CN111932709A - Method for realizing violation safety supervision of inspection operation of gas station based on AI identification - Google Patents
Method for realizing violation safety supervision of inspection operation of gas station based on AI identification Download PDFInfo
- Publication number
- CN111932709A CN111932709A CN202010916273.6A CN202010916273A CN111932709A CN 111932709 A CN111932709 A CN 111932709A CN 202010916273 A CN202010916273 A CN 202010916273A CN 111932709 A CN111932709 A CN 111932709A
- Authority
- CN
- China
- Prior art keywords
- inspection
- gas station
- image
- polling
- identification
- 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
Images
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Alarm Systems (AREA)
Abstract
The invention discloses a method for realizing violation safety supervision of routing inspection operation of a gas station based on AI identification, which comprises the following steps: s1: making a routing inspection rule; s2: generating a polling task; s3: logging in an inspection system; s4: starting to inspect; s5: the polling personnel carry out polling according to the polling task; s6: the inspection system calls an AI image recognition algorithm to compare the pictures shot in inspection, judges whether an abnormality exists, and if the abnormality exists, pushes an early warning message to a relevant responsible person and an inspection person for processing; s7: when the inspection is finished, the inspection system judges whether violation exists in the inspection by combining an AI image recognition algorithm, judges whether the inspection is finished, and generates inspection data; s8: after the inspection is finished, the inspection system records and stores each inspection point according to the inspection route map and uploads the inspection point to the storage server of the inspection system; s9: and the panel evaluation personnel check the picture, the inspection content and the inspection video shot in the inspection through the inspection system, and comment on the inspection quality.
Description
Technical Field
The invention relates to the field of artificial intelligence in the field of computers, in particular to a method for realizing violation safety supervision of routing inspection operation of a gas station based on AI identification.
Background
In order to ensure the safety of the gas station, the staff is required to carry out regular daily inspection on each area of the gas station, such as: and regularly checking whether the equipment of the gas station is normal, checking whether the work of the staff is standard, checking whether a risk area exists and the like.
The inspection mode of the existing gas station is mainly as follows: and the staff of the gas station regularly arrives at each inspection point, records whether each point is normal or not by paper notes, and gives the staff to the gas station manager. The existing inspection mode has the following problems:
1. the patrol personnel can finish the patrol point location of the whole gas station by patrol, and a long time is probably needed. When equipment fails or has problems, the problems cannot be timely found and reported. When the work of the staff is not standard, the operation cannot be standardized in time. When the risk exists in the gas station area, the problem cannot be reported and solved in time.
2. Whether the polling personnel have the in-process of patrolling and examining according to the time, accomplish according to the quality and patrol and examine, current mode of patrolling and examining can't guarantee to patrol and examine whether the operation is standard. The inspection operation of the inspection personnel can not be effectively monitored in real time.
3. When the gas station patrol inspection point has problems or risks, the reason or related responsible persons are difficult to trace in time due to the fact that effective evidences do not exist. The input of the associated risk cannot be reduced.
4. The current mode of patrolling and examining, relevant problem and risk that the in-process exists are patrolled and examined to unable real-time effectual record, to the control and the solution of later stage risk, can't provide effectual evidence support.
5. The relevant data of the inspection operation cannot be effectively counted in real time, so that the management of a gas station and the control of relevant risks are inconvenient.
The existing inspection flow point locations have the following problems:
1. the oiling machine: the tanker aircraft outward appearance is normal, and the pilot lamp is normal, and whether the nozzle is put on the throne, whether the fire control equipment outward appearance is normal, and pressure is normal.
2. Staff image: whether the staff is on duty or not and whether the staff wears the work clothes or not.
3. And (4) field safety: whether the situations of dialing a mobile phone, smoking and the like exist on the site.
4. Sanitation on site: whether there is rubbish on site.
5. Operating the well and the submersible pump: whether the appearance of the equipment is intact, whether the quantity of fire-fighting equipment is correct, whether the appearance is normal and whether the pressure is normal.
6. A liquid level meter: whether the outward appearance is intact, whether the pilot lamp is normal, whether equipment normally operates.
7. The power distribution room: whether block terminal and generator equipment outward appearance are normal, whether the pilot lamp is normal, whether have equipment trouble.
Disclosure of Invention
The invention aims to solve the technical problems that whether each point position is normal or not is recorded by a paper pen, routing inspection is not standard, efficiency is low, related problems and risks existing in the routing inspection process cannot be effectively recorded in real time, and effective evidence support cannot be provided for controlling and solving later-period risks in the conventional gas station, and aims to provide a method for realizing routing inspection operation violation safety supervision of the gas station based on AI identification, so that the problems encountered in the background technology are solved.
The invention is realized by the following technical scheme:
a method for realizing violation safety supervision of routing inspection operation of a gas station based on AI identification comprises the following steps:
s1: and (3) formulating a routing inspection rule: a gas station manager adds a routing inspection rule in a routing inspection system;
s2: the inspection system sequentially generates inspection tasks according to inspection rules; selecting a routing inspection route map in the routing inspection task, wherein the routing inspection route map is selected according to the pictures of the monitoring areas of the gas station, and if monitoring equipment is not installed in some areas, routing inspection routes cannot be made in the areas;
s3: the inspection personnel log in the inspection system through the handheld terminal equipment, the inspection system calls a face recognition algorithm to automatically judge whether the inspection personnel is configured inspection personnel, and if so, the inspection is started;
s4: after the inspection is started, when an inspector enters an inspection route, the handheld terminal device informs the inspector of face recognition of the monitoring device through voice, and the inspection route is confirmed;
s5: the polling personnel carry out polling according to the polling task, and simultaneously use the handheld terminal equipment to take pictures or record videos of the corresponding polling point positions to obtain pictures and videos, and transmit the pictures and the videos to the polling system; specifically, the method comprises the steps that an inspection worker finds a fault or an abnormality in the inspection process, fault repair is conducted on inspection point position contents in a photographing and video recording mode, and picture and video data are transmitted to an inspection system;
s6: the inspection system calls an AI image recognition algorithm to compare the pictures shot in inspection, judges whether an abnormality exists, and if the abnormality exists, pushes an early warning message to a relevant responsible person and an inspection person for processing;
s7: when the inspection is finished, the inspection system judges whether violation exists in the inspection by combining an AI image recognition algorithm, judges whether the inspection is finished, and generates inspection data;
s8: after the inspection is finished, the inspection system records and stores each inspection point according to the inspection route map and uploads the inspection point to the storage server of the inspection system;
s9: and the panel evaluation personnel check the picture, the inspection content and the inspection video shot in the inspection through the inspection system, and comment on the inspection quality.
According to the invention, the pictures of the shot point positions in the inspection process are analyzed and compared through an artificial intelligent AI image recognition algorithm, so that the inspection process is standardized; the staff in the inspection process is compared through an artificial intelligence AI face recognition algorithm, and whether the inspection staff inspects the inspection is judged. When the inspection personnel inspects the site, the inspection is started according to the configured inspection site, the corresponding site is photographed, the system analyzes and compares the picture through an artificial intelligent image recognition algorithm to determine whether the picture is the site picture, and the picture is uploaded to a picture server to be stored; meanwhile, the conditions of the staff at the inspection point can be checked in real time through a configured camera in a computer inspection management background and a mobile phone app program; meanwhile, the camera of the inspection point location can identify the point location inspection personnel through an AI face recognition algorithm to store videos and judge whether the inspection personnel in the inspection plan and the inspection personnel are in a standard state. After the inspection is started, the inspection is not started or is not finished more than half of the inspection time, and early warning messages are pushed to the WeChat public number of the manager for processing.
Further, a method for implementing safety supervision of inspection operation violation of a gas station based on AI identification, the S1 further includes: and adding inspection time, inspection point positions, inspection personnel and review personnel in the inspection rule.
Further, a method for implementing safety supervision of inspection operation violation of a gas station based on AI identification, the S5 further includes:
acquiring a patrol point location video image in real time through a gas station camera and uploading the patrol point location video image to a server for storage; checking the inspection point location video image in real time by using a computer inspection management background or a mobile phone app program;
the method comprises the steps of acquiring a face image of an inspection person in real time through a gas station camera, identifying the face image of the inspection person by using a face identification algorithm, and judging whether the face image is the inspection person in an inspection plan and whether the inspection of the inspection person is standard.
Further, a method for realizing safe supervision of inspection operation violation of a gas station based on AI identification further comprises: and after the polling is started, if the polling is not started or is not completed within half of the polling time, pushing an early warning message to a WeChat public number of a manager for processing.
Further, the method for realizing the violation safety supervision of the routing inspection operation of the gas station based on AI identification is characterized in that the handheld terminal is an explosion-proof flat plate.
Further, a method for realizing violation safety supervision of inspection operation of a gas station based on AI identification, wherein pictures shot in inspection comprise: the image of the appearance of the oiling machine, the image of staff on the site of the gas station, the image of sanitation on the site of the gas station, the image of an operation well and an oil-submerged pump, the image of a liquid level meter and the image of a power distribution room.
Further, the method for realizing violation safety supervision of inspection operation of the gas station based on AI identification further comprises the steps of arranging cameras in an oiling machine and a tank area, acquiring a field picture by using the cameras and transmitting the field picture to an inspection system, comparing the field picture by the inspection system by calling an AI image identification algorithm, judging whether the field picture is abnormal or not, and if the field picture is abnormal, pushing an early warning message to a related responsible person and an inspection person for processing; the abnormity comprises calling and smoking.
Further, the method for realizing the violation safety supervision of the routing inspection operation of the gas station based on AI identification comprises the step of finishing face matting and face correction by adopting MTCNN.
Aiming at the defects of the prior art, the invention early warns the irregular routing inspection flow by combining the mode of collecting the on-site routing inspection flow image by the camera and the intelligent analysis algorithm and pushes the related responsible person.
Compared with the prior art, the invention has the following advantages and beneficial effects:
1. the invention calls an AI image recognition algorithm to compare the pictures taken in the inspection, and judges whether the related equipment is normal, whether faults exist or not and whether the quantity is correct or not. And when the problem exists, the message is pushed to the relevant responsible person and the patrol personnel in time for processing.
2. The invention calls an AI face recognition algorithm to detect the polling personnel in polling, detects whether the polling personnel is on duty or not, and effectively supervises the polling operation of the polling personnel in real time.
Drawings
The accompanying drawings, which are included to provide a further understanding of the embodiments of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the principles of the invention. In the drawings:
fig. 1 is a flow chart of the inspection of the present invention.
FIG. 2 is a three-stage structure diagram of MTCNN.
FIG. 3 is a three-stage flow diagram of MTCNN.
Fig. 4 is an image corner detection.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to examples and accompanying drawings, and the exemplary embodiments and descriptions thereof are only used for explaining the present invention and are not meant to limit the present invention.
Examples
As shown in fig. 1, the method for implementing inspection operation violation safety supervision of a gas station based on AI identification of the present invention includes:
s1: and (3) formulating a routing inspection rule: a gas station manager adds a routing inspection rule in a routing inspection system;
s2: the inspection system sequentially generates inspection tasks according to inspection rules; selecting a routing inspection route map in the routing inspection task, wherein the routing inspection route map is selected according to the pictures of the monitoring areas of the gas station, and if monitoring equipment is not installed in some areas, routing inspection routes cannot be made in the areas;
s3: the inspection personnel log in the inspection system through the handheld terminal equipment, the inspection system calls a face recognition algorithm to automatically judge whether the inspection personnel is configured inspection personnel, and if so, the inspection is started;
s4: after the inspection is started, when an inspector enters an inspection route, the handheld terminal device informs the inspector of face recognition of the monitoring device through voice, and the inspection route is confirmed;
s5: the polling personnel carry out polling according to the polling task, and simultaneously use the handheld terminal equipment to take pictures or record videos of the corresponding polling point positions to obtain pictures and videos, and transmit the pictures and the videos to the polling system; specifically, the method comprises the steps that an inspection worker finds a fault or an abnormality in the inspection process, fault repair is conducted on inspection point position contents in a photographing and video recording mode, and picture and video data are transmitted to an inspection system;
s6: the inspection system calls an AI image recognition algorithm to compare the pictures shot in inspection, judges whether an abnormality exists, and if the abnormality exists, pushes an early warning message to a relevant responsible person and an inspection person for processing;
s7: when the inspection is finished, the inspection system judges whether violation exists in the inspection by combining an AI image recognition algorithm, judges whether the inspection is finished, and generates inspection data;
s8: after the inspection is finished, the inspection system records and stores each inspection point according to the inspection route map and uploads the inspection point to the storage server of the inspection system;
s9: and the panel evaluation personnel check the picture, the inspection content and the inspection video shot in the inspection through the inspection system, and comment on the inspection quality.
According to the invention, the pictures of the shot point positions in the inspection process are analyzed and compared through an artificial intelligent AI image recognition algorithm, so that the inspection process is standardized; the staff in the inspection process is compared through an artificial intelligence AI face recognition algorithm, and whether the inspection staff inspects the inspection is judged. When the inspection personnel inspects the site, the inspection is started according to the configured inspection site, the corresponding site is photographed, the system analyzes and compares the picture through an artificial intelligent image recognition algorithm to determine whether the picture is the site picture, and the picture is uploaded to a picture server to be stored; meanwhile, the conditions of the staff at the inspection point can be checked in real time through a configured camera in a computer inspection management background and a mobile phone app program; meanwhile, the camera of the inspection point location can identify the point location inspection personnel through an AI face recognition algorithm to store videos and judge whether the inspection personnel in the inspection plan and the inspection personnel are in a standard state. After the inspection is started, the inspection is not started or is not finished more than half of the inspection time, and early warning messages are pushed to the WeChat public number of the manager for processing.
The S5 further includes: acquiring a patrol point location video image in real time through a gas station camera and uploading the patrol point location video image to a server for storage; checking the inspection point location video image in real time by using a computer inspection management background or a mobile phone app program; the method comprises the steps of acquiring a face image of an inspection person in real time through a gas station camera, identifying the face image of the inspection person by using a face identification algorithm, and judging whether the face image is the inspection person in an inspection plan and whether the inspection of the inspection person is standard.
A method for realizing violation safety supervision of routing inspection operation of a gas station based on AI identification further comprises the following steps: and after the polling is started, if the polling is not started or is not completed within half of the polling time, pushing an early warning message to a WeChat public number of a manager for processing.
A method for realizing violation safety supervision of inspection operation of a gas station based on AI identification is disclosed, wherein pictures shot in inspection comprise: the image of the appearance of the oiling machine, the image of staff on the site of the gas station, the image of sanitation on the site of the gas station, the image of an operation well and an oil-submerged pump, the image of a liquid level meter and the image of a power distribution room.
The method can solve the following problems existing in the point location of the inspection process:
after a polling person shoots an appearance picture of the oiling machine on site, whether the appearance of the oiling machine is normal, whether an indicator lamp is normal, whether an oiling gun is placed in place, whether the appearance of a fire-fighting device is normal and whether pressure is normal are judged through AI image recognition; if the problem exists, the early warning message is pushed through the WeChat public number, and related responsible persons are notified to process the early warning message.
After the patrol personnel shoot the picture of the staff at the gas station site, whether the staff is on duty is judged through AI face recognition, whether the staff wears a working clothes is judged through AI image recognition, and the violation behavior is recorded into the system.
After the on-site sanitary picture of the gas station is shot by the patrol personnel on site, whether rubbish exists on the site or not is judged through AI image recognition, whether the site is clean and tidy or not is judged, and violation behaviors are recorded to the system.
After a patrol inspector shoots pictures of an operation well, an oil-submerged pump and peripheral equipment on site, whether the appearance of the equipment is intact, whether the number of fire-fighting equipment is correct, whether the appearance is normal and whether the pressure is normal are judged through AI image recognition; if the fault occurs, the early warning message is pushed to the inspection personnel and the related responsible personnel for processing.
After the patrol personnel shoot the liquid level instrument picture on site, whether the appearance of the liquid level instrument is intact or not, whether the indicator lamp is normal or not and whether the equipment is normally operated or not are judged through AI image recognition, and if the equipment is in fault, early warning messages are pushed to the patrol personnel and the related responsible personnel for processing.
After the patrol and examine personnel scene and shoot the distribution room picture, judge whether block terminal and generator equipment outward appearance are normal through AI image recognition, whether the pilot lamp is normal, whether there is the equipment trouble, if break down, then to patrol and examine personnel and relevant responsible person propelling movement early warning message and handle.
A method for realizing violation safety supervision of inspection operation of a gas station based on AI identification further comprises the steps of arranging cameras in an oiling machine and a tank area, acquiring a field picture by using the cameras and transmitting the field picture to an inspection system, comparing the field picture by the inspection system by calling an AI image identification algorithm, judging whether the field picture is abnormal or not, and pushing an early warning message to a related responsible person and an inspection person for processing if the field picture is abnormal; the abnormity comprises calling and smoking.
The cameras are arranged in key areas such as an oiling machine and an oil tank area, and if a person dials a mobile phone and smokes on site, early warning messages are pushed to relevant responsible persons and inspection personnel for processing through the mobile phone through on-site camera AI image recognition.
A method for achieving violation safety supervision of routing inspection operation of a gas station based on AI identification comprises the step of finishing face matting and face correction by adopting MTCNN.
The algorithm used by the invention comprises a face recognition algorithm and an image recognition algorithm:
firstly, a face recognition algorithm:
(1) face matting:
and finishing the matting of the human face by using the MTCNN. The MTCNN is divided into three stages, and the network structure is shown in FIG. 1;
in the first stage, a P-Net full convolution network is used to generate candidate window and bounding box regression vectors. The candidate window is corrected using a block regression approach, and overlapping candidate blocks are merged using non-maximum suppression (NMS).
In the second stage, R-Net is used to improve the candidate window. Candidate windows that pass P-Net are input into R-Net, most false windows are rejected, and block regression and NMS merging continues to be used.
And in the third stage, outputting the final positions of the face frame and the feature point by using O-Net, which is similar to the second step but is different from the second step in that 5 feature point positions are generated.
(2) Face rectification:
calculating an affine matrix H by using the positions of the face subjected to the matting in the step two and five feature points of the face and the feature points of the template; and then directly calculating to obtain an aligned image by using H.
Secondly, an image recognition algorithm:
step 1: establishing a target sample library: images of the same target at different angles and under light are collected.
Step 2: extracting features of a target, mainly extracting 200 angular points in an image, calculating the difference between the peripheral pixel values and the central angular point in a 3-by-3 neighborhood (9 pixel points) by taking the angular points as the center, marking the difference as 1 if the difference is greater than 0, otherwise marking the difference as 0, forming 9-bit 0-1 feature codes for each angular point, taking the feature codes as feature descriptions of the angular points, and arranging the feature descriptions of the 200 angular points in sequence to form the feature description of the whole image.
The feature description formula:
where p is the pixel value in the domain,
is the pixel value at the corner point.
As shown in fig. 4, if the difference between the gray value of 12 continuous pixels and the gray value of p-point exceeds a certain threshold (10 is set in the present invention), the p-point can be considered as a corner point.
And step 3: identifying a specific object through feature comparison, setting a threshold value through calculating Euclidean distance between feature descriptions, and if the threshold value is exceeded, determining that the target is to be identified.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are merely exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (8)
1. The utility model provides a method for realizing gas station inspection operation violation safety supervision based on AI discernment which characterized in that includes:
s1: and (3) formulating a routing inspection rule: a gas station manager adds a routing inspection rule in a routing inspection system;
s2: the inspection system sequentially generates inspection tasks according to inspection rules; selecting an inspection route map in the inspection task, wherein the inspection route map is selected according to the monitoring area picture of the gas station;
s3: the inspection personnel log in the inspection system through the handheld terminal equipment, the inspection system calls a face recognition algorithm to automatically judge whether the inspection personnel is configured inspection personnel, and if so, the inspection is started;
s4: after the inspection is started, when an inspector enters an inspection route, the handheld terminal device informs the inspector of face recognition of the monitoring device through voice, and the inspection route is confirmed;
s5: the polling personnel carry out polling according to the polling task, and simultaneously use the handheld terminal equipment to take pictures or record videos of the corresponding polling point positions to obtain pictures and videos, and transmit the pictures and the videos to the polling system; specifically, the method comprises the steps that an inspection worker finds a fault or an abnormality in the inspection process, fault repair is conducted on inspection point position contents in a photographing and video recording mode, and picture and video data are transmitted to an inspection system;
s6: the inspection system calls an AI image recognition algorithm to compare the pictures shot in inspection, judges whether an abnormality exists, and if the abnormality exists, pushes an early warning message to a relevant responsible person and an inspection person for processing;
s7: when the inspection is finished, the inspection system judges whether violation exists in the inspection by combining an AI image recognition algorithm, judges whether the inspection is finished, and generates inspection data;
s8: after the inspection is finished, the inspection system records and stores each inspection point according to the inspection route map and uploads the inspection point to the storage server of the inspection system;
s9: and the panel evaluation personnel check the picture, the inspection content and the inspection video shot in the inspection through the inspection system, and comment on the inspection quality.
2. The method for implementing safety supervision of inspection work violation at a gas station based on AI identification as claimed in claim 1, wherein said S1 further comprises: and adding inspection time, inspection point positions, inspection personnel and review personnel in the inspection rule.
3. The method for implementing safety supervision of inspection work violation at a gas station based on AI identification as claimed in claim 1, wherein said S6 further comprises:
acquiring a patrol point location video image in real time through a gas station camera and uploading the patrol point location video image to a server for storage; checking the inspection point location video image in real time by using a computer inspection management background or a mobile phone app program;
the method comprises the steps of acquiring a face image of an inspection person in real time through a gas station camera, identifying the face image of the inspection person by using a face identification algorithm, and judging whether the face image is the inspection person in an inspection plan and whether the inspection of the inspection person is standard.
4. The AI-based identification based method for safely supervising inspection work violation of gas stations according to claim 1, further comprising: and after the polling is started, if the polling is not started or is not completed within half of the polling time, pushing an early warning message to a WeChat public number of a manager for processing.
5. The AI-identification-based method for carrying out inspection work violation safety supervision on a gas station according to claim 1, wherein the handheld terminal is an explosion-proof tablet.
6. The AI-based identification based violation safety supervision method for inspection work of gas stations in accordance with claim 1, wherein the pictures taken during inspection comprise: the image of the appearance of the oiling machine, the image of staff on the site of the gas station, the image of sanitation on the site of the gas station, the image of an operation well and an oil-submerged pump, the image of a liquid level meter and the image of a power distribution room.
7. The method for realizing violation safety supervision of inspection work of a gas station based on AI identification as claimed in claim 1, further comprising arranging cameras at the oiling machine and the tank area, acquiring a field picture by using the cameras and transmitting the field picture to the inspection system, comparing the field picture by the inspection system by calling an AI image identification algorithm, judging whether an abnormality exists, and if the abnormality exists, pushing an early warning message to a related responsible person and an inspection person for processing; the abnormity comprises calling and smoking.
8. The AI-based recognition based method for fueling station patrol operation violation security supervision as recited in claim 1, wherein the face recognition algorithm comprises face matting and face rectification using MTCNN.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010916273.6A CN111932709A (en) | 2020-09-03 | 2020-09-03 | Method for realizing violation safety supervision of inspection operation of gas station based on AI identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010916273.6A CN111932709A (en) | 2020-09-03 | 2020-09-03 | Method for realizing violation safety supervision of inspection operation of gas station based on AI identification |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111932709A true CN111932709A (en) | 2020-11-13 |
Family
ID=73309118
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010916273.6A Pending CN111932709A (en) | 2020-09-03 | 2020-09-03 | Method for realizing violation safety supervision of inspection operation of gas station based on AI identification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111932709A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112699750A (en) * | 2020-12-22 | 2021-04-23 | 南方电网深圳数字电网研究院有限公司 | Safety monitoring method and system for intelligent gas station based on edge calculation and AI (Artificial Intelligence) |
| CN113177707A (en) * | 2021-04-25 | 2021-07-27 | 浙江浙石油综合能源销售有限公司 | Intelligent system for comprehensive energy supply service station and inspection method |
| CN113379943A (en) * | 2021-06-16 | 2021-09-10 | 国网山西省电力公司 | AR system of patrolling and examining based on 5G communication |
| CN114241392A (en) * | 2021-12-23 | 2022-03-25 | 苏州企智信息科技有限公司 | Automatic factory specification inspection method based on video behavior recognition |
| CN114999019A (en) * | 2022-05-25 | 2022-09-02 | 深圳市铁越电气有限公司 | Inspection task parallel processing method and system based on camera preset position |
| CN115439948A (en) * | 2022-07-22 | 2022-12-06 | 大连莱立佰信息技术有限公司 | Pump station intelligent inspection method based on image recognition and process video linkage |
| CN115439787A (en) * | 2022-09-07 | 2022-12-06 | 长扬科技(北京)股份有限公司 | AI visual detection method and device for grain depot, electronic equipment and storage medium |
| CN116579609A (en) * | 2023-05-15 | 2023-08-11 | 三峡科技有限责任公司 | Illegal operation analysis method based on inspection process |
| CN116976814A (en) * | 2023-07-31 | 2023-10-31 | 山东龙源电力工程有限公司 | Intelligent management system for safety production of thermal power plant |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105812751A (en) * | 2016-05-10 | 2016-07-27 | 天津同丰信息技术有限公司 | Monitoring system applied to intelligent environmental sanitation system |
| CN106991731A (en) * | 2017-04-07 | 2017-07-28 | 北京燃气绿源达清洁燃料有限公司 | Intelligent polling method and system that integrated equipment is safeguarded |
| CN110456723A (en) * | 2019-08-15 | 2019-11-15 | 成都睿晓科技有限公司 | A kind of emptying area, gas station security management and control system based on deep learning |
| CN110570536A (en) * | 2019-08-26 | 2019-12-13 | 北京许继电气有限公司 | intelligent line patrol system for extra-high voltage transmission line |
| CN110956714A (en) * | 2019-11-26 | 2020-04-03 | 湖北佳狮盾智能技术有限公司 | Inspection system based on face recognition |
| CN111091630A (en) * | 2019-12-24 | 2020-05-01 | 河南旭盛新能源有限公司 | Remote intelligent inspection system for gas station |
-
2020
- 2020-09-03 CN CN202010916273.6A patent/CN111932709A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105812751A (en) * | 2016-05-10 | 2016-07-27 | 天津同丰信息技术有限公司 | Monitoring system applied to intelligent environmental sanitation system |
| CN106991731A (en) * | 2017-04-07 | 2017-07-28 | 北京燃气绿源达清洁燃料有限公司 | Intelligent polling method and system that integrated equipment is safeguarded |
| CN110456723A (en) * | 2019-08-15 | 2019-11-15 | 成都睿晓科技有限公司 | A kind of emptying area, gas station security management and control system based on deep learning |
| CN110570536A (en) * | 2019-08-26 | 2019-12-13 | 北京许继电气有限公司 | intelligent line patrol system for extra-high voltage transmission line |
| CN110956714A (en) * | 2019-11-26 | 2020-04-03 | 湖北佳狮盾智能技术有限公司 | Inspection system based on face recognition |
| CN111091630A (en) * | 2019-12-24 | 2020-05-01 | 河南旭盛新能源有限公司 | Remote intelligent inspection system for gas station |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112699750A (en) * | 2020-12-22 | 2021-04-23 | 南方电网深圳数字电网研究院有限公司 | Safety monitoring method and system for intelligent gas station based on edge calculation and AI (Artificial Intelligence) |
| CN113177707A (en) * | 2021-04-25 | 2021-07-27 | 浙江浙石油综合能源销售有限公司 | Intelligent system for comprehensive energy supply service station and inspection method |
| CN113379943A (en) * | 2021-06-16 | 2021-09-10 | 国网山西省电力公司 | AR system of patrolling and examining based on 5G communication |
| CN114241392A (en) * | 2021-12-23 | 2022-03-25 | 苏州企智信息科技有限公司 | Automatic factory specification inspection method based on video behavior recognition |
| CN114999019A (en) * | 2022-05-25 | 2022-09-02 | 深圳市铁越电气有限公司 | Inspection task parallel processing method and system based on camera preset position |
| CN115439948A (en) * | 2022-07-22 | 2022-12-06 | 大连莱立佰信息技术有限公司 | Pump station intelligent inspection method based on image recognition and process video linkage |
| CN115439787A (en) * | 2022-09-07 | 2022-12-06 | 长扬科技(北京)股份有限公司 | AI visual detection method and device for grain depot, electronic equipment and storage medium |
| CN115439787B (en) * | 2022-09-07 | 2023-08-04 | 长扬科技(北京)股份有限公司 | AI visual detection method and device for grain depot, electronic equipment and storage medium |
| CN116579609A (en) * | 2023-05-15 | 2023-08-11 | 三峡科技有限责任公司 | Illegal operation analysis method based on inspection process |
| CN116579609B (en) * | 2023-05-15 | 2023-11-14 | 三峡科技有限责任公司 | Illegal operation analysis method based on inspection process |
| CN116976814A (en) * | 2023-07-31 | 2023-10-31 | 山东龙源电力工程有限公司 | Intelligent management system for safety production of thermal power plant |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111932709A (en) | Method for realizing violation safety supervision of inspection operation of gas station based on AI identification | |
| CN111310947A (en) | Building facility operation and maintenance method, equipment, storage medium and system based on 5G | |
| WO2020057159A1 (en) | Video analysis system and method for food processing violation behavior in university restaurant | |
| CN105100732A (en) | Machine room server remote monitoring method and system | |
| CN113011833A (en) | Safety management method and device for construction site, computer equipment and storage medium | |
| CN112004061A (en) | Oil discharge flow normative intelligent monitoring method based on computer vision | |
| CN112112629A (en) | Safety business management system and method in drilling operation process | |
| CN110807460A (en) | Transformer substation intelligent patrol system based on image recognition and application method thereof | |
| CN113206978A (en) | Security intelligent monitoring early warning system and method for oil and gas pipeline station | |
| CN210222962U (en) | Intelligent electronic fence system | |
| CN115880631A (en) | Power distribution station fault identification system, method and medium | |
| CN116246416A (en) | Intelligent analysis early warning platform and method for security protection | |
| CN115620192A (en) | Method and device for detecting wearing of safety rope in aerial work | |
| CN116976832A (en) | Intelligent fire-fighting centralized unified supervision platform based on AI, big data and Internet of things | |
| CN110833667A (en) | Fire fighting management method and system | |
| CN114550082A (en) | Easy-to-use efficient AI (Artificial Intelligence) recognition algorithm | |
| CN110928305B (en) | Patrol method and system for patrol robot of railway passenger station | |
| CN112906441B (en) | Image recognition system and method for exploration and maintenance in communication industry | |
| CN114463873A (en) | Patrol system for community | |
| CN115457331A (en) | Intelligent inspection method and system for construction site | |
| CN114387542A (en) | Video acquisition unit abnormity identification system based on portable ball arrangement and control | |
| CN113489929A (en) | Method and device for monitoring supervision of garbage classification, computer equipment and storage medium | |
| CN110796397A (en) | Alarm system and method | |
| CN205647793U (en) | Security and protection in bank network system | |
| CN117729314B (en) | AI vision-based multi-region monitoring system and method |
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: 20201113 |
|
| RJ01 | Rejection of invention patent application after publication |