CN113612902A - Intelligent sentry platform equipment for railway inspection, security patrol guard and nursing guard - Google Patents
Intelligent sentry platform equipment for railway inspection, security patrol guard and nursing guard Download PDFInfo
- Publication number
- CN113612902A CN113612902A CN202110747371.6A CN202110747371A CN113612902A CN 113612902 A CN113612902 A CN 113612902A CN 202110747371 A CN202110747371 A CN 202110747371A CN 113612902 A CN113612902 A CN 113612902A
- Authority
- CN
- China
- Prior art keywords
- video
- abnormal
- processing unit
- central processing
- scene
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000007689 inspection Methods 0.000 title claims description 16
- 230000000474 nursing effect Effects 0.000 title claims description 11
- 230000002159 abnormal effect Effects 0.000 claims abstract description 58
- 238000012545 processing Methods 0.000 claims abstract description 57
- 238000013500 data storage Methods 0.000 claims abstract description 8
- 238000012549 training Methods 0.000 claims description 32
- 238000000034 method Methods 0.000 claims description 14
- 238000003860 storage Methods 0.000 claims description 12
- 238000012706 support-vector machine Methods 0.000 claims description 7
- 230000002265 prevention Effects 0.000 claims description 5
- 238000012847 principal component analysis method Methods 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 4
- 238000005457 optimization Methods 0.000 claims description 4
- 230000001502 supplementing effect Effects 0.000 claims description 4
- 238000012824 chemical production Methods 0.000 claims description 3
- 239000000383 hazardous chemical Substances 0.000 claims description 3
- 238000011835 investigation Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 2
- 238000012544 monitoring process Methods 0.000 abstract description 20
- 230000000694 effects Effects 0.000 abstract description 4
- 230000006870 function Effects 0.000 description 12
- 238000000513 principal component analysis Methods 0.000 description 6
- 238000007726 management method Methods 0.000 description 5
- 239000000047 product Substances 0.000 description 5
- 230000008569 process Effects 0.000 description 3
- 230000007123 defense Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 239000012634 fragment Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000004297 night vision Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000003825 pressing Methods 0.000 description 1
- 230000001681 protective effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000013468 resource allocation Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C1/00—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people
- G07C1/20—Checking timed patrols, e.g. of watchman
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B25/00—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems
- G08B25/01—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium
- G08B25/08—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium using communication transmission lines
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B7/00—Signalling systems according to more than one of groups G08B3/00 - G08B6/00; Personal calling systems according to more than one of groups G08B3/00 - G08B6/00
- G08B7/06—Signalling systems according to more than one of groups G08B3/00 - G08B6/00; Personal calling systems according to more than one of groups G08B3/00 - G08B6/00 using electric transmission, e.g. involving audible and visible signalling through the use of sound and light sources
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Multimedia (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Alarm Systems (AREA)
Abstract
The platform equipment disclosed by the invention comprises a central processing unit, a data storage device and an IP sound post, wherein the central processing unit is electrically connected with a camera, the data storage device and the IP sound post and is wirelessly connected with a mobile phone terminal or a display; during early warning, the camera shoots or shoots a video and transmits the video to the central processing unit; the central processing unit calls the picture or video prestored in the data memory and compares the picture or video with the shot picture or video; if the similarity between the pre-stored picture or video and the shot picture or video reaches more than 90%, the scene is considered to be normal, otherwise, the scene is abnormal; then feeding back the shot abnormal scene picture or video clip to a central processing unit, and sending out a reminding signal by the central processing unit for manual judgment; if the result is really abnormal, the abnormal photo or video is marked and named, then the abnormal photo or video is sent to the data storage to enrich the database information, and the information is sent to the central processing unit, so that the central processing unit sends a starting signal to the IP sound column, and the IP sound column shouts to an abnormal scene. The invention carries out intelligent monitoring through self-learning and improves the identification effect of abnormal conditions.
Description
Technical Field
The invention belongs to the technical field of security and protection early warning, and particularly relates to intelligent sentry platform equipment for railway inspection, security patrol posts and nursing posts.
Background
The security video monitoring industry gradually develops into an industry with large market scale after development and evolution of more than half century. The security video monitoring product continuously expands the new application field and can be roughly divided into three stages. The first stage is as follows: the security video monitoring product is mainly applied to specific fields of government, military and the like and is used for obtaining evidence and monitoring some important safety problems; and a second stage: with the continuous maturity of product technology and the reduction of cost, security video monitoring products are gradually applied to the fields of finance, transportation, schools, hospitals and the like; and a third stage: along with the continuous improvement of the safety consciousness of people and the increasing of the functions of video monitoring technical products, the requirement of an individual on safety gradually turns into the real requirement, and the security video monitoring equipment suitable for the civil consumption fields of families, communities, shops, enterprises, vehicles and the like gradually becomes a market segment with the civil consumption characteristics.
Despite years of development, many problems still exist. In many fields at present, a security monitoring system can only realize simpler functions, for example, some security monitoring systems can only monitor but cannot call; some systems have certain automatic function, but unusual scene recognition rate is low, often takes place the condition of erroneous judgement, leads to many security protection monitored control system to appear like the nominal, and market feedback effect is relatively poor.
Disclosure of Invention
The invention aims to provide intelligent sentinel platform equipment for railway inspection, security patrol and study guard, which has intelligent monitoring and calling functions, can carry out intelligent monitoring through self-learning, and greatly improves the abnormal condition identification effect.
The technical scheme adopted by the invention is as follows:
a kind of intellectual guard platform equipment used for railway patrolling and examining, security patrol guard and nursing guard, including Central Processing Unit (CPU), the electricity of the central processing unit connects with lens, data storage, IP sound post, and connect with the mobile phone terminal or display wirelessly;
the flow of utilizing the platform to equip early warning is as follows:
(1) the camera transmits the shot pictures or videos to the central processing unit;
(2) the central processing unit calls a picture or video training set which is prestored in the data storage and compares the picture or video training set with the corresponding shot picture or video; if the similarity between the picture or video training set and the shot picture or video reaches more than 90%, the scene is considered to be normal, otherwise, the scene is considered to be abnormal;
(3) the shot abnormal scene pictures or video clips are fed back to the central processing unit, the central processing unit sends the abnormal conditions to the mobile phone terminal or the display through the wireless network, and sends out a reminding signal for manual judgment;
(4) if the result is found to be normal by manual judgment, further optimizing the comparison standard; and if the result is found to be really abnormal by manual judgment, marking and naming the abnormal photo or video, and then respectively sending the abnormal photo or video to a data memory and a central processing unit, wherein the former is used for supplementing and enriching database information, the latter is used for exciting the central processing unit to send a command, the central processing unit calls pre-stored audio information in the data memory and sends the pre-stored audio information to the IP sound column, and meanwhile, the IP sound column is started to enable the IP sound column to shout to an abnormal scene.
Further, the alignment method comprises: (1) the method comprises the steps of model training, wherein a part of common normal scene photos or videos and abnormal scene photos or videos are pre-stored in a data storage, and feature extraction is carried out on the scene photos or videos by adopting a Principal Component Analysis (PCA); then, carrying out classification training on the extracted features by adopting a Support Vector Machine (SVM), classifying a correct result and an abnormal result, and updating an optimization standard of training in real time by a manual assistance method in order to better ensure the correctness of a training result; then, a final model result is trained by using MapReduce (the parallel processing capacity provided by MapReduce greatly reduces the overhead of training practice); finally, storing the picture or video classification result in a database of a data memory; (2) evaluating the abnormal result of the newly shot picture or video, and extracting the characteristics of the newly shot picture or video by adopting a principal component analysis method; and then comparing the extracted features with the features of the classified pictures or videos in the database, judging the scene as a normal scene if the extracted features are similar to the normal results, and judging the scene as an abnormal scene if the extracted features are similar to the abnormal results.
Further, the camera is a 360-degree panoramic camera or a rotatable camera.
Furthermore, the platform equipment is arranged on a street lamp, a telegraph pole, a sentry box or an automatic patrol car.
Furthermore, the central processing unit adopts a storage battery and a street lamp power supply system to selectively supply power, and the storage battery is electrically connected with a solar panel arranged on the street lamp; when the solar panel breaks down or the environment where the solar panel is located cannot supply power to the storage battery, the central processing unit automatically switches to the street lamp power supply system to supply power according to the received power supply quantity.
Furthermore, the central processing unit is wirelessly connected with a prevention analysis module, a safety patrol module, an emergency drill module, an emergency treatment module, a safety education module, a hidden danger investigation module, a safety supervision module and a safety assessment module; the emergency disposal module comprises an emergency resource scheduling submodule, an emergency plan one-key promoter module and an emergency instruction one-key issuing submodule.
Furthermore, the time interval of the camera shooting the pictures is 3-10 s.
Further, the application field of the platform equipment comprises railway lines, schools, oil depots, gas stations, oil refineries, markets, trade markets, hazardous chemical production plants and warehouse stores.
The invention has the beneficial effects that:
the platform equipment has the functions of intelligent monitoring and calling, can self-learn, continuously supplements various abnormal conditions into the database along with the continuation of the use duration, and judges the various abnormal conditions more and more accurately and has higher and more intelligent degree through continuous learning and training of the system; the existing monitoring system can only monitor or can only judge whether abnormal conditions exist by utilizing a pre-installed scene, and the intelligent degree is low.
The invention is combined with the street lamps at both sides of the road, the monitoring range is seamless, and the whole scene monitoring is realized; the solar cell panel and the street lamp charging system are used for selective charging, so that power supply is guaranteed.
Drawings
Fig. 1 is a flow chart of a platform equipment early warning process of the present invention.
Fig. 2 and 3 are structural diagrams of a platform equipment module according to the present invention.
FIG. 4 is a software module diagram of the present invention.
Detailed Description
Example 1
As shown in fig. 1 to 4, a smart sentinel platform device for railway inspection, security patrol and study guard is installed on a street lamp, and comprises a Central Processing Unit (CPU), wherein the central processing unit is electrically connected with a 360-degree panoramic camera, a data memory, an IP sound post, and a wireless mobile phone terminal or a display; the central processor adopts a storage battery and a street lamp power supply system to selectively supply power, and the storage battery is electrically connected with a solar panel arranged on the street lamp; when the solar cell panel breaks down or encounters continuous rainy days and power supply cannot be performed to the storage battery at night, the central processing unit automatically switches to the street lamp power supply system to supply power according to the received power supply quantity. The central processing unit is wirelessly connected with a prevention analysis module, a safety patrol module, an emergency drill module, an emergency treatment module, a safety education module, a hidden danger investigation module, a safety supervision module and a safety assessment module; the emergency disposal module comprises an emergency resource scheduling submodule, an emergency plan one-key promoter module and an emergency instruction one-key issuing submodule.
The flow of utilizing the platform to equip early warning is as follows:
(1) the camera takes pictures every 3 seconds, and transmits the taken pictures to the central processing unit;
(2) the central processing unit calls a picture training set prestored in the data memory and compares the picture training set with the corresponding shot picture; if the similarity between the picture training set and the shot pictures reaches more than 90%, the scene is considered to be normal, otherwise, the scene is considered to be abnormal; the comparison method comprises the following steps: (1) model training, namely pre-storing a part of common normal scene photos and abnormal scene photos in a data memory, and extracting the characteristics of the scene photos by adopting a Principal Component Analysis (PCA); then, carrying out classification training on the extracted features by adopting a Support Vector Machine (SVM), classifying a correct result and an abnormal result, and updating an optimization standard of training in real time by a manual assistance method in order to better ensure the correctness of a training result; then, a final model result is trained by using MapReduce (the parallel processing capacity provided by MapReduce greatly reduces the overhead of training practice); finally, storing the picture classification result in a database of a data memory; (2) evaluating the abnormal result of the new shot picture, and extracting the characteristics of the new shot picture by adopting a principal component analysis method; and then comparing the extracted features with the features of the classified pictures in the database, judging the pictures to be normal scenes if the extracted features are similar to the features of the classified pictures in the database, and judging the pictures to be abnormal scenes if the extracted features are similar to the features of the classified pictures in the database.
(3) The shot abnormal scene photo fragments are fed back to a central processing unit, the central processing unit sends the abnormal conditions to a mobile phone terminal or a display through a wireless network, and sends out a reminding signal for manual judgment;
(4) if the result is found to be normal by manual judgment, further optimizing the comparison standard; and if the result is found to be really abnormal by manual judgment, marking and naming the abnormal photo, and then respectively sending the abnormal photo to a data memory and a central processing unit, wherein the former is used for supplementing and enriching database information, the latter is used for exciting the central processing unit to send a command, the central processing unit calls pre-stored audio information in the data memory and sends the pre-stored audio information to the IP sound column, and meanwhile, the IP sound column is started to enable the IP sound column to shout to an abnormal scene.
Example 2
As shown in fig. 1 to 3, a smart sentinel platform device for railway inspection, security patrol and study guard is installed on a street lamp, and comprises a Central Processing Unit (CPU), wherein the central processing unit is electrically connected with a 360-degree panoramic camera, a data memory, an IP sound post, and a wireless mobile phone terminal or a display; the central processor adopts a storage battery and a street lamp power supply system to selectively supply power, and the storage battery is electrically connected with a solar panel arranged on the street lamp; when the solar cell panel breaks down or encounters continuous rainy days and power supply cannot be performed to the storage battery at night, the central processing unit automatically switches to the street lamp power supply system to supply power according to the received power supply quantity.
The flow of utilizing the platform to equip early warning is as follows:
(1) the camera shoots a real-time video and transmits the shot video to the central processing unit;
(2) the central processing unit calls a video training set prestored in the data memory and compares the video training set with the corresponding shot video; if the similarity between the video training set and the shot video clip reaches more than 90%, the scene is considered to be normal, otherwise, the scene is considered to be abnormal; the comparison method comprises the following steps: (1) model training, namely pre-storing a part of common normal scene videos and abnormal scene videos in a data memory, and extracting the characteristics of the scene videos by adopting a Principal Component Analysis (PCA); then, carrying out classification training on the extracted features by adopting a Support Vector Machine (SVM), classifying a correct result and an abnormal result, and updating an optimization standard of training in real time by a manual assistance method in order to better ensure the correctness of a training result; then, a final model result is trained by using MapReduce (the parallel processing capacity provided by MapReduce greatly reduces the overhead of training practice); finally, storing the video classification result in a database of a data memory; (2) evaluating the abnormal result of the newly shot video, and extracting the characteristics of the newly shot video by adopting a principal component analysis method; and then comparing the extracted features with the features of the classified videos in the database, judging the videos to be in a normal scene if the extracted features are similar to the features of the videos in the database, and judging the videos to be in an abnormal scene if the extracted features are similar to the features of the videos in the database.
(3) The shot abnormal scene video clip is fed back to a central processing unit, the central processing unit sends the abnormal situation to a mobile phone terminal or a display through a wireless network, and sends out a reminding signal for manual judgment;
(4) if the result is found to be normal by manual judgment, further optimizing the comparison standard; and if the result is found to be really abnormal by manual judgment, marking and naming the abnormal video, and then respectively sending the abnormal video to a data memory and a central processing unit, wherein the former is used for supplementing and enriching database information, the latter is used for exciting the central processing unit to send a command, the central processing unit calls pre-stored audio information in the data memory and sends the pre-stored audio information to the IP sound column, and meanwhile, the IP sound column is started to enable the IP sound column to shout to an abnormal scene.
The platform equipment has the application fields of railway lines, schools, oil depots, gas stations, oil refineries, markets, trade markets, hazardous chemical production plants and warehouses.
The platform is arranged in the field application, mainly takes a command post as a main part, takes a supervision post and a duty post as an auxiliary part, solidifies the early warning prevention and control environment and distance inside and outside an application field, prompts joint defense team members to make clear responsibility and flexibly maneuver, carries out post-emergency steering early warning in advance, prevents and controls in the process and takes the prevention as the main part, and scientifically constructs a safety application field with 'great safety, great management and great emergency'.
The characteristics and the functions which can be realized of the platform equipment of the invention are as follows:
firstly, the responsibilities of the three stations are respectively: the commanding post is responsible for the comprehensive work of safety management, commanding and scheduling, resource allocation and the like of all the associated posts: investigating, collecting, analyzing, researching, feeding back and reporting relevant social situations, and comprehensively studying and judging information; and the system undertakes the matters of authorizing, commanding, coordinating and processing emergencies, and the like, and calls analysis meetings online and offline in time.
The supervision post is responsible for attendance checking, supervision and unified management of workers; the information is collected and reported to the command post in due time, and objective information data is provided for effectively implementing unified command.
The duty post is responsible for executing various tasks issued by the command post, monitoring the supervision area in all directions and receiving the management of the supervision post.
1. Coverage range: according to actual conditions such as laws and regulations, road traffic conditions, personnel scale and the like, peripheral monitoring channels are planned and arranged, and all-round management is carried out on a supervision area.
2. And (3) monitoring aging: and monitoring in real time within 24 hours according to the activity and the working time of personnel.
3. Checking attendance at a post: and (4) according to the specified post, utilizing the mobile phone APP to scan the code to determine the post and upload the characters to the supervision post, realizing post checking and the platform having the functions of asking for leave and applying for approval.
4. Visual patrol: the command post, the supervision post and the duty post pass through a computer browser, a mobile phone APP, a handset and patrol fixed-point routes, the maneuvering time, the space and the position are crossly patrolled, the eyes of group defense group control personnel are fully utilized, the point and the face are considered, and no dead angle hidden danger is left. The optical zooming of the protective zone camera equipment is 23 times, the movement track of personnel in the range of 200 hectometers can be observed in a high-definition manner, and the defect that the range of artificial visual angles is limited is overcome; meanwhile, the device can assist in standardizing and cleaning peripheral unsafe factors and eliminate hidden dangers.
6. Automatic early warning: the device has the functions of human shape detection, face recognition, black and white list, wandering and staying, personnel gathering, starlight night vision and the like, can timely and simultaneously link a command post, a duty room and duty personnel to form an emergency handling process of a cooperation mechanism, effectively performs sound-light alarm and on-site alarm,
7. emergency linkage: the command post has one-key disposal function and right. The sentry has information exchange and disposal linkage functions, the sentry computer browser is instructed to have a point-to-surface global patrol function, and if an emergency occurs, all parties can be linked to start an emergency plan. The command post shouts through the wireless microphone and the mobile phone APP to persuade people who are not civilized and not standard; HE recedes and deters suspicious people from behavior.
8. Education broadcasting: the device is internally provided with information contents such as safety education courses and public service advertisements of emergent events such as earthquakes and fires, and the formation of common knowledge learning and self-protection consciousness for handling the emergent events of workers is enhanced by using audio and video broadcasting of the personnel in idle time.
9. And (4) happy guard: the LED warning screen guard warning content of equipment is various, rolls with characters and tells with pronunciation at any time, lets relevant personnel experience the happiness of safety guarantee, frightens suspicious personnel, promotes the image brand of unit.
10. One-key alarm: when the staff encounters a difficult situation, the staff can quickly call a security room or a control center by seeking help through one key and two-way hands-free communication and pressing a help-seeking key of the talkback terminal, and the staff on duty can respond at the first time and can timely obtain help for related staff, and the staff can alarm and rescue nearby through one-key alarm buttons.
11. And (4) safety inspection: through the two-dimensional code on the cell-phone APP scanning post, swiftly conveniently carry out safety and patrol and examine, APP can show the detailed clause and requirement that need patrol and examine and prevent, how early warning to the abnormal conditions that probably appear? How are there linkages? How to alarm? The hidden troubles find out what and how to find and the like to solve in detail.
12. And (4) reporting hidden danger: and the patrolman reports the hidden danger information to the corresponding leaders through the APP in a text description mode and a photo every day. Uploading hidden danger information to select types, time and place, hazard degree, processing suggestions and the like. When risks such as public safety events and natural disasters which affect safety may occur at once, the on-site emergency measure scheme can be started through public broadcasting and calling at the first time, and meanwhile, one-key alarming is carried out.
13. Hidden danger treatment: potential hazards reported by patrolmen and an automatic reminding function of a mobile phone APP of a responsible person. The platform presents responses, processing times, procedures, and results.
Claims (8)
1. A intelligent sentinel platform equipment for railway inspection, security patrol posts and study-caring posts is characterized by comprising a central processing unit, wherein the central processing unit is electrically connected with a camera, a data memory, an IP sound post and a mobile phone terminal or a display in a wireless connection manner;
the flow of utilizing the platform to equip early warning is as follows:
(1) the camera transmits the shot pictures or videos to the central processing unit;
(2) the central processing unit calls a picture or video training set which is prestored in the data storage and compares the picture or video training set with the corresponding shot picture or video; if the similarity between the picture or video training set and the shot picture or video reaches more than 90%, the scene is considered to be normal, otherwise, the scene is considered to be abnormal;
(3) the shot abnormal scene pictures or video clips are fed back to the central processing unit, the central processing unit sends the abnormal conditions to the mobile phone terminal or the display through the wireless network, and sends out a reminding signal for manual judgment;
(4) if the result is found to be normal by manual judgment, further optimizing the comparison standard; and if the result is found to be really abnormal by manual judgment, marking and naming the abnormal photo or video, and then respectively sending the abnormal photo or video to a data memory and a central processing unit, wherein the former is used for supplementing and enriching database information, the latter is used for exciting the central processing unit to send a command, the central processing unit calls pre-stored audio information in the data memory and sends the pre-stored audio information to the IP sound column, and meanwhile, the IP sound column is started to enable the IP sound column to shout to an abnormal scene.
2. The intelligent sentinel platform equipment for railway inspection, security patrol and nursing posts according to claim 1, wherein the comparison method comprises:
(1) the method comprises the steps of model training, wherein a part of common normal scene photos or videos and abnormal scene photos or videos are pre-stored in a data storage, and feature extraction is carried out on the scene photos or videos by adopting a principal component analysis method; then, carrying out classification training on the extracted features by adopting a support vector machine, classifying a correct result and an abnormal result, and updating an optimization standard of training in real time by a manual assistance method in order to better ensure the correctness of a training result; then, a final model result is trained by using MapReduce; finally, storing the picture or video classification result in a database of a data memory;
(2) evaluating the abnormal result of the newly shot picture or video, and extracting the characteristics of the newly shot picture or video by adopting a principal component analysis method; and then comparing the extracted features with the features of the classified pictures or videos in the database, judging the scene as a normal scene if the extracted features are similar to the normal results, and judging the scene as an abnormal scene if the extracted features are similar to the abnormal results.
3. The intelligent sentinel platform equipment for railway inspection, security patrol and nursing posts according to claim 1, wherein the camera is a 360 ° panoramic camera or a rotatable camera.
4. The intelligent sentry platform equipment for railway inspection, security patrol and nursing posts according to claim 1, wherein the platform equipment is installed on a street lamp, a telegraph pole, a sentry box or an automatic patrol car.
5. The intelligent sentinel platform equipment for railway inspection, security patrol and nursing posts according to claim 4, wherein the central processor selectively supplies power by adopting a storage battery and a street lamp power supply system, and the storage battery is electrically connected with a solar panel arranged on a street lamp; when the solar panel breaks down or the environment where the solar panel is located cannot supply power to the storage battery, the central processing unit automatically switches to the street lamp power supply system to supply power according to the received power supply quantity.
6. The intelligent sentry platform equipment for railway inspection, security patrol and nursing posts according to claim 1, wherein the central processor is wirelessly connected with a prevention analysis module, a safety inspection module, an emergency exercise module, an emergency treatment module, a safety education module, a hidden danger investigation module, a safety supervision module and a safety assessment module; the emergency disposal module comprises an emergency resource scheduling submodule, an emergency plan one-key promoter module and an emergency instruction one-key issuing submodule.
7. The application of the intelligent sentinel platform equipment for railway inspection, security patrol and nursing guard according to claim 1, wherein the time interval for taking pictures by the camera is 3-10 s.
8. The use of the intelligent sentinel platform equipment for railway inspection, security patrol and nursing posts according to claim 1, wherein the platform equipment is applied in the fields of railway lines, schools, oil-storage-left-stroke gas stations, oil refineries, left-stroke market in shopping malls, hazardous chemical production plants and warehouses.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110747371.6A CN113612902A (en) | 2021-07-02 | 2021-07-02 | Intelligent sentry platform equipment for railway inspection, security patrol guard and nursing guard |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110747371.6A CN113612902A (en) | 2021-07-02 | 2021-07-02 | Intelligent sentry platform equipment for railway inspection, security patrol guard and nursing guard |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113612902A true CN113612902A (en) | 2021-11-05 |
Family
ID=78337177
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110747371.6A Pending CN113612902A (en) | 2021-07-02 | 2021-07-02 | Intelligent sentry platform equipment for railway inspection, security patrol guard and nursing guard |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113612902A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114913447A (en) * | 2022-02-17 | 2022-08-16 | 国政通科技有限公司 | Police intelligent command room system and method based on scene recognition |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201918790U (en) * | 2010-11-12 | 2011-08-03 | 华东师范大学附属杨行中学 | Power supply system for energy-saving street lamp |
| CN210405509U (en) * | 2019-05-06 | 2020-04-24 | 碧桂园智慧物业服务集团股份有限公司 | Efficient community security center |
| CN112446232A (en) * | 2019-08-27 | 2021-03-05 | 贵州数安智能科技有限公司 | Continuous self-learning image identification method and system |
-
2021
- 2021-07-02 CN CN202110747371.6A patent/CN113612902A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201918790U (en) * | 2010-11-12 | 2011-08-03 | 华东师范大学附属杨行中学 | Power supply system for energy-saving street lamp |
| CN210405509U (en) * | 2019-05-06 | 2020-04-24 | 碧桂园智慧物业服务集团股份有限公司 | Efficient community security center |
| CN112446232A (en) * | 2019-08-27 | 2021-03-05 | 贵州数安智能科技有限公司 | Continuous self-learning image identification method and system |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114913447A (en) * | 2022-02-17 | 2022-08-16 | 国政通科技有限公司 | Police intelligent command room system and method based on scene recognition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108833831A (en) | A kind of power construction intelligent safety monitor system | |
| CN107730681A (en) | A kind of Campus Security ensures intelligent supervision early warning system | |
| CN103550892A (en) | Internet of things-based fire control supervisory system | |
| CN116739245B (en) | Intelligent fire-fighting city alarm receiving and scheduling system | |
| CN114971409B (en) | Smart city fire monitoring and early warning method and system based on Internet of things | |
| CN111792487A (en) | Elevator intelligent management system and management method based on big data platform | |
| CN114118847A (en) | Chemical industry park danger source on-line monitoring platform | |
| CN112216010A (en) | Campus security management method, system, equipment and storage medium | |
| CN114444932A (en) | Regional safety emergency integrated platform system and working method thereof | |
| CN211744615U (en) | Big data early warning system of campus security protection | |
| CN115660297A (en) | Automatic AI early warning system and method for construction site safety | |
| CN113762920A (en) | Electric energy metering operation control method, device, equipment and medium | |
| CN112580470A (en) | City visual perception method and device, electronic equipment and storage medium | |
| CN111083451A (en) | Intelligent prison system | |
| CN113612902A (en) | Intelligent sentry platform equipment for railway inspection, security patrol guard and nursing guard | |
| CN111738115A (en) | Mobile camera automatic identification method and system based on artificial intelligence | |
| KR20100119920A (en) | System for pursuit moving object using security crime prevention network and method thereof | |
| CN111553264B (en) | Campus non-safety behavior detection and early warning method suitable for primary and secondary school students | |
| CN114418816A (en) | Municipal affair safety precaution and emergent scheduling platform | |
| CN110675585A (en) | Exhibition safety control system | |
| CN113823071A (en) | Emergency comprehensive management application platform | |
| CN111583074A (en) | Campus security management system and method | |
| CN116308941A (en) | Urban safety risk comprehensive monitoring platform, alarm disposal method thereof and inspection flow | |
| CN115330560A (en) | Engineering supervision system for construction safety | |
| CN115762046A (en) | Early warning and intervention device for building top light life person |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211105 |
|
| RJ01 | Rejection of invention patent application after publication |