CN107563371A - The method of News Search area-of-interest based on line laser striation - Google Patents
The method of News Search area-of-interest based on line laser striation Download PDFInfo
- Publication number
- CN107563371A CN107563371A CN201710573668.9A CN201710573668A CN107563371A CN 107563371 A CN107563371 A CN 107563371A CN 201710573668 A CN201710573668 A CN 201710573668A CN 107563371 A CN107563371 A CN 107563371A
- Authority
- CN
- China
- Prior art keywords
- mrow
- striation
- image
- msub
- interest
- 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
Abstract
The method of News Search area-of-interest of the invention based on line laser striation belongs to computer vision measurement technical field, is related to a kind of method of the News Search area-of-interest based on line laser striation.This method predicts the area-of-interest of striation using the quick method for calculating striation kinematic parameter of packet, one group of time series laser striation scan image is shot first, using the area-of-interest of polygon extraction testee, the area-of-interest of the first striation of rectangular extraction is used.It is then based on laser corner to be grouped all images, mixing difference image is detected using transverse edge, the inter-pixel speed of striation in every group of image is quickly calculated, according to striation area-of-interest in inter-pixel speed Dynamic Extraction image.This method can accurately define the uniform motion scope of line laser striation by being grouped to sequence image, adapt to the situation of striation variable motion, improve the computational efficiency of striation kinematic parameter.Method has high efficiency, high reliability.
Description
Technical field
The invention belongs to computer vision measurement technical field, and it is emerging to be related to a kind of News Search sense based on line laser striation
The method in interesting region.
Background technology
Image characteristics extraction can be analyzed to three parts in a usual computer vision measurement system：Target detection, search
Cable system area-of-interest (ROI)；Image is split, and target is separated from background；Target's feature-extraction.Target detection is as image
The premise of feature extraction, its search quality directly affect successive image processing.For the continuous fortune in plenty of time sequence chart picture
Moving-target, quick and precisely ROI is the key for improving image characteristics extraction quality and efficiency.
Existing object detection method mainly has powerful connections split plot design, adjacent frame differential method, optical flow method and wavelet method etc..The back of the body
Scape split plot design with the characteristic parameter of image sequence compared with background model, is partitioned into background and target by establishing background model,
So as to obtain moving target, but because no high performance rule defines target, the method be only applicable to moving scene fix and
Fairly simple occasion.Adjacent frame differential method is to carry out adjacent two field pictures to seek difference operation, by difference absolute value come
Determine whether to move, the method is applied to the images of multiple moving targets be present, but easily by noise jamming, robustness compared with
Difference.Optical flow method changes over time situation to infer the translational speed of object and direction by the gray value of detection image pixel,
It is not suitable for low frame rate camera or high-speed moving object.Wavelet method is to carry out wavelet transformation to image, is then filtered using band logical
The methods of ripple, handles Wavelet image, obtains target area, and its advantage is can be with the weak target under detection of complex scene, but imitates
Rate and reliability are poor.Feng L,Po L M,X u X,et al.Dynamic ROI based on K-means for
remote photoplethy smography[C].ICASSP,2015:It is proposed that one kind is gathered based on K-means in 1310-1314
The dynamic ROI methods of class algorithm, ROI and piecemeal is fixed to image characteristic region first, calculates the cross-correlation of block image
Two characteristic parameters such as coefficient and signal to noise ratio, it is then based on the two characteristic parameters and is clustered using K-means algorithms, last basis
Once dynamic ROI, measurement experiment result show that dynamic ROI methods can effectively extract target to every two seconds of cluster result, improve
Target signal qualities.Remote et al. the patents of invention number of Zhao Zhi be CN201710156308.9 " a kind of car flow information monitoring device
Method to set up and system " is gradually merged based on the proximity relations between each initial area-of-interest, and it is emerging to obtain new sense
Interesting unit, calculate the quantity of monitoring device needed for information of vehicles monitoring, this method by reducing the fine degree of area-of-interest,
To reduce the demand of monitoring device so that the ability covered to the information of vehicles between area-of-interest is maximum.
The content of the invention
The invention solves technical barrier be for more than noise and a large amount of line laser striation figures complicated, that target area is small
There is the problems such as extraction efficiency is low, serious forgiveness is low, poor robustness in picture, traditional area-of-interest exacting method, invented a kind of base
In the method for the News Search area-of-interest of line laser striation.This method is carried out for one group of vertical line laser striation of shooting
The time-series image of transverse movement, polygon ROI methods extraction testee region is primarily based on, based on rectangle ROI methods
The striation of initial pictures is extracted, then image uniform packet is ensured with group image striation interframe constant airspeed, to mixing difference
Image transverse edge convolution, it is quick to calculate each group striation movement velocity, finally based on striation motion ginseng in testee region
Number prediction striation position, enters Mobile state region of interesting extraction.This method is adapted to line laser by being grouped to sequence image
The situation of variable-speed scanning, improve the correctness and robustness of striation extracted region；After quick analysis transverse edge convolution
Difference image, drastically increase the computational efficiency and reliability of striation kinematic parameter, ensure that the efficiency of method.
The technical solution adopted by the present invention is a kind of method of the News Search area-of-interest based on line laser striation, its
It is characterized in, this method predicts the area-of-interest of striation using the quick method for calculating striation kinematic parameter of packet；Shoot first
One group of time series laser striation scan image, the area-of-interest of testee is extracted using polygon, uses rectangular extraction
The area-of-interest of first striation；It is then based on laser corner to be grouped all images, to mixing difference image using laterally
Rim detection, quickly calculate the inter-pixel speed of striation in every group of image；Finally according to inter-pixel speed Dynamic Extraction figure
The striation area-of-interest as in；Method comprises the following steps that：
First step overall situation polygon ROI and striation Initial R OI
The vision measurement system based on line laser striation is built, the laser line generator 2 on turntable passes through rotary motion
Transversal scanning testee 1, line laser bar is vertically projected on testee 1, laser is as turntable is with ω angular speed
Rotate, the laser striation on testee is moved to the position of last striation 4, striation motion from the position of first striation 3
Speed is v, and the corner of laser is θ in respective process, and shoots one group of time-series image by video camera；
For the time-series image, the quantity of image is N, and every image size is U × V, remembers in this group of image i-th
Image is G (i), i=1,2 ..., N；Two images of head and the tail are done sums average, calculated by formula (1), obtain comprising background and
The image G of head and the tail striationr；
Determine GrThe edge of middle testee, using the polygon coarse extraction edge, obtain polygon area-of-interest, note
For ROI_poly；Coarse extraction GrThe square boundary of initial and end striation on middle testee, ignore the vertical length of rectangle in the picture
Degree and abscissa, obtain the lateral coordinates u of two rectangle upper left angle points1And u2, the lateral length width of rectangle in the picture1With
width2；The Initial R OI region RECV of striation are calculated according to formula (2), i.e., the left margin of first striation is u1, width w=
max(width1,width2)；
RECV={ u1,max(width1,width2)} (2)
Second step is based on packet diagram picture and calculates line laser striation kinematic parameter
Assuming that striation uniform motion in the range of small angle tower, is equally divided into θ groups, jth group includes by N width time-series images
Image is G (j, 1), G (j, 2) ..., G (j, nj), j=1,2 ..., θ.Wherein, njFor the amount of images in jth group and
θ ° is the laser line generator total angle of rotation and θ takes positive integer；
For jth group image, according to formula (3) to the 1st width and n-thjWidth image asks poor, obtains only comprising two striations
Mix difference image Gj；
Gj=abs (G (j, nj)-G(j,1)) (3)
According to formula (4) to image GjConvolution, calculate GjTransverse gradients image Gjx；
Obtain GjxIn 0.4V, 0.45V, 0.5V, 0.55V, 0.6V row grey scale pixel value, be designated as Gjx(k, l), wherein,
L=1,2 ..., U, k ∈ K, K={ 0.4V, 0.45V, 0.5V, 0.55V, 0.6V }；K takes five different values in K, using l as horizontal seat
Mark, Gjx(k, l) is that ordinate draws five histograms, according to k value, is designated as row k histogram；Search row k histogram
In average abscissa corresponding to two crest clustersWithPicture between jth group image striation consecutive frame is calculated according to formula (5)
Plain speed vj；
3rd step striation dynamic ROI
According to the result of the first step, it is known that the ROI left margins of the first width image striation are u in first group11=u1, width w,
Right margin u11+w；The ROI left margins u of pth width striation in jth group is calculated according to formula (6)jp, then right margin is ujp+w；
The polygon area-of-interest of pth width image in jth group is extracted according to ROI_poly, makes all pictures in other regions
The gray value of element is 0；Optical strip image dynamic ROI parameters are calculated, area-of-interest elects rectangle as, and four angle points are (ujp,0)、
(ujp+w,0)、(ujp+ w, V) and (ujp,V)；Region of interest using the rectangle that this four angle points are formed as jth group pth width image
Domain.It is hereby achieved that in all N width images striation area-of-interest.
The beneficial effects of the invention are as follows this method by being grouped to sequence image, the even of line laser striation can be accurately defined
Fast range of movement, the situation of striation variable motion is adapted to, improve the serious forgiveness and reliability of striation extracting method；It is poor in tradition
On the basis of point-score thought, increase motion prediction information, using the difference image after quick analysis transverse edge convolution, improve
The computational efficiency and reliability of striation kinematic parameter, the efficiency of region of interesting extraction is improved, improves striation extracted region
Correctness and robustness.
Brief description of the drawings
Fig. 1 is the vision measurement system schematic diagram based on vertical line laser striation.In figure, 1 is testee, and 2 be that line swashs
Light device, 3 be first striation, and 4 be last striation, and ω is laser rotational angular velocity, and θ is laser corner, and v is measured object
The movement velocity of striation on body.
Fig. 2 is the flow chart of the dynamic ROI methods based on line laser striation.
Embodiment
Describe the embodiment of the present invention in detail below in conjunction with technical scheme and accompanying drawing.
In the present embodiment, the surface of testee 1 is 2.5m × 3.0m t800 composite panels, by wavelength 460nm royal purple
Laser line generator is arranged on turntable, and laser is vertically projected on testee 1, and laser is laterally swept by rotary motion
Retouch.Laser 2 is rotated with ω angular speed with turntable, and the laser striation on testee 1 moves from the position of first striation 3
To the position of a last striation 4, striation movement velocity is v, and the corner of laser is θ in respective process, and is clapped by video camera
One group of time-series image is taken the photograph, as shown in Figure 1.
The present invention is using the video camera shooting optical strip image for configuring wide-angle lens.Video camera model view works VC-
The video cameras of 12MC-M/C 65, resolution ratio：4096 × 3072, imaging sensor：CMOS, frame per second：Silent frame, highest 64.3fps,
Weight：420g.Wide-angle lens model EF 16-35mm f/2.8L II USM, parameter is as follows, lens focus：F=16-
35mm, APS focal length：25.5-52.5 aperture：F2.8, Lens：82×106.Shooting condition is as follows：Picture pixels are 4096
× 3072, lens focus 25mm, object distance 750mm, visual field are about 850mm × 450mm.
Accompanying drawing 2 is the flow chart of the dynamic ROI methods based on line laser striation.According to the operating process, whole target inspection
Survey process is divided into global polygon ROI and striation Initial R OI, calculates line laser striation kinematic parameter, light based on packet diagram picture
Three steps such as bar dynamic ROI.
First step overall situation polygon ROI and striation Initial R OI
The vision measurement system based on line laser striation is built first, as shown in figure 1, shooting one group of time sequence by video camera
Row image.Wherein, the background of all images is constant, and the laser striation in every image crosses the up-and-down boundary of measured object, arbitrarily
The shooting time difference of adjacent two images is steady state value.
The one group of composite laser optical strip image obtained for above-mentioned shooting, amount of images 200, every image size
4096×3072.Remember in this group of image that i-th image is G (i), wherein i=1,2 ..., 200.Calculated and included according to formula (1)
The image G of background and head and the tail striationr.Use polygon ROI manual extractions GrIn multiple material plate tested region, save as ROI_
poly.Use rectangle ROI manual extractions GrThe rectangular area of middle two striations of head and the tail, obtain the upper left angle point u of striation11=u1,
Obtain lateral length width of two rectangular areas in image1And width2, take transverse width w of the higher value as dynamic ROI
=max (width1,width2)。
Second step is based on packet diagram picture and calculates line laser striation kinematic parameter
It is known when shooting above-mentioned 200 time-series images, laser line generator corner be 20 °.These images are divided into 20
Group, it is G (j, 1), G (j, 2) ..., G (j, 10), j=1 that note jth group, which includes image, 2 ..., 20.
For jth group image, according to the transverse gradients image G of head and the tail difference image in formula (3) and (4) calculating groupjx.With
GjxThe gray value of 4096 pixels is ordinate, each pixel in G in 1536th rowjxMiddle lateral coordinates l numerical value is as horizontal seat
Mark (l=1,2 ..., 4096), draw histogram.Wherein, as shown in figure 1, histogram includes four crests, jth group head and the tail are represented
Two striations are in the position of the 1536th row both bounded sides, as crest cluster, to calculate each crest apart from two close crests
The average value of two crest abscissas in clusterWithThe histogram of row k is drawn according to the above method, searches row k
Average abscissa corresponding to two crest clusters in histogramWithWherein k ∈ K, K=1229,1382,1536,1690,
1843}.Pixel speed v between jth group image striation consecutive frame is calculated according to formula (5)j.V is calculated according to the above method1,
v2,…,v10。
3rd step striation dynamic ROI
The ROI left margins of the first width image striation are u in known first group11=u1, width w.Calculated according to formula (6)
The ROI left margins of pth width striation are u in jth groupjp, then right margin is ujp+w。
The polygon area-of-interest of pth width image in jth group is extracted according to ROI_poly, makes all pictures in other regions
The gray value of element is 0.Optical strip image dynamic ROI parameters are calculated, area-of-interest elects rectangle as, and four angle points are (ujp,0)、
(ujp+w,0)、(ujp+ w, 3072) and (ujp,3072)；Sense using the rectangle that this four angle points are formed as jth group pth width image
Interest region.It is hereby achieved that in all images striation area-of-interest.
The present invention a large amount of line laser optical strip images more and complicated, that target area is small, traditional area-of-interest for noise
Extracting method can not find out target region to quick, high accuracy.Based on vertical line laser striation is shot laterally sweep
One group of image of testee is retouched, the light of testee region and initial pictures is extracted using polygon ROI and rectangle ROI methods
Bar, then image is grouped and quickly calculates each group striation movement velocity, is finally moved in testee region based on striation
Parameter prediction striation position, enters Mobile state region of interesting extraction.The present invention is adapted to the situation of line laser variable-speed scanning, carries
The high computational efficiency of striation kinematic parameter, has the characteristics that high serious forgiveness, high efficiency, high reliability.
Claims (1)
1. a kind of method of the News Search area-of-interest based on line laser striation, it is characterized in that, this method is fast using packet
Speed calculates the area-of-interest of the method prediction striation of striation kinematic parameter；One group of time series laser striation scanning is shot first
Image, the area-of-interest of testee is extracted using polygon, uses the area-of-interest of the first striation of rectangular extraction；Then
All images are grouped based on laser corner, mixing difference image is detected using transverse edge, quickly calculates every group of image
The inter-pixel speed of middle striation；Finally according to striation area-of-interest in inter-pixel speed Dynamic Extraction image；Method has
Body step is as follows：
First step overall situation polygon ROI and striation Initial R OI
The vision measurement system based on line laser striation is built, the laser line generator (2) on turntable is horizontal by rotary motion
To scanning testee (1), line laser bar is vertically projected on testee (1), laser is as turntable is with ω angle speed
Degree rotates, and the laser striation on testee is moved to the position of last striation (4), light from the position of first striation (3)
Bar movement velocity is v, and the corner of laser is θ in respective process, and shoots one group of time-series image by video camera；
For the time-series image, the quantity of image is N, and every image size is U × V, remembers i-th image in this group of image
For G (i), wherein i=1,2 ..., N；Two images of head and the tail are done sums average, as shown in formula (1), obtain comprising background with
The image G of head and the tail striationr；
<mrow>
<msub>
<mi>G</mi>
<mi>r</mi>
</msub>
<mo>=</mo>
<mfrac>
<mrow>
<mi>G</mi>
<mrow>
<mo>(</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
<mo>+</mo>
<mi>G</mi>
<mrow>
<mo>(</mo>
<mi>N</mi>
<mo>)</mo>
</mrow>
</mrow>
<mn>2</mn>
</mfrac>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
</mrow>
Determine GrThe edge of middle testee, using the polygon coarse extraction edge, polygon area-of-interest is obtained, is designated as
ROI_poly；Coarse extraction GrThe square boundary of initial and end striation on middle testee, ignore the vertical extension of rectangle in the picture
And abscissa, obtain the lateral coordinates u of two rectangle upper left angle points1And u2, the lateral length width of rectangle in the picture1With
width2；The Initial R OI region RECV of striation are calculated according to formula (2), i.e., the left margin of first striation is u1, width w=
max(width1,width2)；
RECV={ u1,max(width1,width2)} (2)
Second step is based on packet diagram picture and calculates line laser striation kinematic parameter
Assuming that striation uniform motion in the range of small angle tower, is equally divided into θ groups, jth group includes image by N width time-series images
For G (j, 1), G (j, 2) ..., G (j, nj), j=1,2 ..., θ；Wherein, njFor the amount of images in jth group and
θ ° is the laser line generator total angle of rotation and θ takes positive integer；
For jth group image, according to formula (3) to the 1st width and n-thjWidth image asks poor, obtains only including the mixing of two striations
Difference image Gj；
Gj=abs (G (j, nj)-G(j,1)) (3)
According to formula (4) to image GjConvolution, calculate GjTransverse gradients image Gjx；
<mrow>
<msub>
<mi>G</mi>
<mrow>
<mi>j</mi>
<mi>x</mi>
</mrow>
</msub>
<mo>=</mo>
<mfenced open = "[" close = "]">
<mtable>
<mtr>
<mtd>
<mrow>
<mo>-</mo>
<mn>1</mn>
</mrow>
</mtd>
<mtd>
<mn>0</mn>
</mtd>
<mtd>
<mn>1</mn>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mo>-</mo>
<mn>2</mn>
</mrow>
</mtd>
<mtd>
<mn>0</mn>
</mtd>
<mtd>
<mn>2</mn>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mo>-</mo>
<mn>1</mn>
</mrow>
</mtd>
<mtd>
<mn>0</mn>
</mtd>
<mtd>
<mn>1</mn>
</mtd>
</mtr>
</mtable>
</mfenced>
<mo>*</mo>
<msub>
<mi>G</mi>
<mi>j</mi>
</msub>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>4</mn>
<mo>)</mo>
</mrow>
</mrow>
Obtain GjxIn 0.4V, 0.45V, 0.5V, 0.55V, 0.6V row grey scale pixel value, be designated as Gjx(k, l), wherein, l=1,
2 ..., U, k ∈ K, K={ 0.4V, 0.45V, 0.5V, 0.55V, 0.6V }；K takes five different values in K, using l as abscissa, Gjx
(k, l) is that ordinate draws five histograms, according to k value, is designated as row k histogram；Two are searched in row k histogram
Average abscissa corresponding to crest clusterWithPixel speed between jth group image striation consecutive frame is calculated according to formula (5)
vj；
<mrow>
<msub>
<mi>v</mi>
<mi>j</mi>
</msub>
<mo>=</mo>
<mfrac>
<mrow>
<munder>
<mo>&Sigma;</mo>
<mrow>
<mi>k</mi>
<mo>&Element;</mo>
<mi>K</mi>
</mrow>
</munder>
<mrow>
<mo>(</mo>
<msub>
<mover>
<mi>x</mi>
<mo>&OverBar;</mo>
</mover>
<mrow>
<mi>k</mi>
<mo>,</mo>
<mn>2</mn>
</mrow>
</msub>
<mo>-</mo>
<msub>
<mover>
<mi>x</mi>
<mo>&OverBar;</mo>
</mover>
<mrow>
<mi>k</mi>
<mo>,</mo>
<mn>1</mn>
</mrow>
</msub>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<mn>5</mn>
<mrow>
<mo>(</mo>
<msub>
<mi>n</mi>
<mi>j</mi>
</msub>
<mo>-</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
</mrow>
</mfrac>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>5</mn>
<mo>)</mo>
</mrow>
</mrow>
3rd step striation dynamic ROI
According to the result of the first step, it is known that the ROI left margins of the first width image striation are u in first group11=u1, width w, the right
Boundary u11+w；The ROI left margins u of pth width striation in jth group is calculated according to formula (6)jp, then right margin is ujp+w；
<mrow>
<msub>
<mi>u</mi>
<mrow>
<mi>j</mi>
<mi>p</mi>
</mrow>
</msub>
<mo>=</mo>
<msub>
<mi>u</mi>
<mn>1</mn>
</msub>
<mo>+</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>s</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mrow>
<mi>j</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
</munderover>
<msub>
<mi>n</mi>
<mi>s</mi>
</msub>
<msub>
<mi>v</mi>
<mi>s</mi>
</msub>
<mo>+</mo>
<mrow>
<mo>(</mo>
<mi>p</mi>
<mo>-</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
<msub>
<mi>v</mi>
<mi>j</mi>
</msub>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>6</mn>
<mo>)</mo>
</mrow>
</mrow>
The polygon area-of-interest of pth width image in jth group is extracted according to ROI_poly, makes all pixels in other regions
Gray value is 0；Optical strip image dynamic ROI parameters are calculated, area-of-interest elects rectangle as, and four angle points are (ujp,0)、(ujp+w,
0)、(ujp+ w, V) and (ujp,V)；Area-of-interest using the rectangle that this four angle points are formed as jth group pth width image；By
This obtains the area-of-interest of striation in all N width images.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710573668.9A CN107563371B (en) | 2017-07-17 | 2017-07-17 | Method for dynamically searching interesting region based on line laser light strip |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710573668.9A CN107563371B (en) | 2017-07-17 | 2017-07-17 | Method for dynamically searching interesting region based on line laser light strip |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107563371A true CN107563371A (en) | 2018-01-09 |
| CN107563371B CN107563371B (en) | 2020-04-07 |
Family
ID=60973611
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710573668.9A Expired - Fee Related CN107563371B (en) | 2017-07-17 | 2017-07-17 | Method for dynamically searching interesting region based on line laser light strip |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107563371B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108550160A (en) * | 2018-04-03 | 2018-09-18 | 大连理工大学 | Non-homogeneous striation characteristic area extracting method based on light intensity template |
| CN110044292A (en) * | 2018-01-16 | 2019-07-23 | 郑州宇通客车股份有限公司 | A kind of method for three-dimensional measurement and system based on line-structured light |
| CN113487749A (en) * | 2021-07-22 | 2021-10-08 | 梅卡曼德（北京）机器人科技有限公司 | 3D point cloud processing method and device based on dynamic picture |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130129205A1 (en) * | 2010-11-24 | 2013-05-23 | Jue Wang | Methods and Apparatus for Dynamic Color Flow Modeling |
| CN103618900A (en) * | 2013-11-21 | 2014-03-05 | 北京工业大学 | Video region-of-interest extraction method based on encoding information |
| CN104930985A (en) * | 2015-06-16 | 2015-09-23 | 大连理工大学 | Binocular vision three-dimensional morphology measurement method based on time and space constraints |
| US20170191932A1 (en) * | 2016-01-06 | 2017-07-06 | Arizona Board Of Regents On Behalf Of Arizona State University | Sub-doppler intermodulated laser-induced-fluorescence spectrometer |
-
2017
- 2017-07-17 CN CN201710573668.9A patent/CN107563371B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130129205A1 (en) * | 2010-11-24 | 2013-05-23 | Jue Wang | Methods and Apparatus for Dynamic Color Flow Modeling |
| CN103618900A (en) * | 2013-11-21 | 2014-03-05 | 北京工业大学 | Video region-of-interest extraction method based on encoding information |
| CN104930985A (en) * | 2015-06-16 | 2015-09-23 | 大连理工大学 | Binocular vision three-dimensional morphology measurement method based on time and space constraints |
| US20170191932A1 (en) * | 2016-01-06 | 2017-07-06 | Arizona Board Of Regents On Behalf Of Arizona State University | Sub-doppler intermodulated laser-induced-fluorescence spectrometer |
Non-Patent Citations (3)
| Title |
|---|
| CHRISTOPHER WARREN等: "Comparison of FRF measurements and mode shapes determined using optically image based, laser, and accelerometer measurements", 《MECHANICAL SYSTEMS AND SIGNAL PROCESSING》 * |
| YANG LIU等: "An improved image acquisition method for measuring hot forgings using machine vision", 《SENSORS AND ACTUATORS A: PHYSICAL》 * |
| 江勇等: "基于LabVIEW的激光加工路径识别算法", 《电子测量技术》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110044292A (en) * | 2018-01-16 | 2019-07-23 | 郑州宇通客车股份有限公司 | A kind of method for three-dimensional measurement and system based on line-structured light |
| CN108550160A (en) * | 2018-04-03 | 2018-09-18 | 大连理工大学 | Non-homogeneous striation characteristic area extracting method based on light intensity template |
| CN108550160B (en) * | 2018-04-03 | 2020-04-07 | 大连理工大学 | Non-uniform light bar characteristic region extraction method based on light intensity template |
| CN113487749A (en) * | 2021-07-22 | 2021-10-08 | 梅卡曼德（北京）机器人科技有限公司 | 3D point cloud processing method and device based on dynamic picture |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107563371B (en) | 2020-04-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105225482B (en) | Vehicle detecting system and method based on binocular stereo vision | |
| Tang et al. | Fast vehicle detection in UAV images | |
| CN104537659B (en) | The automatic calibration method and system of twin camera | |
| CN103698553B (en) | Novel surface flow field velocity-measuring system and speed-measuring method based on infrared photography | |
| US7899211B2 (en) | Object detecting system and object detecting method | |
| CN102006425B (en) | Method for splicing video in real time based on multiple cameras | |
| Carr et al. | Monocular object detection using 3d geometric primitives | |
| CN100583126C (en) | A video foreground extracting method under conditions of view angle variety based on fast image registration | |
| CN107179322A (en) | A kind of bridge bottom crack detection method based on binocular vision | |
| CN103605953A (en) | Vehicle interest target detection method based on sliding window search | |
| CN104933434A (en) | Image matching method combining length between perpendiculars (LBP) feature extraction method and surf feature extraction method | |
| CN106127145A (en) | Pupil diameter and tracking | |
| CN105059190B (en) | The automobile door opening collision warning device and method of view-based access control model | |
| CN107563371A (en) | The method of News Search area-of-interest based on line laser striation | |
| CN108681718A (en) | A kind of accurate detection recognition method of unmanned plane low target | |
| CN108416798B (en) | A kind of vehicle distances estimation method based on light stream | |
| CN109544635B (en) | Camera automatic calibration method based on enumeration heuristic | |
| CN103438834A (en) | Hierarchy-type rapid three-dimensional measuring device and method based on structured light projection | |
| CN101894380A (en) | Method for tracing target object in panoramic video automatically | |
| CN105678791B (en) | One kind being based on the not unique lane detection and tracking method of parameter | |
| CN111738071B (en) | Inverse perspective transformation method based on motion change of monocular camera | |
| CN115761563A (en) | River surface flow velocity calculation method and system based on optical flow measurement and calculation | |
| CN114724094A (en) | System for measuring number of people in gateway vehicle based on three-dimensional image and radar technology | |
| CN102564924B (en) | Automatic scanning method of single-frame image of blood cell | |
| CN104598906B (en) | Vehicle outline detection method and its device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20200407 Termination date: 20210717 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |