CN115050125B - 2d camera-based safety early warning method, device, equipment and storage medium - Google Patents
2d camera-based safety early warning method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN115050125B CN115050125B CN202210549432.2A CN202210549432A CN115050125B CN 115050125 B CN115050125 B CN 115050125B CN 202210549432 A CN202210549432 A CN 202210549432A CN 115050125 B CN115050125 B CN 115050125B
- Authority
- CN
- China
- Prior art keywords
- information
- personnel
- security level
- early warning
- area
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/30—Individual registration on entry or exit not involving the use of a pass
- G07C9/32—Individual registration on entry or exit not involving the use of a pass in combination with an identity check
- G07C9/37—Individual registration on entry or exit not involving the use of a pass in combination with an identity check using biometric data, e.g. fingerprints, iris scans or voice recognition
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/22—Electrical actuation
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/22—Electrical actuation
- G08B13/24—Electrical actuation by interference with electromagnetic field distribution
- G08B13/2491—Intrusion detection systems, i.e. where the body of an intruder causes the interference with the electromagnetic field
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Electromagnetism (AREA)
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Alarm Systems (AREA)
- Closed-Circuit Television Systems (AREA)
- Emergency Alarm Devices (AREA)
Abstract
The invention belongs to the technical field of image processing, and discloses a 2d camera-based safety early warning method, device and equipment and a storage medium. The method comprises the following steps: acquiring current image information; performing personnel detection according to the current image information; when a person is detected, acquiring the position information of the person and the safety characteristic information of the person; determining early warning information according to the personnel position information and the personnel safety characteristic information; and finishing safety early warning according to the early warning information. Through the mode, according to the combination of the personnel safety characteristics and the positions, whether personnel enter the corresponding area or not is determined, the personnel can be effectively prevented from entering the unsafe area through safety early warning, and therefore the safety degree of the production place is improved.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a 2d camera-based safety early warning method, device and equipment and a storage medium.
Background
Along with the proposal of industry 4.0 and intelligent manufacturing, the industry field is continuously developed from the traditional manufacturing industry to the direction of digitalization, intellectualization and unmanned, in the age that everything can be intelligent, unmanned continuously impacts our eyeballs, the application requirement of unmanned forklift in the intelligent storage industry is increasingly greater, wherein how to prevent personnel from mistakenly entering the unmanned forklift working area is always a difficult point in the industry, and the intelligent unmanned is generally lacking. How to effectively prevent personnel from entering unsafe areas through safety precaution becomes the technical problem to be solved.
The foregoing is provided merely for the purpose of facilitating understanding of the technical solutions of the present invention and is not intended to represent an admission that the foregoing is prior art.
Disclosure of Invention
The invention mainly aims to provide a 2d camera-based safety early warning method, device, equipment and storage medium, and aims to solve the technical problem of how to prevent personnel from mistakenly entering an unmanned forklift working area in the prior art.
In order to achieve the above purpose, the present invention provides a 2d camera-based safety precaution method, which comprises the following steps:
acquiring current image information;
performing personnel detection according to the current image information;
when a person is detected, acquiring the position information of the person and the safety characteristic information of the person;
determining early warning information according to the personnel position information and the personnel safety characteristic information;
and finishing safety early warning according to the early warning information.
Optionally, the determining early warning information according to the personnel location information and the personnel safety feature information includes:
determining the regional security level of the region where the personnel are located based on a preset regional security level division result and the personnel position information;
determining a personnel protection level according to the safety characteristic information;
when the personnel protection level is not matched with the regional security level corresponding to the region where the personnel is located, determining that the early warning information is to start early warning;
and when the personnel protection level is matched with the area security level corresponding to the area where the personnel is located, determining that the early warning information is not started early warning.
Optionally, the regional security level includes: high security level, well security level and low security level, low security level all matches with any personnel protection level, well security level and personnel protection level are the time-phase matching of full protection, high security level all does not match with any personnel protection level.
Optionally, before determining the security level of the area where the person is located according to the person position information, the method further includes:
determining the position of a cargo area and a driving route according to the current image information;
and carrying out security level division on each area according to the goods area position and the driving route to obtain a preset area security level division result.
Optionally, before determining the security level of the area where the person is located according to the person position information, the method further includes:
acquiring area planning information and ground control information of a current place;
and carrying out security level division on each region according to the region planning information and the ground command information to obtain a preset region security level division result.
Optionally, the determining the personnel protection level according to the security feature information includes:
when the head protection information and the body protection information exist in the safety feature information, judging that the personnel protection level is completely protected;
and judging the personnel protection level as unprotected if the head protection information or the body protection information does not exist in the safety characteristic information.
Optionally, the step of completing the safety precaution according to the precaution information includes:
when the early warning information is the start early warning, sending avoidance information to a ground control center, so that the ground control center controls the AGV trolley to avoid risks according to the avoidance information.
In addition, in order to achieve the above object, the present invention further provides a 2d camera-based security early warning device, where the 2d camera-based security early warning device includes:
the acquisition module is used for acquiring real-time current image information;
the detection module is used for detecting personnel according to the current image information;
the acquisition module is also used for acquiring personnel position information and personnel safety characteristic information when the personnel image is detected;
the processing module is used for determining early warning information according to the personnel position information and the personnel safety characteristic information;
and the processing module is also used for completing safety early warning according to the early warning information.
In addition, in order to achieve the above object, the present invention further provides a 2d camera-based security early warning device, where the 2d camera-based security early warning device includes: the system comprises a memory, a processor and a 2d camera-based security pre-warning program stored on the memory and executable on the processor, the 2d camera-based security pre-warning program configured to implement the steps of the 2d camera-based security pre-warning method as described above.
In addition, in order to achieve the above object, the present invention further proposes a storage medium, on which a 2d camera-based security pre-warning program is stored, which when executed by a processor implements the steps of the 2d camera-based security pre-warning method as described above.
The method acquires current image information; performing personnel detection according to the current image information; when a person is detected, acquiring the position information of the person and the safety characteristic information of the person; determining early warning information according to the personnel position information and the personnel safety characteristic information; and finishing safety early warning according to the early warning information. Through the mode, according to the combination of the personnel safety characteristics and the positions, whether personnel enter the corresponding area is safe or not is determined, the personnel are effectively prevented from entering the unsafe area through safety early warning, and therefore the safety degree of the production place is improved.
Drawings
FIG. 1 is a schematic diagram of a 2d camera based security early warning device of a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a flow chart of a first embodiment of a 2d camera-based security pre-warning method according to the present invention;
FIG. 3 is a schematic diagram illustrating intrusion detection of an embodiment of a 2d camera-based security pre-warning method according to the present invention;
FIG. 4 is a flow chart of a second embodiment of a 2d camera based security pre-warning method according to the present invention;
fig. 5 is a block diagram of a first embodiment of a 2d camera based security pre-alarm device according to the present invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Referring to fig. 1, fig. 1 is a schematic structural diagram of a 2d camera-based security early warning device in a hardware operation environment according to an embodiment of the present invention.
As shown in fig. 1, the 2d camera-based security early warning device may include: a processor 1001, such as a central processing unit (Central Processing Unit, CPU), a communication bus 1002, a user interface 1003, a network interface 1004, a memory 1005. Wherein the communication bus 1002 is used to enable connected communication between these components. The user interface 1003 may include a Display, an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may further include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a Wireless interface (e.g., a Wireless-Fidelity (Wi-Fi) interface). The Memory 1005 may be a high-speed random access Memory (Random Access Memory, RAM) Memory or a stable nonvolatile Memory (NVM), such as a disk Memory. The memory 1005 may also optionally be a storage device separate from the processor 1001 described above.
Those skilled in the art will appreciate that the structure shown in fig. 1 does not constitute a limitation of the 2d camera based safety precaution device, and may include more or fewer components than illustrated, or certain components may be combined, or a different arrangement of components.
As shown in fig. 1, an operating system, a network communication module, a user interface module, and a 2d camera-based security precaution program may be included in the memory 1005 as one storage medium.
In the 2d camera based security pre-alarm device shown in fig. 1, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the 2d camera-based security early warning device of the present invention may be disposed in the 2d camera-based security early warning device, where the 2d camera-based security early warning device invokes the 2d camera-based security early warning program stored in the memory 1005 through the processor 1001, and executes the 2d camera-based security early warning method provided by the embodiment of the present invention.
The embodiment of the invention provides a 2d camera-based safety early warning method, and referring to fig. 2, fig. 2 is a flow chart of a first embodiment of the 2d camera-based safety early warning method.
In this embodiment, the 2d camera-based security pre-warning method includes the following steps:
step S10: and acquiring current image information.
It should be noted that, the execution subject of the embodiment is a personnel intrusion early warning system, which may be an image acquisition device and an upper computer thereof, where the upper computer may be a computer, a server, or other devices with the same or similar functions as the computer, which is not limited in this embodiment.
It should be noted that, this embodiment is applied to the situation that personnel invade in the production environment, because the automation and the intelligent degree are higher in the current production environment, for example: and (5) unmanned storage environment. In this case, no personnel are present in the general limited area, and even if personnel are present, the personnel should be equipped with a corresponding protective device, and at present, the alarm is generally given by monitoring the equipment head, so that the alarm is not intelligent, and because the production environment maintenance, measurement, production inspection and other scenes always occur, manual work is required, the personnel invasion judgment according to the area is unreasonable. According to the embodiment, the safety is intelligently pre-warned according to the wearing condition of the protective device of the person and the subdivision of the regional safety level. For example: in some biochemically related scenes, the carrying task is carried out by an unmanned forklift or an unmanned carrier, and at this time, if a person who does not wear protective clothing or a gas mask enters an area, the person is dangerous, so that the differentiated early warning can be carried out through the embodiment, and the production environment and the safety of production personnel are ensured.
In a specific implementation, the current image information can be obtained according to the 2D cameras deployed in the designated area.
Step S20: and detecting personnel according to the current image information.
It should be noted that, according to the current image information, personnel detection is performed, that is, a human body in the image information is identified through a target detection algorithm, for example: personnel detection based on deep learning adopts a YOLO deep learning target detection algorithm to train and detect personnel data, the YOLO deep learning target detection algorithm can carry out data enhancement on images during training, a good detection effect can be achieved only by a small number of samples, the most suitable anchor frame proportion of a training data set is recalculated by utilizing a genetic algorithm and a k mean value, and the detection accuracy can be remarkably improved by utilizing the recalculated anchor frame proportion to train a tray detection model.
Step S30: upon detection of a person, person location information and person security feature information are acquired.
It will be appreciated that upon detection of a person, it is necessary to determine where the person is and the security feature information of the person. The position of the person is an image coordinate, the security level area is an image coordinate frame, the person is judged to be in which area by judging which image coordinate frame the person is in, so that the area where the current person is located is obtained, and then the security level corresponding to the area where the current person is located is confirmed according to the preset condition.
It should be noted that the security feature of the person needs to further confirm the wearing of the person and the classification of the wearing article, for example: the safety features of a person are scarcely present if the person is merely wearing a conventional garment. Personnel garment classification this embodiment proposes a preferred solution, for example: based on a classification algorithm of the resnet, for an area which can allow personnel to wear protective equipment to enter, when personnel entering is detected, whether the personnel wear the protective equipment is classified, and whether the detected personnel wear the protective equipment is classified by adopting a resnet deep learning algorithm, wherein input data of the resnet network is a detection frame output by a yolo deep learning target detection algorithm. It can be identified, on demand, whether the personnel wear protective equipment, for example: helmets, protective wear, gas masks, helmets, light-reflecting waistcoats, goggles and the like, and when the existence of corresponding protective equipment is detected, the target personnel can be confirmed to have the safety features, so that the personnel protection level of the personnel can be determined.
Step S40: and determining early warning information according to the personnel position information and the personnel safety characteristic information.
It should be noted that, determining early warning information according to the personnel position information and the personnel safety feature information, that is, the early warning may not be activated in the area where protection is not required; further confirming whether the safety features of the target personnel are complete or not in the area which needs to be protected and can be accessed, and if not, carrying out early warning and reminding; and when the area where the personnel position is located is a forbidden area, early warning can be carried out no matter whether the safety features are complete or not.
Step S50: and finishing safety early warning according to the early warning information.
It can be appreciated that the emergency degree of the current situation can be known according to the early warning information so as to take different safety early warning measures, for example: the personnel who intrudes the restriction area in the face of no protective equipment direct voice warning can, but when personnel appear in the forbidden area, danger can all appear at any time, consequently need drive personnel away immediately to cooperate ground command system lets unmanned fork truck pause task avoid the accidental injury personnel when forbidden area loading and unloading goods.
In this embodiment, when the early warning information is a start early warning, the ground control center sends avoidance information to control the AGV trolley to avoid risk according to the avoidance information.
It should be noted that the avoidance information includes information of the area where the user is located, and the ground control center can search the AGV trolley intersected with the area where the user is located according to the avoidance information, and pause work or select a standby work area and a standby driving route to avoid risks, so that the safety of personnel in the production place is improved.
In a specific implementation, a preferred implementation scheme of this embodiment is proposed, for example: placing a wide-angle camera above a goods stacking area as shown in fig. 3, monitoring the invasion behavior under the camera, acquiring an image under a current monitoring scene through the camera, dividing a polygonal monitoring area on the image, executing different monitoring tasks on different areas under the camera, prompting the invasion of pedestrians by an early warning system when the pedestrians enter the monitoring area by mistake for the areas which are not strictly allowed to enter as the high-safety-level area in fig. 3, and capturing the invasion behavior, and prompting the people not to wear the safety helmet and capturing the image if the pedestrians do not wear the safety helmet for the areas which are required to wear the safety helmet to enter (the medium-safety-level area); the early warning system can monitor a plurality of monitoring areas of the multi-path camera at the same time, and one set of monitoring system can ensure the area monitoring of the whole factory; and monitoring information can be transmitted to the unmanned forklift, so that the safety risk is avoided. The above examples are only for illustrating the present embodiment, and are not intended to limit the precedence relationship among the steps.
The embodiment obtains current image information; performing personnel detection according to the current image information; when a person is detected, acquiring the position information of the person and the safety characteristic information of the person; determining early warning information according to the personnel position information and the personnel safety characteristic information; and finishing safety early warning according to the early warning information. Through the mode, according to the combination of the personnel safety characteristics and the positions, whether personnel enter the corresponding area is safe or not is determined, the personnel are effectively prevented from entering the unsafe area through safety early warning, and therefore the safety degree of the production place is improved.
Referring to fig. 4, fig. 4 is a flow chart of a second embodiment of a 2d camera-based security pre-warning method according to the present invention.
Based on the first embodiment, in the 2d camera-based safety precaution method of the present embodiment, the step S40 specifically includes:
step S41: and determining the regional security level of the region where the personnel are located based on the preset regional security level classification result and the personnel position information.
It can be understood that the preset area security level division result is preset set area division, and the production environment is divided into a forbidden area and a management and control area or other types of areas. Further, according to the personnel position information, which area the personnel is in can be determined, and then according to the preset area security level dividing result, the security level of the area where the personnel is determined, and whether the area is a forbidden area or a management and control area is judged. The forbidden area cannot be accessed under any condition, and the control area is required to be accessed by personnel wearing corresponding protective equipment.
In this embodiment, the location of the cargo area and the driving route are determined according to the current image information; and carrying out security level division on each area according to the goods area position and the driving route to obtain a preset area security level division result.
It should be noted that if the preset area security level division is manual, then labor is quite wasted, and the general production environment is not small, and the labor is quite consumed, and errors are easy to occur, so the embodiment provides a scheme for automatically performing area division, for example: according to the goods district position and the driving route carries out the security level division to each region, specifically, in unmanned warehouse's place, generally dangerous place that appears easily lies in the place that goods were deposited and unmanned fork truck was driven, because most storage accidents all appear in the goods fall or unmanned truck bumps or falls, consequently can be through the regional that the image information record goods were deposited and define the region of depositing the goods as forbidden zone, the route that the record AGV dolly was driven again, all mark the region that the AGV dolly passed as forbidden zone, wherein, the region that is not marked as forbidden zone all marks as control region can.
In this embodiment, the area planning information and the ground control information of the current location are acquired; and carrying out security level division on each region according to the region planning information and the ground command information to obtain a preset region security level division result.
It can be understood that the scheme of automatically dividing the area can also be that external data is used as a data source, the area planning information is established through the area planning information and the ground command information, the area planning information is obtained from the map data of the production place, and the image acquisition equipment is only required to be calibrated to determine the corresponding relation of the image coordinates at each position in the map coordinates of the production place. The ground command information is directly obtained from the AGV ground control center, traffic planning data and task conditions of the AGV are obtained, the areas where the AGV can pass through under the current task can be determined in real time, the areas can be dynamically divided in this way, when the AGV is in a task state, the areas where the current task is likely to be executed by the AGV are taken as forbidden areas, and after the task is finished, the areas are restored to be management and control areas.
Step S42: and determining the personnel protection level according to the safety characteristic information.
It will be appreciated that from the security feature information it is possible to determine which protective equipment a person is wearing, and when the desired protective equipment of the system is present on the person, it is possible to determine the level of protection of the person as full protection.
In this embodiment, when the head protection information and the body protection information exist in the security feature information, the personnel protection level is judged to be the complete protection; and judging the personnel protection level as unprotected if the head protection information or the body protection information does not exist in the safety characteristic information.
It should be noted that, the protection information may be specifically divided into head protection information and body protection information, so that whether the personal protection device is correctly worn or not is facilitated to be resolved, for example: personnel can take the safety helmet in the hand, and personnel are not effectively protected under the condition, so that safety features corresponding to the head and the body are divided to determine whether the head and the body are correctly protected, safety of personnel intrusion early warning is improved, the corresponding safety features are shown when the head protection information and the body protection information exist in the safety feature information, the personnel protection level is determined to be completely protected, and otherwise, the personnel protection level is determined to be unprotected.
Step S43: and when the personnel protection level is not matched with the area security level corresponding to the area where the personnel is located, determining the early warning information as starting early warning.
It should be noted that, the early warning may not be activated in the area where protection is not required; further confirming whether the safety features of the target personnel are complete or not in the area which needs to be protected and can be accessed, and if not, carrying out early warning and reminding; and when the area where the personnel position is located is a forbidden area, early warning can be carried out no matter whether the safety features are complete or not. Further, the matching may be considered successful when the personnel protection level in the management and control area is complete protection. And otherwise, the personnel protection level is not matched with the area security level corresponding to the area where the personnel are located.
In this embodiment, the regional security level includes: high security level, well security level and low security level, low security level all matches with any personnel protection level, well security level and personnel protection level are the time-phase matching of full protection, high security level all does not match with any personnel protection level.
It can be understood that, as shown in fig. 3, when the personnel protection level is not protected, i.e. the personnel does not wear the protection device as required, the personnel can only move in the area with low security level, i.e. if the personnel is not protected, the personnel is proved to wear the protection device or not wear the protection device correctly, any area except the low security level is regarded as unmatched, and early warning needs to be started at this time; when the personnel protection level is complete protection, personnel can freely move in other areas except the area corresponding to the high safety level; when the personnel protection level is completely protected and the area security level corresponding to the area where the personnel is located is a high security level, the high security level is the security level corresponding to the forbidden area, namely, any personnel cannot be forbidden no matter whether the personnel is completely protected, and the personnel protection level is not matched with the area security level corresponding to the area where the personnel is located.
Step S44: and when the personnel protection level is matched with the area security level corresponding to the area where the personnel is located, determining that the early warning information is not started early warning.
And when the personnel protection level is matched with the area security level corresponding to the area where the personnel is located, determining that the early warning information is not started early warning. And when the personnel protection level is not matched with the area security level corresponding to the area where the personnel is located, determining the early warning information as starting early warning.
The embodiment determines the regional security level of the region where the personnel are located based on the preset regional security level dividing result and the personnel position information; determining a personnel protection level according to the safety characteristic information; when the personnel protection level is not matched with the regional security level corresponding to the region where the personnel is located, determining that the early warning information is to start early warning; and when the personnel protection level is matched with the area security level corresponding to the area where the personnel is located, determining that the early warning information is not started early warning. Through the mode, the regional security level and the personnel protection level are matched, whether personnel appear at a proper position is judged, and the detailed early warning is carried out through subdividing the regional and the personnel protection level, so that the security of the production environment is improved.
In addition, the embodiment of the invention also provides a storage medium, wherein the storage medium is stored with a 2d camera-based security early warning program, and the 2d camera-based security early warning program realizes the steps of the 2d camera-based security early warning method when being executed by a processor.
Referring to fig. 5, fig. 5 is a block diagram illustrating a first embodiment of a 2d camera-based security pre-warning device according to the present invention.
As shown in fig. 5, a 2d camera-based security pre-warning device according to an embodiment of the present invention includes:
the acquisition module 10 is configured to acquire real-time current image information.
And the detection module 20 is used for detecting personnel according to the current image information.
The acquiring module 10 is further configured to acquire personnel location information and personnel security feature information when the personnel image is detected.
A processing module 30, configured to determine early warning information according to the personnel location information and the personnel security feature information;
the processing module 30 is further configured to complete a safety precaution according to the precaution information.
It should be understood that the foregoing is illustrative only and is not limiting, and that in specific applications, those skilled in the art may set the invention as desired, and the invention is not limited thereto.
The acquisition module 10 acquires current image information; the detection module 20 performs personnel detection according to the current image information; the acquisition module 10 acquires personnel position information and personnel safety feature information when detecting personnel; the processing module 30 determines early warning information according to the personnel position information and the personnel safety feature information; the processing module 30 completes the safety precaution according to the precaution information. By the mode, whether the personnel enter the corresponding area is safe or not is determined according to the combination of the personnel safety characteristics and the positions, and therefore the safety degree of the production place is improved.
In an embodiment, the processing module 30 is further configured to determine an area security level of an area where the person is located based on a preset area security level classification result and the person location information;
determining a personnel protection level according to the safety characteristic information;
when the personnel protection level is not matched with the regional security level corresponding to the region where the personnel is located, determining that the early warning information is to start early warning;
and when the personnel protection level is matched with the area security level corresponding to the area where the personnel is located, determining that the early warning information is not started early warning.
In an embodiment, the processing module 30 is further configured to determine a cargo area location and a driving route according to the current image information;
and carrying out security level division on each area according to the goods area position and the driving route to obtain a preset area security level division result.
In an embodiment, the processing module 30 is further configured to obtain area planning information and ground control information of the current location;
and carrying out security level division on each region according to the region planning information and the ground command information to obtain a preset region security level division result.
In an embodiment, the processing module 30 is further configured to determine that the personnel protection level is completely protected when the head protection information and the body protection information exist in the security feature information;
and judging the personnel protection level as unprotected if the head protection information or the body protection information does not exist in the safety characteristic information.
In an embodiment, the processing module 30 is further configured to send avoidance information to a ground control center when the early warning information is an initiation early warning, so that the ground control center controls the AGV trolley to avoid risk according to the avoidance information.
It should be noted that the above-described working procedure is merely illustrative, and does not limit the scope of the present invention, and in practical application, a person skilled in the art may select part or all of them according to actual needs to achieve the purpose of the embodiment, which is not limited herein.
In addition, technical details not described in detail in the present embodiment may refer to the 2d camera-based security early warning method provided in any embodiment of the present invention, which is not described herein.
Furthermore, it should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. Read Only Memory)/RAM, magnetic disk, optical disk) and including several instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method according to the embodiments of the present invention.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
Claims (7)
1. The 2d camera-based safety early warning method is characterized by comprising the following steps of:
acquiring current image information;
performing personnel detection according to the current image information;
when a person is detected, acquiring the position information of the person and the safety characteristic information of the person;
determining early warning information according to the personnel position information and the personnel safety characteristic information;
completing safety early warning according to the early warning information;
the step of determining early warning information according to the personnel position information and the personnel safety characteristic information comprises the following steps:
determining the regional security level of the region where the personnel are located based on a preset regional security level division result and the personnel position information;
determining a personnel protection level according to the safety characteristic information;
when the personnel protection level is not matched with the regional security level corresponding to the region where the personnel is located, determining that the early warning information is to start early warning;
when the personnel protection level is matched with the area security level corresponding to the area where the personnel is located, determining that the early warning information is not started early warning;
before determining the security level of the area where the personnel is located according to the personnel position information, the method further comprises the following steps:
determining the position of a cargo area and a driving route according to the current image information;
carrying out security level division on each area according to the goods area position and the driving route to obtain a preset area security level division result; or (b)
Before determining the security level of the area where the personnel is located according to the personnel position information, the method further comprises the following steps:
acquiring area planning information and ground control information of a current place;
carrying out security level division on each region according to the region planning information and the ground control information to obtain a preset region security level division result;
the personnel safety feature information includes: head protection information and body protection information;
the regional security level includes: high security level, medium security level, and low security level.
2. The method of claim 1, wherein the zone security level comprises: high security level, well security level and low security level, low security level all matches with any personnel protection level, well security level and personnel protection level are the time-phase matching of full protection, high security level all does not match with any personnel protection level.
3. The method of claim 1, wherein said determining a level of personal protection based on said security feature information comprises:
when the head protection information and the body protection information exist in the safety feature information, judging that the personnel protection level is completely protected;
and judging the personnel protection level as unprotected if the head protection information or the body protection information does not exist in the safety characteristic information.
4. The method of claim 1, wherein the performing the security precaution based on the precaution information comprises:
when the early warning information is the start early warning, sending avoidance information to a ground control center, so that the ground control center controls the AGV trolley to avoid risks according to the avoidance information.
5. 2d camera based safety precaution device, characterized in that, 2d camera based safety precaution device includes:
the acquisition module is used for acquiring real-time current image information;
the detection module is used for detecting personnel according to the current image information;
the acquisition module is also used for acquiring personnel position information and personnel safety characteristic information when the personnel image is detected;
the processing module is used for determining early warning information according to the personnel position information and the personnel safety characteristic information;
the processing module is also used for completing safety precaution according to the precaution information;
the processing module is further used for determining the regional security level of the region where the personnel are located based on the preset regional security level dividing result and the personnel position information;
determining a personnel protection level according to the safety characteristic information;
when the personnel protection level is not matched with the regional security level corresponding to the region where the personnel is located, determining that the early warning information is to start early warning;
when the personnel protection level is matched with the area security level corresponding to the area where the personnel is located, determining that the early warning information is not started early warning;
the processing module is also used for determining the position of the goods area and the driving route according to the current image information;
carrying out security level division on each area according to the goods area position and the driving route to obtain a preset area security level division result; or (b)
The processing module is also used for acquiring the regional planning information and the ground control information of the current place;
carrying out security level division on each region according to the region planning information and the ground control information to obtain a preset region security level division result;
the personnel safety feature information includes: head protection information and body protection information;
the regional security level includes: high security level, medium security level, and low security level.
6. A 2d camera-based security pre-warning device, the device comprising: a memory, a processor and a 2d camera based security pre-warning program stored on the memory and executable on the processor, the 2d camera based security pre-warning program configured to implement the steps of the 2d camera based security pre-warning method of any one of claims 1 to 4.
7. A storage medium, wherein a 2d camera based security pre-warning program is stored on the storage medium, the 2d camera based security pre-warning program implementing the steps of the 2d camera based security pre-warning method according to any one of claims 1 to 4 when executed by a processor.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210549432.2A CN115050125B (en) | 2022-05-20 | 2022-05-20 | 2d camera-based safety early warning method, device, equipment and storage medium |
| PCT/CN2022/133337 WO2023221443A1 (en) | 2022-05-20 | 2022-11-21 | 2d camera-based safety early warning method, apparatus and device, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210549432.2A CN115050125B (en) | 2022-05-20 | 2022-05-20 | 2d camera-based safety early warning method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115050125A CN115050125A (en) | 2022-09-13 |
| CN115050125B true CN115050125B (en) | 2023-08-29 |
Family
ID=83159945
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210549432.2A Active CN115050125B (en) | 2022-05-20 | 2022-05-20 | 2d camera-based safety early warning method, device, equipment and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN115050125B (en) |
| WO (1) | WO2023221443A1 (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115050125B (en) * | 2022-05-20 | 2023-08-29 | 劢微机器人科技(深圳)有限公司 | 2d camera-based safety early warning method, device, equipment and storage medium |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE19954408A1 (en) * | 1999-11-12 | 2001-05-17 | Philipp Schmelter | Secure area surveillance method e.g. for hospital nursery, provides warning signal by detection of identification code provided by signal generator attached to person or mobile object unless authorization signal is received |
| JP2006511861A (en) * | 2002-12-06 | 2006-04-06 | コーニンクレッカ フィリップス エレクトロニクス エヌ ヴィ | System and method for providing passengers with security and convenience in public transport terminals |
| CN103208166A (en) * | 2013-04-09 | 2013-07-17 | 宝鸡市公安局交通警察支队 | Early warning protection method for danger and intelligent early warning protector for dangerous events for road workers |
| CN110110657A (en) * | 2019-05-07 | 2019-08-09 | 中冶赛迪重庆信息技术有限公司 | Method for early warning, device, equipment and the storage medium of visual identity danger |
| CN110179198A (en) * | 2019-06-10 | 2019-08-30 | 唐文 | The method for early warning and device of intelligent safety helmet |
| CN110188724A (en) * | 2019-06-05 | 2019-08-30 | 中冶赛迪重庆信息技术有限公司 | The method and system of safety cap positioning and color identification based on deep learning |
| CN110930701A (en) * | 2019-11-22 | 2020-03-27 | 长安大学 | Vehicle grading early warning system and method based on road accident data |
| CN111003027A (en) * | 2019-11-19 | 2020-04-14 | 中国科学院合肥物质科学研究院 | Unmanned mine car safety monitoring method and system |
| CN111083435A (en) * | 2019-10-27 | 2020-04-28 | 恒大智慧科技有限公司 | Security monitoring method and device and computer readable storage medium |
| CN111551204A (en) * | 2020-04-23 | 2020-08-18 | 江苏金恒信息科技股份有限公司 | Dangerous area identification method and device based on intelligent safety helmet |
| CN111985407A (en) * | 2020-08-21 | 2020-11-24 | 杭州翔毅科技有限公司 | Safety early warning method, device, equipment and storage medium |
| CN113115225A (en) * | 2021-04-09 | 2021-07-13 | 国能智慧科技发展(江苏)有限公司 | Electronic fence area generation system based on hazard source monitoring and personnel positioning |
| CN113920543A (en) * | 2021-11-22 | 2022-01-11 | 奇酷软件（深圳）有限公司 | Safety detection method, device, equipment and storage medium for forbidden area |
| WO2022036639A1 (en) * | 2020-08-20 | 2022-02-24 | 唐山哈船科技有限公司 | Marine port safety unmanned aerial vehicle detection system |
| CN216331767U (en) * | 2021-11-08 | 2022-04-19 | 长安大学 | Visual field blind area early warning system for heavy-duty traction truck |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007195130A (en) * | 2006-01-17 | 2007-08-02 | Ara Software:Kk | Video monitoring system |
| US9472077B2 (en) * | 2014-08-01 | 2016-10-18 | Francis Joseph Coviello | Surveillance of a secure area |
| CN110517429A (en) * | 2019-09-10 | 2019-11-29 | 浙江蓝迪电力科技有限公司 | A kind of Intelligent electronic fence system and processing method |
| CN111930125A (en) * | 2020-08-19 | 2020-11-13 | 山东华锐智能技术有限公司 | Low-cost obstacle detection device and method suitable for AGV |
| CN113379830A (en) * | 2021-06-11 | 2021-09-10 | 珠海格力电器股份有限公司 | Anti-collision method and device, storage medium and electronic equipment |
| CN113505704B (en) * | 2021-07-13 | 2023-11-10 | 上海西井科技股份有限公司 | Personnel safety detection method, system, equipment and storage medium for image recognition |
| CN113808354A (en) * | 2021-11-16 | 2021-12-17 | 深圳市思拓通信系统有限公司 | Method, device and medium for early warning of construction site dangerous area |
| CN115050125B (en) * | 2022-05-20 | 2023-08-29 | 劢微机器人科技(深圳)有限公司 | 2d camera-based safety early warning method, device, equipment and storage medium |
-
2022
- 2022-05-20 CN CN202210549432.2A patent/CN115050125B/en active Active
- 2022-11-21 WO PCT/CN2022/133337 patent/WO2023221443A1/en unknown
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE19954408A1 (en) * | 1999-11-12 | 2001-05-17 | Philipp Schmelter | Secure area surveillance method e.g. for hospital nursery, provides warning signal by detection of identification code provided by signal generator attached to person or mobile object unless authorization signal is received |
| JP2006511861A (en) * | 2002-12-06 | 2006-04-06 | コーニンクレッカ フィリップス エレクトロニクス エヌ ヴィ | System and method for providing passengers with security and convenience in public transport terminals |
| CN103208166A (en) * | 2013-04-09 | 2013-07-17 | 宝鸡市公安局交通警察支队 | Early warning protection method for danger and intelligent early warning protector for dangerous events for road workers |
| CN110110657A (en) * | 2019-05-07 | 2019-08-09 | 中冶赛迪重庆信息技术有限公司 | Method for early warning, device, equipment and the storage medium of visual identity danger |
| CN110188724A (en) * | 2019-06-05 | 2019-08-30 | 中冶赛迪重庆信息技术有限公司 | The method and system of safety cap positioning and color identification based on deep learning |
| CN110179198A (en) * | 2019-06-10 | 2019-08-30 | 唐文 | The method for early warning and device of intelligent safety helmet |
| CN111083435A (en) * | 2019-10-27 | 2020-04-28 | 恒大智慧科技有限公司 | Security monitoring method and device and computer readable storage medium |
| CN111003027A (en) * | 2019-11-19 | 2020-04-14 | 中国科学院合肥物质科学研究院 | Unmanned mine car safety monitoring method and system |
| CN110930701A (en) * | 2019-11-22 | 2020-03-27 | 长安大学 | Vehicle grading early warning system and method based on road accident data |
| CN111551204A (en) * | 2020-04-23 | 2020-08-18 | 江苏金恒信息科技股份有限公司 | Dangerous area identification method and device based on intelligent safety helmet |
| WO2022036639A1 (en) * | 2020-08-20 | 2022-02-24 | 唐山哈船科技有限公司 | Marine port safety unmanned aerial vehicle detection system |
| CN111985407A (en) * | 2020-08-21 | 2020-11-24 | 杭州翔毅科技有限公司 | Safety early warning method, device, equipment and storage medium |
| CN113115225A (en) * | 2021-04-09 | 2021-07-13 | 国能智慧科技发展(江苏)有限公司 | Electronic fence area generation system based on hazard source monitoring and personnel positioning |
| CN216331767U (en) * | 2021-11-08 | 2022-04-19 | 长安大学 | Visual field blind area early warning system for heavy-duty traction truck |
| CN113920543A (en) * | 2021-11-22 | 2022-01-11 | 奇酷软件（深圳）有限公司 | Safety detection method, device, equipment and storage medium for forbidden area |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115050125A (en) | 2022-09-13 |
| WO2023221443A1 (en) | 2023-11-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11472337B2 (en) | Industrial vehicle geo-feature system | |
| US9809115B2 (en) | Operator drowsiness detection in surface mines | |
| KR102293390B1 (en) | Use of Electronic Badges in Pass-Through Maneuvering | |
| KR101715001B1 (en) | Display system for safety evaluation in construction sites using of wearable device, and thereof method | |
| CN110419048B (en) | System for identifying defined objects | |
| CN106341661B (en) | Patrol robot | |
| JP2018202531A (en) | Safety control device, method of controlling safety control device, information processing program, and recording medium | |
| CN114466305A (en) | Rescue system, rescue method and server used by rescue system | |
| US20100245554A1 (en) | Vision watching system and method for safety hat | |
| KR102293388B1 (en) | Electronic Badges as Talking Markers | |
| KR20190023071A (en) | Indirect electronic badge tracking | |
| CN114612866B (en) | Intelligent identification method, device and equipment for safety in building site | |
| CN115050125B (en) | 2d camera-based safety early warning method, device, equipment and storage medium | |
| KR20210140771A (en) | Method and apparatus for detecting handle holding state by hand | |
| KR102411052B1 (en) | Apparatus and method for detecting movement of workers based on safety cap | |
| CN113469115B (en) | Method and device for outputting information | |
| KR102332818B1 (en) | Risk notification system and the method thereof using virtual proxy sensor and virtual space-based danger zone setting with rtls sensor | |
| WO2022244747A1 (en) | Workplace management system, workplace management method, and workplace management program | |
| US20220307231A1 (en) | Utility Vehicle and Corresponding Apparatus, Method and Computer Program for a Utility Vehicle | |
| CN114092875A (en) | Operation site safety supervision method and device based on machine learning | |
| KR102541212B1 (en) | Embeded image recognition safety monitering and controling integrated platform comprising ai based image recognition system | |
| CN110286609B (en) | Obstacle avoidance control method and device for intelligent safety helmet | |
| CN116166006A (en) | Unmanned vehicle control method, unmanned vehicle and storage medium | |
| CN113183152B (en) | Motion abnormality determination method, electronic device, and storage medium | |
| CN115393791A (en) | Foreign matter detection method, device and computer readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |