CN115086616A - Dangerous behavior identification method and system based on multiple sensors - Google Patents
Dangerous behavior identification method and system based on multiple sensors Download PDFInfo
- Publication number
- CN115086616A CN115086616A CN202210685531.3A CN202210685531A CN115086616A CN 115086616 A CN115086616 A CN 115086616A CN 202210685531 A CN202210685531 A CN 202210685531A CN 115086616 A CN115086616 A CN 115086616A
- Authority
- CN
- China
- Prior art keywords
- monitoring
- information
- determining
- building
- 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.)
- Withdrawn
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Multimedia (AREA)
- Development Economics (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Signal Processing (AREA)
- Game Theory and Decision Science (AREA)
- Computer Graphics (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Alarm Systems (AREA)
Abstract
The invention relates to the technical field of safety supervision, and particularly discloses a dangerous behavior identification method and system based on multiple sensors, wherein the method comprises the steps of receiving a monitoring request containing range information and input by a user, and determining a monitoring area according to the monitoring request; performing content identification on the monitoring area, and determining the monitoring frequency of each monitoring node according to the content identification result; sending the monitoring frequency to each monitoring node, and acquiring monitoring information based on each monitoring node; and determining the display brightness of the monitoring point location according to the monitoring information, and generating a visual area model according to the monitoring point location containing the display brightness. The invention determines the monitoring area according to the user request, acquires the monitoring information in the monitoring area according to the preset monitoring node, identifies the monitoring information, determines some problem areas, and visually displays the problem areas in real time, thereby greatly reducing the working difficulty of workers, improving the supervision level in a phase-changing manner and being convenient for popularization and use.
Description
Technical Field
The invention relates to the technical field of safety supervision, in particular to a dangerous behavior identification method and system based on multiple sensors.
Background
Middle school students, mostly minor students, are often stressed in learning, for example, parents or teachers urge to promote, students to play with laughter, and learning problems cause the students to face great stress; in addition, the college students around are children with less mature mind, the individual psychological problems of the students cannot be solved, and behaviors which hurt other people or the students can be formed, such as school violence, although most students may smile about the school violence after adults, some students are not excluded from inscription of a lifetime. Therefore, there is a need for certain identification of dangerous behavior of students.
The existing identification mode is still based on the identification mode of the camera, however, the existing identification mode is mainly manual identification, the camera only collects data, and then the staff monitors, and it can be thought that when the number of the cameras is large, the workload of the staff is extremely large, some details are easily ignored, and the supervision effect is influenced. Therefore, how to reduce the supervision pressure of workers and the phase-change optimization supervision capability is the problem to be solved by the invention.
Disclosure of Invention
The present invention provides a method and a system for identifying dangerous behaviors based on multiple sensors, so as to solve the problems in the background art.
In order to achieve the purpose, the invention provides the following technical scheme:
a multi-sensor based hazardous behavior identification method, the method comprising:
receiving a monitoring request containing range information input by a user, and determining a monitoring area according to the monitoring request;
performing content identification on the monitoring area, and determining the monitoring frequency of each monitoring node according to the content identification result;
sending the monitoring frequency to each monitoring node, and acquiring monitoring information based on each monitoring node;
and determining the display brightness of the monitoring point location according to the monitoring information, and generating a visual area model according to the monitoring point location containing the display brightness.
As a further scheme of the invention: the step of receiving a monitoring request containing range information input by a user and determining a monitoring area according to the monitoring request comprises the following steps:
establishing a connection channel with a building database, reading building data of a campus, and generating a campus model according to the building data; a certain scale exists between the campus model and the campus;
generating an information receiving port based on the campus model, and receiving point location information input by a user based on the information receiving port;
determining range information according to the point location information, and determining a monitoring area in the campus model according to the range information.
As a further scheme of the invention: the steps of establishing a connection channel with a building database, reading building data of a campus and generating a campus model according to the building data comprise:
establishing a connection channel with a building database, reading a BIM (building information model) of a campus, and simplifying the BIM to obtain a three-dimensional scene;
reading an engineering drawing of a campus, and obtaining at least one two-dimensional scene of a top view angle according to the engineering drawing;
inserting the three-dimensional scene according to the two-dimensional scene to obtain a campus model;
generating and displaying a reference route according to a preset data acquisition height; displaying a reference route, receiving selection information of a user and determining an acquisition path;
and synchronously acquiring image information based on five different visual angles of one vertical direction and four inclined directions under the acquisition path, and updating the campus model at regular time according to the image information.
As a further scheme of the invention: the step of identifying the content of the monitoring area and determining the monitoring frequency of each monitoring node according to the content identification result comprises the following steps:
obtaining building information in the monitoring area, and determining a passing area according to the building information; wherein the building information comprises a building location and a building orientation;
acquiring heat source information containing time information of the passing area according to a preset heat source monitor, and determining a motion track in the passing area according to the heat source information; the motion track comprises start and stop time;
calculating the exposure rate of the passing area according to the motion trail, and determining the monitoring frequency of each monitoring node according to the exposure rate; wherein the monitoring frequency is proportional to the exposure rate.
As a further scheme of the invention: the step of sending the monitoring frequency to each monitoring node and acquiring monitoring information based on each monitoring node comprises:
sending the monitoring frequency to each monitoring node, receiving monitoring information acquired by each monitoring node according to the monitoring frequency, and inserting the number information of the monitoring node into the monitoring information; wherein the monitoring information comprises audio information and image information;
inputting the audio information into a trained risk analysis model to obtain a risk rate containing time information;
comparing the risk rate with a preset risk threshold, and marking corresponding time information when the risk rate reaches the risk threshold;
and counting the marked time information, and inquiring image information corresponding to the time information to serve as monitoring information.
As a further scheme of the invention: the step of determining the display brightness of the monitoring point location according to the monitoring information and generating the visual region model according to the monitoring point location containing the display brightness comprises the following steps:
carrying out contour recognition on the monitoring information, and determining a motion contour according to a contour recognition result;
extracting monitoring information containing motion profiles according to a preset time interval, and calculating offset pixels of each motion profile;
inputting the offset pixels and the time intervals into a trained motion analysis model to obtain a motion parameter group of each motion contour;
and determining the display brightness of the corresponding monitoring point location according to the motion parameter group, and generating a visual area model according to the monitoring point location containing the display brightness.
As a further scheme of the invention: the step of determining the display brightness of the corresponding monitoring point according to the motion parameter group and generating the visualization region model according to the monitoring point containing the display brightness comprises the following steps:
inputting the motion parameter group into a trained stability analysis model to obtain a stable value of each motion contour;
counting the stable value of each motion contour, calculating the stable value of monitoring information, and determining the display brightness according to the stable value of the monitoring information;
positioning a monitoring point location for acquiring the monitoring information in the campus model, and inserting the display brightness into the monitoring point location to obtain a visual area model; wherein the display brightness contains a color value control parameter.
The technical scheme of the invention also provides a dangerous behavior recognition system based on multiple sensors, which comprises:
the monitoring area determining module is used for receiving a monitoring request which is input by a user and contains range information and determining a monitoring area according to the monitoring request;
the monitoring frequency determining module is used for identifying the content of the monitoring area and determining the monitoring frequency of each monitoring node according to the content identification result;
the monitoring information acquisition module is used for sending the monitoring frequency to each monitoring node and acquiring monitoring information based on each monitoring node;
and the visual display module is used for determining the display brightness of the monitoring point location according to the monitoring information and generating a visual area model according to the monitoring point location containing the display brightness.
As a further scheme of the invention: the monitoring frequency determination module includes:
the passing area determining unit is used for acquiring the building information in the monitoring area and determining a passing area according to the building information; wherein the building information comprises a building location and a building orientation;
the movement track determining unit is used for acquiring heat source information containing time information of the passing area according to a preset heat source monitor and determining a movement track in the passing area according to the heat source information; the motion track comprises start and stop time;
the processing execution unit is used for calculating the exposure rate of the passing area according to the motion trail and determining the monitoring frequency of each monitoring node according to the exposure rate; wherein the monitoring frequency is directly proportional to the exposure rate.
As a further scheme of the invention: the monitoring information acquisition module includes:
the data interaction unit is used for sending the monitoring frequency to each monitoring node, receiving monitoring information acquired by each monitoring node according to the monitoring frequency, and inserting the serial number information of the monitoring node into the monitoring information; wherein the monitoring information comprises audio information and image information;
the risk analysis unit is used for inputting the audio information into a trained risk analysis model to obtain a risk rate containing time information;
the marking unit is used for comparing the risk rate with a preset risk threshold value and marking corresponding time information when the risk rate reaches the risk threshold value;
and the statistic inquiry unit is used for counting the marked time information and inquiring the image information corresponding to the time information as monitoring information.
Compared with the prior art, the invention has the beneficial effects that: the invention determines the monitoring area according to the user request, acquires the monitoring information in the monitoring area according to the preset monitoring node, identifies the monitoring information, determines some problem areas, and visually displays the problem areas in real time, thereby greatly reducing the working difficulty of workers, improving the supervision level in a phase-changing manner and being convenient for popularization and use.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention.
FIG. 1 is a flow chart diagram of a multi-sensor based hazardous behavior identification method.
Fig. 2 is a first sub-flow block diagram of a multi-sensor based hazardous behavior identification method.
Fig. 3 is a second sub-flow block diagram of a multi-sensor based hazardous behavior identification method.
Fig. 4 is a third sub-flow block diagram of a multi-sensor based hazardous behavior identification method.
Fig. 5 is a fourth sub-flow block diagram of a multi-sensor based hazardous behavior identification method.
Fig. 6 is a block diagram of the component structure of the multi-sensor based dangerous behavior recognition system.
Fig. 7 is a block diagram of a monitoring frequency determination module in the multi-sensor based hazardous behavior identification system.
Fig. 8 is a block diagram of a monitoring information acquisition module in the multi-sensor based dangerous behavior recognition system.
Detailed Description
In order to make the technical problems, technical solutions and advantageous effects to be solved by the present invention more clearly apparent, the present invention is further described in 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.
Example 1
Fig. 1 is a flow chart of a hazardous behavior identification method based on multiple sensors, in an embodiment of the present invention, the hazardous behavior identification method based on multiple sensors includes steps S100 to S400:
step S100: receiving a monitoring request containing range information input by a user, and determining a monitoring area according to the monitoring request;
the monitoring is a privacy violation behavior, and the monitoring can be performed only in certain occasions with relevant permission; therefore, there is a need to limit monitoring activity to certain specific areas;
step S200: performing content identification on the monitoring area, and determining the monitoring frequency of each monitoring node according to the content identification result;
the existing monitoring equipment has high quality, and all areas can be monitored by only installing a limited number of monitoring equipment in one monitoring area; in the monitoring area, some positions need to be focused, and the attention of some positions does not need to be too high; for example, dangerous behaviors on a school arterial road are rarely possible, and most dangerous behaviors occur in certain corners behind a certain teaching building; therefore, the content identification is carried out on the monitoring area, the monitoring frequency of each monitoring device can be determined, and the device cost or the use cost of the monitoring device can be properly reduced according to the monitoring frequency; wherein the monitoring device is installed at the monitoring node.
Step S300: sending the monitoring frequency to each monitoring node, and acquiring monitoring information based on each monitoring node;
after the monitoring frequency is determined, the monitoring frequency is sent to each monitoring node and used for controlling monitoring equipment at the monitoring nodes, and after the monitoring equipment at the monitoring nodes obtains the monitoring frequency, monitoring information is obtained based on the monitoring frequency; it should be noted that the monitoring device may obtain video information, where the video information includes audio information and image information.
Step S400: determining the display brightness of the monitoring point location according to the monitoring information, and generating a visual area model according to the monitoring point location containing the display brightness;
after monitoring information fed back by each monitoring device is received, the monitoring information is identified and processed, a display brightness can be determined, a 'flashing' visual model can be set according to the display brightness, and a worker can visually and rapidly locate a problem area.
Fig. 2 is a first sub-flow block diagram of a hazardous behavior identification method based on multiple sensors, where the step of receiving a monitoring request containing range information input by a user and determining a monitoring area according to the monitoring request includes steps S101 to S103:
step S101: establishing a connection channel with a building database, reading building data of a campus, and generating a campus model according to the building data; a certain scale exists between the campus model and the campus;
step S102: generating an information receiving port based on the campus model, and receiving point location information input by a user based on the information receiving port;
step S103: determining range information according to the point location information, and determining a monitoring area in the campus model according to the range information.
The determination process of the monitoring area is specifically described in steps S101 to S103, and first, building data of a campus is obtained, a theoretical model is generated according to the building data, then, point location information input by a user is received based on the theoretical model, and finally, range information is determined according to the point location information, so that the monitoring area can be determined.
Further, the step of establishing a connection channel with a building database, reading building data of the campus, and generating a campus model according to the building data includes:
establishing a connection channel with a building database, reading a BIM (building information model) of a campus, and simplifying the BIM to obtain a three-dimensional scene;
reading an engineering drawing of a campus, and obtaining at least one two-dimensional scene of a top view angle according to the engineering drawing;
inserting the three-dimensional scene according to the two-dimensional scene to obtain a campus model;
generating and displaying a reference route according to a preset data acquisition height; displaying a reference route, receiving selection information of a user and determining an acquisition path;
and synchronously acquiring image information based on five different visual angles of one vertical direction and four inclined directions under the acquisition path, and updating the campus model at regular time according to the image information.
The above content specifically defines the generation process of the campus model, and the campus model is obtained by adopting a 2D/3D common modeling mode. Firstly, obtaining a three-dimensional scene according to a BIM (building information modeling) model of a campus, and then performing some rendering work based on the prior art; finally, reading two-dimensional engineering images, and continuously enriching the details of the three-dimensional scene by using the two-dimensional images; it is worth mentioning that the number of two-dimensional drawings is generally many, and the more the number is, the more the details are perfect.
Specifically, the principle of updating the campus model is the oblique photography technology, which is a high and new technology developed in the international photogrammetry field in the last ten years, and the technology acquires abundant high-resolution textures on the top surface and side view of a building by synchronously acquiring images from a vertical, four oblique and five different viewing angles. The method can truly reflect the ground and object conditions, acquire object texture information with high precision, and generate a real three-dimensional city model through advanced positioning, fusion, modeling and other technologies.
Fig. 3 is a second sub-flow block diagram of the hazardous behavior identification method based on multiple sensors, where the step of performing content identification on the monitored area and determining the monitoring frequency of each monitoring node according to the content identification result includes steps S201 to S203:
step S201: obtaining building information in the monitoring area, and determining a passing area according to the building information; wherein the building information comprises a building location and a building orientation;
step S202: acquiring heat source information containing time information of the passing area according to a preset heat source monitor, and determining a motion track in the passing area according to the heat source information; the motion track comprises start and stop time;
step S203: calculating the exposure rate of the passing area according to the motion trail, and determining the monitoring frequency of each monitoring node according to the exposure rate; wherein the monitoring frequency is directly proportional to the exposure rate.
The types of buildings in the campus are limited, such as canteens, teaching buildings, dormitories and the like, traffic areas exist among the buildings, and the traffic areas can be major roads or minor roads; the traffic flow in the traffic area can be obtained according to a preset heat source monitor, wherein the traffic flow refers to the number of people passing at any time every day; the exposure rate of the traffic area can be calculated according to the traffic volume, and the understanding of the exposure rate is as follows: if one road has more people to walk and the frequency is high, the exposure rate at the position is high, and the possibility of dangerous behaviors is lower; of course, this rule is only a common sense rule and is not a strict functional relationship.
Fig. 4 is a third sub-flow block diagram of the hazardous behavior identification method based on multiple sensors, where the monitoring frequency is sent to each monitoring node, and the step of acquiring monitoring information based on each monitoring node includes steps S301 to S304:
step S301: sending the monitoring frequency to each monitoring node, receiving monitoring information acquired by each monitoring node according to the monitoring frequency, and inserting the number information of the monitoring node into the monitoring information; wherein the monitoring information comprises audio information and image information;
step S302: inputting the audio information into a trained risk analysis model to obtain a risk rate containing time information;
step S303: comparing the risk rate with a preset risk threshold, and marking corresponding time information when the risk rate reaches the risk threshold;
step S304: and counting the marked time information, and inquiring image information corresponding to the time information to serve as monitoring information.
Step S301 to step S304 describe the process of acquiring monitoring information specifically, and first, the determined monitoring frequency and each monitoring node are sent, so as to acquire monitoring information containing a monitoring node number; then, identifying audio information in the monitoring information, and determining problem audios; and finally, inquiring corresponding image information as monitoring information according to the time of the problem audio.
Fig. 5 is a fourth sub-flow block diagram of the hazardous behavior identification method based on multiple sensors, where the step of determining the display brightness of the monitored point location according to the monitoring information and generating the visualized area model according to the monitored point location containing the display brightness includes steps S401 to S404:
step S401: carrying out contour recognition on the monitoring information, and determining a motion contour according to a contour recognition result;
step S402: extracting monitoring information containing motion profiles according to a preset time interval, and calculating offset pixels of each motion profile;
step S403: inputting the offset pixels and the time intervals into a trained motion analysis model to obtain a motion parameter group of each motion contour;
step S404: and determining the display brightness of the corresponding monitoring point location according to the motion parameter group, and generating a visual area model according to the monitoring point location containing the display brightness.
Specifically describing the visual display process of the monitoring point location in steps S401 to S404, firstly, the extracted monitoring information is image information, and the image information is an image data stream; then, carrying out contour identification on each image information, calculating offset pixels of each motion contour, identifying each motion contour, and obtaining motion parameters of each motion contour; the time interval is fixed, two pieces of image information are selected once, and each two pieces of image information can be calculated to obtain one motion parameter, so that more than one motion parameter of each motion contour is obtained; finally, the motion parameter sets of the respective motion profiles are counted, and a value (numerical value) representing the brightness can be determined and expressed by the brightness in the visualization region model.
As a further limitation of the technical solution of the present invention, the step of determining the display brightness of the corresponding monitoring point according to the motion parameter set and generating the visualization area model according to the monitoring point containing the display brightness includes:
inputting the motion parameter group into a trained stability analysis model to obtain a stable value of each motion contour;
counting the stable value of each motion contour, calculating the stable value of monitoring information, and determining the display brightness according to the stable value of the monitoring information;
positioning a monitoring point location for acquiring the monitoring information in the campus model, and inserting the display brightness into the monitoring point location to obtain a visual area model; wherein the display brightness contains a color value control parameter.
The display process is described specifically, first, the stable value of each motion contour is calculated according to the motion parameter set, then, a display brightness is determined according to the stable value of each motion contour, finally, the acquisition point position of the display brightness is positioned according to the monitoring information, namely, the corresponding monitoring point position, and the brightness of the monitoring point position is adjusted according to the display brightness.
It should be noted that the motion parameters mainly include speed and acceleration, and the speed is used for comparing with other people, for example, one of a group of fast people is very slow, or one of a group of very slow people is very fast, which is considered unstable; the acceleration is mainly used for evaluating the speed stability of an individual, and it can be expected that the acceleration hardly changes when the individual walks or takes a rest, and if the acceleration changes frequently, the stability of the monitored object is low.
Example 2
Fig. 6 is a block diagram of a dangerous behavior recognition system based on multiple sensors, in an embodiment of the present invention, the dangerous behavior recognition system based on multiple sensors includes:
the monitoring area determining module 11 is configured to receive a monitoring request including range information, which is input by a user, and determine a monitoring area according to the monitoring request;
a monitoring frequency determining module 12, configured to perform content identification on the monitoring area, and determine the monitoring frequency of each monitoring node according to a content identification result;
a monitoring information obtaining module 13, configured to send the monitoring frequency to each monitoring node, and obtain monitoring information based on each monitoring node;
and the visual display module 14 is configured to determine display brightness of the monitoring point location according to the monitoring information, and generate a visual area model according to the monitoring point location containing the display brightness.
Fig. 7 is a block diagram of a monitoring frequency determination module in a multi-sensor based dangerous behavior identification system, where the monitoring frequency determination module 12 includes:
a passing area determining unit 121, configured to obtain building information in the monitoring area, and determine a passing area according to the building information; wherein the building information comprises a building location and a building orientation;
a motion trajectory determining unit 122, configured to obtain heat source information including time information of the passing area according to a preset heat source monitor, and determine a motion trajectory in the passing area according to the heat source information; the motion track comprises start and stop time;
the processing execution unit 123 is configured to calculate an exposure rate of the passing area according to the motion trajectory, and determine a monitoring frequency of each monitoring node according to the exposure rate; wherein the monitoring frequency is directly proportional to the exposure rate.
Fig. 8 is a block diagram of a monitoring information obtaining module in the hazardous behavior identification system based on multiple sensors, where the monitoring information obtaining module 13 includes:
the data interaction unit 131 is configured to send the monitoring frequency to each monitoring node, receive monitoring information acquired by each monitoring node according to the monitoring frequency, and insert number information of the monitoring node into the monitoring information; wherein the monitoring information comprises audio information and image information;
a risk analysis unit 132, configured to input the audio information into the trained risk analysis model to obtain a risk rate containing time information;
the marking unit 133 is configured to compare the risk rate with a preset risk threshold, and mark corresponding time information when the risk rate reaches the risk threshold;
and a statistic query unit 134, configured to count the marked time information, and query image information corresponding to the time information as monitoring information.
The functions that can be implemented by the multi-sensor based hazardous behavior identification method are all performed by a computer device comprising one or more processors and one or more memories, wherein at least one program code is stored in the one or more memories, and loaded and executed by the one or more processors to implement the functions of the multi-sensor based hazardous behavior identification method.
The processor fetches instructions and analyzes the instructions one by one from the memory, then completes corresponding operations according to the instruction requirements, generates a series of control commands, enables all parts of the computer to automatically, continuously and coordinately act to form an organic whole, realizes the input of programs, the input of data, the operation and the output of results, and the arithmetic operation or the logic operation generated in the process is completed by the arithmetic unit; the Memory comprises a Read-Only Memory (ROM) for storing a computer program, and a protection device is arranged outside the Memory.
Illustratively, a computer program can be partitioned into one or more modules, which are stored in memory and executed by a processor to implement the present invention. One or more of the modules may be a series of computer program instruction segments capable of performing certain functions, which are used to describe the execution of the computer program in the terminal device.
Those skilled in the art will appreciate that the above description of the service device is merely exemplary and not limiting of the terminal device, and may include more or less components than those described, or combine certain components, or different components, such as may include input output devices, network access devices, buses, etc.
The Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may be any conventional processor or the like, which is the control center of the terminal equipment and connects the various parts of the entire user terminal using various interfaces and lines.
The memory may be used to store computer programs and/or modules, and the processor may implement various functions of the terminal device by operating or executing the computer programs and/or modules stored in the memory and calling data stored in the memory. The memory mainly comprises a storage program area and a storage data area, wherein the storage program area can store an operating system, application programs (such as an information acquisition template display function, a product information publishing function and the like) required by at least one function and the like; the storage data area may store data created according to the use of the berth status display system (such as product information acquisition templates corresponding to different product categories, product information that needs to be issued by different product providers, and the like). In addition, the memory may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
The terminal device integrated modules/units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, all or part of the modules/units in the system according to the above embodiment may be implemented by a computer program, which may be stored in a computer-readable storage medium and used by a processor to implement the functions of the embodiments of the system. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying computer program code, recording medium, U.S. disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution media, and the like.
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 apparatus 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 apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A multi-sensor based hazardous behavior identification method, the method comprising:
receiving a monitoring request containing range information input by a user, and determining a monitoring area according to the monitoring request;
performing content identification on the monitoring area, and determining the monitoring frequency of each monitoring node according to the content identification result;
sending the monitoring frequency to each monitoring node, and acquiring monitoring information based on each monitoring node;
and determining the display brightness of the monitoring point location according to the monitoring information, and generating a visual area model according to the monitoring point location containing the display brightness.
2. The multi-sensor based dangerous behavior recognition method of claim 1, wherein said step of receiving a monitoring request containing range information inputted by a user, determining a monitoring area according to said monitoring request comprises:
establishing a connection channel with a building database, reading building data of a campus, and generating a campus model according to the building data; a certain scale exists between the campus model and the campus;
generating an information receiving port based on the campus model, and receiving point location information input by a user based on the information receiving port;
determining range information according to the point location information, and determining a monitoring area in the campus model according to the range information.
3. The multi-sensor based dangerous behavior recognition method of claim 2, wherein said step of establishing a connection channel with a building database, reading building data of the campus, and generating a campus model from said building data comprises:
establishing a connection channel with a building database, reading a BIM (building information model) of a campus, and simplifying the BIM to obtain a three-dimensional scene;
reading an engineering drawing of a campus, and obtaining at least one two-dimensional scene of a top view angle according to the engineering drawing;
inserting the three-dimensional scene according to the two-dimensional scene to obtain a campus model;
generating and displaying a reference route according to a preset data acquisition height; displaying a reference route, receiving selection information of a user and determining an acquisition path;
and synchronously acquiring image information based on five different visual angles of one vertical direction and four inclined directions under the acquisition path, and updating the campus model at regular time according to the image information.
4. The multi-sensor-based dangerous behavior identification method according to claim 1, wherein the step of performing content identification on the monitoring area and determining the monitoring frequency of each monitoring node according to the content identification result comprises:
obtaining building information in the monitoring area, and determining a passing area according to the building information; wherein the building information comprises a building location and a building orientation;
acquiring heat source information containing time information of the passing area according to a preset heat source monitor, and determining a motion track in the passing area according to the heat source information; the motion track comprises start and stop time;
calculating the exposure rate of the passing area according to the motion trail, and determining the monitoring frequency of each monitoring node according to the exposure rate; wherein the monitoring frequency is directly proportional to the exposure rate.
5. The multi-sensor based dangerous behavior identification method according to claim 1, wherein the step of sending the monitoring frequency to each monitoring node, and the step of obtaining monitoring information based on each monitoring node comprises:
sending the monitoring frequency to each monitoring node, receiving monitoring information acquired by each monitoring node according to the monitoring frequency, and inserting the number information of the monitoring node into the monitoring information; wherein the monitoring information comprises audio information and image information;
inputting the audio information into a trained risk analysis model to obtain a risk rate containing time information;
comparing the risk rate with a preset risk threshold, and marking corresponding time information when the risk rate reaches the risk threshold;
and counting the marked time information, and inquiring image information corresponding to the time information to serve as monitoring information.
6. The multi-sensor based dangerous behavior recognition method according to claim 3, wherein the step of determining the display brightness of the monitoring point location according to the monitoring information, and generating the visualization area model according to the monitoring point location with the display brightness comprises:
carrying out contour recognition on the monitoring information, and determining a motion contour according to a contour recognition result;
extracting monitoring information containing motion profiles according to a preset time interval, and calculating offset pixels of each motion profile;
inputting the offset pixels and the time intervals into a trained motion analysis model to obtain a motion parameter group of each motion contour;
and determining the display brightness of the corresponding monitoring point location according to the motion parameter group, and generating a visual area model according to the monitoring point location containing the display brightness.
7. The method according to claim 6, wherein the step of determining the display brightness of the corresponding monitoring point according to the motion parameter set, and the step of generating the visualization area model according to the monitoring point with the display brightness comprises:
inputting the motion parameter group into a trained stability analysis model to obtain a stable value of each motion contour;
counting the stable value of each motion contour, calculating the stable value of monitoring information, and determining the display brightness according to the stable value of the monitoring information;
positioning a monitoring point location for acquiring the monitoring information in the campus model, and inserting the display brightness into the monitoring point location to obtain a visual area model; wherein the display brightness contains a color value control parameter.
8. A multi-sensor based hazardous behavior identification system, the system comprising:
the monitoring area determining module is used for receiving a monitoring request which is input by a user and contains range information and determining a monitoring area according to the monitoring request;
the monitoring frequency determining module is used for identifying the content of the monitoring area and determining the monitoring frequency of each monitoring node according to the content identification result;
the monitoring information acquisition module is used for sending the monitoring frequency to each monitoring node and acquiring monitoring information based on each monitoring node;
and the visual display module is used for determining the display brightness of the monitoring point location according to the monitoring information and generating a visual area model according to the monitoring point location containing the display brightness.
9. The multi-sensor based hazardous behavior identification system of claim 8, wherein said monitoring frequency determination module comprises:
the passing area determining unit is used for acquiring the building information in the monitoring area and determining a passing area according to the building information; wherein the building information comprises a building location and a building orientation;
the movement track determining unit is used for acquiring heat source information containing time information of the passing area according to a preset heat source monitor and determining a movement track in the passing area according to the heat source information; the motion track comprises start and stop time;
the processing execution unit is used for calculating the exposure rate of the passing area according to the motion trail and determining the monitoring frequency of each monitoring node according to the exposure rate; wherein the monitoring frequency is directly proportional to the exposure rate.
10. The multi-sensor based hazardous behavior identification system of claim 8, wherein said monitoring information acquisition module comprises:
the data interaction unit is used for sending the monitoring frequency to each monitoring node, receiving monitoring information acquired by each monitoring node according to the monitoring frequency, and inserting the serial number information of the monitoring node into the monitoring information; wherein the monitoring information comprises audio information and image information;
the risk analysis unit is used for inputting the audio information into a trained risk analysis model to obtain a risk rate containing time information;
the marking unit is used for comparing the risk rate with a preset risk threshold value and marking corresponding time information when the risk rate reaches the risk threshold value;
and the statistic inquiry unit is used for counting the marked time information and inquiring the image information corresponding to the time information as monitoring information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210685531.3A CN115086616A (en) | 2022-06-16 | 2022-06-16 | Dangerous behavior identification method and system based on multiple sensors |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210685531.3A CN115086616A (en) | 2022-06-16 | 2022-06-16 | Dangerous behavior identification method and system based on multiple sensors |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115086616A true CN115086616A (en) | 2022-09-20 |
Family
ID=83253859
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210685531.3A Withdrawn CN115086616A (en) | 2022-06-16 | 2022-06-16 | Dangerous behavior identification method and system based on multiple sensors |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115086616A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115546903A (en) * | 2022-12-05 | 2022-12-30 | 北京联合永道软件股份有限公司 | Campus student behavior risk early warning method and system |
| CN115549313A (en) * | 2022-11-09 | 2022-12-30 | 国网江苏省电力有限公司徐州供电分公司 | Electricity utilization monitoring method and system based on artificial intelligence |
| CN115578689A (en) * | 2022-10-24 | 2023-01-06 | 西宁城市职业技术学院 | Cargo storage area supervision method and system |
| CN117333981A (en) * | 2023-10-31 | 2024-01-02 | 浙江泰源科技有限公司 | Machine room integrated monitoring management method and system |
-
2022
- 2022-06-16 CN CN202210685531.3A patent/CN115086616A/en not_active Withdrawn
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115578689A (en) * | 2022-10-24 | 2023-01-06 | 西宁城市职业技术学院 | Cargo storage area supervision method and system |
| CN115578689B (en) * | 2022-10-24 | 2023-09-12 | 西宁城市职业技术学院 | Cargo storage area supervision method and system |
| CN115549313A (en) * | 2022-11-09 | 2022-12-30 | 国网江苏省电力有限公司徐州供电分公司 | Electricity utilization monitoring method and system based on artificial intelligence |
| CN115549313B (en) * | 2022-11-09 | 2024-03-08 | 国网江苏省电力有限公司徐州供电分公司 | Power consumption monitoring method and system based on artificial intelligence |
| CN115546903A (en) * | 2022-12-05 | 2022-12-30 | 北京联合永道软件股份有限公司 | Campus student behavior risk early warning method and system |
| CN117333981A (en) * | 2023-10-31 | 2024-01-02 | 浙江泰源科技有限公司 | Machine room integrated monitoring management method and system |
| CN117333981B (en) * | 2023-10-31 | 2024-03-22 | 浙江泰源科技有限公司 | Machine room integrated monitoring management method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115086616A (en) | Dangerous behavior identification method and system based on multiple sensors | |
| US11710322B2 (en) | Surveillance information generation apparatus, imaging direction estimation apparatus, surveillance information generation method, imaging direction estimation method, and program | |
| CN110796714B (en) | Map construction method, device, terminal and computer readable storage medium | |
| CN112798811B (en) | Speed measurement method, device and equipment | |
| CN109470233B (en) | Positioning method and device | |
| CN112154445A (en) | Method and device for determining lane line in high-precision map | |
| CN112991742B (en) | Visual simulation method and system for real-time traffic data | |
| CN113192183A (en) | Real scene three-dimensional reconstruction method and system based on oblique photography and panoramic video fusion | |
| CN114445053B (en) | Smart campus data processing method and system | |
| CN114030995A (en) | Steel mill workshop crown block scheduling method and system | |
| CN110969592A (en) | Image fusion method, automatic driving control method, device and equipment | |
| Braun et al. | Process-and computer vision-based detection of as-built components on construction sites | |
| CN113808267A (en) | GIS map-based three-dimensional community display method and system | |
| JP2023064093A (en) | Traffic mark detection method and method of training traffic mark detection model | |
| CN111062970A (en) | Track generation method and system based on thermodynamic diagram | |
| CN111338232A (en) | Automatic driving simulation method and device | |
| CN114861475B (en) | Real-time ocean simulation method and system based on sensing data | |
| CN115982824A (en) | Construction site worker space management method and device, electronic equipment and storage medium | |
| CN115439792A (en) | Monitoring method and system based on artificial intelligence | |
| CN115240140A (en) | Equipment installation progress monitoring method and system based on image recognition | |
| JP2015001791A (en) | Image analysis apparatus | |
| Takayanagi et al. | A Study on Understanding Pedestrian Flow Using Intermittent Recording Images (PIRI) | |
| CN109448051A (en) | One kind is stumbled line method for drafting and device | |
| CN115457674B (en) | Park safety management method, device and storage medium | |
| CN112325780B (en) | Distance measuring and calculating method and device based on community monitoring |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20220920 |
|
| WW01 | Invention patent application withdrawn after publication |