CN116743970B - Intelligent management platform with video AI early warning analysis - Google Patents
Intelligent management platform with video AI early warning analysis Download PDFInfo
- Publication number
- CN116743970B CN116743970B CN202311015244.2A CN202311015244A CN116743970B CN 116743970 B CN116743970 B CN 116743970B CN 202311015244 A CN202311015244 A CN 202311015244A CN 116743970 B CN116743970 B CN 116743970B
- Authority
- CN
- China
- Prior art keywords
- fishing
- abnormal
- early warning
- monitoring
- personnel
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 25
- 238000012544 monitoring process Methods 0.000 claims abstract description 166
- 230000004044 response Effects 0.000 claims abstract description 3
- 230000002159 abnormal effect Effects 0.000 claims description 187
- 230000006399 behavior Effects 0.000 claims description 63
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 50
- 238000012512 characterization method Methods 0.000 claims description 30
- 238000000034 method Methods 0.000 claims description 22
- 241000251468 Actinopterygii Species 0.000 claims description 21
- 230000008569 process Effects 0.000 claims description 20
- 230000003044 adaptive effect Effects 0.000 claims description 9
- 230000009471 action Effects 0.000 claims description 7
- 230000001815 facial effect Effects 0.000 claims description 6
- 241000894007 species Species 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 3
- 230000006698 induction Effects 0.000 description 3
- 230000003111 delayed effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000009977 dual effect Effects 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005303 weighing Methods 0.000 description 1
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
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
- G08B13/19602—Image analysis to detect motion of the intruder, e.g. by frame subtraction
- G08B13/19613—Recognition of a predetermined image pattern or behaviour pattern indicating theft or intrusion
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
- G08B13/19639—Details of the system layout
- G08B13/19645—Multiple cameras, each having view on one of a plurality of scenes, e.g. multiple cameras for multi-room surveillance or for tracking an object by view hand-over
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
- G08B13/19678—User interface
- G08B13/19682—Graphic User Interface [GUI] presenting system data to the user, e.g. information on a screen helping a user interacting with an alarm system
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/182—Level alarms, e.g. alarms responsive to variables exceeding a threshold
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B31/00—Predictive alarm systems characterised by extrapolation or other computation using updated historic data
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/61—Control of cameras or camera modules based on recognised objects
- H04N23/611—Control of cameras or camera modules based on recognised objects where the recognised objects include parts of the human body
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/67—Focus control based on electronic image sensor signals
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/695—Control of camera direction for changing a field of view, e.g. pan, tilt or based on tracking of objects
Abstract
The invention belongs to the technical field of early warning management, and particularly discloses an intelligent management platform with video AI early warning analysis, which comprises a monitoring equipment layout module, a monitoring area real-time sensing monitoring module, a monitoring picture automatic adjustment module, a shouting early warning module, an early warning response identification module, a management information base, a fishing road line analysis module and a fishing early warning information automatic generation module.
Description
Technical Field
The invention belongs to the technical field of early warning management, and particularly relates to an intelligent management platform with video AI early warning analysis.
Background
Video monitoring and early warning systems are increasingly widely used in recent years, such as park security, traffic management, river forbidding monitoring and the like, and play a very important role in ensuring social security by providing real-time monitoring and alarm functions and timely discovering and responding to potential security threats. With the current gradual destruction of water area environment, fish population in water is gradually rare, and in order to protect water area ecological environment and maintain sustainable development of fishery, a plurality of water areas are subject to a forbidden capture policy, so that the application of video monitoring and early warning in river forbidden capture is more and more common.
The specific implementation process of the river forbidden video monitoring and early warning is to utilize a monitoring picture shot by a monitoring camera to sense abnormal personnel and identify whether fishing behaviors exist or not, and then start an early warning function when the fishing behaviors exist, however, at present, when the fishing personnel are identified, the occurrence position of the fishing personnel is unoriented and unpredictable, so that the situation that the abnormal personnel displayed on the monitoring picture is displayed in an excessively small display proportion and excessively deviated position when the abnormal personnel are sensed possibly exists, the identification of the abnormal personnel behaviors is not facilitated, and in order to ensure the identification accuracy of the fishing behaviors, the monitoring picture needs to be actively adjusted by a supervisory personnel, and the adjustment mode is excessively labor-consuming and not intelligent enough, because the manual adjustment has extremely high subjectivity, the defects of untimely adjustment and irregular adjustment exist, the identification efficiency and the identification accuracy of the fishing behaviors are easily reduced, and the reasonable effectiveness of forbidden early warning output is influenced to a certain extent.
On the other hand, the prior art is mainly placed on the violations of fishing behaviors when a video monitoring and early warning system is used for early warning, the risk monitoring on the fishing behaviors of fishing personnel is ignored, although the fishing is illegal, the safety of the fishing personnel is important, the early warning is carried out simply according to the violations of the fishing behaviors, the early warning information is obviously generated in an insufficiently comprehensive way, the early warning information is not humanized, and therefore the personal safety of the fishing personnel is difficult to ensure in the capability range, and the application value of the video monitoring and early warning in the forbidding of rivers is limited.
Disclosure of Invention
In view of this, in order to solve the problems presented in the above background art, an intelligent management platform with video AI early warning analysis is proposed.
The aim of the invention can be achieved by the following technical scheme: an intelligent management platform with video AI pre-alarm analysis, comprising: the monitoring equipment layout module is used for dividing the restricted water area into subareas and laying monitoring cameras and broadcasting megaphone in each subarea.
The monitoring area real-time sensing monitoring module is used for sensing and monitoring each subarea by using the laid monitoring cameras, and taking a subarea as a target subarea when the monitoring cameras sense that abnormal personnel exist in the subarea.
The monitoring picture automatic adjusting module is used for adjusting the focal length and the shooting angle of the monitoring camera of the target subarea, enabling the display of the monitoring picture of the abnormal personnel in the target subarea to be in a central amplifying state, focusing the monitoring picture on the abnormal personnel, capturing the action characteristics of the abnormal personnel, and further identifying whether the abnormal personnel has fishing behaviors or not according to the action characteristics.
And the shouting early warning module is used for carrying out early warning on the abnormal personnel by utilizing the broadcasting shouting of the target subarea when the abnormal personnel are identified to have fishing behaviors, and collecting facial features of the abnormal personnel.
The early warning response identification module is used for identifying whether abnormal personnel are evacuated in a set time period after the end of the shouting early warning, if the abnormal personnel are not evacuated, the fishing state characterization parameters and the fishing risk characterization parameters are extracted from the current monitoring picture of the target subarea, and further, the fishing behavior forbidden coefficients and the fishing behavior risk coefficients corresponding to the abnormal personnel are analyzed according to the fishing state characterization parameters and the fishing risk characterization parameters.
And the management information base is used for storing fishing hazard factors corresponding to various fishing tools, storing protected coefficients corresponding to various fishes, storing historical fishing records and storing fishing severity coefficients corresponding to various early warning levels.
And the fishing path analysis module is used for locking the occurrence time point of the fishing action so as to determine the fishing path of the abnormal personnel entering the water forbidden area to reach the target subarea.
The automatic fishing early warning information generation module is used for automatically generating fishing early warning information according to the fishing behavior forbidden degree coefficient, the fishing behavior risk coefficient and the fishing road line corresponding to the abnormal personnel and reporting the fishing early warning information to the forbidden water area management center.
As a further innovation of the invention, the focal length of the monitoring camera for adjusting the target subarea is specifically described in the following process: when the monitoring cameras of the target subareas sense that abnormal personnel exist, the area of the picture occupied by the abnormal personnel in the current monitoring picture is obtained, and therefore the display proportion of the abnormal personnel in the current monitoring picture is obtained.
And acquiring the focal length of the monitoring camera corresponding to the target subarea when the current monitoring picture is shot, and recording the focal length as an original focal length.
And calculating the adaptive focal length of the monitoring camera of the target subarea based on the display proportion of the abnormal person in the current monitoring picture and the original focal length.
And adjusting the focal length of the monitoring camera of the target subarea according to the adaptive focal length of the monitoring camera of the target subarea.
As a further innovation of the invention, the specific adjustment process of the shooting angle is as follows: when the monitoring cameras of the target subareas sense that abnormal personnel exist, the abnormal personnel display positions in the current monitoring picture are marked, the distance between the abnormal personnel display positions and the central point of the monitoring picture is obtained, and the distance is recorded as the abnormal personnel display offset distance.
And constructing a plane rectangular coordinate system by taking the central point of the current monitoring picture as an origin, dividing the current monitoring picture into four quadrant areas on an x axis and a y axis in the plane coordinate system, connecting the display position of the abnormal person and the central point of the current monitoring picture at the moment to form a connecting line, and further acquiring a quadrant angle corresponding to the connecting line as the display azimuth angle of the abnormal person.
And acquiring the shooting angle of the monitoring camera corresponding to the target subarea when shooting the current monitoring picture, and recording the shooting angle as an original shooting angle.
And determining the direction to be adjusted of the shooting angle of the monitoring camera corresponding to the target subarea according to the display azimuth angle of the abnormal person.
And determining a required shooting angle of the monitoring camera corresponding to the target subarea according to the display offset distance of the abnormal person.
And the shooting angle of the control target subarea corresponding to the monitoring camera is adjusted from the direction to be adjusted to the required shooting angle.
As a further innovation of the invention, the specific implementation process of the pre-warning for disabling fishing to abnormal personnel by using the broadcasting megaphone of the target subarea is as follows: an infrared range finder is arranged on the broadcast megaphone, and then the distance between the current position of the abnormal person and the broadcast megaphone is measured by the infrared range finder and used as an early warning distance.
And matching the pre-warning distance with the preset demand shouting volume corresponding to various pre-warning distances, and matching the demand shouting volume of the broadcasting shouting device for abnormal personnel.
And adjusting the shouting volume of the broadcasting shouting device to enable the broadcasting shouting device to meet the requirement of the shouting volume.
As a further innovation of the present invention, the fishing state characterization parameters include a number of caught fish, a fishing tool, a fishing type, and a fishing type distribution ratio, and the fishing risk characterization parameters include a fishing position water depth, a fishing vessel swing amplitude, and a fishing position where an abnormal person is located on the vessel.
As a further innovation of the invention, the method for analyzing the forbidden coefficient of the fishing behavior corresponding to the abnormal person comprises the following steps: extracting a fishing tool from the fishing state characterization parameters, and matching the fishing tool with fishing hazard factors corresponding to various fishing tools in a management information base, thereby obtaining the fishing hazard factors corresponding to abnormal personnel.
And extracting the fishing types from the fishing state characterization parameters, and comparing the fishing types with the protected coefficients corresponding to various fishes in the management information base, thereby comparing the protected coefficients corresponding to the various fishing types in the fishing of the abnormal personnel.
Using expressionsAnalyzing to obtain the forbidden coefficient of fishing behavior corresponding to abnormal person +.>Wherein->A protected coefficient corresponding to the i-th fishing class, i being the number of the fishing class present in the fish caught by the abnormal person,/>N represents the number of fishing species present in the fish that the abnormal person has caught,expressed as the distribution ratio corresponding to the ith fishing class,/->Expressed as a fishing hazard factor corresponding to a normal person, x expressed as the number of caught fish,/->Represented as a set reference trap number.
As a further innovation of the invention, the analysis of the risk coefficient of the fishing behavior corresponding to the abnormal person comprises the following steps: and extracting the fishing position of the abnormal person on the ship from the fishing risk characterization parameters, and acquiring the fishing deflection distance by combining the central point position of the ship.
Extracting the water depth of the fishing position and the swing amplitude of the fishing ship from the fishing risk characterization parameters, and analyzing the fishing behavior risk coefficient corresponding to abnormal personnel by combining the fishing deflection distance, wherein the analysis expression is thatWherein l, A and H are respectively expressed as fishing deflection distance, swing amplitude of fishing ship, depth of water body at fishing position and +.>、/>、/>Respectively denoted as preconfigurationThe safe fishing deflection distance, the swing amplitude of the fishing vessel and the depth of the water body at the fishing position are respectively expressed as weight factors corresponding to the fishing deflection distance, the swing amplitude of the fishing vessel and the depth of the water body at the fishing position, and e is expressed as a natural constant.
As a further innovation of the invention, the fishing path line for determining that abnormal personnel enter the forbidden water area to reach the target subarea is found in the following process: and (3) extracting monitoring pictures of other subareas except the target subarea forwards from the occurrence time point of the fishing behavior according to a set time interval, identifying abnormal personnel on the monitoring pictures, and recording the corresponding other subareas as an access area and recording the corresponding time as an access time when the abnormal personnel in the other subareas are identified at a certain time.
And arranging the screened access areas according to the sequence from first to last of the access time, wherein the arrangement result is a fishing path of an abnormal person entering the no-fishing water area to reach the target subarea.
As a further innovation of the present invention, the fishing pre-warning information includes target sub-region position, short fishing video, fishing course, fishing pre-warning level, and whether or not a life-saving tool needs to be carried.
As a further innovation of the invention, the specific generation process of the fishing early warning information is as follows: (1) target sub-region position: locating target sub-area position information.
(2) Short fishing video: and (5) carrying out short video recording on the fishing process of the abnormal personnel by using the monitoring cameras of the target subareas.
(3) Fishing early warning grade: extracting historical fishing records from a management information base, further comparing facial features of abnormal persons with all the fishing persons in the historical fishing records, extracting historical fishing information corresponding to the successfully compared fishing persons from the historical fishing records if the comparison is successful, wherein the historical fishing information comprises historical fishing times and fishing behavior contraband coefficients corresponding to each fishing, further counting the historical fishing contraband corresponding to the abnormal persons by utilizing the historical fishing information, if the comparison fails, recording the historical fishing contraband corresponding to the abnormal persons as 0, and then combining the fishing behavior contraband coefficients corresponding to the abnormal persons and the fishing severity coefficients corresponding to the estimated abnormal persons of the historical fishing contraband, and matching the fishing severity coefficients with fishing severity coefficients corresponding to various pre-warning levels stored in the management information base to obtain the fishing pre-warning level.
(4) Whether or not it is necessary to carry a life saving tool: comparing the risk coefficient of the fishing behavior corresponding to the abnormal person with a set threshold value, if the risk coefficient of the fishing behavior corresponding to the abnormal person is larger than the set threshold value, carrying a lifesaving tool, otherwise, not carrying the lifesaving tool.
Compared with the prior art, the invention has the following beneficial effects: 1. when abnormal personnel are sensed by the monitoring camera to the forbidden water area, the focal length and the shooting angle of the monitoring camera are automatically adjusted based on the display position and the display proportion of the abnormal personnel in the current monitoring picture when the abnormal personnel come in and go out, so that the abnormal personnel are displayed in a central amplified state on the monitoring picture, the intelligent and scientific adjustment of the monitoring picture is realized, the work task of the supervisory personnel is greatly relieved without manual work, the defects of manual adjustment in the aspects of adjustment timeliness and adjustment standardization are effectively avoided through the adjustment of the monitoring picture in real time pertinently and standardly, the recognition efficiency and the recognition accuracy of fishing behaviors can be improved to the maximum extent, the reasonable effectiveness of the forbidden early warning output can be ensured, and the occurrence rate of invalid early warning and delayed early warning is greatly reduced.
2. According to the invention, when the fishing behavior of abnormal people is identified, the fishing state and the fishing risk of the fishing people are monitored, and as the early warning level is determined according to the fishing state, whether a life saving tool needs to be carried or not is determined according to the fishing risk, so that the fishing early warning information is generated, the comprehensive and humanized generation of the fishing early warning information is realized, the personal safety of the fishing people can be effectively ensured while the forbidden early warning is realized, the dual guarantee of the safety and the personal safety of the fish shoal in the forbidden water area in the capability range is embodied, and the application value of the video monitoring early warning in the forbidden water of the river is expanded.
3. According to the invention, before the early warning information is generated according to the fishing state and the fishing risk monitoring result of the abnormal personnel, the shouting early warning of the abnormal personnel is further added, whether the abnormal personnel is evacuated or not is recognized within a set time period after the shouting early warning is finished, and the early warning information is generated when the abnormal personnel is not evacuated, so that invalid warning caused by the early evacuation of the abnormal personnel and the generation of the early warning information can be greatly avoided, the saving of warning resources is facilitated, and the effectiveness of each warning is ensured.
4. The invention also increases the generation of the fishing path when the fishing early warning information is generated, the fishing path reflects the passing path of the fishing personnel after reaching the no-catch water area, and the capturing efficiency is greatly improved by acquiring the fishing path, which is beneficial for the police to capture the fishing personnel as soon as possible after reaching the no-catch water area.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of the connection of the modules of the system of the present invention.
Fig. 2 is a schematic diagram of displaying an azimuth angle of an abnormal person in a current monitoring screen according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, the invention provides an intelligent management platform with video AI early warning analysis, which comprises a monitoring equipment layout module, a monitoring area real-time induction monitoring module, a monitoring picture automatic adjustment module, a shouting early warning module, an early warning reaction recognition module, a management information base, a fishing road route analysis module and a fishing early warning information automatic generation module, wherein the monitoring equipment layout module is connected with the monitoring area real-time induction monitoring module, the monitoring area real-time induction monitoring module is connected with the monitoring picture automatic adjustment module, the monitoring picture automatic adjustment module and the monitoring equipment layout module are both connected with the shouting early warning module, the shouting early warning module is connected with the early warning reaction recognition module, the early warning reaction recognition module and the fishing road route analysis module are both connected with the fishing early warning information automatic generation module, and the management information base is respectively connected with the early warning reaction recognition module and the fishing early warning information automatic generation module.
The monitoring equipment layout module is used for dividing the restricted water area into subareas, and arranging monitoring cameras and broadcast megaphone in each subarea.
The monitoring area real-time sensing monitoring module is used for sensing and monitoring each subarea by using the laid monitoring cameras, and when the monitoring cameras sense that abnormal personnel exist in a subarea, the subarea is used as a target subarea.
The automatic monitoring picture adjusting module is used for adjusting the focal length and the shooting angle of the monitoring camera of the target subarea, enabling the display of the monitoring picture of the abnormal person in the target subarea to be in a central amplifying state, focusing the monitoring picture on the abnormal person, capturing the action characteristics of the abnormal person, and further identifying whether the abnormal person has fishing behaviors according to the action characteristics.
In the embodiment of the above scheme, the following process is specifically referred to for adjusting the focal length of the monitoring camera in the target sub-area: when the monitoring cameras of the target subareas sense that abnormal personnel exist, the area of the picture occupied by the abnormal personnel in the current monitoring picture is obtained, and therefore the display proportion of the abnormal personnel in the current monitoring picture is obtained.
Exemplary, the area of the screen occupied by the abnormal person in the current monitoring screen is s, at this time, the current monitoring screenAbnormal person display proportion isWherein->Represented as the area of the current monitor screen.
And acquiring the focal length of the monitoring camera corresponding to the target subarea when the current monitoring picture is shot, and recording the focal length as an original focal length.
And calculating the adaptive focal length of the monitoring camera of the target subarea based on the display proportion of the abnormal person in the current monitoring picture and the original focal length.
On the basis of the scheme, the calculation process of the adaptive focal length of the monitoring camera of the target subarea is as follows: comparing the display proportion of the abnormal person in the current monitoring picture with the set normal display proportion, if the display proportion of the abnormal person in the current monitoring picture is equal to the set normal display proportion, the adaptive focal length of the monitoring camera of the target subarea is the original focal length, and if the display proportion of the abnormal person in the current monitoring picture is smaller than or larger than the set normal display proportion, the focal length corresponding to the normal display proportion is used as the adaptive focal length of the monitoring camera of the target subarea.
And adjusting the focal length of the monitoring camera of the target subarea according to the adaptive focal length of the monitoring camera of the target subarea.
In still another embodiment of the above solution, the specific adjustment process of the image capturing angle is as follows: when the monitoring cameras of the target subareas sense that abnormal personnel exist, the abnormal personnel display positions in the current monitoring picture are marked, the distance between the abnormal personnel display positions and the central point of the monitoring picture is obtained, and the distance is recorded as the abnormal personnel display offset distance.
And constructing a plane rectangular coordinate system by taking the central point of the current monitoring picture as an origin, dividing the current monitoring picture into four quadrant areas on an x axis and a y axis in the plane coordinate system, connecting the display position of the abnormal person and the central point of the current monitoring picture at the moment to form a connecting line, and further acquiring a quadrant angle corresponding to the connecting line as the display azimuth angle of the abnormal person.
Preferably, the abnormal person displays the azimuth angle in the current monitoring screen as shown in fig. 2.
And acquiring the shooting angle of the monitoring camera corresponding to the target subarea when shooting the current monitoring picture, and recording the shooting angle as an original shooting angle.
And determining the direction to be adjusted of the shooting angle of the monitoring camera corresponding to the target subarea according to the display azimuth angle of the abnormal person.
In order to adjust the display position of the abnormal person to the central position, the monitoring camera needs to adjust the imaging angle in the direction opposite to the display azimuth.
And determining a required shooting angle of the monitoring camera corresponding to the target subarea according to the display offset distance of the abnormal person.
As an example of the above solution, a specific determination manner of determining the required camera angle of the target sub-area corresponding to the monitoring camera may be to combine the abnormal person display offset distance with a preset camera angle adjustment value corresponding to the unit display offset distance to obtain a camera angle adjustment value corresponding to the abnormal person display offset distance, and then obtain the required camera angle of the target sub-area corresponding to the monitoring camera by using the original camera angle and the camera angle adjustment value corresponding to the abnormal person display offset distance.
And the shooting angle of the control target subarea corresponding to the monitoring camera is adjusted from the direction to be adjusted to the required shooting angle.
When abnormal personnel are sensed by the monitoring camera to the forbidden water area, the focal length and the shooting angle of the monitoring camera are automatically adjusted based on the display position and the display proportion of the abnormal personnel in the current monitoring picture when the abnormal personnel come in and go out, so that the abnormal personnel are displayed in a central amplified state on the monitoring picture, the intelligent and scientific adjustment of the monitoring picture is realized, the work task of the supervisory personnel is greatly relieved without manual work, the defects of manual adjustment in the aspects of adjustment timeliness and adjustment standardization are effectively avoided through the adjustment of the monitoring picture in real time pertinently and standardly, the recognition efficiency and the recognition accuracy of fishing behaviors can be improved to the maximum extent, the reasonable effectiveness of the forbidden early warning output can be ensured, and the occurrence rate of invalid early warning and delayed early warning is greatly reduced.
The shouting early warning module is used for carrying out early warning on abnormal personnel by utilizing a broadcasting shouting device of a target subarea when the abnormal personnel are identified to have fishing behaviors, and collecting facial features of the abnormal personnel.
Specifically, the specific implementation process of the fishing forbidden early warning to the abnormal personnel by using the broadcasting megaphone of the target subarea is as follows: an infrared range finder is arranged on the broadcast megaphone, and then the distance between the current position of the abnormal person and the broadcast megaphone is measured by the infrared range finder and used as an early warning distance.
And matching the pre-warning distance with the preset demand shouting volume corresponding to various pre-warning distances, and matching the demand shouting volume of the broadcasting shouting device for abnormal personnel.
And adjusting the shouting volume of the broadcasting shouting device to enable the broadcasting shouting device to meet the requirement of the shouting volume.
According to the invention, before the early warning information is generated according to the fishing state and the fishing risk monitoring result of the abnormal personnel, the shouting early warning of the abnormal personnel is further added, whether the abnormal personnel is evacuated or not is recognized within a set time period after the shouting early warning is finished, and the early warning information is generated when the abnormal personnel is not evacuated, so that invalid warning caused by the early evacuation of the abnormal personnel and the generation of the early warning information can be greatly avoided, the saving of warning resources is facilitated, and the effectiveness of each warning is ensured.
The early warning reaction identification module is used for identifying whether abnormal personnel evacuate in a set time period after the end of the shouting early warning, if the abnormal personnel do not evacuate, the fishing state characterization parameters and the fishing risk characterization parameters are extracted from the current monitoring picture of the target subarea, wherein the fishing state characterization parameters comprise the number of the caught fish, the fishing tools, the fishing types and the distribution proportion of the fishing types, the fishing risk characterization parameters comprise the depth of a water body at the fishing position, the swing amplitude of the fishing ship and the fishing position of the abnormal personnel on the ship, and further the fishing behavior forbidden coefficients and the fishing behavior risk coefficients corresponding to the abnormal personnel are analyzed according to the fishing state characterization parameters.
It is known that the fishing position water body depth in the fishing risk characterization parameter is obtained by extracting the water body depth corresponding to each water area position in the forbidden water area from the management information base through the fishing position, and the swing amplitude of the fishing ship and the fishing position of the abnormal person on the ship can be obtained from the monitoring picture.
In a specific embodiment of the invention, the following steps are referred to for analyzing the forbidden coefficients of the fishing behavior corresponding to the abnormal person: extracting a fishing tool from the fishing state characterization parameters, and matching the fishing tool with fishing hazard factors corresponding to various fishing tools in a management information base, thereby obtaining the fishing hazard factors corresponding to abnormal personnel.
Exemplary fishing tools include, but are not limited to, fishing nets, electric sticks, harpoons.
And extracting the fishing types from the fishing state characterization parameters, and comparing the fishing types with the protected coefficients corresponding to various fishes in the management information base, thereby comparing the protected coefficients corresponding to the various fishing types in the fishing of the abnormal personnel.
Using expressionsAnalyzing to obtain the forbidden coefficient of fishing behavior corresponding to abnormal person +.>Wherein->A protected coefficient corresponding to the i-th fishing class, i being the number of the fishing class present in the fish caught by the abnormal person,/>N is expressed as the number of fishing species present in the fish that the abnormal person has caught, < +.>Expressed as the distribution ratio corresponding to the ith fishing class,/->Expressed as a fishing hazard factor corresponding to a normal person, x expressed as the number of caught fish,/->Represented as a set reference trap number.
In yet another embodiment of the present invention, analyzing risk factors of fishing behavior corresponding to abnormal persons includes the steps of: and extracting the fishing position of the abnormal person on the ship from the fishing risk characterization parameters, and acquiring the fishing deflection distance by combining the central point position of the ship.
Extracting the water depth of the fishing position and the swing amplitude of the fishing ship from the fishing risk characterization parameters, and analyzing the fishing behavior risk coefficient corresponding to abnormal personnel by combining the fishing deflection distance, wherein the analysis expression is thatWherein l, A and H are respectively expressed as fishing deflection distance, swing amplitude of fishing ship, depth of water body at fishing position and +.>、/>、/>The weight factors are respectively expressed as a pre-configured safe fishing deflection distance, a safe fishing ship swing amplitude and a safe fishing position water depth, a, b and c are respectively expressed as a fishing deflection distance, a fishing ship swing amplitude and a fishing position water depth, and e is expressed as a natural constant.
The management information base is used for storing fishing hazard factors corresponding to various fishing tools, storing water depths corresponding to water areas in the water forbidden domain, storing protected coefficients corresponding to various fishes, storing historical fishing records and storing fishing severity coefficients corresponding to various early warning levels.
The fishing road line analysis module is used for acquiring a corresponding time point when the abnormal person is identified to have the fishing behavior, and is used as a fishing behavior occurrence time point, so that the fishing behavior occurrence time point is locked, and the fishing road line of the abnormal person entering the forbidden water area to reach the target subarea is determined, wherein the specific determination process is as follows: and (3) extracting monitoring pictures of other subareas except the target subarea forwards from the occurrence time point of the fishing behavior according to a set time interval, identifying abnormal personnel on the monitoring pictures, and recording the corresponding other subareas as an access area and recording the corresponding time as an access time when the abnormal personnel in the other subareas are identified at a certain time.
And arranging the screened access areas according to the sequence from first to last of the access time, wherein the arrangement result is a fishing path of an abnormal person entering the no-fishing water area to reach the target subarea.
The invention also increases the generation of the fishing path when the fishing early warning information is generated, the fishing path reflects the passing path of the fishing personnel after reaching the no-catch water area, and the capturing efficiency is greatly improved by acquiring the fishing path, which is beneficial for the police to capture the fishing personnel as soon as possible after reaching the no-catch water area.
The automatic generation module of the fishing early warning information is used for automatically generating the fishing early warning information according to the fishing behavior forbidden coefficient, the fishing behavior risk coefficient and the fishing road path corresponding to the abnormal personnel and reporting the fishing early warning information to the forbidden water area management center, wherein the fishing early warning information comprises a target subarea position, a fishing short video, the fishing road path, a fishing early warning level and whether a life-saving tool needs to be carried or not, and preferably, the specific generation process of the fishing early warning information is as follows: (1) target sub-region position: locating target sub-area position information.
(2) Short fishing video: and (5) carrying out short video recording on the fishing process of the abnormal personnel by using the monitoring cameras of the target subareas.
(3) Fishing early warning grade: extracting historical fishing records from a management information base, comparing facial features of abnormal people with all the fishing people in the historical fishing records, and extracting successfully compared historical fishing records if the comparison is successfulHistorical fishing information corresponding to fishing personnel, wherein the historical fishing information comprises historical fishing times and fishing behavior contraband coefficients corresponding to each fishing, further average calculation is carried out on the fishing behavior contraband coefficients corresponding to each fishing to obtain historical fishing contraband corresponding to abnormal personnel, if comparison fails, the historical fishing contraband corresponding to the abnormal personnel is recorded as 0, and at the moment, the fishing behavior contraband coefficients corresponding to the abnormal personnel and the fishing severity coefficients corresponding to the historical fishing contraband estimated to the abnormal personnel are combined, wherein the historical fishing contraband coefficients corresponding to the abnormal personnel are calculated according to the historical fishing contraband, and the historical fishing contraband is calculated according to the historical fishing severity, and the historical fishing contraband is calculated according to the historical fishing rule，/>、/>The fishing severity coefficient is respectively expressed as a weighing factor corresponding to the forbidden coefficient of the fishing behavior and the forbidden degree of the historical fishing, and is matched with the fishing severity coefficient corresponding to various early warning levels stored in the management information base, so that the fishing early warning level is matched.
(4) Whether or not it is necessary to carry a life saving tool: comparing the risk coefficient of the fishing behavior corresponding to the abnormal person with a set threshold value, if the risk coefficient of the fishing behavior corresponding to the abnormal person is larger than the set threshold value, carrying a lifesaving tool, otherwise, not carrying the lifesaving tool.
According to the invention, when the fishing behavior of abnormal people is identified, the fishing state and the fishing risk of the fishing people are monitored, and as the early warning level is determined according to the fishing state, whether a life saving tool needs to be carried or not is determined according to the fishing risk, so that the fishing early warning information is generated, the comprehensive and humanized generation of the fishing early warning information is realized, the personal safety of the fishing people can be effectively ensured while the forbidden early warning is realized, the dual guarantee of the safety and the personal safety of the fish shoal in the forbidden water area in the capability range is embodied, and the application value of the video monitoring early warning in the forbidden water of the river is expanded.
The foregoing is merely illustrative and explanatory of the principles of this invention, as various modifications and additions may be made to the specific embodiments described, or similar arrangements may be substituted by those skilled in the art, without departing from the principles of this invention or beyond the scope of this invention as defined in the claims.
Claims (8)
1. An intelligent management platform with video AI early warning analysis, characterized by comprising:
the monitoring equipment layout module is used for dividing the restricted water area into subareas and laying monitoring cameras and broadcasting megaphone in each subarea;
the monitoring area real-time sensing monitoring module is used for sensing and monitoring each subarea by using the distributed monitoring cameras, and taking a subarea as a target subarea when the monitoring cameras sense that abnormal personnel exist in the subarea;
the monitoring picture automatic adjusting module is used for adjusting the focal length and the shooting angle of the monitoring camera of the target subarea, enabling the display of the monitoring picture of the abnormal personnel in the target subarea to be in a central amplifying state, focusing the monitoring picture on the abnormal personnel, capturing the action characteristics of the abnormal personnel, and further identifying whether the abnormal personnel has fishing behaviors according to the action characteristics;
the shouting early warning module is used for carrying out early warning on the abnormal personnel by utilizing a broadcasting shouting device of the target subarea when the abnormal personnel are identified to have fishing behaviors, and collecting facial features of the abnormal personnel;
the early warning response identification module is used for identifying whether abnormal personnel are evacuated in a set time period after the end of the shouting early warning, if the abnormal personnel are not evacuated, extracting fishing state characterization parameters and fishing risk characterization parameters from the current monitoring picture of the target subarea, and further analyzing the fishing behavior forbidden coefficients and the fishing behavior risk coefficients corresponding to the abnormal personnel according to the fishing state characterization parameters and the fishing risk characterization parameters;
the method comprises the following steps of analyzing the forbidden coefficient of the fishing behavior corresponding to the abnormal personnel:
extracting a fishing tool from the fishing state characterization parameters, and matching the fishing tool with fishing hazard factors corresponding to various fishing tools in a management information base, thereby obtaining fishing hazard factors corresponding to abnormal personnel;
extracting fishing types from the fishing state characterization parameters, and comparing the fishing types with the protected coefficients corresponding to various fishes in the management information base, thereby comparing the protected coefficients corresponding to the various fishing types in the fishing of abnormal personnel;
using expressionsAnalyzing to obtain the forbidden coefficient of fishing behavior corresponding to abnormal person +.>Wherein->A protected coefficient corresponding to the i-th fishing class, i being the number of the fishing class present in the fish caught by the abnormal person,/>N is expressed as the number of fishing species present in the fish that the abnormal person has caught, < +.>Expressed as the distribution ratio corresponding to the ith fishing class,/->The fishing hazard factor corresponding to abnormal person, x is the number of caught fish,/->Expressed as a set reference trap number;
the risk coefficient of the fishing behavior corresponding to the abnormal personnel is analyzed, which comprises the following steps:
extracting the fishing position of the abnormal person on the ship from the fishing risk characterization parameters, and acquiring the fishing deflection distance by combining the central point position of the ship;
extracting the water depth of the fishing position and the swing amplitude of the fishing ship from the fishing risk characterization parameters, and analyzing the fishing behavior risk coefficient corresponding to abnormal personnel by combining the fishing deflection distance, wherein the analysis expression is thatWherein l, A and H are respectively expressed as fishing deflection distance, swing amplitude of fishing ship, depth of water body at fishing position and +.>、/>、/>The weight factors are respectively expressed as a pre-configured safe fishing deflection distance, a safe fishing ship swing amplitude and a safe fishing position water depth, a, b and c are respectively expressed as a fishing deflection distance, a fishing ship swing amplitude and a fishing position water depth, and e is expressed as a natural constant;
the management information base is used for storing fishing hazard factors corresponding to various fishing tools, storing protected coefficients corresponding to various fishes, storing historical fishing records and storing fishing severity coefficients corresponding to various early warning levels;
the fishing road line analysis module is used for locking the occurrence time point of the fishing behavior so as to determine the fishing road line of the abnormal person entering the no-fishing water area to reach the target subarea;
the automatic fishing early warning information generation module is used for automatically generating fishing early warning information according to the fishing behavior forbidden degree coefficient, the fishing behavior risk coefficient and the fishing road line corresponding to the abnormal personnel and reporting the fishing early warning information to the forbidden water area management center.
2. The intelligent management platform with video AI-warning analysis of claim 1, wherein: the focal length of the monitoring camera for adjusting the target subarea is specifically shown in the following process:
when a monitoring camera of the target subarea senses that abnormal personnel exist, acquiring the area of a picture occupied by the abnormal personnel in a current monitoring picture, so as to obtain the display proportion of the abnormal personnel in the current monitoring picture;
acquiring the focal length of the monitoring camera corresponding to the target subarea when shooting the current monitoring picture, and recording the focal length as an original focal length;
calculating the adaptive focal length of the monitoring camera of the target subarea based on the display proportion of abnormal personnel in the current monitoring picture and the original focal length;
and adjusting the focal length of the monitoring camera of the target subarea according to the adaptive focal length of the monitoring camera of the target subarea.
3. The intelligent management platform with video AI-warning analysis of claim 1, wherein: the specific adjustment process of the shooting angle is as follows:
when a monitoring camera of the target subarea senses that abnormal personnel exist, marking the display position of the abnormal personnel in the current monitoring picture, and acquiring the distance between the display position of the abnormal personnel and the center point of the monitoring picture, and marking the distance as the display offset distance of the abnormal personnel;
a plane rectangular coordinate system is built by taking the central point of the current monitoring picture as an origin, the current monitoring picture is divided into four quadrant areas on the x axis and the y axis in the plane coordinate system, at the moment, the display position of an abnormal person and the central point of the current monitoring picture are connected to form a connecting line, and then the quadrant angle corresponding to the connecting line is obtained as the display azimuth angle of the abnormal person;
acquiring a shooting angle of a monitoring camera corresponding to a target subarea when shooting a current monitoring picture, and recording the shooting angle as an original shooting angle;
determining a shooting angle waiting direction of the monitoring camera corresponding to the target subarea according to the display azimuth angle of the abnormal person;
determining a required shooting angle of the monitoring camera corresponding to the target subarea according to the display offset distance of the abnormal person;
and the shooting angle of the control target subarea corresponding to the monitoring camera is adjusted from the direction to be adjusted to the required shooting angle.
4. The intelligent management platform with video AI-warning analysis of claim 1, wherein: the specific implementation process of the fishing forbidden early warning to the abnormal personnel by using the broadcasting megaphone of the target subarea is as follows:
an infrared range finder is arranged on the broadcast megaphone, and the distance between the current position of the abnormal person and the broadcast megaphone is measured by the infrared range finder and is used as an early warning distance;
matching the pre-warning distance with the preset demand shouting volume corresponding to various pre-warning distances, and matching the demand shouting volume of the broadcasting shouting device for abnormal personnel;
and adjusting the shouting volume of the broadcasting shouting device to enable the broadcasting shouting device to meet the requirement of the shouting volume.
5. The intelligent management platform with video AI-warning analysis of claim 1, wherein: the fishing state characterization parameters comprise the number of caught fish, fishing tools, fishing types and the distribution proportion of the fishing types, and the fishing risk characterization parameters comprise the water depth of the fishing position, the swing amplitude of the fishing ship and the fishing position of abnormal personnel on the ship.
6. The intelligent management platform with video AI-warning analysis of claim 1, wherein: the fishing path line for determining that the abnormal personnel enter the no-catch water area to reach the target subarea is defined as the following process:
extracting monitoring pictures of other subareas except the target subarea forwards from the occurrence time point of the fishing behavior according to a set time interval, identifying abnormal personnel on the monitoring pictures, and recording the corresponding other subareas as an access area and recording the corresponding time as an access time when identifying the abnormal personnel in the other subareas at a certain time;
and arranging the screened access areas according to the sequence from first to last of the access time, wherein the arrangement result is a fishing path of an abnormal person entering the no-fishing water area to reach the target subarea.
7. The intelligent management platform with video AI-warning analysis of claim 1, wherein: the fishing early warning information comprises a target subarea position, a fishing short video, a fishing road line, a fishing early warning grade and whether a life-saving tool needs to be carried.
8. The intelligent management platform with video AI-alert analysis of claim 7, wherein: the specific generation process of the fishing early warning information is as follows:
(1) Target sub-region position: positioning target subarea position information;
(2) Short fishing video: short video recording is carried out on the fishing process of abnormal personnel by utilizing a monitoring camera of the target subarea;
(3) Fishing early warning grade: extracting historical fishing records from a management information base, further comparing facial features of abnormal persons with all the fishing persons in the historical fishing records, if the comparison is successful, extracting historical fishing information corresponding to the successfully compared fishing persons from the historical fishing records, wherein the historical fishing information comprises historical fishing times and fishing behavior contraband coefficients corresponding to each fishing, further counting the historical fishing contraband corresponding to the abnormal persons by using the historical fishing information, if the comparison is failed, recording the historical fishing contraband corresponding to the abnormal persons as 0, and then combining the fishing behavior contraband coefficients corresponding to the abnormal persons and the fishing severity coefficients corresponding to the historical fishing contraband estimated abnormal persons, and matching the fishing severity coefficients with fishing severity coefficients corresponding to various pre-warning levels stored in the management information base to obtain the fishing pre-warning level;
(4) Whether or not it is necessary to carry a life saving tool: comparing the risk coefficient of the fishing behavior corresponding to the abnormal person with a set threshold value, if the risk coefficient of the fishing behavior corresponding to the abnormal person is larger than the set threshold value, carrying a lifesaving tool, otherwise, not carrying the lifesaving tool.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311015244.2A CN116743970B (en) | 2023-08-14 | 2023-08-14 | Intelligent management platform with video AI early warning analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311015244.2A CN116743970B (en) | 2023-08-14 | 2023-08-14 | Intelligent management platform with video AI early warning analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116743970A CN116743970A (en) | 2023-09-12 |
| CN116743970B true CN116743970B (en) | 2023-11-21 |
Family
ID=87910023
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311015244.2A Active CN116743970B (en) | 2023-08-14 | 2023-08-14 | Intelligent management platform with video AI early warning analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116743970B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117273571B (en) * | 2023-10-12 | 2024-04-02 | 江苏泓鑫科技有限公司 | Intelligent port operation data management system and method based on blockchain |
| CN117079428A (en) * | 2023-10-16 | 2023-11-17 | 合肥航谱时代科技有限公司 | Regional early warning system for monitoring leakage of dangerous chemical gas in factory |
| CN117579993B (en) * | 2024-01-16 | 2024-03-22 | 石家庄学院 | Digital fence safety management system based on big data |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010250775A (en) * | 2009-04-20 | 2010-11-04 | Takenaka Komuten Co Ltd | Crime prevention device and program |
| CN107330803A (en) * | 2017-06-23 | 2017-11-07 | 中船重工鹏力（南京）大气海洋信息系统有限公司 | It is a kind of based on the illegal behavior method of discrimination fished for of multifunction radar ship |
| CN110166741A (en) * | 2019-04-15 | 2019-08-23 | 深圳壹账通智能科技有限公司 | Environment control method, device, equipment and storage medium based on artificial intelligence |
| CN210691345U (en) * | 2019-11-01 | 2020-06-05 | 武汉星形线科技有限公司 | Cloud intelligence safety inspection auxiliary system based on degree of depth learning |
| CN111823240A (en) * | 2019-05-27 | 2020-10-27 | 广东小天才科技有限公司 | Face tracking robot, method, device and storage medium |
| WO2021159604A1 (en) * | 2020-02-12 | 2021-08-19 | 中车唐山机车车辆有限公司 | Monitoring system, monitoring method, and monitoring device for railway train |
| CN113554319A (en) * | 2021-07-27 | 2021-10-26 | 中创智维科技有限公司 | Comprehensive safety risk evaluation system and method |
| CN113936029A (en) * | 2021-11-10 | 2022-01-14 | 上海鹰觉科技有限公司 | Video-based illegal fishing automatic detection method and system |
| WO2022045117A1 (en) * | 2020-08-25 | 2022-03-03 | 日本電気株式会社 | Failure prediction system, failure prediction device, and failure prediction method |
| CN114821947A (en) * | 2021-06-09 | 2022-07-29 | 南京品傲光电科技有限公司 | Automatic fire alarm system in petrochemical tank district |
| CN114973155A (en) * | 2022-08-01 | 2022-08-30 | 鹰驾科技（深圳）有限公司 | Intelligent monitoring, analyzing and managing system based on AI image recognition behaviors |
| CN115399961A (en) * | 2022-08-08 | 2022-11-29 | 浙江大华技术股份有限公司 | Isolation detection cabin and detection method |
| CN115700817A (en) * | 2022-10-20 | 2023-02-07 | 华南师范大学 | Fishery safety monitoring method and metas based on artificial intelligence and digital twin |
| CN115984767A (en) * | 2022-12-13 | 2023-04-18 | 南通市亿控自动化系统有限公司 | Abnormity early warning method and system based on real-time analysis of monitoring picture |
| CN116416579A (en) * | 2023-06-12 | 2023-07-11 | 广东德燊科技有限公司 | Intelligent analysis management system for park security monitoring storage information |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI371689B (en) * | 2008-02-22 | 2012-09-01 | Ind Tech Res Inst | Smart endpoint and smart monitoring system having the same |
| JP2017107512A (en) * | 2015-12-11 | 2017-06-15 | 富士通株式会社 | Risk calculation method, risk calculation program and risk calculation device |
-
2023
- 2023-08-14 CN CN202311015244.2A patent/CN116743970B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010250775A (en) * | 2009-04-20 | 2010-11-04 | Takenaka Komuten Co Ltd | Crime prevention device and program |
| CN107330803A (en) * | 2017-06-23 | 2017-11-07 | 中船重工鹏力（南京）大气海洋信息系统有限公司 | It is a kind of based on the illegal behavior method of discrimination fished for of multifunction radar ship |
| CN110166741A (en) * | 2019-04-15 | 2019-08-23 | 深圳壹账通智能科技有限公司 | Environment control method, device, equipment and storage medium based on artificial intelligence |
| CN111823240A (en) * | 2019-05-27 | 2020-10-27 | 广东小天才科技有限公司 | Face tracking robot, method, device and storage medium |
| CN210691345U (en) * | 2019-11-01 | 2020-06-05 | 武汉星形线科技有限公司 | Cloud intelligence safety inspection auxiliary system based on degree of depth learning |
| WO2021159604A1 (en) * | 2020-02-12 | 2021-08-19 | 中车唐山机车车辆有限公司 | Monitoring system, monitoring method, and monitoring device for railway train |
| WO2022045117A1 (en) * | 2020-08-25 | 2022-03-03 | 日本電気株式会社 | Failure prediction system, failure prediction device, and failure prediction method |
| CN114821947A (en) * | 2021-06-09 | 2022-07-29 | 南京品傲光电科技有限公司 | Automatic fire alarm system in petrochemical tank district |
| CN113554319A (en) * | 2021-07-27 | 2021-10-26 | 中创智维科技有限公司 | Comprehensive safety risk evaluation system and method |
| CN113936029A (en) * | 2021-11-10 | 2022-01-14 | 上海鹰觉科技有限公司 | Video-based illegal fishing automatic detection method and system |
| CN114973155A (en) * | 2022-08-01 | 2022-08-30 | 鹰驾科技（深圳）有限公司 | Intelligent monitoring, analyzing and managing system based on AI image recognition behaviors |
| CN115399961A (en) * | 2022-08-08 | 2022-11-29 | 浙江大华技术股份有限公司 | Isolation detection cabin and detection method |
| CN115700817A (en) * | 2022-10-20 | 2023-02-07 | 华南师范大学 | Fishery safety monitoring method and metas based on artificial intelligence and digital twin |
| CN115984767A (en) * | 2022-12-13 | 2023-04-18 | 南通市亿控自动化系统有限公司 | Abnormity early warning method and system based on real-time analysis of monitoring picture |
| CN116416579A (en) * | 2023-06-12 | 2023-07-11 | 广东德燊科技有限公司 | Intelligent analysis management system for park security monitoring storage information |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116743970A (en) | 2023-09-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116743970B (en) | Intelligent management platform with video AI early warning analysis | |
| CN106341661B (en) | Patrol robot | |
| JP4569190B2 (en) | Suspicious person countermeasure system and suspicious person detection device | |
| CN108802758A (en) | A kind of Intelligent security monitoring device, method and system based on laser radar | |
| CN110097787A (en) | A kind of ship collision warning monitoring system and method based on monitoring navigation light | |
| CN112462774A (en) | Urban road supervision method and system based on unmanned aerial vehicle navigation following and readable storage medium | |
| CN113011833A (en) | Safety management method and device for construction site, computer equipment and storage medium | |
| JP2011123742A (en) | Intruding object detector | |
| CN113591540B (en) | Method and system for monitoring and early warning illegal fishing in fishery | |
| CN111461078A (en) | Anti-fishing monitoring method based on computer vision technology | |
| KR101454644B1 (en) | Loitering Detection Using a Pedestrian Tracker | |
| WO2021208314A1 (en) | Marine sea area informatization supervision system | |
| CN114419537A (en) | Power transmission line warning method and device based on deep learning | |
| CN116994389A (en) | Monitoring alarm driving system and method based on artificial intelligence and image recognition | |
| CN116453276A (en) | Marine wind power electronic fence monitoring and early warning method and system | |
| CN114220069A (en) | Object monitoring method, electronic device and computer-readable storage medium | |
| CN116740874A (en) | Intrusion detection method and related device | |
| CN114612771A (en) | Fire source monitoring method and system based on neural network | |
| CN111223335B (en) | Ship superelevation early warning method, device and system | |
| CN113076797A (en) | Charging station electric vehicle fire alarm method and system based on intelligent video identification | |
| JP2022081882A (en) | Wild animal monitoring system, wild animal monitoring method, and program | |
| CN112949502B (en) | Method, system and electronic device for detecting swimming pool safety officer looking around | |
| CN113963502B (en) | All-weather illegal behavior automatic inspection method and system | |
| Hubner et al. | Audio-video sensor fusion for the detection of security critical events in public spaces | |
| CN115019463B (en) | Water area supervision system based on artificial intelligence technology |
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 |