CN106599885A - Monitoring system and method for container Bay - Google Patents
Monitoring system and method for container Bay Download PDFInfo
- Publication number
- CN106599885A CN106599885A CN201610770423.0A CN201610770423A CN106599885A CN 106599885 A CN106599885 A CN 106599885A CN 201610770423 A CN201610770423 A CN 201610770423A CN 106599885 A CN106599885 A CN 106599885A
- Authority
- CN
- China
- Prior art keywords
- container
- bay
- point
- information
- image
- 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
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000012544 monitoring process Methods 0.000 title claims abstract description 26
- 230000008569 process Effects 0.000 claims abstract description 15
- 230000001960 triggered effect Effects 0.000 claims abstract description 4
- 238000013507 mapping Methods 0.000 claims description 36
- 238000003384 imaging method Methods 0.000 claims description 10
- 238000005516 engineering process Methods 0.000 claims description 8
- 239000011159 matrix material Substances 0.000 claims description 8
- 230000014509 gene expression Effects 0.000 claims description 5
- 230000009466 transformation Effects 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 2
- 238000007726 management method Methods 0.000 claims description 2
- 235000015170 shellfish Nutrition 0.000 claims description 2
- 230000011218 segmentation Effects 0.000 claims 1
- 238000012795 verification Methods 0.000 description 6
- 238000004806 packaging method and process Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000006073 displacement reaction Methods 0.000 description 2
- 238000012804 iterative process Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 210000004556 brain Anatomy 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000000977 initiatory effect Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000013439 planning Methods 0.000 description 1
- 239000011435 rock Substances 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 238000012384 transportation and delivery Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66C—CRANES; LOAD-ENGAGING ELEMENTS OR DEVICES FOR CRANES, CAPSTANS, WINCHES, OR TACKLES
- B66C13/00—Other constructional features or details
- B66C13/16—Applications of indicating, registering, or weighing devices
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30232—Surveillance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30241—Trajectory
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Mechanical Engineering (AREA)
- Artificial Intelligence (AREA)
- Development Economics (AREA)
- Evolutionary Computation (AREA)
- Entrepreneurship & Innovation (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a monitoring system for a container Bay. A first image capture device is installed on the bottom of a trolley for carrying out real-time tracking on a container; a second image capture device is installed on the center position of the front big arm of a bridge crane cross beam for monitoring container Bay information; at least one third image capture device is installed on the seaside of a wharf for identifying a container number; the landside of the wharf is provided with at least one fourth image capture device for identifying the container number; a travelling bridge PLC (Programmable Logic Controller) and an identification server are arranged in a travelling bridge control room; the PLC carries out linkage control on the identification server to send the real-time coordinates of a travelling bridge trolley and a sling for lifting loads to the image capture devices to enable the image capture devices to obtain the real-time position of the container; in a container loading and unloading process, the image capture devices on different positions are triggered to carry out accurate capture on a plurality of surfaces of the containers; and obtained image information is uploaded to the identification server to identify the number of the container, and is uploaded to a monitoring management center.
Description
Technical field
The invention belongs to the automatic tally technical field in harbour, more particularly to a kind of container Bay level monitoring systems and method.
Background technology
Quickening and increased, the large-scale pivotal port work of modernization of international economic activity with global integration process
It is that the propeller that the modern logistics based on communications and transportation and storage dispensing are serviced increasingly is dashed forward with the critical role of connector
Go out.Tally is produced with the appearance of trade transportation waterborne, and English is TALLY, and its implication is the chip of counting.Tally
Refer to ship or the owner of cargo according to contract of transportation when port of shipment and port discharge are received with hand over of goods, entrust harbour tally mechanism
What agency completed is counted to goods, is checked damage cargo, the verification of Bay positions at harbour, instructs stowage stowage, makes relevant single
The work such as card.Occur to carry out joining the work of notarization when property rights are shifted between carrier, consignor, consignee.
Tally at this stage be all based on artificial, by tally-man scene soon, the pure physical mode pair such as hand-written, brain note
The container of entering and leaving port ship is recorded.Due to work under bad environment, high labor intensive.There is not high and easy of operating efficiency
The hidden danger of raw security incident.
The content of the invention
Method proposed by the present invention is mainly used in the automatic monitoring of container Bay positions, and whole process is without the need for manual intervention.One kind collection
Vanning Bay level monitoring systems, including bridge crane control room dolly, install the first image snapshot device, for packaging in dolly bottom
Case carries out real-time tracking,
Large arm center is provided with the second image snapshot device before bridge crane crossbeam, for monitoring containers shellfish position information,
At least one the 3rd image snapshot device is installed in the extra large side of harbour, for container number identification,
At least one the 4th image snapshot device is installed in the land side of harbour, for container number identification, in bridge crane control
Interior processed is provided with bridge crane PLC and identification server, PLC coordinated signals identification server, by bridge crane trolley and the real-time seat of suspender
Mark issues image snapshot device so as to obtain container real time position, and the image of diverse location is triggered during container handling
Capture device accurately to capture the multiple faces of container, these faces include case face and packaging before container sea land side, container
Chamber door after case, the image information of acquisition is uploaded to into identification server carries out the identification of container number, and uploads to monitoring pipe
Reason center, the container to placing errors present carries out automatic alarm, is cased according to Proposed Shipping Schedule in time.
Result is uploaded to supervision and management center, monitoring management by identification server by switching equipment and wireless bridge
Center is provided with storage array.
A kind of container Bay position monitoring methods, it is characterised in that after container number is obtained, matching pre-stowage plan and dress
Ship planning chart, there is step:
S101, obtains Bay message bit patterns;
S102, mapping relations are demarcated;
S103, tracks container;
S104, judges whether container is sling, if it is not, waiting slinging, if sling, turns S105;
S105, obtains plc data;
S106, judges whether container falls, if it is not, determine present container and first container apart from and
Bay bitmaps are updated, turns S109, if container falls, turn S107;
S107, determines present container position;
S108, calculates Bay bitmaps;
S109, obtains Bay positions information;
S110, judges whether identical with known Bay positions information, if it is not the same, then reporting to the police, if identical, turns S102.
After S105 obtains container hoisting information by PLC, using Mean-shift target tracking algorisms, packaging is obtained
Case movement locus, with this container landing place is determined.
The method of present container position is determined in S107 is,
It is assumed that first container for falling is in correct Bay bitmaps, and after other container motion tracks are obtained, meter
Its respective distances with first container is calculated, according to the width of container, you can determine if in correct position,
To obtain respective distances, known cabin is demarcated, implement step as follows:
Described mapping relations step of setting up includes demarcating mapping point and sets up mapping table step,
Described demarcation mapping point, is by determining the position of video camera, inside and outside parameter and setting up imaging model determining
The corresponding relation between object and its imaging on the image plane in world coordinate system,
In practical application scene, due to there is the position information cut-off rule demarcated in cabin, and respectively split distance between centers of tracks
From certain, as container width, therefore by demarcating to known point, with reference to video camera imaging principle, and then can obtain
Required mapping relations;
Described sets up mapping table, i.e.,
If certain coordinate of point in world coordinate system is W (X, Y, Z), because the proportionate relationship of similar triangles can obtain its throwing
Shadow point I (x, y), wherein
F is the intersecting point coordinate of subpoint and world coordinate system;
The division arithmetic of variable is contained in above formula, belongs to nonlinear transformation, when homogeneous coordinates are introduced line is converted thereof into
Property matrix is calculated, it follows that homogeneous coordinates matrix such as following formula
In car speed calculating process, it is not necessary to know the elevation information of vehicle, therefore above formula is simplified, obtain following
Transformation matrix
The coordinate expressions that can obtain world coordinate system midpoint (X, Y) by above formula are
Actual range of the known distance point in image coordinate system in pixel coordinate and world coordinate system is substituted into into above formula, is asked
Go out the mapping relations of pixel distance and actual range, thus set up Two coordinate system mapping table, i.e. mapping table MapTable
[IMAGE_SIZE], wherein IMAGE_SIZE are the product of picture traverse and height, in follow-up calculating process, when input needs
The pixel coordinate of the impact point of inquiry can obtain the corresponding actual range of point;
Described speed calculation step is that each point locus in moving vehicle target trajectory is substituted into into described mapping to close
It is table upper table, obtains the actual range that each impact point is represented in track,
Wherein, Disi[i].x、Disi[i] .y is certain point corresponding actual range of transverse direction and longitudinal direction, and MapTable is institute
State the mapping table of foundation.
Present container place Bay positions information is obtained by PLC control information and video processing technique, will both information phases
With reference to being compared with actual Bay bitmaps table, if both can match, illustrate that present container puts position correctly, no
Processed, if the case position of container is inconsistent with pre-stowage plan, but still on the case position at identical harbour, then given a warning, such as
The case position of fruit container is inconsistent with pre-stowage plan, and does not report to the police and notify field personnel on the case position at identical harbour
Process.
Compared with prior art, there is following technique effect using the present invention:
1st, it is advanced
The design of system should have technical advance, and the theory for being adopted, technology should be leading in the industry.It is existing at present
There is the monitoring of the Bay positions in tallying system to need artificial exercising supervision at the scene to check, work under bad environment is dangerous high.Part
Using semi-automatic Bay positions monitoring, i.e., front end adopts video monitoring, staff to carry out verification verification on backstage at harbour, but
Still need to artificial participation.The method that the present invention is adopted is capable of achieving the full-automatic detection of Bay positions, without the need for artificial participation, substantially reduces
Person works intensity.
2nd, PLC is combined with video technique
The present invention in combination with video technique, by PLC the information such as suspender lifting altitude, position is obtained using PLC technology,
Pre- judgement is carried out to Bay positions to be carried out Bay positions and automatically updates in conjunction with video technique, is eliminated because harbour wind speed, wave etc. are led
Ship movement is caused to cause to carry out the error that the anticipation of Bay positions is caused by plc data.
3rd, stability
Method described in the invention is a complication system that system concern is more, running environment is severe, uninterruptedly use.
To consider device therefor and control system during system design as a whole, meet the job development side of current techniques and operating administration
To simultaneity factor reduces the technical risk of system from ripe technology.
Description of the drawings
Fig. 1 Bay positions overhaul flow charts of the present invention;
Fig. 2 present system mounting structure figures;
Fig. 3 present system topological diagrams;
Fig. 4 container cabin Bay positions information profile;
The method schematic diagram of Fig. 5 container numbers identification;
Fig. 6 Mean-shift principle schematics;
Fig. 7 camera imaging models;
Specific embodiment
Technical scheme is further illustrated with reference to the accompanying drawings and examples.
Present invention aims to defect present in prior art, there is provided one kind can automatic identification Bay position, and
Present container placement location is judged, the Aulomatizeted Detect of container Bay positions is completed, and identification information is uploaded to into clothes
Business device, recognition result is compared with pre-stowage plan and Proposed Shipping Schedule figure, and the container of placement location mistake is reported to the police, whole
Individual process is all automatically performed without the need for manual intervention, and wherein system installation structure figure is as shown in Figure 2.
To achieve these goals, system topological figure of the invention is as shown in Figure 3.
The system framework is to install 1 set of smart camera in bridge crane driver's cabin i.e. dolly bottom, is easy to carry out reality to container
When track;Large arm installs a set of smart camera before bridge crane crossbeam, realizes the monitoring to cabin Bay positions.And in extra large side and land side
Diverse location installs video camera, for container number identification.By control software to the real-time video information for obtaining and PLC letters
Breath is analyzed process, and result is uploaded to into Surveillance center, and the container to placing errors present carries out automatic alarm.
The implementation method of the present invention is as follows:
First, container ship case Bay positional representations
Premised on genesis analysis, each case position represents case position with 6 bit digitals.Front two is line number, represents the vertical of case position
To coordinate;Middle two is row number, represents the lateral coordinates of case position;Afterwards two is level number, represents the vertical coordinate of case position.Packaging
Case cabin profile is as shown in Figure 4.
Wherein,
1) line number (BayNo.) represents the lengthwise position of case position, arranges from bow to stern.
Confess one's crime to tail with 01,02,03,04 ... ... expression.
Odd number of confessing one's crime to tail 20 ' with 01,03,05 ... ... is represented;
40 ' with 02,06,10 ... ..., and even number is represented;
40 ' with 04,08,12 ... ..., and even number is represented.
2) row number (Row No.or Slot No.) represents the lateral attitude of container space.
From starboard aport, represent with 01,02,03 ... ....
On the basis of central fore-and-aft vertical plane, from centre to two sides of a ship:
Starboard is with 01,03,05 ... ..., and odd number is represented;
Larboard is with 02,04,06 ... ..., and even number is represented;
If the total columns in ship case position is odd number, has one on central fore-and-aft vertical plane and arrange, numbering is 00.
3) level number (Tier No.) represents the vertical line position of container space.
In cabin from the bottom, with H1, H2, H3 ... ... are represented;
Deck is started at from on-deck, and with D1, D2, D3 ... ... are represented.
In cabin from the bottom, with 02,04,06 ... ..., even number is represented;
Deck is started at from on-deck, and with 82,84,86 ... ..., even number is represented.
2nd, container number identification
System is mainly responsible for video acquisition by front end candid camera, negative by PLC coordinated signals main frames (identification server)
The transition translation of duty linkage PLC control signals, and the real-time coordinates of dolly and suspender are issued into candid camera acquisition container
Real time position, diverse location ball machine is triggered during container handling 5 faces of container is accurately captured with (container sea
Chamber door after case face, container before land side, container).The HD video obtained by high definition snapshot video camera is uploaded to container
Identification main frame carries out the identification of container number, and uploads to supervision and management center.
Container number, as the unique identity information of container, is represented with matching for corresponding data in database.Its
It is made up of 11 codings, including three parts:
1) Part I is made up of 4 English alphabets.Front three code mainly illustrates case master, operator, the 4th code
Illustrate the type of container.
2) Part II is made up of 6 bit digitals.It is casing registration code, for unique mark that a container body is held
Know.
3) Part III is check code.Obtained through the regular computing of verification by front 4 letters and 6 bit digitals, for recognizing
Whether make a mistake in verification.That is the 11st bit digital.
The correspondence of one computing is had according to each letter and number of the regular case number (CN) of verification.Front 10 letters of case number (CN)
With digital respective value from 0 to Z, correspondence numeral can not be to 11 delivery numbers, so to remove N positions for 0 to 38,11,22,33
Case number (CN) respective value is multiplied by respectively again 2N(N=1,2...10).
Wherein, container number identification main technological route is as shown in Figure 5.
3rd, PLC obtains control information
It is as follows that PLC obtains data form:
The address H00 high bytes of data 1 retain
Low byte 0-255 does not stop conversion, if constant:Communication failure
The address H01 of data 2 is opened and closed lock status
Bit0:Locking
Bit1:Unlock
Bit2:Case
Bit3:Double box modes
Bit4:20 chis
Bit5:40 chis
Bit6:45 chis
The address H02 lifting altitude units of data 3:cm
The little truck position units of the address H03 of data 4:cm
The address H04 Container Weight units of data 5:ton
From the above mentioned, by Bit0 lockings in data 2 and Bit1 unlocking signals, you can know that container is sling information, by
In Bit2 case i.e. understand container fall signal, by Bit3 and Bit4 i.e. understand Container Dimensions, thus speculate its be located
No. Bay, i.e. line number.Understand present container apart from the position of operating room according to little truck position in data 4.
4th, Bay positions tentatively judge
Heretofore described method is mainly used in the monitoring of Bay positions, and all analyses are all based on assuming first in certain Bay
Individual container is positioned in correct position, and carries out the accuracy judgement of subsequent bit on this basis, and this method does not consider Bay positions
Layer information in figure.Its main thought is to obtain data message according to PLC, pre- judgement is carried out to container Bay positions, due to port
Mouth working environment is complex, due to sea wind reason during bridge crane, suspender can be caused to rock and ship movement, all can give
Error is brought in Bay positions with judgement, is to eliminate the error, and the present invention is with reference to tracking and ranging technology in Video Analysis Technology to anticipation
As a result it is corrected, and anticipation result and correction result is combined and contrasted with cargo plan and Proposed Shipping Schedule figure, with this
Realize that container Bay positions are monitored, the container for aligning placement location mistake is reported to the police, and its position is corrected in time so as to meet dress
Ship plan.
The information obtained by PLC, when being located at first container of placement in a certain Bay, lifting appliance moving distance is little parking stall
It is set to D1, it is in place n, and container width has unified national standard, is set to w, and the number of every Bay middle positions is
Know, be set to N, then
Then suspender is to the distance of ship side:
D=D1-(N-n)*w
The corresponding PLC displacements of n-th ' individual position container should be:
D'=D+ (N-n') * w=D1+(n-n')*w
Thus, lifting appliance moving distance can be obtained according to PLC feedback informations and pre- judgement is carried out to container place Bay positions.
5th, target following
After container hoisting information is obtained by PLC, container is tracked by the first image snapshot device, is passed through
Based on the target tracking algorism of video technique, container motion track is obtained, container landing place is determined with this, and combine mark
Determine technology, container width combined by moving track calculation container actual motion distance, obtain container institute information in place,
Realize based on the container Bay positions information correction of video technique.
The present invention selects Mean-shift target tracking algorisms to obtain target trajectory.Its general principle is by respectively
The characteristic value probability of pixel obtains the description with regard to object module and candidate family in calculating target area and candidate region, utilizes
Similar function measures the similitude of candidate's masterplate of initial frame object module and present frame, and selection makes the maximum candidate of similar function
Model simultaneously obtains vectorial with regard to the Mean-shift of object module, obtains the actual position of target, reaches the purpose of tracking.
Fig. 6 is the principle schematic of the method.Target following starts from data point(soft dot) table
What is shown is central point, and what subscript was represented is iterations, and the black round dot of surrounding represents the window sample point in continuous movement, empty
What line circle was represented is the size of density estimation window).Arrow represents shift vectors of the sample point relative to kernel function central point,
Average shift vectors can point to the most intensive direction of sample point, i.e. gradient direction.Because Mean-shift methods are convergences,
Therefore in the current frame by the region that sample point in the search characteristics space that iterates is most intensive, Searching point is close along sample point
Local density's maximal point point is arrived in the direction " drift " that degree increasesNamely imputed target location, so as to reach tracking
Purpose, tracking process terminates.
1. object module description
For the target being partitioned into, it is assumed that wherein there is n pixel, its position is { zi}I=1...n, the ash to target area
Degree color space is evenly dividing, and obtains the grey level histogram being made up of m equal interval.The q of object moduleuProbability density (u
=1 ..., m) it is represented by:
Wherein,Represent the normalization location of pixels with target's center as origin, (x0,y0) it is target's center's coordinate.K is
Kernel function, often selects Epanechikov kernel functions, b (zi) represent ziWhich histogram is place's pixel belong to, and u is histogrammic
Color index.δ[b(zi)-u] effect of function is to judge pixel z in target areaiWhether the gray value at place belongs in histogram
U-th unit.C is normalization coefficient.
2. candidate family description
In t frames, according to the target's center position f of t-1 frames0, with f0For the center of search window, candidate's mesh is obtained
Target center position coordinates f, calculate the candidate target region histogram of present frame.Pixel { the z in the regioni}I=1...nRepresent,
Then the probability density of candidate family is:H is kernel function window size, is determined
Weight distribution, other specification is described with object module.
3. similarity measurement
Similarity function is used to describe the similarity degree between object module and candidate target.The present invention is adopted
Used as similarity function, it is defined as Bhattacharyya coefficients:Similar function is more big by then two
Individual model is more similar.By the center f of target in former frame0As the center of search window, find and cause similar function most
Big candidate region, is the position of the target in this frame.
4.Mean-shift iterative process
The iterative process of average drifting, that is, the process of target location search.To make similar function maximum, above formula is entered
Row Taylor expansion, obtains the approximate expression of Bhattacharyya coefficients:
Only have Section 2 to change with f in above formula, its maximization process just can be by candidate region center to real estate
The Meanshift iterative equations at center are completed:
Wherein, g (x)=- K'(x), Mean-shift methods are exactly from fkRise to two models and compare color change maximum
Direction constantly move, to the last twice displacement is less than threshold value, that is, find the target location of present frame, and in this, as
The initiating searches window center of next frame, so repeats.
6th, distance is calculated
Due to assuming that first container for falling in correct Bay bitmaps, is obtaining it in specific a certain Bay
Behind his container motion track, only its respective distances with first container need to be calculated, according to the width of container, you can
Determine if in correct position.
Want to obtain corresponding actual range, then need to demarcate known cabin, concrete methods of realizing is as follows:
Described mapping relations step of setting up includes demarcating mapping point and sets up mapping table step,
Described demarcation mapping point, is by determining the position of video camera, inside and outside parameter and setting up imaging model determining
The corresponding relation between object and its imaging on the image plane in world coordinate system,
In practical application scene, due to there is the position information cut-off rule demarcated in cabin, and respectively split distance between centers of tracks
From certain, as container width, therefore by demarcating to known point, with reference to video camera imaging principle, and then can obtain
Required mapping relations;
Described sets up mapping table, i.e.,
If certain coordinate of point in world coordinate system is W (X, Y, Z), because the proportionate relationship of similar triangles can obtain its throwing
Shadow point I (x, y), wherein
F is the intersecting point coordinate of subpoint and world coordinate system;
The division arithmetic of variable is contained in above formula, belongs to nonlinear transformation, when homogeneous coordinates are introduced line is converted thereof into
Property matrix is calculated, it follows that homogeneous coordinates matrix such as following formula
In car speed calculating process, it is not necessary to know the elevation information of vehicle, therefore above formula is simplified, obtain following
Transformation matrix
The coordinate expressions that can obtain world coordinate system midpoint (X, Y) by above formula are
Actual range of the known distance point in image coordinate system in pixel coordinate and world coordinate system is substituted into into above formula, is asked
Go out the mapping relations of pixel distance and actual range, thus set up Two coordinate system mapping table, i.e. mapping table MapTable
[IMAGE_SIZE], wherein IMAGE_SIZE are the product of picture traverse and height, in follow-up calculating process, when input needs
The pixel coordinate of the impact point of inquiry can obtain the corresponding actual range of point;
Described speed calculation step is that each point locus in moving vehicle target trajectory is substituted into into described mapping to close
It is table, obtains the actual range that each impact point is represented in track,
Wherein, Disi[i].x、Disi[i] .y is certain point corresponding actual range of transverse direction and longitudinal direction, and MapTable is institute
State the mapping table of foundation.
By the mapping relations and the sum of known certain Bay middle position of acquisition, container institute information in place is calculated, by this
As a result it is corrected with the position information result calculated by plc data, obtains the accurate position information of certain container, and and pre-stowage plan
And Proposed Shipping Schedule figure is contrasted, the real-time monitoring of container Bay positions is realized.
7th, Bay positions information checking
By above-mentioned introduction respectively by PLC control information and video processing technique acquisition present container place Bay positions
Information, both information is combined and is compared with actual pre-stowage plan and Proposed Shipping Schedule figure, if both can match, is illustrated
Present container puts position correctly, is not processed, if both mismatch, illustrates that present container is put out of alignment
Really, need to be reported to the police, and reappose the container to meet pre-stowage plan requirement according to Proposed Shipping Schedule figure.
Claims (6)
1. a kind of container Bay level monitoring systems, including bridge crane control room dolly, in dolly bottom the first video capture is installed
Device, for carrying out real-time tracking to container,
Large arm center is provided with the second image snapshot device before bridge crane crossbeam, for monitoring containers shellfish position information,
At least one the 3rd image snapshot device is installed in the extra large side of harbour, for container number identification,
At least one the 4th image snapshot device is installed in the land side of harbour, for container number identification, in bridge crane control room
Bridge crane PLC and identification server are inside provided with, PLC coordinated signals identification server sends out the real-time coordinates of bridge crane trolley and suspender
To image snapshot device so as to obtain container real time position, the video capture of diverse location is triggered during container handling
Device is accurately captured to the multiple faces of container, after these faces are including case face before container sea land side, container and container
Chamber door, the image information of acquisition is uploaded to into identification server carries out the identification of container number, and uploads in monitoring management
The heart, the container to placing errors present carries out automatic alarm.
2. container Bay level monitoring systems as claimed in claim 1, it is characterised in that identification server passes through switching equipment
Result is uploaded to into supervision and management center with wireless bridge, supervision and management center is provided with storage array.
3. a kind of container Bay position monitoring methods, it is characterised in that obtaining container number, correspondence number in matching database
According to rear, there is step:
S101, obtains Bay message bit patterns;
S102, mapping relations are demarcated;
S103, tracks container;
S104, judges whether container is sling, if it is not, waiting slinging, if sling, turns S105;
S105, obtains plc data;
S106, judges whether container falls, if it is not, determining present container and first container distance and updating
Bay bitmaps, turn S109, if container falls, turn S107;
S107, determines present container position;
S108, calculates Bay bitmaps;
S109, obtains Bay positions information;
S110, judges whether identical with known Bay positions information, if it is not the same, then reporting to the police, if identical, turns S102.
4. container Bay position monitoring methods as claimed in claim 3, it is characterised in that when S105 obtains container by PLC
After lifting information, using Mean-shift target tracking algorisms, container motion track is obtained, container landing position is determined with this
Put.
5. container Bay position monitoring methods as claimed in claim 3, it is characterised in that present container institute is determined in S107
Method in position is,
It is assumed that first container for falling is in correct Bay bitmaps, after other container motion tracks are obtained, calculate
Its respective distances with first container, according to the width of container, you can determine if in correct position,
To obtain respective distances, known cabin is demarcated, implement step as follows:
Described mapping relations step of setting up includes demarcating mapping point and sets up mapping table step,
Described demarcation mapping point, is by determining the position of video camera, inside and outside parameter and setting up imaging model determining the world
The corresponding relation between object and its imaging on the image plane in coordinate system,
In practical application scene, due to having the position information cut-off rule demarcated, and each segmentation wire spacing one in cabin
Determine, as container width, therefore by demarcating to known point, with reference to video camera imaging principle, and then can obtain required
Mapping relations;
Described sets up mapping table, i.e.,
If certain coordinate of point in world coordinate system is W (X, Y, Z), because the proportionate relationship of similar triangles can obtain its subpoint
I (x, y), wherein
F is the intersecting point coordinate of subpoint and world coordinate system;
The division arithmetic of variable is contained in formula (1), belongs to nonlinear transformation, when homogeneous coordinates are introduced linear moment is converted thereof into
Battle array is calculated, it follows that homogeneous coordinates matrix such as following formula (2)
In car speed calculating process, it is not necessary to know the elevation information of vehicle, therefore above formula is simplified, following conversion is obtained
Matrix
The coordinate expressions that can obtain world coordinate system midpoint (X, Y) by above formula (3) are
Actual range of the known distance point in image coordinate system in pixel coordinate and world coordinate system is substituted into into above formula, picture is obtained
Plain distance and the mapping relations of actual range, thus set up Two coordinate system mapping table, i.e. mapping table MapTable [IMAGE_
SIZE], wherein IMAGE_SIZE is the product of picture traverse and height, in follow-up calculating process, when input needs inquiry
The pixel coordinate of impact point can obtain the corresponding actual range of point;
Described speed calculation step is that each point locus in moving vehicle target trajectory is substituted into into described mapping table
Upper table, obtains the actual range that each impact point is represented in track,
Wherein, Disi[i].x、Disi[i] .y is certain point corresponding actual range of transverse direction and longitudinal direction, and MapTable is described building
Vertical mapping table.
6. container Bay position monitoring methods as claimed in claim 3, it is characterised in that at PLC control information and video
Reason technology obtains present container place Bay positions information, both information is combined and is compared with pre-stowage plan and Proposed Shipping Schedule,
If both can match, illustrate that present container puts position correctly, is not processed, if the case position of container with match somebody with somebody
Carry figure inconsistent, but still on the case position at identical harbour, then give a warning, if the case position of container is inconsistent with pre-stowage plan,
And not on the case position at identical harbour, report to the police and notify that field personnel is processed.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610770423.0A CN106599885B (en) | 2016-08-30 | 2016-08-30 | Bay level monitoring system and method for container |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610770423.0A CN106599885B (en) | 2016-08-30 | 2016-08-30 | Bay level monitoring system and method for container |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106599885A true CN106599885A (en) | 2017-04-26 |
CN106599885B CN106599885B (en) | 2020-08-11 |
Family
ID=58556002
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610770423.0A Active CN106599885B (en) | 2016-08-30 | 2016-08-30 | Bay level monitoring system and method for container |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106599885B (en) |
Cited By (23)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108182552A (en) * | 2018-02-02 | 2018-06-19 | 上海西井信息科技有限公司 | Loading-unloading method, system, equipment and the storage medium of container ship |
CN108394814A (en) * | 2018-02-05 | 2018-08-14 | 上海振华重工(集团)股份有限公司 | Gantry crane cart based on image recognition guides system and method |
CN108681702A (en) * | 2018-05-11 | 2018-10-19 | 中远网络物流信息科技有限公司 | A kind of container handling stowage shellfish position information determines method and system |
CN108706362A (en) * | 2018-08-16 | 2018-10-26 | 广州港集团有限公司 | A kind of container shipment stowage location monitoring device and monitoring method |
CN109523553A (en) * | 2018-11-13 | 2019-03-26 | 华际科工(北京)卫星通信科技有限公司 | A kind of container unusual fluctuation monitoring method based on LSD straight-line detection partitioning algorithm |
CN110070324A (en) * | 2019-04-24 | 2019-07-30 | 大连大学 | A kind of container terminal intelligence tallying system |
CN110196562A (en) * | 2019-04-12 | 2019-09-03 | 南京中理外轮理货有限公司 | Container intelligence tally information system and management method |
CN110712875A (en) * | 2018-07-12 | 2020-01-21 | 北京图森未来科技有限公司 | Checkpoint control method and device and container |
CN110969054A (en) * | 2018-09-29 | 2020-04-07 | 杭州海康威视数字技术股份有限公司 | Container number identification method and device |
CN111401172A (en) * | 2020-03-06 | 2020-07-10 | 大连海事大学 | Port hoisting material bag automatic counting method based on video |
CN112193370A (en) * | 2020-09-27 | 2021-01-08 | 浙江星寰科技有限公司 | Ship box positioning system and positioning method thereof |
CN112215885A (en) * | 2020-09-16 | 2021-01-12 | 深圳市平方科技股份有限公司 | Container position identification method and device based on autonomous learning |
CN112550979A (en) * | 2020-10-14 | 2021-03-26 | 宁波大榭招商国际码头有限公司 | Method for realizing monitoring of container door opening |
CN113112862A (en) * | 2021-04-16 | 2021-07-13 | 重庆航易大数据研究院有限公司 | Vehicle management method and system for commodity garage yard |
CN113361953A (en) * | 2021-06-28 | 2021-09-07 | 广东嘉贸通科技有限公司 | Customs port cargo pipe on-site robot inspection method and system |
CN113419480A (en) * | 2021-06-01 | 2021-09-21 | 镇江港务集团有限公司 | Machine vision-based log recognition and intelligent tallying system for port |
CN113433598A (en) * | 2021-08-26 | 2021-09-24 | 泰豪信息技术有限公司 | Self-constriction behavior monitoring method, device and system applied to prison |
CN114219386A (en) * | 2021-11-12 | 2022-03-22 | 武汉众智鸿图科技有限公司 | Dangerous cargo container yard isolation checking method, system and storage medium |
CN115159181A (en) * | 2022-08-12 | 2022-10-11 | 青岛港国际股份有限公司 | Automatic container wharf quay bridge monitoring method |
CN115170650A (en) * | 2022-07-11 | 2022-10-11 | 深圳市平方科技股份有限公司 | Container vehicle-mounted position identification method and device, electronic equipment and storage medium |
WO2023273871A1 (en) * | 2021-06-29 | 2023-01-05 | 中移(上海)信息通信科技有限公司 | Port information processing method and apparatus, and related device |
CN115690061A (en) * | 2022-11-08 | 2023-02-03 | 北京国泰星云科技有限公司 | Container terminal truck collection detection method based on vision |
CN116152243A (en) * | 2023-04-19 | 2023-05-23 | 深圳市平方科技股份有限公司 | Method for detecting container loading and unloading operation state based on image analysis |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030167214A1 (en) * | 2002-03-04 | 2003-09-04 | Kang Kyung Won | Scheduling method for loading and unloading containers at the terminal and a computer readable recording medium recorded a computer programming of the same |
CN101251381A (en) * | 2007-12-29 | 2008-08-27 | 武汉理工大学 | Dual container positioning system based on machine vision |
CN101365116A (en) * | 2008-09-28 | 2009-02-11 | 上海外轮理货有限公司 | Real-time monitoring system for container loading, unloading and checking |
CN204314917U (en) * | 2015-01-07 | 2015-05-06 | 厦门外轮理货有限公司 | Container number recognition device |
CN105431370A (en) * | 2013-08-12 | 2016-03-23 | Abb技术有限公司 | Method and system for automatically landing containers on a landing target using a container crane |
CN105893940A (en) * | 2016-03-29 | 2016-08-24 | 南京大学 | Method for realizing container hoisting crashproof aligning system based on edge detection |
-
2016
- 2016-08-30 CN CN201610770423.0A patent/CN106599885B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030167214A1 (en) * | 2002-03-04 | 2003-09-04 | Kang Kyung Won | Scheduling method for loading and unloading containers at the terminal and a computer readable recording medium recorded a computer programming of the same |
CN101251381A (en) * | 2007-12-29 | 2008-08-27 | 武汉理工大学 | Dual container positioning system based on machine vision |
CN101365116A (en) * | 2008-09-28 | 2009-02-11 | 上海外轮理货有限公司 | Real-time monitoring system for container loading, unloading and checking |
CN105431370A (en) * | 2013-08-12 | 2016-03-23 | Abb技术有限公司 | Method and system for automatically landing containers on a landing target using a container crane |
CN204314917U (en) * | 2015-01-07 | 2015-05-06 | 厦门外轮理货有限公司 | Container number recognition device |
CN105893940A (en) * | 2016-03-29 | 2016-08-24 | 南京大学 | Method for realizing container hoisting crashproof aligning system based on edge detection |
Cited By (34)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108182552A (en) * | 2018-02-02 | 2018-06-19 | 上海西井信息科技有限公司 | Loading-unloading method, system, equipment and the storage medium of container ship |
CN108182552B (en) * | 2018-02-02 | 2018-12-07 | 上海西井信息科技有限公司 | Loading-unloading method, system, equipment and the storage medium of container ship |
CN108394814A (en) * | 2018-02-05 | 2018-08-14 | 上海振华重工(集团)股份有限公司 | Gantry crane cart based on image recognition guides system and method |
CN108681702A (en) * | 2018-05-11 | 2018-10-19 | 中远网络物流信息科技有限公司 | A kind of container handling stowage shellfish position information determines method and system |
CN108681702B (en) * | 2018-05-11 | 2020-10-23 | 中远海运科技(北京)有限公司 | Method and system for determining loading and unloading stowage decibel information of container |
CN110712875B (en) * | 2018-07-12 | 2022-02-08 | 北京图森智途科技有限公司 | Checkpoint control method and device and container |
CN110712875A (en) * | 2018-07-12 | 2020-01-21 | 北京图森未来科技有限公司 | Checkpoint control method and device and container |
CN108706362A (en) * | 2018-08-16 | 2018-10-26 | 广州港集团有限公司 | A kind of container shipment stowage location monitoring device and monitoring method |
CN108706362B (en) * | 2018-08-16 | 2023-11-24 | 广州港集团有限公司 | Device and method for monitoring loading position of container loading |
CN110969054A (en) * | 2018-09-29 | 2020-04-07 | 杭州海康威视数字技术股份有限公司 | Container number identification method and device |
CN110969054B (en) * | 2018-09-29 | 2023-09-26 | 杭州海康威视数字技术股份有限公司 | Container number identification method and device |
CN109523553B (en) * | 2018-11-13 | 2022-10-18 | 华际科工(北京)卫星通信科技有限公司 | Container abnormal movement monitoring method based on LSD linear detection segmentation algorithm |
CN109523553A (en) * | 2018-11-13 | 2019-03-26 | 华际科工(北京)卫星通信科技有限公司 | A kind of container unusual fluctuation monitoring method based on LSD straight-line detection partitioning algorithm |
CN110196562A (en) * | 2019-04-12 | 2019-09-03 | 南京中理外轮理货有限公司 | Container intelligence tally information system and management method |
CN110070324A (en) * | 2019-04-24 | 2019-07-30 | 大连大学 | A kind of container terminal intelligence tallying system |
CN110070324B (en) * | 2019-04-24 | 2023-04-07 | 大连大学 | Intelligent tallying system for container terminal |
CN111401172B (en) * | 2020-03-06 | 2023-10-27 | 大连海事大学 | Port crane ladle automatic counting method based on video |
CN111401172A (en) * | 2020-03-06 | 2020-07-10 | 大连海事大学 | Port hoisting material bag automatic counting method based on video |
CN112215885A (en) * | 2020-09-16 | 2021-01-12 | 深圳市平方科技股份有限公司 | Container position identification method and device based on autonomous learning |
CN112193370A (en) * | 2020-09-27 | 2021-01-08 | 浙江星寰科技有限公司 | Ship box positioning system and positioning method thereof |
CN112193370B (en) * | 2020-09-27 | 2022-07-22 | 浙江星寰科技有限公司 | Box positioning system on ship |
CN112550979A (en) * | 2020-10-14 | 2021-03-26 | 宁波大榭招商国际码头有限公司 | Method for realizing monitoring of container door opening |
CN113112862A (en) * | 2021-04-16 | 2021-07-13 | 重庆航易大数据研究院有限公司 | Vehicle management method and system for commodity garage yard |
CN113419480A (en) * | 2021-06-01 | 2021-09-21 | 镇江港务集团有限公司 | Machine vision-based log recognition and intelligent tallying system for port |
CN113361953A (en) * | 2021-06-28 | 2021-09-07 | 广东嘉贸通科技有限公司 | Customs port cargo pipe on-site robot inspection method and system |
CN113361953B (en) * | 2021-06-28 | 2022-08-26 | 广东嘉贸通科技有限公司 | Customs port cargo pipe on-site robot inspection method and system |
WO2023273871A1 (en) * | 2021-06-29 | 2023-01-05 | 中移(上海)信息通信科技有限公司 | Port information processing method and apparatus, and related device |
CN113433598A (en) * | 2021-08-26 | 2021-09-24 | 泰豪信息技术有限公司 | Self-constriction behavior monitoring method, device and system applied to prison |
CN114219386A (en) * | 2021-11-12 | 2022-03-22 | 武汉众智鸿图科技有限公司 | Dangerous cargo container yard isolation checking method, system and storage medium |
CN115170650A (en) * | 2022-07-11 | 2022-10-11 | 深圳市平方科技股份有限公司 | Container vehicle-mounted position identification method and device, electronic equipment and storage medium |
CN115159181A (en) * | 2022-08-12 | 2022-10-11 | 青岛港国际股份有限公司 | Automatic container wharf quay bridge monitoring method |
CN115690061A (en) * | 2022-11-08 | 2023-02-03 | 北京国泰星云科技有限公司 | Container terminal truck collection detection method based on vision |
CN115690061B (en) * | 2022-11-08 | 2024-01-05 | 北京国泰星云科技有限公司 | Vision-based container terminal truck collection detection method |
CN116152243A (en) * | 2023-04-19 | 2023-05-23 | 深圳市平方科技股份有限公司 | Method for detecting container loading and unloading operation state based on image analysis |
Also Published As
Publication number | Publication date |
---|---|
CN106599885B (en) | 2020-08-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106599885A (en) | Monitoring system and method for container Bay | |
KR102206662B1 (en) | Vision camera system to manage an entrance and exit management of vehicles and to recognize objects of camera video data in a port container terminal and method thereof | |
CN109685066B (en) | Mine target detection and identification method based on deep convolutional neural network | |
KR102206658B1 (en) | Vision camera system to be communicated with Terminal Operating System through middleware in a port container terminal and method thereof | |
CN112907491B (en) | Laser point cloud loop detection method and system suitable for underground roadway | |
CN104183127B (en) | Traffic surveillance video detection method and device | |
CN103268616B (en) | The moveable robot movement human body tracing method of multi-feature multi-sensor | |
CN109344928A (en) | The accurate checking method of cargo and system based on unmanned plane in a kind of bulk storage plant | |
CN105550692B (en) | The homing vector landing concept of unmanned plane based on marker color and contour detecting | |
CN105447459A (en) | Unmanned plane automation detection target and tracking method | |
CN106910204B (en) | A kind of method and system to the automatic Tracking Recognition of sea ship | |
CA2994508A1 (en) | Vegetation management for power line corridor monitoring using computer vision | |
CN111598952B (en) | Multi-scale cooperative target design and online detection identification method and system | |
CN110989687A (en) | Unmanned aerial vehicle landing method based on nested square visual information | |
CN102081801A (en) | Multi-feature adaptive fused ship tracking and track detecting method | |
CN108734103A (en) | The detection of moving target and tracking in satellite video | |
CN102447835A (en) | Non-blind-area multi-target cooperative tracking method and system | |
CN109828267A (en) | The Intelligent Mobile Robot detection of obstacles and distance measuring method of Case-based Reasoning segmentation and depth camera | |
CN106934817A (en) | Based on multiattribute multi-object tracking method and device | |
CN108830224A (en) | A kind of high-resolution remote sensing image Ship Target Detection method based on deep learning | |
CN113920436A (en) | Remote sensing image marine vessel recognition system and method based on improved YOLOv4 algorithm | |
CN108871409A (en) | A kind of fault detection method and system | |
CN114926422B (en) | Method and system for detecting passenger flow of getting on and off vehicles | |
CN111768417A (en) | Railway wagon overrun detection method based on monocular vision 3D reconstruction technology | |
CN103679128B (en) | A kind of Aircraft Targets detection method of anti-interference of clouds |
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 | ||
CB02 | Change of applicant information | ||
CB02 | Change of applicant information |
Address after: 200135 No. 600 Minsheng Road, Shanghai, Pudong New Area Applicant after: COSCO SHIPPING TECHNOLOGY Co.,Ltd. Applicant after: COSCO Shipping Technology (Beijing) Co., Ltd Address before: 200135 No. 600 Minsheng Road, Shanghai, Pudong New Area Applicant before: CHINA SHIPPING NETWORK TECHNOLOGY Co.,Ltd. Applicant before: COSCO ONLINE LOGISTICS INFORMATION SCIENCE & TECHNOLOGY Co.,Ltd. |
|
GR01 | Patent grant | ||
GR01 | Patent grant |