CN113807212A - Well lid anti-theft method and device based on image recognition - Google Patents
Well lid anti-theft method and device based on image recognition Download PDFInfo
- Publication number
- CN113807212A CN113807212A CN202111010290.4A CN202111010290A CN113807212A CN 113807212 A CN113807212 A CN 113807212A CN 202111010290 A CN202111010290 A CN 202111010290A CN 113807212 A CN113807212 A CN 113807212A
- Authority
- CN
- China
- Prior art keywords
- information
- obtaining
- well lid
- feature
- action set
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
- G01L5/00—Apparatus for, or methods of, measuring force, work, mechanical power, or torque, specially adapted for specific purposes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/44—Program or device authentication
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computer Security & Cryptography (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Hardware Design (AREA)
- Software Systems (AREA)
- Alarm Systems (AREA)
Abstract
The application discloses a well lid anti-theft method and device based on image recognition, wherein the method comprises the following steps: acquiring first image information by acquiring images according to the miniature intelligent camera; performing behavior characteristic analysis on the first image information to obtain a first real-time characteristic action set; acquiring first similarity information according to the first real-time characteristic action set and the first historical characteristic action set; acquiring stress data of a first sub well cover according to the first sensor to obtain first stress information; inputting the first similarity information and the first stress information into an early warning evaluation model, and obtaining a first risk coefficient according to the early warning evaluation model; and obtaining first alarm information according to the first risk coefficient. The effect of theftproof can be played after having reached to current ordinary well lid transformation to intelligent monitoring well lid process of uncapping, in case the unusual early warning that sends immediately of appearance reminds, thereby reduce the technological effect of well lid theftproof cost.
Description
Technical Field
The application relates to the field of artificial intelligence, in particular to a well lid anti-theft method and device based on image recognition.
Background
Generally, underground drainage channels and underground pipeline channels are provided with inspection wells, inspection well covers are installed at inlet openings of the inspection wells, and the inspection well covers arranged on urban roads and sidewalks are subjected to a large amount of rolling, so that most of the inspection well covers are made of rolling-resistant cast iron. However, the manhole cover made of cast iron is often stolen after being installed and used, and serious potential safety hazards are brought to the passing of vehicles and pedestrians. The theftproof well lid prevents mainly that the thief steals the well lid, avoids the pedestrian to meet an emergency.
In the process of implementing the technical solution in the embodiment of the present application, the inventor of the present application finds that the above-mentioned technology has at least the following technical problems:
the existing anti-theft well lid in the prior art can not be used by transforming the existing common well lid, the redesign and casting of the anti-theft well lid lead to too large cost, the existing anti-theft well lid is complex in design, and the technical problem of inconvenient construction operation in the well lid exists in practical application.
Disclosure of Invention
In view of this, the embodiment of the present application provides a manhole cover anti-theft method and device based on image recognition, where the method includes: acquiring first image information by acquiring images according to the miniature intelligent camera; performing behavior characteristic analysis on the first image information to obtain a first real-time characteristic action set; acquiring first similarity information according to the first real-time characteristic action set and the first historical characteristic action set; acquiring stress data of a first sub well cover according to the first sensor to obtain first stress information; inputting the first similarity information and the first stress information into an early warning evaluation model, and obtaining a first risk coefficient according to the early warning evaluation model; and obtaining first alarm information according to the first risk coefficient. . The anti-theft well lid solves the technical problems that the existing common well lid cannot be transformed and used, the existing anti-theft well lid is redesigned and cast, so that the cost is too large, the existing anti-theft well lid is complex in design, and the construction operation in the well lid is inconvenient in practical application. The effect of theftproof can be played after having reached to current ordinary well lid transformation to intelligent monitoring well lid process of uncapping, in case the unusual early warning that sends immediately of appearance reminds, thereby reduce the technological effect of well lid theftproof cost.
In view of the above problems, the embodiments of the present application provide a manhole cover anti-theft method and device based on image recognition.
In a first aspect, the present application provides an image recognition-based manhole cover anti-theft method, which is implemented by an image recognition-based manhole cover anti-theft device, wherein the method includes: acquiring first image information by acquiring images according to the miniature intelligent camera; performing behavior characteristic analysis on the first image information to obtain a first real-time characteristic action set; acquiring first similarity information according to the first real-time characteristic action set and the first historical characteristic action set; acquiring stress data of a first sub well cover according to the first sensor to obtain first stress information; inputting the first similarity information and the first stress information into an early warning evaluation model, and obtaining a first risk coefficient according to the early warning evaluation model; and obtaining first alarm information according to the first risk coefficient.
In another aspect, the present application further provides an image recognition-based manhole cover anti-theft device for performing the image recognition-based manhole cover anti-theft method according to the first aspect, wherein the device includes: a first obtaining unit: the first obtaining unit is used for carrying out image acquisition according to the miniature intelligent camera to obtain first image information; a second obtaining unit: the second obtaining unit is used for obtaining a first real-time characteristic action set by performing behavior characteristic analysis on the first image information; a third obtaining unit: the third obtaining unit is used for obtaining first similarity information according to the first real-time characteristic action set and the first historical characteristic action set; a fourth obtaining unit: the fourth obtaining unit is used for obtaining first stress information according to stress data of the first sub well lid collected by the first sensor; a fifth obtaining unit: the fifth obtaining unit is used for inputting the first similarity information and the first stress information into an early warning evaluation model, and obtaining a first risk coefficient according to the early warning evaluation model; a sixth obtaining unit: the sixth obtaining unit is used for obtaining first alarm information according to the first risk coefficient.
In a third aspect, an embodiment of the present application further provides an image recognition-based manhole cover anti-theft device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the steps of the method according to the first aspect when executing the program.
One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:
1. acquiring first image information by acquiring images according to the miniature intelligent camera; performing behavior characteristic analysis on the first image information to obtain a first real-time characteristic action set; acquiring first similarity information according to the first real-time characteristic action set and the first historical characteristic action set; acquiring stress data of a first sub well cover according to the first sensor to obtain first stress information; inputting the first similarity information and the first stress information into an early warning evaluation model, and obtaining a first risk coefficient according to the early warning evaluation model; and obtaining first alarm information according to the first risk coefficient. The effect of theftproof can be played after having reached to current ordinary well lid transformation to intelligent monitoring well lid process of uncapping, in case the unusual early warning that sends immediately of appearance reminds, thereby reduce the technological effect of well lid theftproof cost.
2. Theftproof well lid includes the female well lid of outside and inside sub-well lid, and interior well lid is equipped with the sensor, and when the well lid was opened to female well, the sensor can detect operating personnel sign information, links the camera promptly in case the discovery is unusual and records a video, records operating personnel characteristics. The technical effect of tracking and analyzing corresponding operators is achieved.
3. When the female well lid of theftproof well lid left corresponding sub-well lid, the gag lever post that sub-well lid was equipped with will be locked immediately, and the outside needs the mandate just can further open sub-well lid this moment, has reached the technological effect that prevents the secondary and steal, and the while gag lever post locking can effectively prevent female well lid from losing the accident that causes the personnel to fall into in the well.
The foregoing description is only an overview of the technical solutions of the present application, and the present application can be implemented according to the content of the description in order to make the technical means of the present application more clearly understood, and the following detailed description of the present application is given in order to make the above and other objects, features, and advantages of the present application more clearly understandable.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only exemplary, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a schematic flow chart of a manhole cover anti-theft method based on image recognition according to an embodiment of the present application;
fig. 2 is a schematic flow chart illustrating the process of obtaining first image information in the manhole cover anti-theft method based on image recognition according to the embodiment of the present application;
fig. 3 is a schematic flow chart illustrating obtaining of first similarity information in a manhole cover anti-theft method based on image recognition according to an embodiment of the present application;
fig. 4 is a schematic flowchart of a process of obtaining first stress information in a manhole cover anti-theft method based on image recognition according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of a top view of a manhole cover anti-theft device based on image recognition according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of a left side view of a manhole cover anti-theft device based on image recognition according to an embodiment of the present application;
fig. 7 is a schematic structural diagram of a bottom view of a manhole cover anti-theft device based on image recognition according to an embodiment of the present application;
fig. 8 is a schematic structural diagram of a manhole cover anti-theft device based on image recognition according to an embodiment of the present application;
fig. 9 is a schematic structural diagram of an exemplary electronic device according to an embodiment of the present application.
Description of reference numerals:
interior well lid body 1, camera hidden hole 2, infrared sensor 3, hydraulic pump (flee for one's life) 4, mechanical handle 5, mechanical lock body 6, triaxial locking lever 7, thing allies oneself with gateway 8, large capacity lithium cell 9, flexible gag lever post 10, intelligent lockhole 11, first acquisition unit 11, second acquisition unit 12, third acquisition unit 13, fourth acquisition unit 14, fifth acquisition unit 15, sixth acquisition unit 16, bus 300, receiver 301, treater 302, send ware 303, memory 304, bus interface 305.
Detailed Description
The embodiment of the application provides a well lid anti-theft method and device based on image recognition, and solves the technical problems that an existing common well lid cannot be transformed and used by an anti-theft well lid in the prior art, the cost is too high due to redesign and casting of the anti-theft well lid, the existing anti-theft well lid is complex in design, and construction operation in the well lid is inconvenient in practical application. The effect of theftproof can be played after having reached to current ordinary well lid transformation to intelligent monitoring well lid process of uncapping, in case the unusual early warning that sends immediately of appearance reminds, thereby reduce the technological effect of well lid theftproof cost.
In the following, the technical solutions in the embodiments of the present application will be clearly and completely described with reference to the accompanying drawings, and it is to be understood that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present application without making any creative effort, shall fall within the protection scope of the present application. It should be further noted that, for the convenience of description, only some but not all of the elements relevant to the present application are shown in the drawings.
Summary of the application
Generally, underground drainage channels and underground pipeline channels are provided with inspection wells, inspection well covers are installed at inlet openings of the inspection wells, and the inspection well covers arranged on urban roads and sidewalks are subjected to a large amount of rolling, so that most of the inspection well covers are made of rolling-resistant cast iron. However, the manhole cover made of cast iron is often stolen after being installed and used, and serious potential safety hazards are brought to the passing of vehicles and pedestrians. The theftproof well lid prevents mainly that the thief steals the well lid, avoids the pedestrian to meet an emergency.
The existing anti-theft well lid in the prior art can not be used by transforming the existing common well lid, the redesign and casting of the anti-theft well lid lead to too large cost, the existing anti-theft well lid is complex in design, and the technical problem of inconvenient construction operation in the well lid exists in practical application.
In view of the above technical problems, the technical solution provided by the present application has the following general idea:
the application provides a well lid anti-theft method based on image recognition, which is applied to a well lid anti-theft device based on image recognition, wherein the method comprises the following steps: acquiring first image information by acquiring images according to the miniature intelligent camera; performing behavior characteristic analysis on the first image information to obtain a first real-time characteristic action set; acquiring first similarity information according to the first real-time characteristic action set and the first historical characteristic action set; acquiring stress data of a first sub well cover according to the first sensor to obtain first stress information; inputting the first similarity information and the first stress information into an early warning evaluation model, and obtaining a first risk coefficient according to the early warning evaluation model; and obtaining first alarm information according to the first risk coefficient.
Having thus described the general principles of the present application, various non-limiting embodiments thereof will now be described in detail with reference to the accompanying drawings.
Example one
Referring to fig. 1, an embodiment of the present application provides a manhole cover anti-theft method based on image recognition, where the method is applied to a manhole cover anti-theft device based on image recognition, the device is in communication connection with a micro intelligent camera and a first sensor, and the method specifically includes the following steps:
step S100: acquiring an image according to the miniature intelligent camera to obtain first image information;
specifically, the well lid anti-theft method based on image recognition is that well lid operation personnel operation process data are recorded through an intelligent camera, a sensor and the like, information such as operation characteristics of the operation personnel is analyzed through the recorded operation image data, risk assessment is carried out on the well lid operation at the time, and corresponding reminding is sent out to prevent the well lid from being stolen. The well lid anti-theft device based on image recognition means the well lid in communication connection with the miniature intelligent camera and the first sensor, wherein the well lid is provided with an external female well lid and an internal sub-well lid. The miniature intelligent camera is hidden on the inner well cover of the well cover, can monitor the operation flow of well cover operators at multiple angles and multiple distances, and simultaneously records information such as images and videos related to operation, namely the first image information. Through recording information such as the operation flow of the well lid operator, the technical effect of recording the relevant personal information of the operator is achieved.
Step S200: performing behavior characteristic analysis on the first image information to obtain a first real-time characteristic action set;
specifically, the cover opening process of the well lid operator is recorded through the micro intelligent camera, and further, each action in the cover opening process of the operator is analyzed to obtain a behavior characteristic analysis result of the first image information, namely the first real-time characteristic action set. Through analyzing the uncapping action of the operator, the continuous action characteristic set of the well lid operator is obtained.
Step S300: acquiring first similarity information according to the first real-time characteristic action set and the first historical characteristic action set;
specifically, the first historical characteristic action set is an action characteristic set in a series of operation processes from the opening of the manhole cover by a stealer to the stealing of the manhole cover in a historical case that the manhole cover is stolen based on big data. And analyzing the current uncapping action characteristic according to the first historical characteristic action set, and judging the similarity of the action characteristic of an operator in the current uncapping operation flow and the operation flow when the historical well lid is stolen to obtain the first similarity information. Through the operation when current operation of uncapping and historical well lid are stolen of contrast, obtain the similarity information of two operations, through the similarity information of two operations promptly, obtain the possibility that current operation is for stealing the well lid operation, reached and made preliminary judgement's technological effect to the stolen risk of well lid under the current operation of uncapping.
Step S400: acquiring stress data of a first sub well cover according to the first sensor to obtain first stress information;
particularly, the theftproof well lid is including outside female well lid and inside sub-well lid. The first sensor with well lid anti-theft device communication connection based on image recognition, install in on the interior well lid of theftproof well lid. The first sensor is used for collecting force data of the well lid when an operator opens the cover, namely the stress data of the well lid, and based on the first sensor, stress information of the well lid during corresponding cover opening operation is obtained, namely the first stress information. By acquiring the stress process information of the well lid in the opening process of an operator, the technical effect of determining the well opening force application information is achieved.
Step S500: inputting the first similarity information and the first stress information into an early warning evaluation model, and obtaining a first risk coefficient according to the early warning evaluation model;
step S600: and obtaining first alarm information according to the first risk coefficient.
Specifically, the early warning evaluation model is used for evaluating the risk coefficient of the whole uncovering process of the current uncovering operator, and the risk coefficient of the stolen well lid caused by the current operation can be estimated based on the similarity degree of the uncovering operation of the current operator and the operation of the stolen historical well lid and the force application condition of the well lid in the uncovering operation of the current operator, so that the first risk coefficient is obtained. Based on the first risk coefficient, the system automatically sends out corresponding reminding information, namely the first early warning information to remind related personnel of taking precautions. Through the current risk of uncapping of intelligent aassessment, reached intelligent monitoring well lid process of uncapping, send early warning information's technological effect when the process of uncapping appears unusually, intelligent control and early warning have reduced the degree of difficulty of manpower supervision well lid, prevent that the well lid is stolen simultaneously.
Further, the manhole cover anti-theft device based on image recognition further includes a second sensor, as shown in fig. 2, step S100 in this embodiment of the present application further includes:
step S110: acquiring first real-time detection data according to the second sensor;
step S120: judging whether the first sub-well cover is in a first abnormal state or not according to the first real-time detection data;
step S130: when the first sub-well cover is in the first abnormal state, obtaining a first recording instruction;
step S140: the miniature intelligent camera carries out video recording according to the first recording instruction to obtain the first image information;
step S150: performing personnel feature analysis according to the first image information to obtain a first personnel feature;
step S160: storing the first person characteristic into the first alert information.
Specifically, the second sensor is an infrared sensor, is installed on the first sub-well lid, and is used for monitoring the stress condition of the first sub-well lid in real time, so as to obtain the first real-time detection data. Further, whether the current state of the first sub well lid is abnormal or not is judged based on the first real-time detection data, when the first sub well lid is in the first abnormal state, the stress condition of the first sub well lid is recorded, and the first recording instruction is obtained, wherein the first abnormal state refers to whether a mother well lid exists or not except the sub well lid of the current well lid, and if the mother well lid is stolen, the state of the corresponding sub well lid is the abnormal state. That is, the well lid in the normal state includes the female well lid and the sub well lid. And judging whether the current state of the sub well lid is abnormal or not based on the second sensor, and sending a corresponding recording instruction once the current state of the sub well lid is abnormal.
Furthermore, when the state of the sub-well lid is abnormal, the system sends out a corresponding instruction to record and store the video of the current well lid opening process, the opening process is recorded and recorded by the miniature intelligent camera according to the first recording instruction, and the first image information is recorded and obtained. And performing personnel characteristic analysis on the well lid opening operator in the first image information to obtain the characteristic information of the current well lid opening operator, wherein the characteristic information comprises related information such as sex, age, facial form, skin color, clothing and the like, namely the first personnel characteristic. And finally, storing the first person characteristic into the first alarm information for early warning and reminding.
The state of the sub well lid is monitored through the sensor, the system automatically starts to record an instruction once the state of the sub well lid is abnormal, the current nearby condition of the well lid is recorded through the camera, and the operation process comprises the operation process of a well lid opening operator. The technical effects of automatically monitoring the well lid and recording the operation process of an operator and the relevant information of the operator are achieved.
Further, step S120 in the embodiment of the present application further includes:
step S121: when the first sub-well cover is in the first abnormal state, a first safety protection mechanism is started, wherein the first safety protection mechanism comprises a locking protection mechanism and an authorization protection mechanism;
step S122: locking the limiting rod of the first sub well cover according to the locking protection mechanism;
step S123: obtaining a first unlocking instruction according to a first unlocking user;
step S124: judging whether the authorization authentication of the first unlocking instruction passes according to the authorization protection mechanism;
step S125: and when the authorization authentication of the first unlocking instruction is not passed, obtaining second alarm information.
Specifically, the first safety protection mechanism comprises a locking protection mechanism and an authorization protection mechanism, wherein the locking protection mechanism is arranged on the first sub-well cover and used for locking a limiting rod of the first sub-well cover, so that vehicles and pedestrians are prevented from accidentally falling into the well due to the fact that the vehicles and the pedestrians cannot observe the well cover in time; the authorization protection mechanism is intelligently controlled by the system, an operator needs to obtain a corresponding authorization party to open the manhole cover, otherwise, the manhole cover cannot be opened by destroying due to the fact that the mechanical lock body is not arranged outside the manhole cover. When the main well cover corresponding to the first sub well cover is lost, namely is in the first abnormal state, the system starts a first safety protection mechanism, namely the locking protection mechanism and the authorization protection mechanism. And according to the locking protection mechanism, the system automatically locks the limiting rod of the first sub-well cover. Further, an operator needs to perform authorization verification, that is, the first unlocking user needs to perform verification according to the corresponding first unlocking instruction, and the authorization protection mechanism determines whether the authorization authentication of the first unlocking instruction passes. When the authorization authentication of the first unlocking instruction is not passed, it is indicated that the first unlocking user does not obtain corresponding authorization currently, and the first unlocking user may be a thief, and the system sends corresponding reminding information, namely, the second alarm information reminds a related responsible person to take precautions.
When the system monitors that the state of the sub-well cover is abnormal, the limiting rod is locked through a locking protection mechanism, corresponding operators need to be verified further, namely whether the first unlocking person has the cover opening authorization or not is judged, the operation can be further performed if the verification is successful, the next operation cannot be performed if the verification is unsuccessful, and meanwhile system alarm information is triggered. The dual protection mechanism has reached perfect protective effect, when guaranteeing to possess the normal maintenance personal of mandate and continuing the operation, prevents not obtaining the further operation of authorized other personnel, and the gag lever post can prevent that pedestrian, vehicle accident from falling into in the well simultaneously.
Further, as shown in fig. 3, step S300 of the embodiment of the present application further includes:
step S310: obtaining first environment information of the first sub well cover;
step S320: constructing a first video information base according to the first environment information;
step S330: extracting actions of all video information in the first video information base to obtain a characteristic action set corresponding to each video;
step S340: generating a first coincidence characteristic action set by performing coincidence characteristic analysis on the characteristic action set corresponding to each video;
step S350: and taking the first coincident feature action set as the first historical feature action set.
Particularly, according to the operating personnel well lid operation process that intelligence miniature camera head recorded, obtain the environmental aspect around the current well lid, promptly first environmental information of first sub-well lid. And constructing a video information library of a corresponding environment based on the environment condition around the current well lid, wherein the first video information library comprises other well lid opening video information similar to the environment near the current well lid. And extracting the actions of all the well lid opening video information in the first video information library to obtain a well lid opening characteristic action set corresponding to each video. Through analyzing the characteristic action set corresponding to each well lid opening video, other opening videos with high similarity to the current well lid opening action can be obtained, and the first coincidence characteristic action set can be generated. Further, the first set of coincident feature actions is taken as the first set of historical feature actions. Through big data analysis, video information of historical similar uncapping processes of the well lid in the same environment is obtained, and the target range is narrowed for finding the uncapping action video with the highest similarity in the later period.
Further, as shown in fig. 3, step S300 of the embodiment of the present application further includes:
step S360: constructing a plurality of grading information according to the first contact ratio;
step S370: carrying out hierarchical division on the first historical feature action set according to the plurality of hierarchical information to generate a first feature comparison tree;
step S380: inputting the first real-time feature action set into the first feature comparison tree for traversing to obtain a first feature traversal result;
step S390: and obtaining the first similarity information according to the first feature traversal result.
Specifically, the first coincidence degree refers to the coincidence degree of the current manhole cover uncovering process action and the historical uncovering action. And constructing a plurality of similarity grading information according to the first contact ratio, and further performing grading division on the first historical feature action set according to the grading information to generate a first feature comparison tree. Inputting each action in the current well lid opening process, namely inputting the first real-time characteristic action set into the first characteristic comparison tree for traversing, so as to obtain a corresponding first characteristic traversal result, and obtaining the first similarity information according to the first characteristic traversal result, wherein the first similarity information comprises the similarity information of the current well lid opening process and each historical opening video. And obtaining each similarity result through feature traversal, and providing reference for further analyzing the current uncapping action.
Further, step S390 in the embodiment of the present application further includes:
step S391: obtaining a multi-level feature traversal result according to the first feature traversal result;
step S392: obtaining first proportion information according to the multi-level feature traversal result and the plurality of grading information;
step S393: obtaining the mean value similarity of each level according to the multi-level feature traversal result;
step S394: and performing similarity calculation according to the first ratio information and the mean similarity of each level to obtain the first similarity information.
Specifically, according to the first feature traversal result, a multi-level feature traversal result of each action in the current well lid opening process and each action feature in the historical opening process can be obtained. The action with high contact ratio is used as a first grading characteristic, the action with general contact ratio is used as a second grading characteristic, and the action with low contact ratio is used as a third grading characteristic. And obtaining first proportion information according to the multi-level feature traversal result and the plurality of grading information. Wherein, the proportion information refers to a weight coefficient obtained based on the similarity condition of each level. And obtaining the average similarity degree of the actions of each level according to the multi-level feature traversal result, namely the average similarity degree. And performing similarity calculation according to the first proportion information and the mean similarity of each level, and obtaining similarity information of each action in the current well lid opening process and each action characteristic in the historical opening process, namely the first similarity information. And obtaining the historical uncapping action with the highest similarity to the current uncapping action through further comparison and calculation.
Further, as shown in fig. 4, step S400 in the embodiment of the present application further includes:
step S410: constructing a first stress trend graph according to the stress data of the first sub well cover;
step S420: performing inflection point extraction according to the first stress trend graph to obtain a first inflection point coordinate set;
step S430: obtaining first slope data by performing slope calculation on the inflection point coordinates in the first inflection point coordinate set;
step S440: and taking the first slope data as the first stress information.
Specifically, according to the stress data information of the first sub-well lid, the stress process of the first sub-well lid can be obtained, and the first stress trend graph can be constructed. And extracting inflection points in the trend chart according to the first stress trend chart, obtaining coordinates of all the inflection points in the trend chart, and forming a first inflection point coordinate set. Slope calculation is performed on the inflection point coordinates in the first inflection point coordinate set, so that the slope at each inflection point, that is, the first slope data, can be obtained. Analyzing the first slope data as the first stress information. By analyzing the stress information of the sub-well cover and using an intelligent model to evaluate the stress information, the technical effect of possibility of stealing the well cover is achieved.
In summary, the embodiments of the present application provide the following technical effects:
1. acquiring first image information by acquiring images according to the miniature intelligent camera; performing behavior characteristic analysis on the first image information to obtain a first real-time characteristic action set; acquiring first similarity information according to the first real-time characteristic action set and the first historical characteristic action set; acquiring stress data of a first sub well cover according to the first sensor to obtain first stress information; inputting the first similarity information and the first stress information into an early warning evaluation model, and obtaining a first risk coefficient according to the early warning evaluation model; and obtaining first alarm information according to the first risk coefficient. The effect of theftproof can be played after having reached to current ordinary well lid transformation to intelligent monitoring well lid process of uncapping, in case the unusual early warning that sends immediately of appearance reminds, thereby reduce the technological effect of well lid theftproof cost.
2. Theftproof well lid includes the female well lid of outside and inside sub-well lid, and interior well lid is equipped with the sensor, and when the well lid was opened to female well, the sensor can detect operating personnel sign information, links the camera promptly in case the discovery is unusual and records a video, records operating personnel characteristics. The technical effect of tracking and analyzing corresponding operators is achieved.
3. When the female well lid of theftproof well lid left corresponding sub-well lid, the gag lever post that sub-well lid was equipped with will be locked immediately, and the outside needs the mandate just can further open sub-well lid this moment, has reached the technological effect that prevents the secondary and steal, and the while gag lever post locking can effectively prevent female well lid from losing the accident that causes the personnel to fall into in the well.
Example two
Based on the invention concept of the well lid anti-theft method based on the image recognition in the foregoing embodiment, the invention also provides a well lid anti-theft device based on the image recognition, wherein the device comprises: interior well lid body 1, camera hide hole 2, infrared sensor 3, hydraulic pump (flee for one's life) 4, mechanical handle 5, mechanical lock body 6, triaxial locking lever 7, thing allies oneself with gateway 8, large capacity lithium cell 9, flexible gag lever post 10, intelligent lockhole 11.
Specifically, as shown in fig. 5, fig. 6, fig. 7, interior well lid body 1 means the inside well lid of theftproof well lid, promptly sub-well lid, be equipped with on interior well lid body 1 the camera hides hole 2, infrared sensor 3, hydraulic pump (flee) 4, mechanical handle 5, mechanical lock body 6. The intelligent miniature camera is arranged in the camera hiding hole 2 and is used for shooting image information of well lid opening operators. The infrared sensor 3 is used for monitoring the stress condition of the inner well cover body 1. When hydraulic pump (flee) 4 was used for personnel in the pit to flee, under the condition that the female well lid in top was not opened, inside personnel can't flee, and the hydraulic pump has been equipped with the pull ring, can directly upwards start to strike the bullet and open female well lid. The mechanical handle 5 and the mechanical lock body 6 are used for automatically locking the limiting rod when the infrared sensor 3 monitors that the state of the inner well lid body 1 is abnormal. The host of the internet of things gateway 8 can record and transmit video data and alarm data in real time, can record and transmit information of people who cover the cover and can record and transmit information of people who steal. The telescopic limiting rod 10 can be automatically locked when the state of the inner well cover body 1 is abnormal, and pedestrians and vehicles are prevented from accidentally falling into the well. The high-capacity lithium battery 9 can supply power to the anti-theft well cover to maintain normal operation of each device in the anti-theft well cover. The intelligent lock hole 11 is used for verifying the authorization condition of a manhole cover opening operator. The effect of theftproof can be played after having reached to current ordinary well lid transformation to intelligent monitoring well lid process of uncapping, in case the unusual early warning that sends immediately of appearance reminds, thereby reduce the technological effect of well lid theftproof cost.
EXAMPLE III
Based on the same inventive concept as the well lid anti-theft method based on image recognition in the foregoing embodiment, the present invention further provides a well lid anti-theft device based on image recognition, referring to fig. 8, where the device includes:
the first obtaining unit 11 is used for acquiring an image according to the miniature intelligent camera to obtain first image information;
a second obtaining unit 12, where the second obtaining unit 12 is configured to obtain a first real-time feature action set by performing behavior feature analysis on the first image information;
a third obtaining unit 13, where the third obtaining unit 13 is configured to obtain first similarity information according to the first real-time feature action set and the first historical feature action set;
the fourth obtaining unit 14 is configured to obtain first stress information according to the stress data of the first sub well lid collected by the first sensor by the fourth obtaining unit 14;
a fifth obtaining unit 15, where the fifth obtaining unit 15 is configured to input the first similarity information and the first stress information into an early warning evaluation model, and obtain a first risk coefficient according to the early warning evaluation model;
a sixth obtaining unit 16, where the sixth obtaining unit 16 is configured to obtain first alarm information according to the first risk coefficient.
Further, the system further comprises:
a seventh obtaining unit, configured to obtain first real-time detection data according to the second sensor;
the first judging unit is used for judging whether the first sub-well cover is in a first abnormal state or not according to the first real-time detection data;
an eighth obtaining unit, configured to obtain a first recording instruction when the first sub-well lid is in the first abnormal state;
a ninth obtaining unit, configured to record a video by the smart micro-camera according to the first recording instruction, so as to obtain the first image information;
a tenth obtaining unit, configured to perform person feature analysis according to the first image information to obtain a first person feature;
a first storage unit for storing the first person characteristic into the first alert information.
Further, the system further comprises:
a first execution unit, configured to open a first safety protection mechanism when the first sub-well lid is in the first abnormal state, where the first safety protection mechanism includes a lockout protection mechanism and an authorization protection mechanism;
the second execution unit is used for locking the limiting rod of the first sub-well cover according to the locking protection mechanism;
an eleventh obtaining unit, configured to obtain a first unlocking instruction according to a first unlocking user;
a second judging unit, configured to judge whether the authorization authentication of the first unlocking instruction passes according to the authorization protection mechanism;
and the twelfth obtaining unit is used for obtaining second alarm information when the authorization authentication of the first unlocking instruction is not passed.
Further, the system further comprises:
a thirteenth obtaining unit, configured to obtain first environment information of the first sub well lid;
the first construction unit is used for constructing a first video information base according to the first environment information;
a fourteenth obtaining unit, configured to obtain a feature action set corresponding to each video by performing action extraction on all video information in the first video information base;
the first generation unit is used for generating a first coincidence characteristic action set by performing coincidence characteristic analysis on the characteristic action set corresponding to each video;
a first setting unit configured to take the first coincidence feature action set as the first history feature action set.
Further, the system further comprises:
a second construction unit configured to construct a plurality of hierarchical information according to the first degree of coincidence;
the second generation unit is used for carrying out hierarchical division on the first historical feature action set according to the plurality of hierarchical information to generate a first feature comparison tree;
a fifteenth obtaining unit, configured to input the first real-time feature action set into the first feature comparison tree for traversal, so as to obtain a first feature traversal result;
a sixteenth obtaining unit, configured to obtain the first similarity information according to the first feature traversal result.
Further, the system further comprises:
a seventeenth obtaining unit, configured to obtain a multi-level feature traversal result according to the first feature traversal result;
an eighteenth obtaining unit, configured to obtain first ratio information according to the multi-level feature traversal result and the plurality of hierarchical information;
a nineteenth obtaining unit, configured to obtain a mean similarity of each level according to the multi-level feature traversal result;
a twentieth obtaining unit, configured to perform similarity calculation according to the first ratio information and the mean similarity of each hierarchy to obtain the first similarity information.
Further, the system further comprises:
the third construction unit is used for constructing a first stress trend graph according to the stress data of the first sub well lid;
a twenty-first obtaining unit, configured to perform inflection point extraction according to the first stress trend graph to obtain a first inflection point coordinate set;
a twenty-second obtaining unit configured to obtain first slope data by performing slope calculation on a knee coordinate in the first knee coordinate set;
a second setting unit configured to take the first slope data as the first stress information.
In the present description, each embodiment is described in a progressive manner, and the focus of the description of each embodiment is on the difference from other embodiments, the aforementioned well lid anti-theft method based on image recognition in the first embodiment of fig. 1 and the specific example are also applicable to the well lid anti-theft device based on image recognition in this embodiment, and through the foregoing detailed description of the well lid anti-theft method based on image recognition, a person skilled in the art can clearly know the well lid anti-theft device based on image recognition in this embodiment, so for the brevity of the description, detailed description is not repeated here. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Exemplary electronic device
The electronic apparatus of the embodiment of the present application is described below with reference to fig. 9.
Fig. 9 illustrates a schematic structural diagram of an electronic device according to an embodiment of the present application.
Based on the inventive concept of the image recognition-based manhole cover anti-theft method in the foregoing embodiments, the present invention further provides an image recognition-based manhole cover anti-theft device, on which a computer program is stored, and the computer program, when executed by a processor, implements the steps of any one of the foregoing image recognition-based manhole cover anti-theft methods.
Where in fig. 9 a bus architecture (represented by bus 300), bus 300 may include any number of interconnected buses and bridges, bus 300 linking together various circuits including one or more processors, represented by processor 302, and memory, represented by memory 304. The bus 300 may also link together various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. A bus interface 305 provides an interface between the bus 300 and the receiver 301 and transmitter 303. The receiver 301 and the transmitter 303 may be the same element, i.e., a transceiver, providing a means for communicating with various other apparatus over a transmission medium.
The processor 302 is responsible for managing the bus 300 and general processing, and the memory 304 may be used for storing data used by the processor 302 in performing operations.
The application provides a well lid anti-theft method based on image recognition, which is applied to a well lid anti-theft device based on image recognition, wherein the method comprises the following steps: acquiring first image information by acquiring images according to the miniature intelligent camera; performing behavior characteristic analysis on the first image information to obtain a first real-time characteristic action set; acquiring first similarity information according to the first real-time characteristic action set and the first historical characteristic action set; acquiring stress data of a first sub well cover according to the first sensor to obtain first stress information; inputting the first similarity information and the first stress information into an early warning evaluation model, and obtaining a first risk coefficient according to the early warning evaluation model; and obtaining first alarm information according to the first risk coefficient. The anti-theft well lid solves the technical problems that the existing common well lid cannot be transformed and used, the existing anti-theft well lid is redesigned and cast, so that the cost is too large, the existing anti-theft well lid is complex in design, and the construction operation in the well lid is inconvenient in practical application. The effect of theftproof can be played after having reached to current ordinary well lid transformation to intelligent monitoring well lid process of uncapping, in case the unusual early warning that sends immediately of appearance reminds, thereby reduce the technological effect of well lid theftproof cost.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, apparatus, or computer program product. Accordingly, the present application may take the form of an entirely software embodiment, an entirely hardware embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application is in the form of a computer program product that may be embodied on one or more computer-usable storage media having computer-usable program code embodied therewith. And such computer-usable storage media include, but are not limited to: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk Memory, a Compact Disc Read-Only Memory (CD-ROM), and an optical Memory.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a system for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction system which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks. While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (9)
1. An image recognition-based well lid anti-theft method is applied to an image recognition-based well lid anti-theft device which is in communication connection with a miniature intelligent camera and a first sensor, and comprises the following steps:
acquiring an image according to the miniature intelligent camera to obtain first image information;
performing behavior characteristic analysis on the first image information to obtain a first real-time characteristic action set;
acquiring first similarity information according to the first real-time characteristic action set and the first historical characteristic action set;
acquiring stress data of a first sub well cover according to the first sensor to obtain first stress information;
inputting the first similarity information and the first stress information into an early warning evaluation model, and obtaining a first risk coefficient according to the early warning evaluation model;
and obtaining first alarm information according to the first risk coefficient.
2. The method of claim 1, wherein the acquiring of the image from the miniature smart camera obtains first image information, the apparatus further comprising a second sensor, the method further comprising:
acquiring first real-time detection data according to the second sensor;
judging whether the first sub-well cover is in a first abnormal state or not according to the first real-time detection data;
when the first sub-well cover is in the first abnormal state, obtaining a first recording instruction;
the miniature intelligent camera carries out video recording according to the first recording instruction to obtain the first image information;
performing personnel feature analysis according to the first image information to obtain a first personnel feature;
storing the first person characteristic into the first alert information.
3. The method of claim 2, wherein the determining whether the first sub-wellbore lid is in a first abnormal state from the first real-time probe data further comprises:
when the first sub-well cover is in the first abnormal state, a first safety protection mechanism is started, wherein the first safety protection mechanism comprises a locking protection mechanism and an authorization protection mechanism;
locking the limiting rod of the first sub well cover according to the locking protection mechanism;
obtaining a first unlocking instruction according to a first unlocking user;
judging whether the authorization authentication of the first unlocking instruction passes according to the authorization protection mechanism;
and when the authorization authentication of the first unlocking instruction is not passed, obtaining second alarm information.
4. The method of claim 1, wherein prior to obtaining first similarity information based on the first set of real-time feature actions and the first set of historical feature actions, the method further comprises:
obtaining first environment information of the first sub well cover;
constructing a first video information base according to the first environment information;
extracting actions of all video information in the first video information base to obtain a characteristic action set corresponding to each video;
generating a first coincidence characteristic action set by performing coincidence characteristic analysis on the characteristic action set corresponding to each video;
and taking the first coincident feature action set as the first historical feature action set.
5. The method of claim 4, wherein the obtaining first similarity information is based on the first set of real-time feature actions and a first set of historical feature actions, the method further comprising:
constructing a plurality of grading information according to the first contact ratio;
carrying out hierarchical division on the first historical feature action set according to the plurality of hierarchical information to generate a first feature comparison tree;
inputting the first real-time feature action set into the first feature comparison tree for traversing to obtain a first feature traversal result;
and obtaining the first similarity information according to the first feature traversal result.
6. The method of claim 5, wherein the obtaining the first similarity information is based on the first feature traversal result, the method further comprising:
obtaining a multi-level feature traversal result according to the first feature traversal result;
obtaining first proportion information according to the multi-level feature traversal result and the plurality of grading information;
obtaining the mean value similarity of each level according to the multi-level feature traversal result;
and performing similarity calculation according to the first ratio information and the mean similarity of each level to obtain the first similarity information.
7. The method of claim 1, wherein the obtaining of the first force information is based on the first sensor collecting force data of the first sub-well lid, the method further comprising:
constructing a first stress trend graph according to the stress data of the first sub well cover;
performing inflection point extraction according to the first stress trend graph to obtain a first inflection point coordinate set;
obtaining first slope data by performing slope calculation on the inflection point coordinates in the first inflection point coordinate set;
and taking the first slope data as the first stress information.
8. An image recognition based manhole cover anti-theft device, wherein the device comprises:
a first obtaining unit: the first obtaining unit is used for carrying out image acquisition according to the miniature intelligent camera to obtain first image information;
a second obtaining unit: the second obtaining unit is used for obtaining a first real-time characteristic action set by performing behavior characteristic analysis on the first image information;
a third obtaining unit: the third obtaining unit is used for obtaining first similarity information according to the first real-time characteristic action set and the first historical characteristic action set;
a fourth obtaining unit: the fourth obtaining unit is used for obtaining first stress information according to stress data of the first sub well lid collected by the first sensor;
a fifth obtaining unit: the fifth obtaining unit is used for inputting the first similarity information and the first stress information into an early warning evaluation model, and obtaining a first risk coefficient according to the early warning evaluation model;
a sixth obtaining unit: the sixth obtaining unit is used for obtaining first alarm information according to the first risk coefficient.
9. An image recognition based manhole cover theft protection device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program implements the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111010290.4A CN113807212B (en) | 2021-08-31 | 2021-08-31 | Well lid anti-theft method and device based on image recognition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111010290.4A CN113807212B (en) | 2021-08-31 | 2021-08-31 | Well lid anti-theft method and device based on image recognition |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113807212A true CN113807212A (en) | 2021-12-17 |
CN113807212B CN113807212B (en) | 2022-06-07 |
Family
ID=78942219
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111010290.4A Active CN113807212B (en) | 2021-08-31 | 2021-08-31 | Well lid anti-theft method and device based on image recognition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113807212B (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104298353A (en) * | 2014-10-08 | 2015-01-21 | 宁波熵联信息技术有限公司 | Inverse kinematics based vehicle monitoring and burglary preventing method and system |
US20200302763A1 (en) * | 2016-03-28 | 2020-09-24 | Zhejiang Geely Holding Group Co., Ltd. | Theft prevention monitoring device and system and method |
CN112949445A (en) * | 2021-02-24 | 2021-06-11 | 中煤科工集团重庆智慧城市科技研究院有限公司 | Urban management emergency linkage system and method based on spatial relationship |
-
2021
- 2021-08-31 CN CN202111010290.4A patent/CN113807212B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104298353A (en) * | 2014-10-08 | 2015-01-21 | 宁波熵联信息技术有限公司 | Inverse kinematics based vehicle monitoring and burglary preventing method and system |
US20200302763A1 (en) * | 2016-03-28 | 2020-09-24 | Zhejiang Geely Holding Group Co., Ltd. | Theft prevention monitoring device and system and method |
CN112949445A (en) * | 2021-02-24 | 2021-06-11 | 中煤科工集团重庆智慧城市科技研究院有限公司 | Urban management emergency linkage system and method based on spatial relationship |
Non-Patent Citations (2)
Title |
---|
RICHARD BALEJA: "Measurement of Outdoor Lighting with a Focus on Watchdog Lighting System in the Area of Electric Station TR Čechy Střcd", 《2018 VII. LIGHTING CONFERENCE OF THE VISEGRAD COUNTRIES》, 18 November 2018 (2018-11-18) * |
张远文: "电动车防盗定位装置和***", 《中国新通信》, 31 December 2014 (2014-12-31) * |
Also Published As
Publication number | Publication date |
---|---|
CN113807212B (en) | 2022-06-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US7350615B2 (en) | Vehicle anti theft system, vehicle anti theft method, and computer program | |
KR20200057768A (en) | Vehicle control method and system, vehicle-mounted intelligent system, electronic device, medium | |
CN107992739A (en) | User authentication method, apparatus and system | |
Kwak et al. | Driver identification based on wavelet transform using driving patterns | |
CN111753711A (en) | Electric vehicle, control method and device thereof, electronic equipment and storage medium | |
CN108985530A (en) | Vehicle risk behavior management method and device | |
CN104900228A (en) | Suspicious door opening sound identification apparatus and identification method | |
CN103612617A (en) | Automobile anti-theft anti-robbery system | |
CN110033578A (en) | A kind of vehicle safety monitoring method and device | |
CN111126153A (en) | Safety monitoring method, system, server and storage medium based on deep learning | |
CN115604425B (en) | Iron tower vision system applied to tilling intelligent security scene | |
CN113807212B (en) | Well lid anti-theft method and device based on image recognition | |
CN106564389A (en) | Charging port anti-theft device based on electric automobile and anti-theft method thereof | |
CN112609765A (en) | Excavator safety control method and system based on facial recognition | |
CN116778657A (en) | Method and system for intelligently identifying intrusion behavior | |
Zhou et al. | Development of a camera-based driver state monitoring system for cost-effective embedded solution | |
CN115497245B (en) | Anti-theft supervision method and device, computer equipment and storage medium | |
Li et al. | Vehicle safety evaluation based on driver drowsiness and distracted and impaired driving performance using evidence theory | |
Aiordachioaie et al. | Change Detection by Feature Extraction and Processing from Time-Frequency Images | |
CN114973568B (en) | Intelligent door lock safety system linkage early warning method and device | |
CN112651275A (en) | Intelligent system for recognizing pedaling accident inducement behaviors in intensive personnel places | |
JP2009238032A (en) | Support system for improvement of theft prevention consciousness | |
Srinivas et al. | Fingerprint Based Vehicle Anti-Theft Detection and Alerting System | |
CN113128540A (en) | Detection method and device for vehicle stealing behavior of non-motor vehicle and electronic equipment | |
Nithesh et al. | Anomaly Detection in Surveillance Videos Using Deep Learning |
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 |