intelligent helmet and management platform |
| CN118411677A (en) * | 2024-07-03 | 2024-07-30 | 深圳市银雁科技有限公司 | Image detection post-processing method and device, electronic equipment and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110751809A (en) * | 2019-10-14 | 2020-02-04 | 万翼科技有限公司 | Construction safety monitoring method and related product |
| CN110889941A (en) * | 2019-10-23 | 2020-03-17 | 万翼科技有限公司 | Constructor safety monitoring system and method |
| CN111083441A (en) * | 2019-12-18 | 2020-04-28 | 广州穗能通能源科技有限责任公司 | Construction site monitoring method and device, computer equipment and storage medium |
| US20200184658A1 (en) * | 2018-12-05 | 2020-06-11 | Ankobot (Shenzhen) Smart Technologies Co., Ltd. | Monitoring method and device for mobile target, monitoring system and mobile robot |
| CN111414873A (en) * | 2020-03-26 | 2020-07-14 | 广州粤建三和软件股份有限公司 | Alarm prompting method, device and alarm system based on wearing state of safety helmet |
| CN113409391A (en) * | 2021-06-25 | 2021-09-17 | 浙江商汤科技开发有限公司 | Visual positioning method and related device, equipment and storage medium |
| CN113819890A (en) * | 2021-06-04 | 2021-12-21 | 腾讯科技（深圳）有限公司 | Distance measuring method, distance measuring device, electronic equipment and storage medium |
-
2022
- 2022-06-27 CN CN202210733600.3A patent/CN115100595A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200184658A1 (en) * | 2018-12-05 | 2020-06-11 | Ankobot (Shenzhen) Smart Technologies Co., Ltd. | Monitoring method and device for mobile target, monitoring system and mobile robot |
| CN110751809A (en) * | 2019-10-14 | 2020-02-04 | 万翼科技有限公司 | Construction safety monitoring method and related product |
| CN110889941A (en) * | 2019-10-23 | 2020-03-17 | 万翼科技有限公司 | Constructor safety monitoring system and method |
| CN111083441A (en) * | 2019-12-18 | 2020-04-28 | 广州穗能通能源科技有限责任公司 | Construction site monitoring method and device, computer equipment and storage medium |
| CN111414873A (en) * | 2020-03-26 | 2020-07-14 | 广州粤建三和软件股份有限公司 | Alarm prompting method, device and alarm system based on wearing state of safety helmet |
| CN113819890A (en) * | 2021-06-04 | 2021-12-21 | 腾讯科技（深圳）有限公司 | Distance measuring method, distance measuring device, electronic equipment and storage medium |
| CN113409391A (en) * | 2021-06-25 | 2021-09-17 | 浙江商汤科技开发有限公司 | Visual positioning method and related device, equipment and storage medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117204639A (en) * | 2023-09-18 | 2023-12-12 | 山东矿机华能装备制造有限公司 | Intelligent helmet and management platform |
| CN118411677A (en) * | 2024-07-03 | 2024-07-30 | 深圳市银雁科技有限公司 | Image detection post-processing method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110781750A (en) | Dangerous person monitoring processing method and device, computer equipment and storage medium | |
| CN115100595A (en) | Potential safety hazard detection method and system, computer equipment and storage medium | |
| CN109766755B (en) | Face recognition method and related product | |
| CN112272288A (en) | Nuclear power operation monitoring method and device, computer equipment and storage medium | |
| CN112364715A (en) | Nuclear power operation abnormity monitoring method and device, computer equipment and storage medium | |
| Guillermo et al. | Detection and classification of public security threats in the philippines using neural networks | |
| CN114359976B (en) | Intelligent security method and device based on person identification | |
| CN108288025A (en) | A kind of car video monitoring method, device and equipment | |
| CN111008621A (en) | Object tracking method and device, computer equipment and storage medium | |
| CN116206255A (en) | Dangerous area personnel monitoring method and device based on machine vision | |
| CN110659564A (en) | Method and device for tracking users in area, computer equipment and storage medium | |
| Chen et al. | Safety Helmet‐Wearing Detection System for Manufacturing Workshop Based on Improved YOLOv7 | |
| Ji et al. | A high-performance framework for personal protective equipment detection on the offshore drilling platform | |
| JP2016103690A (en) | Monitoring system, monitoring apparatus, and monitoring method | |
| CN114550951A (en) | Rapid medical treatment method and device, computer equipment and storage medium | |
| JP2017167800A (en) | Monitoring system, information processor, monitoring method, and monitoring program | |
| US11722763B2 (en) | System and method for audio tagging of an object of interest | |
| JP2014215747A (en) | Tracking device, tracking system, and tracking method | |
| JP6226859B2 (en) | Work monitoring system | |
| KR20230131678A (en) | A method and apparatus for tracking worker movement in AI-VISION based multi-camera environment | |
| TWI730605B (en) | Artificial intelligence patrol system and artificial intelligence patrol method | |
| CN113657142A (en) | Method and system for detecting abnormal behaviors in community based on intelligent rod | |
| KR102633147B1 (en) | Edge-cloud platform system | |
| CN113723308B (en) | Image-based epidemic prevention kit detection method, system, equipment and storage medium | |
| TWI606426B (en) | System and method for personal circumference surrounding safety notification |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220923 |