CN113923418A - System and method for detecting abnormal opening of box door based on video analysis - Google Patents
System and method for detecting abnormal opening of box door based on video analysis Download PDFInfo
- Publication number
- CN113923418A CN113923418A CN202111262607.3A CN202111262607A CN113923418A CN 113923418 A CN113923418 A CN 113923418A CN 202111262607 A CN202111262607 A CN 202111262607A CN 113923418 A CN113923418 A CN 113923418A
- Authority
- CN
- China
- Prior art keywords
- container
- box door
- door
- opening detection
- detection system
- 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
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 50
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000004458 analytical method Methods 0.000 title claims abstract description 27
- 238000001514 detection method Methods 0.000 claims abstract description 101
- 230000003993 interaction Effects 0.000 claims abstract description 8
- 238000012545 processing Methods 0.000 claims abstract description 6
- 230000003068 static effect Effects 0.000 claims description 36
- 230000008569 process Effects 0.000 claims description 10
- 238000012549 training Methods 0.000 claims description 10
- 238000004891 communication Methods 0.000 claims description 8
- 230000005540 biological transmission Effects 0.000 claims description 7
- 238000013527 convolutional neural network Methods 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 6
- 238000009499 grossing Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 239000000203 mixture Substances 0.000 claims description 3
- 239000002994 raw material Substances 0.000 claims description 3
- 230000026676 system process Effects 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 210000003128 head Anatomy 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G08B21/18—Status alarms
- G08B21/24—Reminder alarms, e.g. anti-loss alarms
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Emergency Alarm Devices (AREA)
Abstract
The invention relates to a video analysis-based box door differential opening detection system, which comprises a camera, a detection module and a control module, wherein the camera is arranged on a port lifting appliance and is used for acquiring images and/or videos of the top end of a container on the port lifting appliance; based on a computer vision identification method, processing the image and/or the video, identifying whether a door on the container is abnormally opened, outputting alarm information under the condition that the door of the container is abnormally opened, controlling the working state of the door abnormal opening detection system, receiving the alarm information output by the door abnormal opening detection system, performing information interaction with the PLC, displaying the alarm information output by the PLC and sending an alarm signal; the invention can automatically judge whether the box door is abnormally opened, does not need to arrange a specially-assigned person to check the abnormal conditions of the box doors of all containers on site, and reduces the labor cost.
Description
Technical Field
The invention relates to the technical field of wharf or port monitoring systems, in particular to a system and a method for detecting abnormal opening of a box door based on video analysis.
Background
In the port container hoisting operation, whether the hoisted container door is closed or not relates to the material and property and the personal safety of a port, once the container door is not closed, the cargo falls to cause port property loss, and if falling cargo in the container hits production personnel or vehicles below, casualties can be caused, so that whether the container door is normally closed or not is detected in the operation process of hoisting the container, and the method is a very important safety production technical means.
The current methods for checking whether the container door is normally closed in the market mainly include the following methods:
mode 1: whether the container door is normally closed or not is checked by naked eyes through a portal crane hoisting assistant person on site, and the method needs to be matched by workers on site, so that the labor cost is increased.
Mode 2: the alarm, i.e. the electronic lead seal, is given by an electronic sensor mounted at the door, which gives an alarm signal once the door is opened. This approach requires an electronic lead seal to be installed on each container and requires the alarm signal to be sent to the monitoring center via RFID or 3G, 4G transmission. For port management, the method is inconvenient to manage, firstly, the electronic lead seal is required to be installed at the door of a container, the containers come from all parts of the world, the electronic lead seal is not required to be arranged on the containers pulled by each cargo ship, in addition, the power supply time of the electronic lead seal is limited, batteries need to be replaced periodically, the maintenance cost is very high, the method is inconvenient to popularize in a large range, and the method is only suitable for port groups to manage the containers special for the port groups.
Mode 3: monitoring through the radar, radar detection mode adopts the radar detection ware of installing on the hoist of portal crane, whether the detection container chamber door is opened, and radar detection mode is with high costs, and can't provide the video picture to the driver, in case radar detection ware sends alarm signal, the portal crane driver is difficult to through the problem that the on-the-spot was observed to the naked eye, need supporting the camera of installing on the dolly frame of hoist top, the container chamber door is observed in the cooperation, will lead to the overall cost of system too high like this.
Disclosure of Invention
In order to solve the problems that in the prior art, the labor cost is increased and the detection omission occurs due to the negligence of detection personnel under the condition that whether the container door is normally closed is manually detected; the invention provides a box door differential opening detection system based on video analysis.
The technical scheme for solving the technical problems is as follows:
the utility model provides a chamber door is different to open detecting system based on video analysis which characterized in that: comprises the steps of (a) preparing a mixture of a plurality of raw materials,
set up the camera on harbour hoist: the port spreader is used for acquiring images and/or videos of the top end of a container on the port spreader, wherein the images and/or videos are images and/or videos of the front end and the rear end of the container;
detection system is opened to chamber door difference: processing the image and/or the video based on a computer vision identification method, identifying whether a door of the container is abnormally opened, and outputting alarm information under the condition that the door of the container is abnormally opened;
PLC: the alarm system is used for controlling the working state of the box door differential opening detection system and receiving alarm information output by the box door differential opening detection system;
an alarm system: the PLC is used for carrying out information interaction with the PLC, displaying alarm information output by the PLC and sending out an alarm signal; and processing abnormal opening of the door on the container by judging the alarm information.
The invention has the beneficial effects that: the method comprises the steps that a camera is installed on a port lifting appliance, pictures or videos above the front end and the rear end of a container are shot through the camera, and whether the situation that the door of the container is opened abnormally exists at the front end and the rear end of the container is analyzed through a computer vision recognition technology; because the camera can acquire pictures or videos of the front end and the rear end of the container, in the hoisting process of the port spreader, the abnormal opening state of the box door of the container can be monitored by the box door abnormal opening detection system no matter whether the box door of the container is in the front or the rear. According to the invention, through computer vision recognition and analysis of the pictures or videos acquired by the camera, whether the box door is abnormally opened or not is automatically judged, and no special person is required to check the abnormal conditions of the box doors of all containers on site, so that the labor cost is reduced.
Further, the alarm information comprises images and/or videos of the front end and the rear end of the container; the alarm system comprises a video display device and an alarm, wherein the video display device is used for displaying images and/or videos at the front end and the rear end of the container, and the alarm sends out an alarm signal.
The beneficial effect of adopting above-mentioned further scheme is that its alarm information presents through image or video mode, lets harbour hoist managers can judge directly perceivedly through the video whether the different open detecting system of chamber door appears the condition such as erroneous judgement, and the manual work of being convenient for utilizes the manual work to carry out further inspection to the result that the different open detecting system of chamber door judges, under the unusual condition of chamber door of not additionally arranging the special messenger to inspect the container of different open of chamber door, monitors the different open container of chamber door effectively.
Further, in the present invention,
the PLC is particularly adapted to be used in,
sending a detection starting instruction to the box door differential opening detection system;
controlling the port lifting appliance to stop lifting, and after the worker handles the container with the abnormal door, controlling the port lifting appliance to continue lifting by the PLC;
after the port lifting appliance is lifted, the PLC controls the box door differential opening detection system to stop working;
the box door differential opening detection system is particularly used for,
and after receiving the detection starting instruction, the box door abnormal opening detection system starts to analyze the image and/or the video and sends an instruction for stopping operation to the PLC.
The beneficial effects of adopting above-mentioned further scheme are that, utilize opening or stopping of PLC control chamber door different opening detecting system, can open or close chamber door different opening detecting system according to the operating condition that the harbour hoist hung, improve chamber door different opening detecting system's utilization ratio, when the port hoist did not hoist and mount the container, chamber door different opening detecting system can not work, reduce chamber door different opening detecting system's work load, improve chamber door different opening detecting system analysis efficiency.
Further, the method also comprises the following steps of,
an encoder: the camera is used for converting the images and/or videos acquired by the camera into digital signals for communication, transmission and storage;
a collection switch: the alarm system is used for transmitting the digital signal to the box door abnormal opening detection system and the alarm system.
Further, the method for identifying whether the door on the container is abnormally opened includes,
step 1, performing image characteristic training on a box door lock seat of the container by using a convolutional neural network, and establishing a characteristic model of the box door lock seat of the container, wherein the characteristic model is the image characteristic model of the box door lock seat when a box door lock rod is not clamped;
and 3, analyzing whether the characteristics consistent with the characteristic model exist on all the preprocessed static images, and if at least one preprocessed static image has the characteristics consistent with the characteristic model, judging that the door of the container is opened abnormally.
The beneficial effect who adopts above-mentioned further scheme is that, through the chamber door lock seat of discernment container, the unusual condition of opening of analysis container chamber door, can discern all states that container chamber door is unusually opened effectively, because all be provided with the chamber door lock seat on the lintel of container chamber door to through chamber door locking lever and chamber door lock seat block locking chamber door, consequently in case chamber door is abnormal to open detecting system and is arrived, no case lock lever on certain chamber door lock seat blocks with it, just can judge that its chamber door is abnormal to open. Therefore, when the characteristic model of abnormal opening of the box door is established, only the analysis on whether the box door lock rod is clamped in the box door lock seat is needed, the data volume of characteristic model training is reduced, the cost is reduced, and an effective characteristic model can be obtained.
A method for detecting abnormal opening of a box door based on video analysis comprises,
step 1, arranging a camera on a port lifting appliance, wherein the camera acquires images and/or videos of the top end of a container on the port lifting appliance, and the images and/or videos are images and/or videos of the front end and the rear end of the container;
step 3, setting a PLC (programmable logic controller), wherein the PLC controls the working state of the box door differential opening detection system and receives alarm information output by the box door differential opening detection system;
step 4, setting an alarm system, wherein the alarm system performs information interaction with the PLC, displays alarm information output by the PLC and sends an alarm signal; and the operator processes the abnormal opening of the door on the container by judging the alarm information.
Further, the alarm information comprises images and/or videos of the front end and the rear end of the container; the alarm system comprises a video display device and an alarm, wherein the video display device is used for displaying images and/or videos at the front end and the rear end of the container, and the alarm sends out an alarm signal.
Further, the method for controlling the working state of the box door differential opening detection system by the PLC comprises the following steps,
step 1, a port lifting appliance picks up a container;
step 3, after the box door differential opening detection system receives the detection starting instruction, the box door differential opening detection system starts to analyze the image and/or the video;
step 4, when the box door differential opening detection system detects that the box door of the container is abnormally opened, the box door differential opening detection system sends an instruction for stopping operation to the PLC, the PLC controls the port lifting appliance to stop lifting, and after a worker handles the container with the abnormal box door, the PLC controls the port lifting appliance to continue lifting;
and 5, after the port lifting appliance is lifted, the PLC controls the box door differential opening detection system to stop working.
Further, the method also comprises the following steps of,
step 5, setting an encoder, wherein the encoder converts the images and/or videos acquired by the camera into digital signals for communication, transmission and storage;
and 6, setting a collection switch, wherein the collection switch transmits the digital signals to the box door differential opening detection system and the alarm system.
Further, the method for identifying whether the door on the container is abnormally opened includes,
step 1, performing image characteristic training on a box door lock seat of the container by using a convolutional neural network, and establishing a characteristic model of the box door lock seat of the container, wherein the characteristic model is the image characteristic model of the box door lock seat when a box door lock rod is not clamped;
and 3, analyzing whether the characteristics consistent with the characteristic model exist on all the preprocessed static images, and if at least one preprocessed static image has the characteristics consistent with the characteristic model, judging that the door of the container is opened abnormally.
Drawings
FIG. 1 is a system architecture diagram of the present invention;
FIG. 2 is a block diagram of the workflow of the present invention;
FIG. 3 is a block diagram of the system shutdown process of the present invention;
FIG. 4 is a schematic view of a container with its doors normally closed;
FIG. 5 is a first schematic view of an abnormal opening of a door of a container;
FIG. 6 is a second schematic view of the abnormal opening of the door of the container;
fig. 7 is a third schematic view showing the abnormal opening of the door of the container.
Detailed Description
The principles and features of this invention are described below in conjunction with the following drawings, which are set forth by way of illustration only and are not intended to limit the scope of the invention.
Example one
As shown in fig. 1, the present invention provides a system for detecting abnormal opening of a box door based on video analysis, which comprises a camera arranged on a port spreader: the port spreader is used for acquiring images and/or videos of the top end of a container on the port spreader, wherein the images and/or videos are images and/or videos of the front end and the rear end of the container;
detection system is opened to chamber door difference: processing the image and/or the video based on a computer vision identification method, identifying whether a door of the container is abnormally opened, and outputting alarm information under the condition that the door of the container is abnormally opened;
PLC: the alarm system is used for controlling the working state of the box door differential opening detection system and receiving alarm information output by the box door differential opening detection system;
an alarm system: the PLC is used for carrying out information interaction with the PLC, displaying alarm information output by the PLC and sending out an alarm signal; the operator processes the abnormal opening of the door of the container by judging the alarm information; wherein the alarm information comprises images and/or videos of the front end and the rear end of the container; the alarm system comprises a video display device and an alarm, wherein the video display device is used for displaying images and/or videos at the front end and the rear end of the container, and the alarm sends out an alarm signal.
An encoder: the camera is used for converting the images and/or videos acquired by the camera into digital signals for communication, transmission and storage;
a collection switch: the alarm system is used for transmitting the digital signal to the box door abnormal opening detection system and the alarm system.
Specifically, two special cameras are respectively installed on two sides of a lifting column of a port lifting appliance, such as a gantry crane lifting appliance, the camera lenses of the two cameras face downwards, the cameras can extend or shorten along with the lifting column, and therefore, the opening and closing states of door openings at the front end and the rear end of a container can be monitored no matter the gantry crane lifts 20-foot, 40-foot and 45-foot containers, and the whole process from the lifting of the lifting appliance to the putting down of the containers can be monitored. By carrying out computer vision identification analysis on the video stream of the lifting appliance camera, whether the box door is abnormal or not is automatically judged, a specially-assigned person is not required to be arranged to check the abnormal conditions of the box doors of all containers on site, and the labor cost is reduced.
The technology of the patent does not need to design a contact switch, a radar, a wireless communication module, a battery and other communication devices or power supply devices for detecting whether the box door is closed on the container, and does not increase the manufacturing cost of the container; the PLC and the alarm system can be carried by the port lifting appliance, so that the cost for installing the PLC and the alarm system is saved, and only a box door differential opening detection system needs to be added.
The method of identifying whether a door on a container is abnormally opened includes the steps of,
step 1, performing image characteristic training on a box door lock seat of the container by using a convolutional neural network, and establishing a characteristic model of the box door lock seat of the container, wherein the characteristic model is the image characteristic model of the box door lock seat when a box door lock rod is not clamped; when the characteristic training of the door lock base image is carried out, the image at least comprises the image characteristics of day, night, rainy weather, sunny weather, different time periods every day, different colors of the door lock base and the new and old degree of the door lock base, the characteristic capacity is improved, and the analysis comprehensiveness is improved.
and 3, analyzing whether the characteristics consistent with the characteristic model exist on all the preprocessed static images, and if at least one preprocessed static image has the characteristics consistent with the characteristic model, judging that the door of the container is opened abnormally.
The abnormal opening condition of the container door is analyzed by identifying the door lock seat of the container, all states of abnormal opening of the container door can be effectively identified, and the door lock seat is arranged on the door head of the container door, and the container door is locked by the box door lock rod and the box door lock seat in a clamping manner, so that once the abnormal opening detection system of the container door analyzes, the abnormal opening of the container door can be judged by clamping the box door lock rod without the box door on a certain box door lock seat. Therefore, when the characteristic model of abnormal opening of the box door is established, only the analysis on whether the box door lock rod is clamped in the box door lock seat is needed, the data volume of characteristic model training is reduced, the cost is reduced, and an effective characteristic model can be obtained.
As shown in fig. 2 to 3, the interaction process between the PLC and the door differential opening detection system is specifically as follows,
step 1, a port lifting appliance picks up a container;
step 3, after the box door differential opening detection system receives the detection starting instruction, the box door differential opening detection system starts to analyze the image and/or the video;
step 4, when the box door differential opening detection system detects that the box door of the container is abnormally opened, the box door differential opening detection system sends an instruction for stopping operation to the PLC, the PLC controls the port lifting appliance to stop lifting, and after a worker handles the container with the abnormal box door, the PLC controls the port lifting appliance to continue lifting;
and 5, after the port lifting appliance is lifted, the PLC controls the box door differential opening detection system to stop working.
Utilize opening or stopping of PLC control chamber door different opening detecting system, can open or close chamber door different opening detecting system according to the operating condition that the harbour hoist hung, improve chamber door different opening detecting system's utilization ratio, when the harbour hoist did not hoist and mount the container, chamber door different opening detecting system can not work, reduces chamber door different opening detecting system's work load, improves chamber door different opening detecting system analysis efficiency. In case of detecting the abnormal opening condition of the box door, the box door abnormal opening detection system automatically pushes an alarm picture screenshot or a video stream to a driver of the port lifting appliance under the control of the PLC, so that the driver can conveniently judge the condition of the on-site container.
As shown in fig. 4 to fig. 4, when the door is normally closed, the lock rod is fastened to the door lock base of the container, and the U-shaped image of the door lock base does not appear on the image collected by the camera.
As shown in fig. 5 to 7, when the door is opened abnormally, performing image feature training on the door lock base of the container by using a convolutional neural network, and establishing a feature model of the door lock base of the container, where the feature model is an image feature model of the door lock base when the door lock rod is not locked in the container; the feature set of the container door lock base of the container comprises a U-shaped structure feature of the container door lock base and/or a saw-toothed feature formed by the container door lock base and a container body provided with the container door lock base.
Example two
As shown in fig. 1, the present embodiment provides a method for detecting abnormal opening of a box door based on video analysis, which includes,
step 1, arranging a camera on a port lifting appliance, wherein the camera acquires images and/or videos of the top end of a container on the port lifting appliance, and the images and/or videos are images and/or videos of the front end and the rear end of the container;
step 3, setting a PLC (programmable logic controller), wherein the PLC controls the working state of the box door differential opening detection system and receives alarm information output by the box door differential opening detection system;
step 4, setting an alarm system, wherein the alarm system performs information interaction with the PLC, displays alarm information output by the PLC and sends an alarm signal; the operator processes the abnormal opening of the door of the container by judging the alarm information; the alarm information comprises images and/or videos of the front end and the rear end of the container; the alarm system comprises a video display device and an alarm, wherein the video display device is used for displaying images and/or videos at the front end and the rear end of the container, and the alarm sends out an alarm signal;
step 5, setting an encoder, wherein the encoder converts the images and/or videos acquired by the camera into digital signals for communication, transmission and storage;
and 6, setting a collection switch, wherein the collection switch transmits the digital signals to the box door differential opening detection system and the alarm system.
The method for controlling the working state of the box door abnormal opening detection system by the PLC comprises the following steps,
step 1, a port lifting appliance picks up a container;
step 3, after the box door differential opening detection system receives the detection starting instruction, the box door differential opening detection system starts to analyze the image and/or the video;
step 4, when the box door differential opening detection system detects that the box door of the container is abnormally opened, the box door differential opening detection system sends an instruction for stopping operation to the PLC, the PLC controls the port lifting appliance to stop lifting, and after a worker handles the container with the abnormal box door, the PLC controls the port lifting appliance to continue lifting;
and 5, after the port lifting appliance is lifted, the PLC controls the box door differential opening detection system to stop working.
The invention has the advantages that the box door abnormal opening detection system starts to monitor the abnormal opening of the box door only when a port lifting appliance grabs a container, the position of a lifting appliance camera relative to the box door of the container is unchanged in the whole process of lifting the box by the port lifting appliance, the position of the container in a video picture in an alarm system is fixed and unchanged, other objects appear in the video picture, the false alarm possibly caused is judged by an operator through alarm information, and therefore, in the lifting operation of the port lifting appliance, the invention can improve the accuracy rate of the identification of the box door abnormal opening system, has low cost and is convenient for market popularization.
As shown in fig. 4 to 6, the method of identifying whether the doors of the container are abnormally opened includes,
step 1, performing image characteristic training on a container door lock seat of the container by using a convolutional neural network, and establishing a characteristic model of the container door lock seat of the container, wherein the characteristic model is an image characteristic model of the container door lock seat when a container door lock rod is not clamped, and the characteristic model can also be a characteristic model of a container door; because the image or video acquired by the camera is acquired from the upper end of the container, when the container door is taken as the feature set of computer vision identification, the feature model is the overhead projection of the container door, wherein, fig. 4 is a schematic diagram of the normal door closing state, and the comparison feature is the linear feature without the door; the images corresponding to the schematic diagrams shown in fig. 5 to 7 are used as feature model sets to be identified, and as shown in fig. 5, when the abnormal opening amount of the container door is small, the door edge lines of the container door can still be clearly identified, so that the door edge lines of the container doors at the front end and the rear end of the container can be subjected to computer deep learning by using the feature set, and whether the container door is abnormally opened or not can be judged by identifying the door edge lines of the container doors on the end surfaces at the front end and the rear end of the container.
and 3, analyzing whether the characteristics consistent with the characteristic model exist on all the preprocessed static images, and if at least one preprocessed static image has the characteristics consistent with the characteristic model, judging that the door of the container is opened abnormally.
The PLC in this patent refers to a programmable logic controller, which employs a programmable memory, in which instructions for performing operations such as logic operation, sequence control, timing, counting, and arithmetic operation are stored, and controls various types of mechanical devices or production processes through digital or analog input and output.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (10)
1. The utility model provides a chamber door is different to open detecting system based on video analysis which characterized in that: comprises the steps of (a) preparing a mixture of a plurality of raw materials,
set up the camera on harbour hoist: the port spreader is used for acquiring images and/or videos of the top end of a container on the port spreader, wherein the images and/or videos are images and/or videos of the front end and the rear end of the container;
detection system is opened to chamber door difference: processing the image and/or the video based on a computer vision identification method, identifying whether a door of the container is abnormally opened, and outputting alarm information under the condition that the door of the container is abnormally opened;
PLC: the alarm system is used for controlling the working state of the box door differential opening detection system and receiving alarm information output by the box door differential opening detection system;
an alarm system: the PLC is used for carrying out information interaction with the PLC, displaying alarm information output by the PLC and sending out an alarm signal; and processing the abnormal opening problem of the door on the container by judging the alarm information.
2. The video analysis-based door differential opening detection system according to claim 1, wherein: the alarm information comprises images and/or videos of the front end and the rear end of the container; the alarm system comprises a video display device and an alarm, wherein the video display device is used for displaying images and/or videos at the front end and the rear end of the container, and the alarm sends out an alarm signal.
3. The video analysis-based door differential opening detection system according to claim 1, wherein: the PLC is particularly adapted to be used in,
sending a detection starting instruction to the box door differential opening detection system;
controlling the port lifting appliance to stop lifting, and after the worker handles the container with the abnormal door, controlling the port lifting appliance to continue lifting by the PLC;
after the port lifting appliance is lifted, the PLC controls the box door differential opening detection system to stop working;
the box door differential opening detection system is particularly used for,
and after receiving the detection starting instruction, the box door abnormal opening detection system starts to analyze the image and/or the video and sends an instruction for stopping operation to the PLC.
4. The video analysis-based door differential opening detection system according to claim 1, wherein: also comprises the following steps of (1) preparing,
an encoder: the camera is used for converting the images and/or videos acquired by the camera into digital signals for communication, transmission and storage;
a collection switch: the alarm system is used for transmitting the digital signal to the box door abnormal opening detection system and the alarm system.
5. The video analysis-based door differential opening detection system according to claim 1, wherein: the method of identifying whether a door on a container is abnormally opened includes,
step 1, performing image characteristic training on a box door lock seat of the container by using a convolutional neural network, and establishing a characteristic model of the box door lock seat of the container, wherein the characteristic model is the image characteristic model of the box door lock seat when a box door lock rod is not clamped;
step 2, dividing the image and/or video into a plurality of static pictures, eliminating redundant information in all the static pictures, and preprocessing all the static pictures without the redundant information by utilizing a smoothing and filtering method to obtain a plurality of preprocessed static pictures;
and 3, analyzing whether the characteristics consistent with the characteristic model exist on all the preprocessed static images, and if at least one preprocessed static image has the characteristics consistent with the characteristic model, judging that the door of the container is opened abnormally.
6. A box door differential opening detection method based on video analysis is characterized in that: comprises the steps of (a) preparing a mixture of a plurality of raw materials,
step 1, arranging a camera on a port lifting appliance, wherein the camera acquires images and/or videos of the top end of a container on the port lifting appliance, and the images and/or videos are images and/or videos of the front end and the rear end of the container;
step 2, establishing a box door differential opening detection system based on a computer vision identification method, wherein the box door differential opening detection system processes the image and/or the video, identifies whether a box door on the container is abnormally opened, and outputs alarm information under the condition that the box door of the container is abnormally opened;
step 3, setting a PLC (programmable logic controller), wherein the PLC controls the working state of the box door differential opening detection system and receives alarm information output by the box door differential opening detection system;
step 4, setting an alarm system, wherein the alarm system performs information interaction with the PLC, displays alarm information output by the PLC and sends an alarm signal; and the operator processes the abnormal opening of the door on the container by judging the alarm information.
7. The video analysis-based door differential opening detection method according to claim 6, characterized in that: the alarm information comprises images and/or videos of the front end and the rear end of the container; the alarm system comprises a video display device and an alarm, wherein the video display device is used for displaying images and/or videos at the front end and the rear end of the container, and the alarm sends out an alarm signal.
8. The video analysis-based door differential opening detection method according to claim 6, characterized in that: the method for controlling the working state of the box door abnormal opening detection system by the PLC comprises the following steps,
step 1, a port lifting appliance picks up a container;
step 2, the PLC sends a detection starting instruction to the box door differential opening detection system;
step 3, after the box door differential opening detection system receives the detection starting instruction, the box door differential opening detection system starts to analyze the image and/or the video;
step 4, when the box door differential opening detection system detects that the box door of the container is abnormally opened, the box door differential opening detection system sends an instruction for stopping operation to the PLC, the PLC controls the port lifting appliance to stop lifting, and after a worker handles the container with the abnormal box door, the PLC controls the port lifting appliance to continue lifting;
and 5, after the port lifting appliance is lifted, the PLC controls the box door differential opening detection system to stop working.
9. The video analysis-based door differential opening detection method according to claim 6, characterized in that: also comprises the following steps of (1) preparing,
step 5, setting an encoder, wherein the encoder converts the images and/or videos acquired by the camera into digital signals for communication, transmission and storage;
and 6, setting a collection switch, wherein the collection switch transmits the digital signals to the box door differential opening detection system and the alarm system.
10. The video analysis-based door differential opening detection method according to claim 6, characterized in that: the method of identifying whether a door on a container is abnormally opened includes,
step 1, performing image characteristic training on a box door lock seat of the container by using a convolutional neural network, and establishing a characteristic model of the box door lock seat of the container, wherein the characteristic model is the image characteristic model of the box door lock seat when a box door lock rod is not clamped;
step 2, dividing the image and/or video into a plurality of static pictures, eliminating redundant information in all the static pictures, and preprocessing all the static pictures without the redundant information by utilizing a smoothing and filtering method to obtain a plurality of preprocessed static pictures;
and 3, analyzing whether the characteristics consistent with the characteristic model exist on all the preprocessed static images, and if at least one preprocessed static image has the characteristics consistent with the characteristic model, judging that the door of the container is opened abnormally.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111262607.3A CN113923418A (en) | 2021-10-28 | 2021-10-28 | System and method for detecting abnormal opening of box door based on video analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111262607.3A CN113923418A (en) | 2021-10-28 | 2021-10-28 | System and method for detecting abnormal opening of box door based on video analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113923418A true CN113923418A (en) | 2022-01-11 |
Family
ID=79243302
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111262607.3A Pending CN113923418A (en) | 2021-10-28 | 2021-10-28 | System and method for detecting abnormal opening of box door based on video analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113923418A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114429616A (en) * | 2022-01-26 | 2022-05-03 | 中煤科工集团重庆智慧城市科技研究院有限公司 | Box abnormal state identification method based on computer vision |
| CN114500950A (en) * | 2022-01-26 | 2022-05-13 | 中煤科工集团重庆智慧城市科技研究院有限公司 | A cabinet abnormal state detection system and method based on smart city |
| CN115171261A (en) * | 2022-05-25 | 2022-10-11 | 北京国基科技股份有限公司 | Access control system and access control method |
| CN116400373A (en) * | 2023-04-20 | 2023-07-07 | 上海安渊电子科技有限公司 | Machine vision system-based card collecting box door detection equipment |
| CN116994354A (en) * | 2023-09-28 | 2023-11-03 | 上海闪马智能科技有限公司 | Road electric facility inspection method and device, storage medium and electronic device |
| CN117173468A (en) * | 2023-08-31 | 2023-12-05 | 广西钦州保税港区盛港码头有限公司 | Container door abnormal opening detection method, device, electronic equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009004993A1 (en) * | 2007-06-29 | 2009-01-08 | Rohm Co., Ltd. | Alarming apparatus |
| CN201882785U (en) * | 2010-02-02 | 2011-06-29 | 南通通镭软件有限公司 | Position image recognition and correction system for container gantry crane |
| CN206466834U (en) * | 2017-01-13 | 2017-09-05 | 广东云本科技有限公司 | A kind of IP types cab top data acquisition equipment |
| CN206705544U (en) * | 2017-04-25 | 2017-12-05 | 武汉利德测控技术有限公司 | Container gantry crane is automatically positioned heap and taken and case deviation load detection system |
| CN108639956A (en) * | 2018-06-27 | 2018-10-12 | 上海沪东集装箱码头有限公司 | The container crane intelligent early-warning system and method for view-based access control model detection technique |
| CN109335964A (en) * | 2018-09-21 | 2019-02-15 | 北京航天自动控制研究所 | Container twist lock detection system and detection method |
-
2021
- 2021-10-28 CN CN202111262607.3A patent/CN113923418A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009004993A1 (en) * | 2007-06-29 | 2009-01-08 | Rohm Co., Ltd. | Alarming apparatus |
| CN201882785U (en) * | 2010-02-02 | 2011-06-29 | 南通通镭软件有限公司 | Position image recognition and correction system for container gantry crane |
| CN206466834U (en) * | 2017-01-13 | 2017-09-05 | 广东云本科技有限公司 | A kind of IP types cab top data acquisition equipment |
| CN206705544U (en) * | 2017-04-25 | 2017-12-05 | 武汉利德测控技术有限公司 | Container gantry crane is automatically positioned heap and taken and case deviation load detection system |
| CN108639956A (en) * | 2018-06-27 | 2018-10-12 | 上海沪东集装箱码头有限公司 | The container crane intelligent early-warning system and method for view-based access control model detection technique |
| CN109335964A (en) * | 2018-09-21 | 2019-02-15 | 北京航天自动控制研究所 | Container twist lock detection system and detection method |
Non-Patent Citations (1)
| Title |
|---|
| 叶海浪;伍昕;廖平;周受钦;: "基于无线通信的智能集装箱监测系统设计" * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114429616A (en) * | 2022-01-26 | 2022-05-03 | 中煤科工集团重庆智慧城市科技研究院有限公司 | Box abnormal state identification method based on computer vision |
| CN114500950A (en) * | 2022-01-26 | 2022-05-13 | 中煤科工集团重庆智慧城市科技研究院有限公司 | A cabinet abnormal state detection system and method based on smart city |
| CN114500950B (en) * | 2022-01-26 | 2024-11-29 | 中煤科工集团重庆智慧城市科技研究院有限公司 | Box abnormal state detection system and method based on smart city |
| CN115171261A (en) * | 2022-05-25 | 2022-10-11 | 北京国基科技股份有限公司 | Access control system and access control method |
| CN116400373A (en) * | 2023-04-20 | 2023-07-07 | 上海安渊电子科技有限公司 | Machine vision system-based card collecting box door detection equipment |
| CN117173468A (en) * | 2023-08-31 | 2023-12-05 | 广西钦州保税港区盛港码头有限公司 | Container door abnormal opening detection method, device, electronic equipment and storage medium |
| CN116994354A (en) * | 2023-09-28 | 2023-11-03 | 上海闪马智能科技有限公司 | Road electric facility inspection method and device, storage medium and electronic device |
| CN116994354B (en) * | 2023-09-28 | 2024-01-23 | 上海闪马智能科技有限公司 | Road electric facility inspection method and device, storage medium and electronic device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113923418A (en) | System and method for detecting abnormal opening of box door based on video analysis | |
| CN211393664U (en) | Intelligent monitoring system for safe operation of tower crane | |
| CN104709828A (en) | Safety monitoring management system for hoisting equipment | |
| CN111888685A (en) | Single-hook safety belt and safety management system | |
| CN109142904A (en) | A kind of extra-high voltage direct-current transmission converter valve fault monitoring method and device | |
| CN108178069A (en) | Container handling operation intelligent early-warning system | |
| CN112661034A (en) | Tower crane bin safety system and method for tower crane bin safety system | |
| CN109823941A (en) | A kind of wirerope monitoring device applied on active safety elevator | |
| CN113885419A (en) | Tower crane safety monitoring system | |
| CN108227617A (en) | A kind of tyre crane remote detection and assessment system | |
| CN110784681B (en) | Mining breaker front end personnel protection system based on image recognition | |
| CN115930887A (en) | Intelligent monitoring safety early warning system is covered in reinforced concrete structure construction | |
| CN212356120U (en) | Mine cage number management and control device | |
| CN106657915B (en) | Working method of safety data and video integrated monitoring and management system for hoisting machinery | |
| CN108466894A (en) | A kind of Cargo Lift real time execution early warning system | |
| CN108529377A (en) | A kind of elevator real time execution maintenance examination and repair system | |
| CN116147697B (en) | Unattended monitoring method and system for aluminum hydroxide | |
| CN107416625B (en) | A kind of coal mine main shaft vertical shaft hoisting skip bucket clean boot monitoring device and monitoring method | |
| CN210029792U (en) | Tower crane inclination detection system | |
| CN112299181A (en) | Elevator monitoring system based on Internet of things | |
| CN209306770U (en) | Elevator safety monitoring management system | |
| CN210915110U (en) | Safety control system of hydraulic lifting platform | |
| CN214692750U (en) | Construction elevator integrated monitoring system | |
| CN215186948U (en) | Container detection device, security protection vehicle-mounted system and security protection monitoring system | |
| CN116012784A (en) | AI robot recognition-based coal mining process inspection method and system |
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: 20220111 |
|
| RJ01 | Rejection of invention patent application after publication |