CN116824476A - Logging well site management system based on video intelligent recognition - Google Patents
Logging well site management system based on video intelligent recognition Download PDFInfo
- Publication number
- CN116824476A CN116824476A CN202211606323.6A CN202211606323A CN116824476A CN 116824476 A CN116824476 A CN 116824476A CN 202211606323 A CN202211606323 A CN 202211606323A CN 116824476 A CN116824476 A CN 116824476A
- Authority
- CN
- China
- Prior art keywords
- logging
- monitoring
- image
- imaging
- information
- 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
- 238000012544 monitoring process Methods 0.000 claims abstract description 158
- 230000002159 abnormal effect Effects 0.000 claims abstract description 39
- 238000004364 calculation method Methods 0.000 claims abstract description 28
- 238000003384 imaging method Methods 0.000 claims description 83
- 238000012937 correction Methods 0.000 claims description 15
- 230000009471 action Effects 0.000 claims description 9
- 230000008921 facial expression Effects 0.000 claims description 6
- 230000005856 abnormality Effects 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 238000004519 manufacturing process Methods 0.000 abstract description 20
- 238000007689 inspection Methods 0.000 abstract description 11
- 238000000034 method Methods 0.000 abstract description 11
- 238000011835 investigation Methods 0.000 description 5
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000004062 sedimentation Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/12—Details of acquisition arrangements; Constructional details thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- 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
- G06V40/20—Movements or behaviour, e.g. gesture recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20112—Image segmentation details
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Human Computer Interaction (AREA)
- Alarm Systems (AREA)
Abstract
The invention provides a logging well site management system based on video intelligent identification, which comprises: the image acquisition module is used for being distributed at a plurality of monitoring points and acquiring image information of the monitoring points; the first terminal is used for carrying out encryption storage and local calculation on the monitoring point image information acquired by the image acquisition module, and generating a first alarm instruction to the first alarm module when abnormal monitoring occurs; encrypting and transmitting the local calculation result of the monitoring point to a cloud; the second terminal is used for acquiring a local calculation result transmitted by the first terminal from the cloud and generating an image-text information instruction from the calculation result and sending the image-text information instruction to the display module; when the image-text information instruction comprises a first alarm instruction, the first alarm instruction is sent to the second alarm module. The method is used for realizing the purpose of automatically monitoring the logging monitoring point through intelligent video identification, thereby reducing the situation that potential safety hazards are generated in production operation due to manual inspection or loopholes.
Description
Technical Field
The invention relates to the technical field of well logging site management, in particular to a well logging site management system based on video intelligent identification.
Background
Logging well site management generally refers to the safe investigation of personnel at the well site or the regular inspection or investigation of equipment at the well site, and when the equipment does not meet the inspection or investigation requirements, the operation should be stopped immediately, and the items which do not meet the requirements are rectified to ensure the safe, effective and stable well site operation;
the existing well site management is mainly used for checking the safety of the well site by manpower or judging whether illegal operation exists for personnel; the manual operation has a certain loophole checking and time delay; for example, the logging constructor at the position A has illegal operation, and cannot find the condition of the illegal operation when the logging constructor does not reach the position A in the manual inspection process, so that certain potential safety hazards are brought to production operation; or, missing check points or check items occur in the manual check process, so that certain potential safety hazards are brought to production operation;
therefore, a system or a method for improving the safety management of a logging well site is lacking, so that the aim of automatic monitoring is fulfilled through the system or the method, and the situation that potential safety hazards are generated in production operation due to manual inspection or loopholes are reduced.
Disclosure of Invention
The invention provides a logging well site management system based on video intelligent recognition, which is used for realizing the purpose of automatically monitoring logging monitoring points through the video intelligent recognition, thereby reducing the situation that potential safety hazards are generated in production operation due to manual inspection or loopholes.
The invention provides a logging well site management system based on video intelligent identification, which comprises:
the image acquisition module is used for being distributed at a plurality of monitoring points and acquiring image information of the monitoring points;
the first terminal is used for carrying out encryption storage and local calculation on the monitoring point image information acquired by the image acquisition module, and generating a first alarm instruction to the first alarm module when abnormal monitoring occurs;
encrypting and transmitting the local calculation result of the monitoring point to a cloud;
the second terminal is used for acquiring a local calculation result transmitted by the first terminal from the cloud and generating an image-text information instruction from the calculation result and sending the image-text information instruction to the display module; when the image-text information instruction comprises a first alarm instruction, the first alarm instruction is sent to the second alarm module.
Preferably, the first alarm module, the image acquisition module and the first terminal are all arranged at the monitoring point;
the monitoring point is also provided with a first microphone module which is connected with a second alarm module through a local area network or a mobile network;
the second alarm module, the second terminal and the display module are all arranged in the monitoring room;
the first alarm module and the second alarm module are both loudspeakers.
Preferably, the first alarm instruction is used for alarming illegal projects of the monitoring points; and is used for prompting constructors of monitoring points or monitoring personnel of monitoring rooms to check or exclude illegal projects respectively.
Preferably, the local calculation of the monitoring point image information acquired by the image acquisition module includes:
imaging modeling is carried out on the acquired image information of the monitoring point, and the imaging modeling is used for carrying out distortion correction on imaging;
comparing the imaging information after distortion correction with pre-stored information, determining whether the monitoring point is abnormal or not based on a comparison result, and if the monitoring point is abnormal, sending a first alarm instruction through the first alarm module and the second alarm module respectively.
Preferably, the method further comprises the steps of acquiring voice information of the monitoring point through the first microphone module, and judging illegal actions by combining the voice information with image information;
cloud computing is carried out on the voice information, and judgment of whether the voice information is boring or not is obtained; if the chatting exists, a first alarm instruction is sent;
and performing violation judgment on the facial expression and the body action of the worker by utilizing the image information acquired by the image acquisition module;
and if the facial expression of the worker is stored and the eyes are closed for a long time, and the eyes are closed frequently within a preset time, and the limb actions enter a dangerous area, a first alarm instruction is sent.
Preferably, distortion correction of the imaging includes:
selecting monitoring point image information acquired by an image acquisition module, wherein the image information is logging information, and acquiring depth a and inner diameter d of the logging information; the image acquisition module is a camera, acquires the height H1 of the camera above the logging, and constructs a logging model;
constructing a logging center imaging model based on the logging model; constructing a logging eccentric imaging model based on the logging center imaging model; correcting the logging eccentric imaging model;
and comparing the corrected logging eccentric imaging model with pre-stored information, and determining whether the monitoring point is abnormal or not based on a comparison result.
Preferably, the log image information acquired by the monitoring points is subjected to equal division of m sections, and the distance P between an object in the monitoring points and a camera is calculated:
P＝m*L1+H1 (1)
wherein L1 is the length of m-segment equal segmentation in the logging image information;
a logging model is constructed based on the pitch P.
Preferably, the spatial coordinates O1 (x 1, y1, z 1) of any point k of the log are taken and used to construct a log model:
wherein d is the logging inner diameter; a is the logging depth;
when the center of the camera is positioned at a logging center coordinate O (0, H1 +H2), logging grid imaging in the equal-division image information of m sections is equidistant concentric circles, and the coordinate of k points in the logging grid imaging is O2 (x 2, y 2):
constructing a logging center imaging model based on the coordinates of the k points in the logging grid imaging as O2 (x 2, y 2);
wherein P is the distance from the object in the monitoring point to the camera; d is the logging inner diameter;
when the image information obtained by the monitoring points deviates, the camera deviates from the logging center coordinates and is positioned at coordinates O (ox 2, oy2, H1+H2), a logging eccentric imaging model is constructed by using the logging center imaging model, and the coordinates of k points in logging grid imaging are O3 (x 3, y 3):
wherein P is the distance from the object in the monitoring point to the camera; d is the logging inner diameter; s is the eccentric distance.
Preferably, performing offset correction on the constructed logging off-center imaging model includes:
expanding the constructed logging eccentric imaging model to obtain a plane model of the logging eccentric imaging model, and correcting the logging image information acquired by the monitoring points of the m sections divided equally in sequence transversely and longitudinally based on the plane model so as to vertically and horizontally correct the intersecting line between two adjacent sections; recovering the corrected plane model into a cylindrical logging model again, and obtaining the corrected cylindrical logging model;
marking monitoring points in the corrected cylindrical logging model, comparing the image information of the monitoring points with pre-stored information, determining whether the monitoring points are abnormal or not based on comparison results, and sending first alarm instructions through the first alarm module and the second alarm module respectively if the monitoring points are abnormal.
Preferably, the multiple logging eccentric imaging models are compared, the deformation error rate of the logging eccentric imaging models is calculated, if the error rate R is more than 0 and less than 1, distortion correction is not performed any more, statistics is performed on the logging eccentric imaging models corrected in the past, and a plurality of logging eccentric imaging information closest to average error is extracted based on the statistics result;
extracting non-alarming image information from a plurality of logging eccentric imaging information closest to the average error as comparison information;
using the contrast information as abnormal alarm monitoring contrast in the eccentric imaging image;
in the monitoring process, if the deviation of the comparison result of the comparison information and the latest shot monitoring image information is u, the fact that the latest shot monitoring image has a focal length or shooting direction changes is indicated, the latest shot monitoring image is defined as a new monitoring image at the moment t, and a logging eccentric imaging model is built for the new monitoring image at the moment t; and then monitoring the monitoring position for abnormality.
The working principle and the beneficial effects of the invention are as follows:
the invention provides a logging well site management system based on video intelligent identification, which comprises: the image acquisition module is used for being distributed at a plurality of monitoring points and acquiring image information of the monitoring points; the first terminal is used for carrying out encryption storage and local calculation on the monitoring point image information acquired by the image acquisition module, and generating a first alarm instruction to the first alarm module when abnormal monitoring occurs; encrypting and transmitting the local calculation result of the monitoring point to a cloud; the second terminal is used for acquiring a local calculation result transmitted by the first terminal from the cloud and generating an image-text information instruction from the calculation result and sending the image-text information instruction to the display module; when the image-text information instruction comprises a first alarm instruction, the first alarm instruction is sent to the second alarm module. The method is used for realizing the purpose of automatically monitoring the logging monitoring point through intelligent video identification, thereby reducing the situation that potential safety hazards are generated in production operation due to manual inspection or loopholes.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention may be realized and attained by the structure particularly pointed out in the written description and drawings.
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
fig. 1 is a schematic structural view of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described below with reference to the accompanying drawings, it being understood that the preferred embodiments described herein are for illustration and explanation of the present invention only, and are not intended to limit the present invention.
According to fig. 1, an embodiment of the present invention provides a logging wellsite management system based on intelligent video recognition, which is characterized by comprising:
the image acquisition module is used for being distributed at a plurality of monitoring points and acquiring image information of the monitoring points;
the first terminal is used for carrying out encryption storage and local calculation on the monitoring point image information acquired by the image acquisition module, and generating a first alarm instruction to the first alarm module when abnormal monitoring occurs;
encrypting and transmitting the local calculation result of the monitoring point to a cloud;
the second terminal is used for acquiring a local calculation result transmitted by the first terminal from the cloud and generating an image-text information instruction from the calculation result and sending the image-text information instruction to the display module; when the image-text information instruction comprises a first alarm instruction, the first alarm instruction is sent to the second alarm module.
The method is used for realizing the purpose of automatically monitoring the logging monitoring point through intelligent video identification, thereby reducing the situation that potential safety hazards are generated in production operation due to manual inspection or loopholes.
Specifically, when the monitoring point monitoring system works, the camera is used for collecting image information of the monitoring point, after calculation and comparison are carried out on the collected image information of the monitoring point, whether the monitoring point is abnormal or not is determined by utilizing a comparison result, and if the monitoring point is abnormal, abnormal alarm is carried out on the monitoring point; and, also carry on the unusual alarm in the monitoring center;
when the staff at the monitoring point hear the abnormal alarm, the abnormal state can be immediately checked; if no staff is used for checking the abnormal state after the monitoring point alarms for a period of time, the monitoring center can allocate the staff nearby for checking the abnormal state in a dispatching mode. The automatic safety management purpose of the logging well site is achieved, and production faults or production accidents caused by the fact that abnormal conditions cannot be found in time due to manual inspection or the fact that the abnormal conditions cannot be responded quickly due to the manual inspection are reduced. The configuration of well site inspection personnel is effectively saved, the production cost is reduced, the production efficiency and the production quality are improved, and the production safety is improved.
Meanwhile, unsafe behavior of a person, unsafe factors of the environment and the like can be detected by utilizing information collected by the camera, such as installation work clothes identification, safety helmet identification, work shoe identification, chat identification, on-duty identification and the like; the automatic safety production device has the advantages that the aim of replacing manual full-automatic safety production by a machine is fulfilled, visualization and early warning are realized, the waste of human resources is greatly saved, and the utilization rate of information is improved.
In one embodiment, the first alarm module, the image acquisition module and the first terminal are all arranged at a monitoring point;
the monitoring point is also provided with a first microphone module which is connected with a second alarm module through a local area network or a mobile network;
the second alarm module, the second terminal and the display module are all arranged in the monitoring room;
the first alarm module and the second alarm module are both loudspeakers.
The first alarm instruction is used for alarming illegal projects of the monitoring points; and is used for prompting constructors of monitoring points or monitoring personnel of monitoring rooms to check or exclude illegal projects respectively.
The local calculation of the monitoring point image information acquired by the image acquisition module comprises the following steps:
imaging modeling is carried out on the acquired image information of the monitoring point, and the imaging modeling is used for carrying out distortion correction on imaging;
comparing the imaging information after distortion correction with pre-stored information, determining whether the monitoring point is abnormal or not based on a comparison result, and if the monitoring point is abnormal, sending a first alarm instruction through the first alarm module and the second alarm module respectively.
In the scheme, data acquisition is carried out on fixed monitoring objects of the monitoring points, such as whether sedimentation displacement exists in logging of the monitoring points, whether articles are placed in an irregular manner in the monitoring points, whether equipment illegal opening exists in the monitoring points, and whether working personnel guard shifting conditions exist; the abnormal information is reported, so that on one hand, staff can be prompted to conduct abnormal state investigation and correction; on the other hand, the monitoring center can be used for carrying out omnibearing monitoring on a logging well site and carrying out personnel scheduling on abnormal states which are not removed in time for urgent investigation.
Through correcting the monitoring point information of gathering for the information of gathering can be better compares with prestored information, thereby improves the alarm accuracy of monitoring point abnormal information, reduces the condition of misinformation, missing report, has improved production efficiency and production security greatly.
In one embodiment, the method further comprises the steps of acquiring voice information of the monitoring point through the first microphone module, and judging illegal actions by combining the voice information with image information;
cloud computing is carried out on the voice information, and judgment of whether the voice information is boring or not is obtained; if the chatting exists, a first alarm instruction is sent;
and performing violation judgment on the facial expression and the body action of the worker by utilizing the image information acquired by the image acquisition module;
and if the facial expression of the worker is stored and the eyes are closed for a long time, and the eyes are closed frequently within a preset time, and the limb actions enter a dangerous area, a first alarm instruction is sent.
According to the scheme, through data acquisition of the working state of the worker, the worker can carry out standard production operation according to the safety construction standard, the situation that the worker is distracted due to boring or fatigue is reduced, and the situation that accidents occur due to the distraction is further reduced; so that the safety of production operation is effectively improved.
In one embodiment, distortion correcting imaging includes:
selecting monitoring point image information acquired by an image acquisition module, wherein the image information is logging information, and acquiring depth a and inner diameter d of the logging information; the image acquisition module is a camera, acquires the height H1 of the camera above the logging, and constructs a logging model;
constructing a logging center imaging model based on the logging model; constructing a logging eccentric imaging model based on the logging center imaging model; correcting the logging eccentric imaging model;
and comparing the corrected logging eccentric imaging model with pre-stored information, and determining whether the monitoring point is abnormal or not based on a comparison result.
The logging image information acquired by the monitoring points is subjected to equal division of m sections, and the distance P between an object in the monitoring points and a camera is calculated:
P＝m*L1+H1 (1)
wherein L1 is the length of m-segment equal segmentation in the logging image information;
a logging model is constructed based on the pitch P.
Taking the spatial coordinates O1 (x 1, y1, z 1) of any point k of the well logging, and constructing a well logging model:
wherein d is the logging inner diameter; a is the logging depth;
when the center of the camera is positioned at a logging center coordinate O (0, H1 +H2), logging grid imaging in the equal-division image information of m sections is equidistant concentric circles, and the coordinate of k points in the logging grid imaging is O2 (x 2, y 2):
constructing a logging center imaging model based on the coordinates of the k points in the logging grid imaging as O2 (x 2, y 2);
wherein P is the distance from the object in the monitoring point to the camera; d is the logging inner diameter;
when the image information obtained by the monitoring points deviates, the camera deviates from the logging center coordinates and is positioned at coordinates O (ox 2, oy2, H1+H2), a logging eccentric imaging model is constructed by using the logging center imaging model, and the coordinates of k points in logging grid imaging are O3 (x 3, y 3):
wherein P is the distance from the object in the monitoring point to the camera; d is the logging inner diameter; s is the eccentric distance.
Performing offset correction on the constructed logging eccentric imaging model comprises:
expanding the constructed logging eccentric imaging model to obtain a plane model of the logging eccentric imaging model, and correcting the logging image information acquired by the monitoring points of the m sections divided equally in sequence transversely and longitudinally based on the plane model so as to vertically and horizontally correct the intersecting line between two adjacent sections; recovering the corrected plane model into a cylindrical logging model again, and obtaining the corrected cylindrical logging model;
marking monitoring points in the corrected cylindrical logging model, comparing the image information of the monitoring points with pre-stored information, determining whether the monitoring points are abnormal or not based on comparison results, and sending first alarm instructions through the first alarm module and the second alarm module respectively if the monitoring points are abnormal.
In the scheme, a logging center imaging model is further built on the logging model by building the logging model according to the acquired monitoring point image information, and a logging eccentric imaging model is built by using the logging center imaging model; when the camera is installed at a monitoring point, the monitoring point is initialized to obtain an initial value, and shot monitoring point photos are compared based on the initial value (the logging model and the logging center imaging center), so that the purpose of calibrating distorted photos is achieved; the method comprises the steps that whether abnormal conditions exist or not can be obtained through model calculation and comparison of a plurality of monitoring positions on monitoring points arranged on logging; and further alarms the monitored abnormal situation.
In one embodiment, to improve the computing efficiency, the method further includes: comparing the logging eccentric imaging models for multiple times, calculating the error rate of logging deformation, and if the error rate R is more than 0 and less than 1, not correcting distortion, counting the logging eccentric imaging models corrected in the past, and extracting a plurality of logging eccentric imaging information closest to average error based on the counting result;
extracting non-alarming image information from a plurality of logging eccentric imaging information closest to the average error as comparison information;
using the contrast information as abnormal alarm monitoring contrast in the eccentric imaging image;
in the monitoring process, if the deviation of the comparison result of the comparison information and the latest shot monitoring image information is u, the fact that the latest shot monitoring image has a focal length or shooting direction changes is indicated, the latest shot monitoring image is defined as a new monitoring image at the moment t, and a logging eccentric imaging model is built for the new monitoring image at the moment t; and then monitoring the monitoring position for abnormality.
In the scheme, correction calculation is not needed for many times under the condition that the shooting focal length of the camera is unchanged and the shooting angle or position is unchanged, so that the calculation efficiency of the system is improved, and the system data redundancy caused by many times of calculation is reduced; and the abnormal state quick response is improved by reducing multiple times of calculation, so that the first alarm instruction is quickly generated; when the camera moves or parameters are adjusted, the correction calculation is carried out again, so that the purpose of intelligent monitoring is realized; and further, the safety production monitoring of the logging well site is more intelligent.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (10)
1. Well logging field management system based on video intelligent recognition, characterized by comprising:
the image acquisition module is used for being distributed at a plurality of monitoring points and acquiring image information of the monitoring points;
the first terminal is used for carrying out encryption storage and local calculation on the monitoring point image information acquired by the image acquisition module, and generating a first alarm instruction to the first alarm module when abnormal monitoring occurs;
encrypting and transmitting the local calculation result of the monitoring point to a cloud;
the second terminal is used for acquiring a local calculation result transmitted by the first terminal from the cloud and generating an image-text information instruction from the calculation result and sending the image-text information instruction to the display module; when the image-text information instruction comprises a first alarm instruction, the first alarm instruction is sent to the second alarm module.
2. The well logging site management system based on intelligent video identification as defined in claim 1, wherein the first alarm module, the image acquisition module and the first terminal are all arranged at monitoring points;
the monitoring point is also provided with a first microphone module which is connected with a second alarm module through a local area network or a mobile network;
the second alarm module, the second terminal and the display module are all arranged in the monitoring room;
the first alarm module and the second alarm module are both loudspeakers.
3. The well logging site management system based on intelligent video identification as defined in claim 1, wherein the first alarm instruction is used for alarming illegal projects of a monitoring point; and is used for prompting constructors of monitoring points or monitoring personnel of monitoring rooms to check or exclude illegal projects respectively.
4. The video intelligent identification-based logging wellsite management system of claim 1, wherein locally calculating the monitoring point image information acquired by the image acquisition module comprises:
imaging modeling is carried out on the acquired image information of the monitoring point, and the imaging modeling is used for carrying out distortion correction on imaging;
comparing the imaging information after distortion correction with pre-stored information, determining whether the monitoring point is abnormal or not based on a comparison result, and if the monitoring point is abnormal, sending a first alarm instruction through the first alarm module and the second alarm module respectively.
5. The well logging site management system based on intelligent video recognition as defined in claim 1, further comprising obtaining voice information of the monitoring point through the first microphone module, and performing illegal action judgment by combining the voice information with image information;
cloud computing is carried out on the voice information, and judgment of whether the voice information is boring or not is obtained; if the chatting exists, a first alarm instruction is sent;
and performing violation judgment on the facial expression and the body action of the worker by utilizing the image information acquired by the image acquisition module;
and if the facial expression of the worker is stored and the eyes are closed for a long time, and the eyes are closed frequently within a preset time, and the limb actions enter a dangerous area, a first alarm instruction is sent.
6. The video intelligent identification-based well site management system of claim 5, wherein distortion correcting imaging comprises:
selecting monitoring point image information acquired by an image acquisition module, wherein the image information is logging information, and acquiring depth a and inner diameter d of the logging information; the image acquisition module is a camera, acquires the height H1 of the camera above the logging, and constructs a logging model;
constructing a logging center imaging model based on the logging model; constructing a logging eccentric imaging model based on the logging center imaging model; correcting the logging eccentric imaging model;
and comparing the corrected logging eccentric imaging model with pre-stored information, and determining whether the monitoring point is abnormal or not based on a comparison result.
7. The well logging site management system based on intelligent video recognition as claimed in claim 6, wherein the well logging image information acquired by the monitoring points is divided into m segments in equal parts, and the distance P from the object in the monitoring points to the camera is calculated:
P＝m*L1+H1 (1)
wherein L1 is the length of m-segment equal segmentation in the logging image information;
a logging model is constructed based on the pitch P.
8. The well site management system for well logging based on intelligent video recognition as set forth in claim 7, wherein,
taking the spatial coordinates O1 (x 1, y1, z 1) of any point k of the well logging, and constructing a well logging model:
wherein d is the logging inner diameter; a is the logging depth;
when the center of the camera is positioned at a logging center coordinate O (0, H1 +H2), logging grid imaging in the equal-division image information of m sections is equidistant concentric circles, and the coordinate of k points in the logging grid imaging is O2 (x 2, y 2):
constructing a logging center imaging model based on the coordinates of the k points in the logging grid imaging as O2 (x 2, y 2);
wherein P is the distance from the object in the monitoring point to the camera; d is the logging inner diameter;
when the image information obtained by the monitoring points deviates, the camera deviates from the logging center coordinates and is positioned at coordinates O (ox 2, oy2, H1+H2), a logging eccentric imaging model is constructed by using the logging center imaging model, and the coordinates of k points in logging grid imaging are O3 (x 3, y 3):
wherein P is the distance from the object in the monitoring point to the camera; d is the logging inner diameter; s is the eccentric distance.
9. The video intelligent identification-based well site management system of claim 8, wherein performing offset correction on the constructed well logging off-center imaging model comprises:
expanding the constructed logging eccentric imaging model to obtain a plane model of the logging eccentric imaging model, and correcting the logging image information acquired by the monitoring points of the m sections divided equally in sequence transversely and longitudinally based on the plane model so as to vertically and horizontally correct the intersecting line between two adjacent sections; recovering the corrected plane model into a cylindrical logging model again, and obtaining the corrected cylindrical logging model;
marking monitoring points in the corrected cylindrical logging model, comparing the image information of the monitoring points with pre-stored information, determining whether the monitoring points are abnormal or not based on comparison results, and sending first alarm instructions through the first alarm module and the second alarm module respectively if the monitoring points are abnormal.
10. The well logging site management system based on intelligent video recognition according to claim 8, wherein the well logging site management system is characterized in that the well logging eccentric imaging models are compared for a plurality of times, the deformation error rate of the well logging eccentric imaging models is calculated, if the error rate R is more than 0 and less than 1, distortion correction is not performed, statistics is performed on the well logging eccentric imaging models corrected in the past, and a plurality of pieces of well logging eccentric imaging information closest to average error are extracted based on the statistics result;
extracting non-alarming image information from a plurality of logging eccentric imaging information closest to the average error as comparison information;
using the contrast information as abnormal alarm monitoring contrast in the eccentric imaging image;
in the monitoring process, if the deviation of the comparison result of the comparison information and the latest shot monitoring image information is u, the fact that the latest shot monitoring image has a focal length or shooting direction changes is indicated, the latest shot monitoring image is defined as a new monitoring image at the moment t, and a logging eccentric imaging model is built for the new monitoring image at the moment t; and then monitoring the monitoring position for abnormality.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211606323.6A CN116824476A (en) | 2022-12-14 | 2022-12-14 | Logging well site management system based on video intelligent recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211606323.6A CN116824476A (en) | 2022-12-14 | 2022-12-14 | Logging well site management system based on video intelligent recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116824476A true CN116824476A (en) | 2023-09-29 |
Family
ID=88115521
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211606323.6A Pending CN116824476A (en) | 2022-12-14 | 2022-12-14 | Logging well site management system based on video intelligent recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116824476A (en) |
-
2022
- 2022-12-14 CN CN202211606323.6A patent/CN116824476A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109240311B (en) | Outdoor electric power field construction operation supervision method based on intelligent robot | |
| CN112804498B (en) | Wearing condition monitoring system and method for safety protection harness | |
| CN112308510A (en) | Green and environment-friendly building construction management system and method | |
| CN111932709A (en) | Method for realizing violation safety supervision of inspection operation of gas station based on AI identification | |
| CN113191699A (en) | Power distribution construction site safety supervision method | |
| CN110070155A (en) | A kind of comprehensive Activity recognition method and system of the inmate based on wearable device | |
| CN111506011A (en) | Construction safety monitoring method and device | |
| CN113343854A (en) | Fire operation flow compliance detection method based on video monitoring | |
| CN103885406A (en) | Industry gas production equipment fault intelligent diagnosis and monitoring system based on multi-data fusion | |
| CN113206978A (en) | Security intelligent monitoring early warning system and method for oil and gas pipeline station | |
| CN115100813B (en) | Intelligent community system based on digital twins | |
| CN113743725B (en) | Ascending qualification detection method and system for ascending operators based on edge calculation | |
| CN107895453A (en) | Building safety warning system and method | |
| CN112906441B (en) | Image recognition system and method for exploration and maintenance in communication industry | |
| CN106081958A (en) | A kind of derrick crane on-line monitoring system | |
| CN108388873A (en) | A kind of supervisory systems of machine vision, method and client computer, storage medium | |
| CN113887310A (en) | Worker standard dressing identification method, system and medium | |
| CN116824476A (en) | Logging well site management system based on video intelligent recognition | |
| TW201037473A (en) | System and method for remotely monitoring the scene of industry | |
| CN116311729A (en) | AI-based power grid infrastructure site safety management system | |
| CN115953815A (en) | Monitoring method and device for infrastructure site | |
| CN114419475A (en) | Construction safety discrimination method and system based on video information behavior pattern recognition | |
| CN213457742U (en) | Welding operation monitoring system | |
| CN112101180B (en) | Method and system for identifying unsafe behaviors of people | |
| CN114314347A (en) | Safety monitoring and management system for hoisting machinery |
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 |