CN110460813A - A kind of container representation acquisition device and acquisition method based on video flowing - Google Patents
A kind of container representation acquisition device and acquisition method based on video flowing Download PDFInfo
- Publication number
- CN110460813A CN110460813A CN201910740684.1A CN201910740684A CN110460813A CN 110460813 A CN110460813 A CN 110460813A CN 201910740684 A CN201910740684 A CN 201910740684A CN 110460813 A CN110460813 A CN 110460813A
- Authority
- CN
- China
- Prior art keywords
- image
- container
- truck
- acquisition
- video
- 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
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000012545 processing Methods 0.000 claims abstract description 82
- 230000006698 induction Effects 0.000 claims description 18
- 230000001629 suppression Effects 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 10
- 230000011218 segmentation Effects 0.000 claims description 9
- 230000008859 change Effects 0.000 claims description 8
- 238000001514 detection method Methods 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 8
- 238000012360 testing method Methods 0.000 claims description 4
- 230000004927 fusion Effects 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 230000007704 transition Effects 0.000 claims description 3
- 230000001960 triggered effect Effects 0.000 claims description 3
- 238000013316 zoning Methods 0.000 claims description 3
- 238000004806 packaging method and process Methods 0.000 claims 2
- 238000007689 inspection Methods 0.000 claims 1
- 230000008439 repair process Effects 0.000 claims 1
- 238000013461 design Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000003708 edge detection Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000000149 penetrating effect Effects 0.000 description 2
- 238000012876 topography Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000000470 constituent Substances 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4038—Image mosaicing, e.g. composing plane images from plane sub-images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/148—Segmentation of character regions
- G06V30/153—Segmentation of character regions using recognition of characters or words
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/66—Remote control of cameras or camera parts, e.g. by remote control devices
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/698—Control of cameras or camera modules for achieving an enlarged field of view, e.g. panoramic image capture
-
- 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
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The present invention provides a kind of container representation acquisition device based on video flowing, is arranged on the lane that container truck passes through, comprising: truck station acquisition device, control device, image acquisition and processing device and high-definition network camera.Present invention is mainly applied to the acquisition that container yard or customs, harbour container inlet realize container representation, have the characteristics that video stream signal acquisition, required number of devices are few, adaptable, acquisition is accurate, at low cost.The present invention also discloses a kind of container representation acquisition method based on video flowing.
Description
Technical field
The present invention relates to automatic control technology fields, acquire more particularly to a kind of container representation based on video flowing
Device and acquisition method.
Background technique
It is container management and tracking to the acquisition and recording of container number at container yard and customs, harbour entrance
One of important process, there are mainly two types of implementations at present, and one is by manual record case number (CN), another kind is known by case number (CN)
Other system acquisition.Manual record case number (CN) is the vehicle-mounted collection of truck for passing through truck vehicle passage by operating personnel scene manual record
Vanning case number (CN), which not only waste of manpower, but also there is some potential safety problems during the work time, case number (CN) identifying system is adopted
Collection case number (CN) is to acquire container representation by installing video camera in lane two sides, and this scheme is usually to install 4- in a lane
8 video cameras, 4-6 are switched to infrared emission and other control equipment, realizes vehicle location and container representation acquisition, the program
The number of devices needed is more, at high cost, and can only acquire the topography of container, (single case, double for container box
Case, long case) differentiation it is relatively difficult, case number (CN) discrimination is lower.
Summary of the invention
The embodiment of the invention provides a kind of container representation acquisition device and acquisition method based on video flowing solves existing
Have containerized shipment scheme need number of devices it is more, it is at high cost, and can only acquire container topography the problem of.
A kind of container representation acquisition device based on video flowing, is arranged on the lane that container truck passes through, comprising:
Truck station acquisition device, control device, image acquisition and processing device and high-definition network camera, wherein
Truck station acquisition device, including being arranged in the ground induction coil of lane initial position, connecting with inductance coil
Vehicle checker and two couples of infrared emission switch A being sequentially arranged along lane direction of advance1-A2And A3-A4, wherein two pairs infrared
To penetrate the distance between switch be greater than container truck headstock length but be less than the length of container truck entirety, lane
The PLC connection that coil passes through vehicle checker and control device is felt, for detecting whether truck enters lane, when truck passes through
When, ground induction coil generates trigger signal and is transferred to vehicle checker, and vehicle checker transfers signals to the PLC of control device, and 2 pairs are infrared right
The PLC connection for penetrating switch and control device, when container truck is without lane, infrared emission switch is in connected state, when
When container truck is by lane, infrared emission switch is first blocked by container to be connected to afterwards, and control device collects infrared signal
Variation, pass through logic judgment realize container truck location information；
Control device, including PLC and the network switch, PLC switch collected collection according to ground induction coil and infrared emission
Vanning truck location information judges that video camera starts to shoot and stopping is shot by control logic, and output phase should shoot or stop
The instruction of shooting is transferred to image acquisition and processing device, sends shooting instruction by image acquisition and processing device and takes the photograph to high-definition network
Camera, control high-definition network camera start or stop shooting vision signal；
Image acquisition and processing device mainly includes image acquisition and processing server, graphic display terminal, image acquisition and processing
Server is connected by the network switch of cable and control device, what image acquisition and processing server receiving control device was sent
It takes pictures control instruction, control video camera shoots vision signal, and by vision signal storage into server, and realizes and be based on video
The pictures subsequent of stream is handled, and graphic display terminal is connect with server by interchanger, for showing image acquisition and processing service
Device treated container complete image and the container number of identification；
High-definition network camera, C1、C2It is arranged symmetrically in the top of lane two sides, and is set to two pairs of infrared emissions and opens
Between pass, for receiving the video capture control instruction of image acquisition and processing device, to the truck vehicle-mounted container by lane
Carry out video capture.
Selectively, in truck station acquisition device, when truck has just enter into lane, the triggering of lane ground induction coil,
Infrared emission switch A1-A2It is gone off by connection, in truck traveling process, since headstock length is much smaller than container case
Body length, so when headstock front does not reach infrared emission switch A3-A4When, i.e. infrared emission switch A3-A4When still in connection
State, infrared emission switch A1-A2Become being connected to via disconnection, indicates that truck headstock passes through A1-A2Not yet reach A3-A4,
After headstock all passes through, as infrared emission switch A1-A2When going off again, indicate that container body begins through A1-A2,
Truck continues on, and works as A3-A4Disconnection and A1-A2Connection, container body pass through A1-A2Into A3-A4, work as A1-A2And A3-A4
It is also turned on, container judges truck by infrared emission switch monitors region, by the state change that infrared emission switchs
Advanced positions information.
Selectively, in image acquisition and processing device, when truck passes through Intelligent gateway lane, truck truck position is triggered
The ground induction coil and infrared emission of acquisition device switch, and control device PLC takes pictures control instruction to figure according to logic judgment transmission
As acquisition processing device, image acquisition and processing device controls 2 high-definition network cameras and acquires vision signal respectively, in order to obtain
The panoramic picture of entire container, with the difference of adjacent two interframe of video stream signal, to key frame figure in the video flowing of acquisition
As carrying out feature extraction, registration and splicing, complete container body panoramic picture, image recognizing and processing equipment pair are eventually formed
Image is handled, and is identified container number and is shown case number (CN) and image on graphic display terminal computer.
A kind of container representation acquisition method based on video flowing, comprising:
Step 1: when truck enters lane, the triggering of lane ground induction coil, since headstock stops, infrared emission switch
A1-A2It is gone off by connection, in truck traveling process, since headstock length is less than container body length, so working as vehicle
Head front does not reach infrared emission switch A3-A4When, i.e. infrared emission switch A3-A4Still in connected state, infrared emission switch
A1-A2Become being connected to via disconnection, indicates that truck headstock passes through A1-A2Not yet reach A3-A4；
Step 2: headstock passes through A1-A2, as infrared emission switch A1-A2When going off again, container body is indicated
Begin through A1-A2, A1-A2State change image acquisition and processing device is transferred to by control device PLC, at Image Acquisition
It manages device and controls C1、C2Start recorded video；
Step 3: truck continues on, work as A3-A4Disconnection and A1-A2Connection, container body pass through A1-A2Into A3-
A4；
Step 4: working as A1-A2And A3-A4It is also turned on, indicates that container and truck pass through infrared detection region, A1-A2
And A3-A4Status signal image acquisition and processing device is transferred to by control device PLC, image recognizing and processing equipment controls C1、
C2Stop recorded video；
Step 5: from C1、C2Start video record to C1、C2Stop video record, forms two sections of complete container bodies
Video, vision signal are stored by interchanger into image acquisition and processing device server；
Step 6: obtaining the video sequence I of acquisition vision signal by the acquisition frame rate (fps) of setting video camera1(x,
y),I2(x,y),…,In(x,y)；
Step 7: calculating video sequence I1(x,y),I2(x,y),…,InThe texture feature vector of (x, y)
V=[f1,f2,f3]
Wherein
f1For second-order matrix feature, f2For entropy feature, f3For local stationary feature；
Step 8: extracting key frame, i is the key frame chosen in setting video sequence, is needed under video sequence one
A key frame j chooses, the similarity relation calculating formula of two width container digital pictures are as follows:
Wherein, i, j are the sequence code name of frame in video, and T is that the threshold value of measurement similar situation is in key frame extraction
Raising picture quality, first frame, last frame are key frame；
Step 9: the fusion of key frame, is merged, it is assumed that f using image of the weighted mean method to key frame1,f2It is two
Image to be spliced, by image f1And f2In space overlapping, then fused image pixel f is represented by f (x, y)
Wherein, d1,d2Indicate weighted value, and d1+d2=1,0≤d1≤1,0≤d2≤ 1, in overlapping region, d1Become by 1
It is 0, d2Become 1 from 0, is achieved in overlapping region f1To f2Smooth transition；
Step 10: being saved based on container panoramic picture f (x, y) is formed after the splicing of video flowing key frame to Image Acquisition
Processing device server；
Step 11: panoramic picture gray processing is handled, the processing of the gray processing of image recognizing and processing equipment can enhance character and
The contrast of background color filters out color characteristic unrelated with identification in image, convenient for carrying out side to container panoramic picture
Edge detection, using weighted average method, is given to image pixel for the average value I for distributing three color components of different weights
I=(PRR+PGG+PBB)/3
Wherein PR, PG, PBIt is the weighting coefficient of each tri- components of pixel R, G, B respectively, image is after obtaining gray processing
F ' (x, y), take 0.299,0.587,0.114 respectively in embodiment；
Step 12: image recognizing and processing equipment denoising, uses second order to the panoramic picture f ' (x, y) after gray processing
Zero-mean gaussian filter function G (x, y) is denoised
F " (x, y)=f ' (x, y) * G (x, y)
Wherein,For second order zero-mean gaussian filter function, σ is standard deviation, is used to generation
Fuzzy factor in table image-detection process, r are blur radius, and (x, y) is the coordinate of pixel；
Step 13: the partial gradient based on Canny operator calculates
The amplitude g (x, y) and direction θ of partial gradient at image each point (x, y) based on Canny operatorgIt calculates as follows:
θg=arctan (gx/gy)
Wherein
Step 14: the non-maxima suppression based on Canny operator
To obtain the maximum point of gradient strength on gradient direction, to local gradient amplitude g (x, y) and gradient direction θg
Non-maxima suppression is carried out, defining two sub-pix point gradient values at coordinate (x, y) on gradient direction is gt1And gt2, then have:
gt1=g2+tanθg×(g1-g2)
gt2=g4+tanθg×(g3-g4)
In formula: g1、g2、g3And g4Gradient value at pixel respectively；θgFor the gradient direction at coordinate (x, y), in determination
Two sub-pix point gradient value g at coordinate (x, y) on gradient directiont1And gt2Afterwards, compare the gradient value g (x, y) at (x, y)
With gt1、gt2Size, if g (x, y) is maximum, the pixel value f " (x, y) at (x, y) be equal to 1, be otherwise suppressed to 0, that is, have:
To image f " in (x, y) all positions (x, y) repeat the above steps, complete to the non-maximum of image f " (x, y)
Inhibit, so that image f " (x, y) is converted into image GTThe binary edge contour images of (x, y).
Step 15: based on the threshold method Edge Search of Canny operator with connect
In order to guarantee not omit edge pixel information while eliminating noise, to the edge result f " of non-maxima suppression
(x, y) using threshold method Edge Search with connect, given threshold [Th1,Th2], image f " that non-maxima suppression is obtained (x,
Y) gradient value is greater than T inh2Pixel be taken as strong edge pixel, constitute image GT2(x, y), by gradient value in Th1And Th2Between
Pixel is taken as weak edge pixel, constitutes image GT1(x, y) has:
Image GT2(x, y)) it is provided with higher threshold value, therefore image eliminates most of noise while, is also lost perhaps
More correctly edge pixel information, and image GT1(x, y)) setting threshold value it is lower, remain the same of correct edge pixel information
When also contain a large amount of ambient noise Canny operators by the way that searching threshold is low, the complete image G of marginal informationT1(x, y) is repaired
Noise is small but the incomplete image G of marginal informationT2(x, y) is filtered out absolutely to realize while obtaining all Single pixel edges
Most of noise, i.e., to image GT2Every bit in (x, y) has:
In formula: m (x, y) is the set of 8 pixel coordinates in coordinate (x, y) neighborhood, by threshold method Edge Search and side
The image G of edge connectionT2(x, y) is the processing result of testing image f " (x, y).
Step 16: character targets extracted region, carries out connected domain division to image according to marginal information, image is drawn
It is divided into different connected domains；Each connected domain is scanned line by line, the pixel in collecting zone calculates each connection
Mean pixel width w in domainiWith the high H of mean pixeli, finally calculate the depth-width ratio example of connected region, i-th of connected region
The Aspect Ratio in domainAccording to the high width M × N, zoning matching degree e in target area；
(- e, e) is calculated into connected domain as territory, it is final to determine character targets region；
Step 17: Character segmentation, using the character segmentation method based on rank scanning, to positioning 0 ° of direction of image into
Line scans carry out points to character targets and search element, when fullSearched plain region prospect points be more than to
Fixed threshold value TjWhen, tentatively assert that the region is character row region, determine its row bound, 90 ° of column then are carried out to the region and are swept
It retouches,I.e. prospect points in region are more than given threshold value TiWhen, tentatively assert that the region is character zone, really
Fixed its arranges boundary, and in conjunction with ranks boundary, respective symbols are oriented in segmentation；
Step 18: image recognition is finally identified using classifier, is identified using weighted template matching algorithm
Container code characters finally show container distant view photograph and the case number (CN) identified on graphic display terminal；
Step 19: redundancy check and box judge, for C1、C2The panoramic picture of two video cameras shooting, Image Acquisition
Processing software identifies respectively, carries out redundancy check after identifying case number (CN), obtains effective container number, if the case identified
It number is one group of data, then it is 40 feet of long casees or 20 feet of single casees that truck is contained, if identifying 2 groups of case number (CN)s, truck
It is 2 each 20 feet of double casees that vehicle is contained, if A1-A2And A3-A4Simultaneously switch off, then can judge truck it is contained for long case or
Double casees, the comprehensive single case, long case or double case boxes that may determine that the contained container of truck.
The purpose of the present invention is to propose to a kind of container representation acquisition device based on video flowing, a lane only needs
2 video cameras, 2 pairs of infrared emission switches, simplify design scheme, reduce number of devices, reduce construction cost, by taking the photograph
Camera acquires video stream signal when trucks entering lane, and the splicing of image is completed using video flowing key frame splicing, spells
The panoramic picture for picking out container improves the quality of Image Acquisition, has correspondinglyd increase the discrimination of case number (CN).Work as container truck
By when, judge that truck enters lane by the ground induction coil being laid on lane, examined by the infrared facilitys of lane two sides
The advanced positions of container truck are surveyed, triggering video camera shoots container video, when truck after detection zone by stopping
Video record realizes the extraction of container panoramic picture finally by key frame images in video flowing, is realized and is collected by OCR technique
The identification of vanning case number (CN).
Present invention is mainly applied to container yards or customs, harbour container inlet to realize adopting for container representation
Collection has the characteristics that video stream signal acquisition, required number of devices are few, adaptable, acquisition is accurate, at low cost.
Detailed description of the invention
Fig. 1 is a kind of function structure chart of container Intelligent gateway container representation acquisition device based on video flowing；
Fig. 2 is a kind of container representation acquisition device structure chart based on video flowing.
Specific embodiment
The feature and exemplary embodiment of various aspects of the invention is described more fully below.In following detailed description
In, many details are proposed, in order to provide complete understanding of the present invention.But to those skilled in the art
It will be apparent that the present invention can be implemented in the case where not needing some details in these details.Below to implementation
The description of example is used for the purpose of providing by showing example of the invention and better understanding of the invention.The present invention never limits
In any concrete configuration set forth below and algorithm, but cover under the premise of without departing from the spirit of the present invention element,
Any modification, replacement and the improvement of component and algorithm.In the following description, well known structure and technology is not shown, so as to
It avoids causing the present invention unnecessary fuzzy.
Example embodiment is described referring now to ground, example embodiment can be implemented in a variety of forms, and should not be by
It is considered limited to embodiment set forth herein；On the contrary, thesing embodiments are provided so that the present invention more comprehensively and completely, and will
The design of example embodiment is comprehensively communicated to those skilled in the art.
In addition, described feature, structure or characteristic can be incorporated in one or more implementations in any suitable manner
In example.In the following description, many details are provided to provide and fully understand to the embodiment of the present invention.However,
It will be appreciated by persons skilled in the art that technical solution of the present invention can be practiced without one in the specific detail or more
It is more, or can be using other methods, constituent element, material etc..In other cases, be not shown in detail or describe known features,
Material or operation are to avoid major technique intention of the invention is obscured.
As shown in Figs. 1-2, the present invention provides a kind of container representation acquisition device based on video flowing, is arranged in container
On the lane of trucks entering, comprising: truck station acquisition device, control device, image acquisition and processing device and high-definition network
Video camera, wherein
Truck station acquisition device, including being arranged in the ground induction coil of lane initial position, connecting with inductance coil
Vehicle checker and two couples of infrared emission switch A being sequentially arranged along lane direction of advance1-A2And A3-A4, wherein two pairs infrared
To penetrate the distance between switch be greater than container truck headstock length but be less than the length of container truck entirety, lane
The PLC connection that coil passes through vehicle checker and control device is felt, for detecting whether truck enters lane, when truck passes through
When, ground induction coil generates trigger signal and is transferred to vehicle checker, and vehicle checker transfers signals to the PLC of control device, and 2 pairs are infrared right
The PLC connection for penetrating switch and control device, when container truck is without lane, infrared emission switch is in connected state, when
When container truck is by lane, infrared emission switch is first blocked by container to be connected to afterwards, and control device collects infrared signal
Variation, pass through logic judgment realize container truck location information；
Control device, including PLC and the network switch, PLC switch collected collection according to ground induction coil and infrared emission
Vanning truck location information judges that video camera starts to shoot and stopping is shot by control logic, and output phase should shoot or stop
The instruction of shooting is transferred to image acquisition and processing device, sends shooting instruction by image acquisition and processing device and takes the photograph to high-definition network
Camera, control high-definition network camera start or stop shooting vision signal；
Image acquisition and processing device mainly includes image acquisition and processing server, graphic display terminal, image acquisition and processing
Server is connected by the network switch of cable and control device, what image acquisition and processing server receiving control device was sent
It takes pictures control instruction, control video camera shoots vision signal, and by vision signal storage into server, and realizes and be based on video
The pictures subsequent of stream is handled, and graphic display terminal is connect with server by interchanger, for showing image acquisition and processing service
Device treated container complete image and the container number of identification；
High-definition network camera, C1、C2It is arranged symmetrically in the top of lane two sides, and is set to two pairs of infrared emissions and opens
Between pass, for receiving the video capture control instruction of image acquisition and processing device, to the truck vehicle-mounted container by lane
Carry out video capture.
Selectively, in truck station acquisition device, when truck has just enter into lane, the triggering of lane ground induction coil,
Infrared emission switch A1-A2It is gone off by connection, in truck traveling process, since headstock length is much smaller than container case
Body length, so when headstock front does not reach infrared emission switch A3-A4When, i.e. infrared emission switch A3-A4When still in connection
State, infrared emission switch A1-A2Become being connected to via disconnection, indicates that truck headstock passes through A1-A2Not yet reach A3-A4,
After headstock all passes through, as infrared emission switch A1-A2When going off again, indicate that container body begins through A1-A2,
Truck continues on, and works as A3-A4Disconnection and A1-A2Connection, container body pass through A1-A2Into A3-A4, work as A1-A2And A3-A4
It is also turned on, container judges truck by infrared emission switch monitors region, by the state change that infrared emission switchs
Advanced positions information.
Selectively, in image acquisition and processing device, when truck passes through Intelligent gateway lane, truck truck position is triggered
The ground induction coil and infrared emission of acquisition device switch, and control device PLC takes pictures control instruction to figure according to logic judgment transmission
As acquisition processing device, image recognizing and processing equipment controls 2 high-definition network cameras and acquires vision signal respectively, in order to obtain
The panoramic picture of entire container, with the difference of adjacent two interframe of video stream signal, to key frame figure in the video flowing of acquisition
As carrying out feature extraction, registration and splicing, complete container body panoramic picture, image recognizing and processing equipment pair are eventually formed
Image is handled, and is identified container number and is shown case number (CN) and image on graphic display terminal computer.
A kind of container representation acquisition method based on video flowing, comprising:
Step 1: when truck enters lane, the triggering of lane ground induction coil, since headstock stops, infrared emission switch
A1-A2It is gone off by connection, in truck traveling process, since headstock length is less than container body length, so working as vehicle
Head front does not reach infrared emission switch A3-A4When, i.e. infrared emission switch A3-A4Still in connected state, infrared emission switch
A1-A2Become being connected to via disconnection, indicates that truck headstock passes through A1-A2Not yet reach A3-A4；
Step 2: headstock passes through A1-A2, as infrared emission switch A1-A2When going off again, container body is indicated
Begin through A1-A2, A1-A2State change image acquisition and processing device is transferred to by control device PLC, at Image Acquisition
It manages device and controls C1、C2Start recorded video；
Step 3: truck continues on, work as A3-A4Disconnection and A1-A2Connection, container body pass through A1-A2Into A3-
A4；
Step 4: working as A1-A2And A3-A4It is also turned on, indicates that container and truck pass through infrared detection region, A1-A2
And A3-A4Status signal image acquisition and processing device is transferred to by control device PLC, image recognizing and processing equipment controls C1、
C2Stop recorded video；
Step 5: from C1、C2Start video record to C1、C2Stop video record, forms two sections of complete container bodies
Video, vision signal are stored by interchanger into image acquisition and processing device server；
Step 6: obtaining the video sequence I of acquisition vision signal by the acquisition frame rate (fps) of setting video camera1(x,
y),I2(x,y),…,In(x,y)；
Step 7: calculating video sequence I1(x,y),I2(x,y),…,InThe texture feature vector of (x, y)
V=[f1,f2,f3]
Wherein:
f1For second-order matrix feature, f2For entropy feature, f3For local stationary feature；
Step 8: extracting key frame, i is the key frame chosen in setting video sequence, is needed under video sequence one
A key frame j chooses, the similarity relation calculating formula of two width container digital pictures are as follows:
Wherein, i, j are the sequence code name of frame in video, and T is that the threshold value of measurement similar situation is in key frame extraction
Raising picture quality, first frame, last frame are key frame；
Step 9: the fusion of key frame, is merged, it is assumed that f using image of the weighted mean method to key frame1,f2It is two
Image to be spliced, by image f1And f2In space overlapping, then fused image pixel f is represented by f (x, y)
Wherein, d1,d2Indicate weighted value, and d1+d2=1,0≤d1≤1,0≤d2≤ 1, in overlapping region, d1Become by 1
It is 0, d2Become 1 from 0, is achieved in overlapping region f1To f2Smooth transition；
Step 10: being saved based on container panoramic picture f (x, y) is formed after the splicing of video flowing key frame to Image Acquisition
Processing device server；
Step 11: panoramic picture gray processing is handled, the processing of the gray processing of image recognizing and processing equipment can enhance character and
The contrast of background color filters out color characteristic unrelated with identification in image, convenient for carrying out side to container panoramic picture
Edge detection, using weighted average method, is given to image pixel for the average value I for distributing three color components of different weights
I=(PRR+PGG+PBB)/3
Wherein PR, PG, PBIt is the weighting coefficient of each tri- components of pixel R, G, B respectively, image is after obtaining gray processing
F ' (x, y) takes 0.299,0.587,0.114 respectively in embodiment；
Step 12: image recognizing and processing equipment denoising, uses second order to the panoramic picture f ' (x, y) after gray processing
Zero-mean gaussian filter function G (x, y) is denoised
F " (x, y)=f ' (x, y) * G (x, y)
Wherein,For second order zero-mean gaussian filter function, σ is standard deviation, is used to generation
Fuzzy factor in table image-detection process, r are blur radius, and (x, y) is the coordinate of pixel；
Step 13: the partial gradient based on Canny operator calculates
The amplitude g (x, y) and direction θ of partial gradient at image each point (x, y) based on Canny operatorgIt calculates as follows:
θg=arctan (gx/gy)
Wherein
Step 14: the non-maxima suppression based on Canny operator
To obtain the maximum point of gradient strength on gradient direction, to local gradient amplitude g (x, y) and gradient direction θg
Non-maxima suppression is carried out, defining two sub-pix point gradient values at coordinate (x, y) on gradient direction is gt1And gt2, then have:
gt1=g2+tanθg×(g1-g2)
gt2=g4+tanθg×(g3-g4)
In formula: g1、g2、g3And g4Gradient value at pixel respectively；θgFor the gradient direction at coordinate (x, y), in determination
Two sub-pix point gradient value g at coordinate (x, y) on gradient directiont1And gt2
Afterwards, compare gradient value g (x, y) and the g at (x, y)t1、gt2Size, if g (x, y) is maximum, the picture at (x, y)
Element value f " (x, y) is equal to 1, is otherwise suppressed to 0, that is, has:
To image f " in (x, y) all positions (x, y) repeat the above steps, complete to the non-maximum of image f " (x, y)
Inhibit, so that image f " (x, y) is converted into image GTThe binary edge contour images of (x, y).
Step 15: based on the threshold method Edge Search of Canny operator with connect
In order to guarantee not omit edge pixel information while eliminating noise, to the edge result f " of non-maxima suppression
(x, y) using threshold method Edge Search with connect, given threshold [Th1,Th2], image f " that non-maxima suppression is obtained (x,
Y) gradient value is greater than T inh2Pixel be taken as strong edge pixel, constitute image GT2(x, y), by gradient value in Th1And Th2Between
Pixel is taken as weak edge pixel, constitutes image GT1(x, y) has:
Image GT2(x, y)) it is provided with higher threshold value, therefore image eliminates most of noise while, is also lost perhaps
More correctly edge pixel information, and image GT1(x, y)) setting threshold value it is lower, remain the same of correct edge pixel information
When also contain a large amount of ambient noise Canny operators by the way that searching threshold is low, the complete image G of marginal informationT1(x, y) is repaired
Noise is small but the incomplete image G of marginal informationT2(x, y) is filtered out absolutely to realize while obtaining all Single pixel edges
Most of noise, i.e., to image GT2Every bit in (x, y) has:
In formula: m (x, y) is the set of 8 pixel coordinates in coordinate (x, y) neighborhood, by threshold method Edge Search and side
The image G of edge connectionT2(x, y) is the processing result of testing image f " (x, y).
Step 16: character targets extracted region, carries out connected domain division to image according to marginal information, image is drawn
It is divided into different connected domains；Each connected domain is scanned line by line, the pixel in collecting zone calculates each connection
Mean pixel width w in domainiWith the high H of mean pixeli, finally calculate the depth-width ratio example of connected region, i-th of connected region
The Aspect Ratio in domainAccording to the high width M × N, zoning matching degree e in target area；
(- e, e) is calculated into connected domain as territory, it is final to determine character targets region；
Step 17: Character segmentation, using the character segmentation method based on rank scanning, to positioning 0 ° of direction of image into
Line scans carry out points to character targets and search element, when fullSearched plain region prospect points be more than to
Fixed threshold value TjWhen, tentatively assert that the region is character row region, determine its row bound, 90 ° of column then are carried out to the region and are swept
It retouches,I.e. prospect points in region are more than given threshold value TiWhen, tentatively assert that the region is character zone, really
Fixed its arranges boundary, and in conjunction with ranks boundary, respective symbols are oriented in segmentation；
Step 18: image recognition is finally identified using classifier, is identified using weighted template matching algorithm
Container code characters finally show container distant view photograph and the case number (CN) identified on graphic display terminal；
Step 19: redundancy check and box judge, for C1、C2The panoramic picture of two video cameras shooting, Image Acquisition
Processing software identifies respectively, carries out redundancy check after identifying case number (CN), obtains effective container number, if the case identified
It number is one group of data, then it is 40 feet of long casees or 20 feet of single casees that truck is contained, if identifying 2 groups of case number (CN)s, truck
It is 2 each 20 feet of double casees that vehicle is contained, if A1-A2And A3-A4Simultaneously switch off, then can judge truck it is contained for long case or
Double casees, the comprehensive single case, long case or double case boxes that may determine that the contained container of truck.
The purpose of the present invention is to propose to a kind of container representation acquisition device based on video flowing, a lane only needs
2 video cameras, 2 pairs of infrared emission switches, simplify design scheme, reduce number of devices, reduce construction cost, by taking the photograph
Camera acquires video stream signal when trucks entering lane, and the splicing of image is completed using video flowing key frame splicing, spells
The panoramic picture for picking out container improves the quality of Image Acquisition, has correspondinglyd increase the discrimination of case number (CN).Work as container truck
By when, judge that truck enters lane by the ground induction coil being laid on lane, examined by the infrared facilitys of lane two sides
The advanced positions of container truck are surveyed, triggering video camera shoots container video, when truck after detection zone by stopping
Video record realizes the extraction of container panoramic picture finally by key frame images in video flowing, is realized and is collected by OCR technique
The identification of vanning case number (CN).
Present invention is mainly applied to container yards or customs, harbour container inlet to realize adopting for container representation
Collection has the characteristics that video stream signal acquisition, required number of devices are few, adaptable, acquisition is accurate, at low cost.
In the present embodiment, the specifications and models that each component devices use are as follows:
Those skilled in the art will be understood that above-described embodiment is illustrative and not restrictive.In different embodiments
The different technologies feature of middle appearance can be combined, to obtain beneficial effect.Those skilled in the art research specification and
On the basis of claims, the embodiment of other variations of revealed embodiment is will be understood that and realized.In claim
In book, term " comprising " is not precluded from other devices or steps；Indefinite article "one" be not excluded for it is multiple；Term " first ", " the
Two " for indicating title not for any specific sequence of expression.
Claims (4)
1. a kind of container representation acquisition device based on video flowing, is arranged on the lane that container truck passes through, comprising: collection
Truck station acquisition device, control device, image acquisition and processing device and high-definition network camera, wherein
Truck station acquisition device, including being arranged in the ground induction coil of lane initial position, the car test connecting with inductance coil
Device and two couples of infrared emission switch A being sequentially arranged along lane direction of advance1-A2And A3-A4, wherein two pairs of infrared emissions
The distance between switch is greater than the length of the headstock of container truck but is less than the length of container truck entirety, feels line to lane
Circle passes through the PLC connection of vehicle checker and control device, for detecting whether truck enters lane, when truck passes through, and ground
Sense coil generates trigger signal and is transferred to vehicle checker, and vehicle checker transfers signals to the PLC of control device, and 2 pairs of infrared emissions are opened
Pass is connect with the PLC of control device, and when container truck is without lane, infrared emission switch is in connected state, works as packaging
When case truck is by lane, infrared emission switch is first blocked by container to be connected to afterwards, and control device collects the change of infrared signal
Change, container truck location information is realized by logic judgment；
Control device, including PLC and the network switch, PLC switch collected container according to ground induction coil and infrared emission
Truck location information judges that video camera starts to shoot and stopping is shot by control logic, and output phase should shoot or stop shooting
Instruction, be transferred to image acquisition and processing device, shooting instruction sent to high-definition network camera by image acquisition and processing device,
Control high-definition network camera starts or stops shooting vision signal；
Image acquisition and processing device mainly includes image acquisition and processing server, graphic display terminal, image acquisition and processing service
Device is connected by the network switch of cable and control device, and what image acquisition and processing server receiving control device was sent takes pictures
Control instruction, control video camera shoot vision signal, and by vision signal storage into server, and realize based on video flowing
Pictures subsequent processing, graphic display terminal is connect with server by interchanger, for showing at image acquisition and processing server
Container complete image after reason and the container number of identification；
High-definition network camera, C1、C2It is arranged symmetrically in the top of lane two sides, and is set to two pairs of infrared emissions and switchs it
Between, for receiving the video capture control instruction of image acquisition and processing device, to the truck vehicle-mounted container progress by lane
Video capture.
2. image collecting device as described in claim 1, which is characterized in that
In truck station acquisition device, when truck has just enter into lane, the triggering of lane ground induction coil, infrared emission switch A1-
A2It is gone off by connection, in truck traveling process, since headstock length is much smaller than container body length, so working as vehicle
Head front does not reach infrared emission switch A3-A4When, i.e. infrared emission switch A3-A4When still in connected state, infrared emission is opened
Close A1-A2Become being connected to via disconnection, indicates that truck headstock passes through A1-A2Not yet reach A3-A4, after headstock all passes through,
As infrared emission switch A1-A2When going off again, indicate that container body begins through A1-A2, truck continues on,
Work as A3-A4Disconnection and A1-A2Connection, container body pass through A1-A2Into A3-A4, work as A1-A2And A3-A4It is also turned on, container
By infrared emission switch monitors region, truck advanced positions information is judged by the state change that infrared emission switchs.
3. image collecting device as described in claim 1, which is characterized in that
In image acquisition and processing device, when truck passes through Intelligent gateway lane, the ground of truck station acquisition device is triggered
Feel coil and infrared emission switchs, control device PLC sends control instruction of taking pictures according to logic judgment and fills to image acquisition and processing
The image recognizing and processing equipment set, image recognizing and processing equipment control 2 high-definition network cameras and acquire vision signal respectively, are
The panoramic picture of entire container is obtained, with the difference of adjacent two interframe of video stream signal, to closing in the video flowing of acquisition
Key frame image carries out feature extraction, registration and splicing, eventually forms complete container body panoramic picture, image recognition processing
Device handles image, identifies container number and shows case number (CN) and image on graphic display terminal computer.
4. a kind of container representation acquisition method based on video flowing, comprising:
Step 1: when truck enters lane, the triggering of lane ground induction coil, since headstock stops, infrared emission switch A1-A2
It is gone off by connection, in truck traveling process, since headstock length is less than container body length, so before headstock
Portion does not reach infrared emission switch A3-A4When, i.e. infrared emission switch A3-A4Still in connected state, infrared emission switch A1-A2
Become being connected to via disconnection, indicates that truck headstock passes through A1-A2Not yet reach A3-A4；
Step 2: headstock passes through A1-A2, as infrared emission switch A1-A2When going off again, indicate that container body starts to lead to
Cross A1-A2, A1-A2State change image acquisition and processing device, image acquisition and processing device are transferred to by control device PLC
Control C1、C2Start recorded video；
Step 3: truck continues on, work as A3-A4Disconnection and A1-A2Connection, container body pass through A1-A2Into A3-A4；
Step 4: working as A1-A2And A3-A4It is also turned on, indicates that container and truck pass through infrared detection region, A1-A2And A3-
A4Status signal image acquisition and processing device is transferred to by control device PLC, image acquisition and processing device controls C1、C2Stop
Only recorded video；
Step 5: from C1、C2Start video record to C1、C2Stop video record, form two sections of complete container body videos,
Vision signal is stored by interchanger into image acquisition and processing device server；
Step 6: obtaining the video sequence I of acquisition vision signal by the acquisition frame rate (fps) of setting video camera1(x,y),I2
(x,y),…,In(x,y)；
Step 7: calculating video sequence I1(x,y),I2(x,y),…,InThe texture feature vector of (x, y)
V=[f1,f2,f3]
Wherein:
f1For second-order matrix feature, f2For entropy feature, f3For local stationary feature；
Step 8: extracting key frame, i is the key frame chosen in setting video sequence, is needed to the next pass of video sequence
Key frame j chooses, the similarity relation calculating formula of two width container digital pictures are as follows:
Wherein, i, j are the sequence code name of frame in video, and T is the threshold value for measuring similar situation, in key frame extraction, in order to mention
High picture quality, first frame, last frame are key frame；
Step 9: the fusion of key frame, is merged, it is assumed that f using image of the weighted mean method to key frame1,f2It is that two width wait for
The image of splicing, by image f1And f2In space overlapping, then fused image pixel f is represented by f (x, y)
Wherein, d1,d2Indicate weighted value, and d1+d2=1,0≤d1≤1,0≤d2≤ 1, in overlapping region, d1Become 0, d from 12
Become 1 from 0, is achieved in overlapping region f1To f2Smooth transition；
Step 10: being saved based on container panoramic picture f (x, y) is formed after the splicing of video flowing key frame to image acquisition and processing
Device server；
Step 11: panoramic picture gray processing is handled, the gray processing processing of image recognizing and processing equipment can enhance character and background
The contrast of color filters out color characteristic unrelated with identification in image, convenient for carrying out edge inspection to container panoramic picture
It surveys, using weighted average method, the average value I for distributing three color components of different weights is given to image pixel
I=(PRR+PGG+PBB)/3
Wherein PR, PG, PBIt is the weighting coefficient of each tri- components of pixel R, G, B respectively, image is f ' after obtaining gray processing
(x, y) takes 0.299,0.587,0.114 respectively in embodiment；
Step 12: image recognizing and processing equipment denoising, equal using second order zero to the panoramic picture f ' (x, y) after gray processing
Value Gaussian filter function G (x, y) is denoised
F " (x, y)=f ' (x, y) * G (x, y)
Wherein,For second order zero-mean gaussian filter function, σ is standard deviation, for representing figure
As the fuzzy factor in detection process, r is blur radius, and (x, y) is the coordinate of pixel；
Step 13: the partial gradient based on Canny operator calculates
The amplitude g (x, y) and direction θ of partial gradient at image each point (x, y) based on Canny operatorgIt calculates as follows:
θg=arctan (gx/gy)
Wherein
Step 14: the non-maxima suppression based on Canny operator
To obtain the maximum point of gradient strength on gradient direction, to local gradient amplitude g (x, y) and gradient direction θgIt carries out
Non-maxima suppression, defining two sub-pix point gradient values at coordinate (x, y) on gradient direction is gt1And gt2, then have:
gt1=g2+tanθg×(g1-g2)
gt2=g4+tanθg×(g3-g4)
In formula: g1、g2、g3And g4Gradient value at pixel respectively；θgFor the gradient direction at coordinate (x, y), coordinate is being determined
Two sub-pix point gradient value g at (x, y) on gradient directiont1And gt2Afterwards, compare gradient value g (x, y) and the g at (x, y)t1、
gt2Size, if g (x, y) is maximum, the pixel value f " (x, y) at (x, y) be equal to 1, be otherwise suppressed to 0, that is, have:
To image f " in (x, y) all positions (x, y) repeat the above steps, complete to the non-maxima suppression of image f " (x, y),
To which image f " (x, y) is converted into image GTThe binary edge contour images of (x, y).
Step 15: based on the threshold method Edge Search of Canny operator with connect
In order to guarantee not omit edge pixel information while eliminating noise, to the edge result f " (x, y) of non-maxima suppression
Using threshold method Edge Search with connect, given threshold [Th1,Th2], the image f " that non-maxima suppression is obtained is terraced in (x, y)
Angle value is greater than Th2Pixel be taken as strong edge pixel, constitute image GT2(x, y), by gradient value in Th1And Th2Between pixel take
For weak edge pixel, image G is constitutedT1(x, y) has:
Image GT2(x, y)) be provided with higher threshold value, therefore image eliminates most of noise while be also lost it is many just
True edge pixel information, and image GT1(x, y)) setting threshold value it is lower, while remaining correct edge pixel information
A large amount of ambient noise Canny operators are contained by the way that searching threshold is low, the complete image G of marginal informationT1(x, y) repairs noise
The incomplete image G of small but marginal informationT2(x, y) filters out exhausted big portion to realize while obtaining all Single pixel edges
Divide noise, i.e., to image GT2Every bit in (x, y) has:
In formula: m (x, y) is the set of 8 pixel coordinates in coordinate (x, y) neighborhood, is connected by threshold method Edge Search and edge
The image G connectT2(x, y) is the processing result of testing image f " (x, y).
Step 16: character targets extracted region, carries out connected domain division to image according to marginal information, divides an image into not
Same connected domain；Each connected domain is scanned line by line, the pixel in collecting zone calculates in each connected domain
Mean pixel width wiWith the high H of mean pixeli, finally calculate the depth-width ratio example of connected region, the length of i-th of connected region
Wide ratioAccording to the high width M × N, zoning matching degree e in target area；
(- e, e) is calculated into connected domain as territory, it is final to determine character targets region；
Step 17: Character segmentation, using the character segmentation method based on rank scanning, to positioning 0 ° of direction of image into going
Scanning carries out points to character targets and searches element, when fullIt is more than given for being searched plain region prospect points
Threshold value TjWhen, tentatively assert that the region is character row region, determine its row bound, 90 ° of column scans then are carried out to the region,I.e. prospect points in region are more than given threshold value TiWhen, tentatively assert that the region is character zone, determines
It arranges boundary, and in conjunction with ranks boundary, respective symbols are oriented in segmentation；
Step 18: image recognition is finally identified using classifier using weighted template matching algorithm, is identified packaging
Case case number (CN) character finally shows container distant view photograph and the case number (CN) identified on graphic display terminal；
Step 19: redundancy check and box judge, for C1、C2The panoramic picture of two video cameras shooting, image acquisition and processing
Software identifies respectively, carries out redundancy check after identifying case number (CN), obtains effective container number, if the case number (CN) identified is
One group of data, then it is 40 feet of long casees or 20 feet of single casees that truck is contained, if identifying 2 groups of case number (CN)s, truck institute
It carries as 2 each 20 feet of double casees, if A1-A2And A3-A4It simultaneously switches off, then can judge that truck is contained for long case or double casees,
The comprehensive single case, long case or double case boxes that may determine that the contained container of truck.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910740684.1A CN110460813A (en) | 2019-08-12 | 2019-08-12 | A kind of container representation acquisition device and acquisition method based on video flowing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910740684.1A CN110460813A (en) | 2019-08-12 | 2019-08-12 | A kind of container representation acquisition device and acquisition method based on video flowing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110460813A true CN110460813A (en) | 2019-11-15 |
Family
ID=68485969
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910740684.1A Pending CN110460813A (en) | 2019-08-12 | 2019-08-12 | A kind of container representation acquisition device and acquisition method based on video flowing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110460813A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110942461A (en) * | 2019-12-20 | 2020-03-31 | 上海撬动网络科技有限公司 | Intelligent testing and viewing system for fixed-scene container |
| CN112102215A (en) * | 2020-09-03 | 2020-12-18 | 广州南沙联合集装箱码头有限公司 | Image fast splicing method based on error statistics |
| CN114157808A (en) * | 2021-12-13 | 2022-03-08 | 北京国泰星云科技有限公司 | Efficient container gate image acquisition system and method |
| CN114339159A (en) * | 2021-12-31 | 2022-04-12 | 深圳市平方科技股份有限公司 | Image acquisition method and device, electronic equipment and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101556692A (en) * | 2008-04-09 | 2009-10-14 | 西安盛泽电子有限公司 | Image mosaic method based on neighborhood Zernike pseudo-matrix of characteristic points |
| CN102426649A (en) * | 2011-10-13 | 2012-04-25 | 石家庄开发区冀科双实科技有限公司 | Simple steel seal digital automatic identification method with high accuracy rate |
| CN104376322A (en) * | 2014-12-01 | 2015-02-25 | 上海海事大学 | Intelligent detecting and evaluating method for container number preprocessing quality of containers |
| CN105469055A (en) * | 2015-11-26 | 2016-04-06 | 上海斐讯数据通信技术有限公司 | Cloud computing-based license plate recognition system and method |
| CN106372641A (en) * | 2016-08-30 | 2017-02-01 | 北京华力兴科技发展有限责任公司 | Container number identification method and device for carrying vehicle and carrying vehicle |
| CN107038683A (en) * | 2017-03-27 | 2017-08-11 | 中国科学院自动化研究所 | The method for panoramic imaging of moving target |
| CN107452007A (en) * | 2017-07-05 | 2017-12-08 | 国网河南省电力公司 | A kind of visible ray insulator method for detecting image edge |
-
2019
- 2019-08-12 CN CN201910740684.1A patent/CN110460813A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101556692A (en) * | 2008-04-09 | 2009-10-14 | 西安盛泽电子有限公司 | Image mosaic method based on neighborhood Zernike pseudo-matrix of characteristic points |
| CN102426649A (en) * | 2011-10-13 | 2012-04-25 | 石家庄开发区冀科双实科技有限公司 | Simple steel seal digital automatic identification method with high accuracy rate |
| CN104376322A (en) * | 2014-12-01 | 2015-02-25 | 上海海事大学 | Intelligent detecting and evaluating method for container number preprocessing quality of containers |
| CN105469055A (en) * | 2015-11-26 | 2016-04-06 | 上海斐讯数据通信技术有限公司 | Cloud computing-based license plate recognition system and method |
| CN106372641A (en) * | 2016-08-30 | 2017-02-01 | 北京华力兴科技发展有限责任公司 | Container number identification method and device for carrying vehicle and carrying vehicle |
| CN107038683A (en) * | 2017-03-27 | 2017-08-11 | 中国科学院自动化研究所 | The method for panoramic imaging of moving target |
| CN107452007A (en) * | 2017-07-05 | 2017-12-08 | 国网河南省电力公司 | A kind of visible ray insulator method for detecting image edge |
Non-Patent Citations (2)
| Title |
|---|
| 高延鹏，李小平，张晓康，孙艳春: "铁路货场智能大门集装箱全景图像采集方法研究", 《物流科技》 * |
| 高延鹏: "基于全景图像的铁路集装箱货场智能大门研究与设计", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110942461A (en) * | 2019-12-20 | 2020-03-31 | 上海撬动网络科技有限公司 | Intelligent testing and viewing system for fixed-scene container |
| CN112102215A (en) * | 2020-09-03 | 2020-12-18 | 广州南沙联合集装箱码头有限公司 | Image fast splicing method based on error statistics |
| CN114157808A (en) * | 2021-12-13 | 2022-03-08 | 北京国泰星云科技有限公司 | Efficient container gate image acquisition system and method |
| CN114157808B (en) * | 2021-12-13 | 2022-11-29 | 北京国泰星云科技有限公司 | Efficient container gate image acquisition system and method |
| CN114339159A (en) * | 2021-12-31 | 2022-04-12 | 深圳市平方科技股份有限公司 | Image acquisition method and device, electronic equipment and storage medium |
| CN114339159B (en) * | 2021-12-31 | 2023-06-27 | 深圳市平方科技股份有限公司 | Image acquisition method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110460813A (en) | A kind of container representation acquisition device and acquisition method based on video flowing | |
| CN109460709B (en) | RTG visual barrier detection method based on RGB and D information fusion | |
| CN102722704B (en) | Method and system for recognizing vehicle license plate by integrating video dynamic tracking | |
| Kong et al. | Detecting abandoned objects with a moving camera | |
| CN103425967B (en) | A kind of based on stream of people's monitoring method of pedestrian detection and tracking | |
| CN101673396B (en) | Image fusion method based on dynamic object detection | |
| CN107305627A (en) | A kind of automobile video frequency monitoring method, server and system | |
| CN109446917B (en) | Vanishing point detection method based on cascading Hough transform | |
| CN104951775A (en) | Video technology based secure and smart recognition method for railway crossing protection zone | |
| CN105702048A (en) | Automobile-data-recorder-based illegal lane occupation identification system and method for automobile on highway | |
| CN106548451A (en) | A kind of car passenger flow crowding computational methods and device | |
| CN108320575A (en) | A kind of guiding of parking stall and reverse vehicle searching system and its parking space-detecting device, method | |
| CN101123039A (en) | Red light overriding detection system and method based on digital video camera | |
| CN101937614A (en) | Plug and play comprehensive traffic detection system | |
| CN105976392B (en) | Vehicle tyre detection method and device based on maximum output probability | |
| CN106815583A (en) | A kind of vehicle at night license plate locating method being combined based on MSER and SWT | |
| CN107122740A (en) | A kind of vehicle type recognition device and method based on twin camera | |
| CN107038683A (en) | The method for panoramic imaging of moving target | |
| CN104506800A (en) | Scene synthesis and comprehensive monitoring method and device for electronic police cameras in multiple directions | |
| CN106780886A (en) | A kind of vehicle identification system and vehicle are marched into the arena, appearance recognition methods | |
| CN110008771B (en) | Code scanning system and code scanning method | |
| CN114049612A (en) | Highway vehicle charge auditing system based on graph searching technology and dual-obtaining and checking method for driving path | |
| CN109523583A (en) | A kind of power equipment based on feedback mechanism is infrared and visible light image registration method | |
| Li et al. | Panoramic image mosaic technology based on sift algorithm in power monitoring | |
| CN107729814A (en) | A kind of method and device for detecting lane line |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191115 |