CN111597903A - Intelligent monitoring box for distribution network and monitoring method thereof - Google Patents
Intelligent monitoring box for distribution network and monitoring method thereof Download PDFInfo
- Publication number
- CN111597903A CN111597903A CN202010303418.5A CN202010303418A CN111597903A CN 111597903 A CN111597903 A CN 111597903A CN 202010303418 A CN202010303418 A CN 202010303418A CN 111597903 A CN111597903 A CN 111597903A
- Authority
- CN
- China
- Prior art keywords
- foreign object
- signal
- person
- color
- distribution network
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 80
- 238000009826 distribution Methods 0.000 title claims abstract description 35
- 238000000034 method Methods 0.000 title claims abstract description 33
- 230000004044 response Effects 0.000 claims description 36
- 231100001261 hazardous Toxicity 0.000 claims description 18
- 238000012545 processing Methods 0.000 claims description 12
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 239000003086 colorant Substances 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 4
- 238000011156 evaluation Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 description 8
- 238000003860 storage Methods 0.000 description 5
- 238000004519 manufacturing process Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000003384 imaging method Methods 0.000 description 2
- 230000001681 protective effect Effects 0.000 description 2
- 206010019196 Head injury Diseases 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000036544 posture Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 238000004579 scanning voltage microscopy Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- 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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C11/00—Photogrammetry or videogrammetry, e.g. stereogrammetry; Photographic surveying
- G01C11/04—Interpretation of pictures
- G01C11/30—Interpretation of pictures by triangulation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J3/00—Spectrometry; Spectrophotometry; Monochromators; Measuring colours
- G01J3/46—Measurement of colour; Colour measuring devices, e.g. colorimeters
-
- 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
- G06V40/103—Static body considered as a whole, e.g. static pedestrian or occupant recognition
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
-
- 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)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Theoretical Computer Science (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Signal Processing (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Alarm Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a distribution network intelligent monitoring box and a monitoring method thereof, wherein a current image of a working area is shot through a camera unit; defining a danger area in a work area; detecting a foreign object using a foreign object detector; classifying whether the foreign object is a human object using a classifier; identifying whether the foreign object satisfies the following condition using a color identifier: the set color exists, and the position and the proportion of the set color accord with the setting; an alarm is issued. Therefore, the wearing of the intelligent and automatic monitoring safety helmet is realized.
Description
Technical Field
The invention relates to the field of safety monitoring, in particular to an intelligent monitoring box for a distribution network and a monitoring method thereof.
Background
Production safety is a crucial part of the production. In a construction site, the safety helmet is used as the most common and practical personal protection appliance, and can effectively prevent and reduce the head injury caused by an external dangerous source. However, for a long time, the problems of low comprehensive quality and weak safety consciousness of working personnel in construction areas in China generally exist, especially the wearing consciousness of basic protection facilities (such as safety helmets) is lacked, and the working risk is greatly increased. Many work sites additionally demarcate hazardous areas in the work area and require that workers in the hazardous areas must take protective measures. However, if a specially-assigned person is set at any time for supervision, the labor cost is easily increased. The method provides an automatic and intelligent scheme, which is a problem to be solved urgently in the field of safety monitoring at present.
Disclosure of Invention
The invention aims to at least solve one of the technical problems in the prior art and provides an intelligent monitoring box for a distribution network and a monitoring method thereof.
The technical scheme adopted by the invention for solving the problems is as follows:
in a first aspect of the present invention, a monitoring method for a distribution network intelligent monitoring box includes the following steps:
capturing a current image of the working area at defined time intervals by means of at least one camera unit;
defining at least one hazard zone in the work area;
processing the current image using a foreign object detector, the foreign object detector generating a first signal if a foreign object is detected in the hazardous area;
classifying the foreign object using a classifier in response to the first signal, the classifier generating a second signal if the foreign object is identified as a person;
identifying the foreign object using a color identifier in response to a second signal if the foreign object does not satisfy the following condition: the set color exists, and the position and the proportion of the set color accord with the setting; the color identifier generates a third signal;
an alarm is issued in response to the third signal.
According to a first aspect of the present invention, a monitoring method for a distribution network intelligent monitoring box further includes the following steps:
processing the current image using a foreign object detector, the foreign object detector generating a fourth signal if a foreign object is detected in a non-hazardous area within the working area;
classifying the foreign object using a classifier in response to the fourth signal, the classifier generating a fifth signal if the foreign object is identified as a person;
tracking the identified person through a series of corresponding current images using a person tracking algorithm in response to a fifth signal, generating a sixth signal if the identified person has a tendency to move toward the hazardous area and the identified person is within a set distance from the hazardous area;
identifying the foreign object using a color identifier in response to a sixth signal if the foreign object does not satisfy the following condition: the color recognizer generates a seventh signal when a set color exists and the position and the proportion of the set color accord with the set color;
an alarm is issued in response to the seventh signal.
According to a first aspect of the present invention, a monitoring method for a distribution network intelligent monitoring box further includes the following steps:
monitoring the working area by at least one thermal sensor, the at least one thermal sensor generating an eighth signal if the temperature of the working area is identified to exceed a setting;
an alarm is issued in response to the eighth signal.
According to a first aspect of the present invention, a monitoring method for a distribution network intelligent monitoring box further includes the following steps:
in a check-in mode;
shooting a current face image through one shooting unit;
and matching the face images with the images in the check-in image library one by one.
According to the first aspect of the present invention, the foreign object detector compares the current image with a standard background image, and marks a continuous difference pixel point in the current image with the standard background image as one of the foreign objects; the standard background image is an image of the working area aligned with the camera unit when the working area is in a state without a foreign object.
According to a first aspect of the present invention, a monitoring method for a distribution network intelligent monitoring box, wherein the set colors include red, yellow, white and blue.
According to a first aspect of the present invention, a monitoring method for an intelligent monitoring box of a distribution network, the positions and the proportions of the set colors are specifically as follows: the set color is positioned at the topmost part of the foreign object, and accounts for 5% -10% of the range.
According to the first aspect of the present invention, the tendency of the identified person to move to the dangerous area is judged as follows: the person tracking algorithm processes two continuous current images arranged according to a time sequence to obtain first position information representing a linear distance between a person identified in the first current image and the dangerous area and second position information representing a linear distance between a person identified in the second current image and the dangerous area, wherein the second position information is smaller than the first position information.
According to the first aspect of the present invention, the distance of the identified person from the dangerous area is determined as follows: the second position information is less than a setting.
In a second aspect of the present invention, a distribution network intelligent monitoring box includes:
at least one camera unit for capturing current images of the working area at defined time intervals;
a configuration unit for defining at least one danger zone in the working area;
an evaluation unit having a foreign object detector, a classifier, and a color identifier;
the foreign object detector is configured to: processing a current image, and generating a first signal if a foreign object is detected in the dangerous area;
the classifier is configured to: classifying the foreign object in response to the first signal, generating a second signal if the foreign object is identified as a person;
the color identifier is configured to: responding to a second signal, identifying the foreign object, and if the foreign object has a set color and the position and the proportion of the set color conform to the set, generating a third signal by the color identifier;
an alarm for issuing an alarm in response to the third signal.
The technical scheme at least has the following beneficial effects:
additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The invention is further illustrated with reference to the following figures and examples.
Fig. 1 is a flowchart of a monitoring method for a distribution network intelligent monitoring box according to an embodiment of the present invention;
fig. 2 is another flowchart of a monitoring method for a distribution network intelligent monitoring box according to an embodiment of the present invention;
FIG. 3 is a schematic view of monitoring whether a foreign object in the hazardous area is wearing a hard hat;
fig. 4 is a schematic view of monitoring whether a foreign object in a non-hazardous area is wearing a hard hat.
Detailed Description
Reference will now be made in detail to the present preferred embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to like elements throughout.
In the description of the present invention, the meaning of a plurality of means is one or more, the meaning of a plurality of means is two or more, and larger, smaller, larger, etc. are understood as excluding the number, and larger, smaller, inner, etc. are understood as including the number. If the first and second are described for the purpose of distinguishing technical features, they are not to be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated or implicitly indicating the precedence of the technical features indicated.
In the description of the present invention, unless otherwise explicitly limited, terms such as arrangement, installation, connection and the like should be understood in a broad sense, and those skilled in the art can reasonably determine the specific meanings of the above terms in the present invention in combination with the specific contents of the technical solutions.
Referring to fig. 1 and 3, an embodiment of the present invention provides a monitoring method for a distribution network intelligent monitoring box, including the following steps:
step S110, capturing a current image of the working area 10 at defined time intervals by at least one image capturing unit;
step S120, defining at least one danger area 11 in the working area 10;
step S130, processing the current image by using a foreign object 21 detector, and if the foreign object 21 is detected in the dangerous area 11, generating a first signal by using the foreign object 21 detector;
step S140, classifying the foreign object 21 using a classifier in response to the first signal, the classifier generating a second signal if the foreign object 21 is identified as a person;
step S150, identifying the foreign object 21 using the color identifier in response to the second signal, if the foreign object 21 does not satisfy the following condition: if the set color exists and the position and the proportion of the set color accord with the set color, the color recognizer generates a third signal;
and step S160, sending out an alarm in response to the third signal.
In this embodiment, the camera unit employs cameras, a stereoscopic camera system is made up of more than two cameras, each camera providing an image at the current time, each image being offset from the other images, and the offset being known, then using a trigonometric relationship, a specific distance relationship can be determined. In other embodiments, the camera unit may be a time-of-flight range imaging camera that provides an image of the current time of the work area 10 and determines the specific distance relationship from the time-of-flight.
In addition, at least one camera unit will take the whole working area 10 inside together; a single camera element may only capture a portion of the working area 10 and multiple camera elements may capture working areas 10 that include overlapping portions.
By processing the current image with an image processing algorithm, a dangerous area 11 can be planned in the working area 10, and the dangerous area 11 can be marked.
The foreign object 21 detector compares each pixel of the current image with each pixel of the standard background image, and marks a plurality of continuous difference pixels of the current image and the standard background image as a foreign object 21. The standard background image is an image of the working area 10 aligned with one imaging unit in a state where there is no foreign object 21. The number of consecutive difference pixel points is less than a set threshold and will not be marked as a foreign object 21. If there are multiple consecutive delta pixel regions, each consecutive delta pixel region is marked as a foreign object 21. In one embodiment, the foreign object 21 detector is a color comparator, which compares the color difference between each pixel of the current image and each pixel of the standard background image, and determines the corresponding pixel of the current image as a difference pixel when the color difference is higher than a predetermined threshold.
In response to the first signal, the classifier is activated; of course in other embodiments, the classifier may be active at all times. The first signal contains at least one foreign object 21 identified by the foreign object 21 detector. The classifier classifies the foreign object 21 and generates a second signal if the foreign object 21 is identified as a person. The classifier can accurately identify human objects with different angles and different postures through multiple times of training. At present, there are many classifiers used for image classification, such as SVM, decision tree, random forest, etc., and the classifier in the present invention may be one of them, or other types of classifiers.
In response to the second signal, the color identifier is activated; of course in other embodiments the color identifier may be active at all times. The color identifier identifies the foreign object 21 if the foreign object 21 does not satisfy the following condition: if the set color exists and the position and the proportion of the set color accord with the set color, a third signal is generated. Specifically, the colors that can be set include red, yellow, white, and blue; the positions and the occupied proportions of the set colors are specifically as follows: the position of the set color is located at the topmost part of the foreign object 21, and the proportion of the set color is 5% -10%. In fact, in this embodiment, in order to detect that the foreign object 21 entering the dangerous area 11 is a person, whether the helmet is properly worn on the top of the head is present.
The color of the top of the foreign object 21 is preferentially detected to determine whether the top of the foreign object 21, i.e., the head of the person, has a predetermined color. When a person wears the safety helmet on the top of the head, the safety helmet occupies about half of the head, and whether the proportion of the number of pixels with set colors at the top to the total number of pixels of an external image is within the range of 5% -10% is judged according to the proportion of the head to the human body.
The set colors including red, yellow, white and blue are due to the classification of the safety helmet in China as follows: the safety helmet used in the regulations of the mandatory standard for safety production of the latest electric power enterprise in 2006, the safety operation regulations for field operation and the safety accident prevention and treatment practice book is divided into four colors of red, yellow, white and blue. The manager wears red, the operator on duty wears yellow, the external inspection and visit personnel wear white, and the field operation (overhaul, test and construction) personnel wear blue safety helmets.
Of course, in other embodiments, other objects can be identified by changing the type of color to be identified and the proportion of the color of the type, for example, whether the protective clothing is worn correctly or not.
The alarm is in response to the third signal sent by the color identifier. The alarm can be an audio player installed in a distribution network intelligent monitoring box of the field equipment, and the audio player plays stored alarm sound; the alarm can also be an on-line alarm module, and sends audio or text information to monitoring personnel through the network for alarming. The alarm can alarm through sound or through text information.
The monitoring method of the intelligent monitoring box of the distribution network can effectively monitor a construction site, judge whether personnel in the construction site correctly wear safety helmets to enter a dangerous area 11, and give an alarm for dangerous operation, thereby realizing production safety monitoring of the construction site, realizing intelligent chemical monitoring and improving monitoring efficiency.
Referring to fig. 2 and 4, further, a monitoring method for a distribution network intelligent monitoring box further includes the following steps:
step S210, processing the current image by using a foreign object 21 detector, and if the foreign object 21 is detected in the non-dangerous area 12 in the working area 10, generating a fourth signal by using the foreign object 21 detector;
step S220, classifying the foreign object 21 using a classifier according to the fourth signal, and if the foreign object 21 is identified as a person, the classifier generates a fifth signal;
step S230, tracking the identified person through a series of corresponding current images using a person tracking algorithm in response to the fifth signal, and generating a sixth signal if the identified person has a tendency to move toward the dangerous area 11 and the distance between the identified person and the dangerous area 11 meets a set value;
step S240, identifying the foreign object 21 using the color identifier in response to the sixth signal, if the foreign object 21 does not satisfy the following condition: the set color exists, the position and the proportion of the set color accord with the set color, and the color recognizer generates a seventh signal;
and step S250, sending out an alarm in response to the seventh signal.
In this embodiment, the non-hazardous area 12 is an area within the working area 10 other than the hazardous area 11. The foreign object 21 detector and classifier may use modules consistent with the functionality and structure described previously. Of course, the foreign object 21 detector and classifier that performs this step process may be shared with the above steps. The person tracking algorithm processes two continuous current images arranged according to a time sequence to obtain first position information representing the linear distance between the recognized person in the first current image and the dangerous area 11 and second position information representing the linear distance between the recognized person in the second current image and the dangerous area 11, wherein the second position information is smaller than the first position information; that is, the direction of movement of the identified person is in the direction toward the dangerous area 11, and the identified person tends to move toward the dangerous area 11. When the second position information is smaller than the set value, it is determined that the distance between the recognized person and the dangerous area 11 matches the set value, that is, the recognized person approaches the dangerous area 11 and the recognized person is about to enter the dangerous area 11. Likewise, whether the foreign object 21 detected as "person" with the color identifier as described above satisfies the setting, i.e., whether the person about to enter the dangerous area 11 wears a helmet overhead is detected. If the situation is monitored, the color recognizer sends a seventh signal to the alarm, and the alarm gives an alarm.
Further, the monitoring method of the intelligent monitoring box of the distribution network further comprises the following steps:
monitoring the working area 10 by means of at least one thermal sensor, the at least one thermal sensor generating an eighth signal if the temperature of the working area 10 is identified to be outside a set value;
an alarm is issued in response to the eighth signal.
In this embodiment, the working area 10 is monitored for signs of fire, and when the temperature recognized by the thermal sensor exceeds a set value, it is determined that there are signs of fire. If there is evidence of a fire, an alarm is issued.
Further, the monitoring method of the intelligent monitoring box of the distribution network further comprises the following steps:
in a check-in mode;
shooting a current face image through a shooting unit;
and matching the face images with the images in the check-in image library one by one.
In this embodiment, a worker is checked in and out of work. The check-in image library stores front face images of a plurality of workers, the front face images are collected and shot in advance, and each front face image is paired with the name of the worker one by one. When the user wants to sign, the key is pressed down to enable the intelligent distribution network monitoring box to operate in a sign-in mode, and the intelligent distribution network monitoring box shoots a face image which is located in front of the camera shooting unit at present through the camera shooting unit. The face image is matched with the images in the check-in image library one by one, and the face matching algorithm can use the existing technology, such as Eigenface or PCA technology, and the details are not described herein. When the face image is successfully matched with one front face image in the check-in image library, the name of a worker paired with the front face image is marked in a check-in list to represent the check-in of the worker, and the check-in time is recorded, so that the function of checking cards on work and off duty is realized.
Another embodiment of the present invention provides a distribution network intelligent monitoring box, including:
at least one camera unit for capturing current images of the working area 10 at defined time intervals;
a configuration unit for defining at least one danger zone 11 in the working area 10;
an evaluation unit having a foreign object 21 detector, a classifier and a color identifier;
the foreign object 21 detector is configured to: processing the current image, generating a first signal if a foreign object 21 is detected in the hazardous area 11;
the classifier is configured to: classifying the foreign object 21 in response to the first signal, generating a second signal if the foreign object 21 is identified as a person;
the color identifier is configured to: responding to the second signal, identifying the foreign object 21, and if the foreign object 21 has the set color and the position and the proportion of the set color conform to the setting, generating a third signal by the color identifier;
an alarm for issuing an alarm in response to the third signal.
Further, in the distribution network intelligent monitoring box,
the foreign object 21 detector is further configured to: processing the current image, and generating a fourth signal if a foreign object 21 is detected in a non-hazardous area 12 in the working area 10;
the classifier is further configured to: classifying the foreign object 21 in response to the fourth signal, and generating a fifth signal if the foreign object 21 is recognized as a person;
the tracking module is further configured to: tracking the identified person through a series of corresponding current images in response to the fifth signal, and generating a sixth signal if the identified person has a tendency to move toward the hazardous area 11 and the distance of the identified person from the hazardous area 11 corresponds to a setting; it should be noted that, the tracking module determines that the identified person has a tendency to move toward the dangerous area 11 and the distance between the identified person and the dangerous area 11 is as above, and it is not repeated here;
the color identifier is further configured to: identifying the foreign object 21 in response to the sixth signal if the foreign object 21 does not satisfy the following condition: if the set color exists and the position and the proportion of the set color accord with the set color, a seventh signal is generated;
and the alarm is also used for giving an alarm in response to the seventh signal.
Further, this net intelligent monitoring case that joins in marriage still includes:
at least one thermal sensor for monitoring the working area 10, generating an eighth signal if the temperature of the working area 10 is identified to exceed a set value;
wherein the alarm is further responsive to the eighth signal to issue an alarm.
Further, the camera shooting unit is also used for shooting the current face image; the utility model provides a join in marriage net intelligence monitoring box still includes:
a key is pressed to enable the intelligent monitoring box of the distribution network to enter a sign-in mode;
a check-in image library configured to: storing front face images of a plurality of workers, wherein the front face images are paired with the names of the workers one by one;
a matching module configured to: and matching the face images with the images in the check-in image library one by one.
Further, a join in marriage net intelligence monitoring box still includes:
a controller, which adopts a Mini Windows host;
the POE switch is used for transmitting data and supplying power to the at least one camera unit;
and the router is used for connecting the network.
According to another embodiment of the invention, a storage medium is provided, which stores executable instructions that can be executed by a computer, so that the computer drives a distribution network intelligent monitoring box connected with the computer to monitor a construction site according to the monitoring method, thereby ensuring the safety of the construction site.
Examples of storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device.
The above description is only a preferred embodiment of the present invention, and the present invention is not limited to the above embodiment, and the present invention shall fall within the protection scope of the present invention as long as the technical effects of the present invention are achieved by the same means.
Claims (10)
1. A monitoring method of an intelligent monitoring box of a distribution network is characterized by comprising the following steps:
capturing a current image of the working area at defined time intervals by means of at least one camera unit;
defining at least one hazard zone in the work area;
processing the current image using a foreign object detector, the foreign object detector generating a first signal if a foreign object is detected in the hazardous area;
classifying the foreign object using a classifier in response to the first signal, the classifier generating a second signal if the foreign object is identified as a person;
identifying the foreign object using a color identifier in response to a second signal if the foreign object does not satisfy the following condition: if the set color exists and the position and the proportion of the set color accord with the set color, the color recognizer generates a third signal;
an alarm is issued in response to the third signal.
2. The monitoring method of the intelligent monitoring box of the distribution network according to claim 1, further comprising the following steps:
processing the current image using a foreign object detector, the foreign object detector generating a fourth signal if a foreign object is detected in a non-hazardous area within the working area;
classifying the foreign object using a classifier in response to the fourth signal, the classifier generating a fifth signal if the foreign object is identified as a person;
tracking the identified person through a series of corresponding current images using a person tracking algorithm in response to a fifth signal, generating a sixth signal if the identified person has a tendency to move toward the hazardous area and the identified person is within a set distance from the hazardous area;
identifying the foreign object using a color identifier in response to a sixth signal if the foreign object does not satisfy the following condition: the color recognizer generates a seventh signal when a set color exists and the position and the proportion of the set color accord with the set color;
an alarm is issued in response to the seventh signal.
3. The monitoring method of the intelligent monitoring box of the distribution network according to claim 1 or 2, characterized by further comprising the following steps:
monitoring the working area by at least one thermal sensor, the at least one thermal sensor generating an eighth signal if the temperature of the working area is identified to exceed a setting;
an alarm is issued in response to the eighth signal.
4. The monitoring method of the intelligent monitoring box of the distribution network according to claim 1 or 2, characterized by further comprising the following steps:
in a check-in mode;
shooting a current face image through one shooting unit;
and matching the face images with the images in the check-in image library one by one.
5. The monitoring method of the intelligent monitoring box of the distribution network according to claim 1 or 2, characterized in that the foreign object detector compares the current image with a standard background image, and marks a continuous difference pixel point in the current image with the standard background image as one of the foreign objects; the standard background image is an image of the working area aligned with the camera unit when the working area is in a state without a foreign object.
6. The monitoring method of the intelligent monitoring box of the distribution network according to claim 1 or 2, wherein the set colors comprise red, yellow, white and blue.
7. The monitoring method of the intelligent monitoring box of the distribution network according to claim 6, wherein the set color positions and proportions specifically correspond to the set color positions and proportions: the set color is positioned at the topmost part of the foreign object, and accounts for 5% -10% of the range.
8. The monitoring method of the intelligent monitoring box of the distribution network, according to claim 2, characterized in that the identified tendency of the person to move to the dangerous area is judged as follows: the person tracking algorithm processes two continuous current images arranged according to a time sequence to obtain first position information representing a linear distance between a person identified in the first current image and the dangerous area and second position information representing a linear distance between a person identified in the second current image and the dangerous area, wherein the second position information is smaller than the first position information.
9. The monitoring method of the intelligent monitoring box of the distribution network according to claim 8, wherein the distance between the identified person and the dangerous area is determined according to the following: the second position information is less than a setting.
10. The utility model provides a join in marriage net intelligence monitoring box which characterized in that includes:
at least one camera unit for capturing current images of the working area at defined time intervals;
a configuration unit for defining at least one danger zone in the working area;
an evaluation unit having a foreign object detector, a classifier, and a color identifier;
the foreign object detector is configured to: processing a current image, and generating a first signal if a foreign object is detected in the dangerous area;
the classifier is configured to: classifying the foreign object in response to the first signal, generating a second signal if the foreign object is identified as a person;
the color identifier is configured to: responding to a second signal, identifying the foreign object, and if the foreign object has a set color and the position and the proportion of the set color conform to the set, generating a third signal by the color identifier;
an alarm for issuing an alarm in response to the third signal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010303418.5A CN111597903B (en) | 2020-04-17 | 2020-04-17 | Intelligent monitoring box for distribution network and monitoring method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010303418.5A CN111597903B (en) | 2020-04-17 | 2020-04-17 | Intelligent monitoring box for distribution network and monitoring method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111597903A true CN111597903A (en) | 2020-08-28 |
| CN111597903B CN111597903B (en) | 2023-04-28 |
Family
ID=72181363
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010303418.5A Active CN111597903B (en) | 2020-04-17 | 2020-04-17 | Intelligent monitoring box for distribution network and monitoring method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111597903B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104169630A (en) * | 2012-03-16 | 2014-11-26 | 皮尔茨公司 | Method and device for securing a hazardous working area |
| CN106447845A (en) * | 2016-08-31 | 2017-02-22 | 广西建工集团第五建筑工程有限责任公司 | Pre-job safety education and management system |
| CN108319934A (en) * | 2018-03-20 | 2018-07-24 | 武汉倍特威视系统有限公司 | Safety cap wear condition detection method based on video stream data |
| CN108416968A (en) * | 2018-01-31 | 2018-08-17 | 国家能源投资集团有限责任公司 | Fire alarm method and apparatus |
| CN110232795A (en) * | 2019-06-20 | 2019-09-13 | 中煤电气有限公司 | A kind of monitoring method and system based on infrared thermal imaging technique |
| CN210088360U (en) * | 2019-06-12 | 2020-02-18 | 江苏伟瑞建筑工程有限公司 | Comprehensive monitoring device for construction site of house building engineering |
-
2020
- 2020-04-17 CN CN202010303418.5A patent/CN111597903B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104169630A (en) * | 2012-03-16 | 2014-11-26 | 皮尔茨公司 | Method and device for securing a hazardous working area |
| CN106447845A (en) * | 2016-08-31 | 2017-02-22 | 广西建工集团第五建筑工程有限责任公司 | Pre-job safety education and management system |
| CN108416968A (en) * | 2018-01-31 | 2018-08-17 | 国家能源投资集团有限责任公司 | Fire alarm method and apparatus |
| CN108319934A (en) * | 2018-03-20 | 2018-07-24 | 武汉倍特威视系统有限公司 | Safety cap wear condition detection method based on video stream data |
| CN210088360U (en) * | 2019-06-12 | 2020-02-18 | 江苏伟瑞建筑工程有限公司 | Comprehensive monitoring device for construction site of house building engineering |
| CN110232795A (en) * | 2019-06-20 | 2019-09-13 | 中煤电气有限公司 | A kind of monitoring method and system based on infrared thermal imaging technique |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111597903B (en) | 2023-04-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107645652A (en) | A kind of illegal geofence system based on video monitoring | |
| CN113223046B (en) | Method and system for identifying prisoner behaviors | |
| CN110867046A (en) | Intelligent car washer video monitoring and early warning system based on cloud computing | |
| CN209543514U (en) | Monitoring and alarm system based on recognition of face | |
| CN109938439A (en) | Safety cap, security system, the management method of personnel | |
| KR102585066B1 (en) | Combined fire alarm system using stand-alone fire alarm and visible light camera | |
| CN109286788A (en) | A kind of safety defense monitoring system based on cloud computing | |
| CN112183394A (en) | Face recognition method and device and intelligent security management system | |
| CN109544870A (en) | Alarm decision method and intelligent monitor system for intelligent monitor system | |
| KR20080044812A (en) | The automatic guard system to prevent the crime and accident using computer video image analysis technology | |
| CN114333273A (en) | Intelligent analysis system and method for nuclear power construction site | |
| CN116823529A (en) | Security intelligent management system based on behavior big data analysis | |
| CN114913323B (en) | Charging pile area night open fire detection method | |
| CN112381435A (en) | Gridding directional pushing management method for dynamic risk in hydropower station operation process | |
| CN107920224B (en) | Abnormity warning method, abnormity warning equipment and video monitoring system | |
| CN111508121A (en) | Visual multicolor laser intelligent virtual gate control system | |
| CN114092875A (en) | Operation site safety supervision method and device based on machine learning | |
| CN111597903B (en) | Intelligent monitoring box for distribution network and monitoring method thereof | |
| CN213457742U (en) | Welding operation monitoring system | |
| CN113887310A (en) | Worker standard dressing identification method, system and medium | |
| CN113314230A (en) | Intelligent epidemic prevention method, device, equipment and storage medium based on big data | |
| CN112656081A (en) | Indoor positioning system based on vector position and attitude measurement technology | |
| CN207530963U (en) | A kind of illegal geofence system based on video monitoring | |
| CN117309040A (en) | Switch cabinet data acquisition system | |
| Jadhav et al. | Realtime Safety Helmet Detection Using Deep Learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |