CN106934832B - A kind of simple straight line automatic positioning method towards vision line walking - Google Patents
A kind of simple straight line automatic positioning method towards vision line walking Download PDFInfo
- Publication number
- CN106934832B CN106934832B CN201710178728.7A CN201710178728A CN106934832B CN 106934832 B CN106934832 B CN 106934832B CN 201710178728 A CN201710178728 A CN 201710178728A CN 106934832 B CN106934832 B CN 106934832B
- Authority
- CN
- China
- Prior art keywords
- straight line
- cut
- rule
- indicate
- paramd
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a kind of simple straight line automatic positioning method towards vision line walking, belong to the machine vision applications fields such as robot, trolley line walking and unmanned plane cruise, when solving that video is described using linear feature in existing line walking technology, extract all straight line information in image, ignore contacting between frame and frame, to increase the time of straight line positioning, and the result caused has the problem of biggish error.The present invention, by straight line segmentation at two parts, to seek position of form center respectively based on centroid formula and point-slope form straight-line equation, and then obtains slope and the position of straight line in scene bianry image.It is different from traditional cut-off rule and region to immobilize mode, the present invention takes the positioning result identified in conjunction with former frame straight line, cut-off rule equation and region is automatically updated, to achieve the effect that automatic vision positions.
Description
Technical field
A kind of simple straight line automatic positioning method towards vision line walking, it is fast automatic for being carried out to the straight line in video
Positioning, and equivalent straight line equation is extracted, belong to the machine vision applications fields such as robot, trolley line walking and unmanned plane cruise.
Background technique
Linear feature is as middle layer highly important in video descriptor, in characteristic matching, aviation and navigation image analysing computer,
The fields such as machine learning suffer from important researching value.
At present in the technologies in machine vision applications field such as robot, trolley line walking and unmanned plane cruise, mostly use
The straight line for directly extracting a certain frame in video, is commonly used Straight Line Extraction such as Hough transformation (Hough Transform), phase
Algorithm etc. is organized into groups, reuses the position and slope guided robot of extracted straight line, trolley and unmanned plane carry out line walking or cruise.
Algorithm and phase coding sequences algorithm etc. are before the use for Straight Line Extraction such as Hough transformation (Hough Transform)
Need to carry out Canny edge detection toward contact, Canny edge detection operator is that John F.Canny developed in 1986
One multistage edge detection algorithm, effect are preferable.
The specific method of Hough transformation (Hough Transform) algorithm line walking is: using first pretreatment image
Canny operator carries out edge detection, obtains the edge image of binaryzation；It then will be in a space with coordinate space transformations
Curve or straight line with same shape are mapped on a point of another coordinate space and form peak value；Then by threshold value
It is defeated as a result to obtain the linear order that the biggish several peak points of Hough transformation (Hough Transform) response represent for reason
Out；The respective slope of linear order and position are finally obtained, guided robot, trolley and unmanned plane carry out line walking or cruise.
The specific method of phase coding sequences algorithm line walking is: carrying out edge inspection using Canny operator to pretreatment image first
It surveys, obtains the edge image of binaryzation；Then the gradient direction for calculating edge image, carries out phase coding sequences；Then edge is connected
Position is adjacent on image and the identical pixel of phase, obtains a series of linear orders；It is respective tiltedly to finally obtain linear order
Rate and position, guided robot, trolley and unmanned plane carry out line walking or cruise.
Both the above Straight Line Extraction ignores contacting between frame and frame, and is searched based on edge detection and full figure
Rope extracts all possible straight line on a certain frame image, wherein including not only target line, but also including unrelated straight line.And it is right
In line walking technical field, handled object is usually video, certainly exists connection between each frame of video, and ignores frame
Contacting between frame, each frame image of isolated processing, such as both the above algorithm, bring is Time & Space Complexity
Rise the increase with error.
Summary of the invention
The present invention provides a kind of simple straight line automatic positioning method towards vision line walking in view of the above shortcomings, solution
When video being described using linear feature in certainly existing line walking technology, all straight line information in image are extracted, are ignored
Contacting between frame and frame, to increase the time of straight line positioning, and the result caused has the problem of biggish error.
The technical solution adopted by the invention is as follows:
A kind of simple straight line automatic positioning method towards vision line walking, which comprises the following steps:
Step 1: video is obtained, according to the initial position and gradient of the straight line mark of required positioning in video, initialization
The central point P of cut-off rule equationex, slope kexWith parameter paramex, obtain cut-off rule equation；
Step 2: first frame image f is read from videot(x,y)；
Step 3: to first frame image ft(x, y) carries out threshold process, obtains bianry image b (x, y)；
Step 4: in bianry image b (x, y), obtaining with point PexFor the center of circle, RminFor the cut zone C (P of radiusex,
Rmin)；
Step 5: according to cut-off rule equation, cut-off rule is obtained, using cut-off rule by cut zone C (Pex,Rmin) it is divided into C1
And C2Two regions, judge that straight line is identified whether in C1And C2In two regions, if so, thening follow the steps 6, step is otherwise executed
Rapid 2, handle the next frame in video；
Step 6: respectively in C1And C2Inside find out centroid P1And P2, according to centroid P1And P2Calculate the center of equivalent straight line equation
Point Ptmp, slope KDWith parameter paramD, equivalent straight line equation is obtained, wherein when parameter paramD is 0, indicate that equivalent straight line hangs down
Directly in x-axis, and when paramD is 1, indicate that equivalent straight line is not orthogonal to x-axis；
Step 7: judge whether video terminates, if terminated, equivalent straight line is obtained according to equivalent straight line equation, it will be equivalent straight
Time and again positioning result is stored in text file line, otherwise, calculates the midpoint P of equivalent straight line and bianry image b (x, y) intersection pointc,
Update the central point P of cut-off ruleexFor Pc, update the slope k of cut-off ruleexWith parameter paramex, obtain updated cut-off rule side
Journey executes step 2, handles the next frame in video.
Further, in the step 1, the formula of cut-off rule equation is as follows:
Lex(Pex(xex,yex),kex,paramex)=paramex(y-yex)-kex(x-xex)=0；
Wherein, LexIndicate cut-off rule, PexIndicate the central point of cut-off rule, xex,yexRespectively indicate PexCross, ordinate,
X, y respectively indicate the cross, ordinate at any point on cut-off rule, kexIndicate the slope of cut-off rule, paramexIndicating cut-off rule is
It is no perpendicular to x-axis.
Further, in the step 4, cut zone C (Pex,Rmin) radius RminCalculation formula is as follows:
Rmin=min (Wide/2-xex,Wide/2+xex,Height/2-yex,Height/2+yex)；
Wherein, Wide is the width of bianry image b (x, y), and Height is the height of bianry image b (x, y).
Further, in the step 6, centroid P1And P2Calculation formula it is as follows:
Wherein, X and Y is respectively centroid P1And P2Cross, ordinate, xiAnd yjRespectively straight line mark is in C1And C2Interior pixel
Cross, the ordinate of point, N indicate region C1Or C2Interior pixel sum；
The central point P of equivalent straight line equationtmpCalculation formula it is as follows:
Wherein, xtmp、ytmpCentered on point PtmpCross, ordinate, x1、x2Respectively centroid P1And P2Abscissa, y1And y2
For centroid P1And P2Ordinate；
Work as x1=x2, it enables:
ParamD=0, kD=1；
Work as x1≠x2, it enables:
Obtain expression formula of the equivalent straight line in rectangular coordinate system xoy are as follows:
LD(Ptmp(xtmp,ytmp),kD, paramD) and=paramD (y-ytmp)-kD(x-xtmp)=0,
Wherein, LDIndicate equivalent straight line, kDIndicate that equivalent straight line slope, paramD indicate equivalent straight line whether perpendicular to x
Axis.
Further, in the step 7, the slope k of cut-off ruleexWith parameter paramexUpdate it is specific as follows:
Work as paramD=0, enable:
paramex=1, kex=0；
Work as kD=0, it enables:
paramex=0, kex=1；
As paramD ≠ 0 and kD≠ 0, it enables:
In conclusion by adopting the above-described technical solution, the beneficial effects of the present invention are:
One, the present invention more emphasizes frame different from each frame of isolated processing video relative to currently used line walking algorithm
Contacting between frame, 0.99999 or more, Euclidean distance generally in 2 pixels or so, is guaranteeing the COS distance of straight line positioning
Under the premise of algorithm steps refining, there is a higher accuracy；
Two, the present invention has the characteristics that followability segmentation, and followability is mainly reflected in following two:
(1) position for following straight line to identify, automatically updates cut-off rule equation, relative to the changeless side of cut-off rule equation
Formula, to the vision positioning of the straight line mark of any position and inclination angle, accuracy all with higher；
(2) position for following straight line to identify, automatically updates cut zone, during reducing background to straight line marker extraction
Influence, improve accuracy；
Three, the present invention is extremely low to hardware platform requirements, and processing speed is fast, strong real-time.
Detailed description of the invention
Fig. 1 is the overall flow in the present invention；
Fig. 2 is the geometrical analysis figure of straight line positioning in the present invention；
Fig. 3 is the original image of first frame image in the present invention；
Fig. 4 is the binary image of first frame image in the present invention；
Fig. 5 is the effect picture of the progress straight line positioning of first frame image in the present invention；
Fig. 6 is the datagram for the COS distance that time and again straight line positions in the present invention；
Fig. 7 is the datagram for the Euclidean distance that time and again straight line positions in the present invention.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that described herein, specific examples are only used to explain the present invention, not
For limiting the present invention.
A kind of simple straight line automatic positioning method towards vision line walking, in scene bianry image, with centroid formula and
Based on point-slope form straight-line equation, by straight line segmentation at two parts, position of form center is sought respectively, and then obtain the slope of straight line
The position and.It is different from traditional cut-off rule and region to immobilize mode, the present invention takes to be determined in conjunction with what former frame straight line identified
Position is as a result, automatically update cut-off rule equation and cut zone, to achieve the effect that automatic vision positions, to hardware platform requirements
Extremely low, processing speed is very fast.Detailed process is as shown in Figure 1, a kind of simple straight line automatic positioning method towards vision line walking, such as
Lower step:
Step 1: video is obtained, according to the initial position and gradient of the straight line mark of required positioning in video, initialization
The central point P of cut-off rule equationex, slope kexWith parameter paramex, cut-off rule equation is obtained, as shown in Fig. 2, being video image
Rectangular coordinate system XOY is established, polygon EFGH indicates the geometric profile of straight line mark, and ab is cut-off rule；Wherein cut-off rule equation
Formula it is as follows:
Lex(Pex(xex,yex),kex,paramex)=paramex(y-yex)-kex(x-xex)=0；
Wherein, LexIndicate cut-off rule, PexIndicate central point, (xex,yex) respectively indicate PexTransverse and longitudinal coordinate, kexIt indicates to divide
Secant slope, paramexCut-off rule is indicated whether perpendicular to x-axis, x, y respectively indicate the horizontal, vertical of any point on cut-off rule and sit
Mark,.
The initial position P of the straight line mark of required positioning in setting video0(x0,y0) and gradient k0, P0(x0,y0) indicate straight
The position of form center of line mark, k0Indicate the tangent value of straight line mark and video window angle, the initialization of cut-off rule equation parameter is public
Formula is as follows:
Pex=P0；
Work as k0=0, it enables:
paramex=0, kex=1；
Work as k0=∞ is enabled:
paramex=1, kex=0.
Step 2: first frame image f is read from videot(x, y), as shown in Figure 3；
Step 3: to first frame image ft(x, y) carries out threshold process, obtains bianry image b (x, y), as shown in Figure 4；
Step 4: in bianry image b (x, y), obtaining with point PexFor the center of circle, RminFor the cut zone C (P of radiusex,
Rmin)；
Cut zone C (Pex,Rmin) radius RminCalculation formula is as follows:
Rmin=min (Wide/2-xex,Wide/2+xex,Height/2-yex,Height/2+yex)；
Wherein, Wide is the width of bianry image b (x, y), and Height is the height of bianry image b (x, y).
Step 5: according to cut-off rule equation, cut-off rule is obtained, using cut-off rule by cut zone C (Pex,Rmin) it is divided into C1
And C2Two regions, judge that straight line is identified whether in C1And C2In two regions, if so, thening follow the steps 6, step is otherwise executed
Rapid 2, handle the next frame in video；
Step 6: respectively in C1And C2Inside find out centroid P1And P2, according to centroid P1And P2Calculate the center of equivalent straight line equation
Point Ptmp, slope KDWith parameter paramD, equivalent straight line equation is obtained, wherein when parameter paramD is 0, indicate that equivalent straight line hangs down
Directly in x-axis, and when paramD is 1, indicate that equivalent straight line is not orthogonal to x-axis；As shown in Fig. 2, being obtained by equivalent straight line equation
When equivalent straight line mn, parameter paramD are 0, indicate that equivalent straight line perpendicular to x-axis, and when paramD is 1, indicates equivalent straight line not
Perpendicular to x-axis.The effect picture that first frame straight line positions in video is as shown in Figure 5；
Wherein, centroid P1And P2Calculation formula it is as follows:
Wherein, X and Y is respectively centroid P1And P2Cross, ordinate, xiAnd yjRespectively straight line mark is in C1And C2Interior pixel
Cross, the ordinate of point, N indicate region C1Or C2Interior pixel sum；
The central point P of equivalent straight line equationtmpCalculation formula it is as follows:
Wherein, xtmp、ytmpCentered on point PtmpCross, ordinate, x1、x2Respectively centroid P1And P2Abscissa, y1And y2
For centroid P1And P2Ordinate；
Work as x1=x2, it enables:
ParamD=0, kD=1；
Work as x1≠x2, it enables:
Obtain expression formula of the equivalent straight line in rectangular coordinate system XOY are as follows:
LD(Ptmp(xtmp,ytmp),kD, paramD) and=paramD (y-ytmp)-kD(x-xtmp)=0.
Wherein, LDIndicate equivalent straight line, kDIndicate that equivalent straight line slope, paramD indicate equivalent straight line whether perpendicular to x
Axis.
Step 7: judge whether video terminates, if terminated, equivalent straight line is obtained according to equivalent straight line equation, it will be equivalent straight
Time and again positioning result is stored in text file line, otherwise, calculates equivalent straight line LDWith the midpoint of bianry image b (x, y) intersection point
Pc, update the central point P of cut-off ruleexFor Pc, update the slope k of cut-off ruleexWith parameter paramex, obtain updated cut-off rule
Equation executes step 2, handles the next frame in video.
Wherein, the slope slope k of cut-off ruleexWith parameter paramexUpdate it is specific as follows:
Work as paramD=0, enable:
paramnex=1, knex=0；
Work as kD=0, it enables:
paramnex=0, knex=1；
As paramD ≠ 0 and kD≠ 0, it enables:
The straight line mark of this case indicates tracker wire, and equivalent straight line indicates the middle line of tracker wire two edges.Equivalent straight line is time and again
Locating effect is indicated that Fig. 6 indicates that time and again the COS distance of straight line positioning, Fig. 7 indicate time and again the Europe of straight line positioning by Fig. 6 and Fig. 7
Formula distance.COS distance is the cosine value of straight line positioning tilt angle error, shown in Fig. 6, it can be seen that straight line positioning of the present invention
COS distance reached 0.99999 or more；Euclidean distance is the central point of straight line positioning to the distance between centroid, can from Fig. 2
When finding out that working as straight line mark EFGH passes through the turning of image b (x, y) window, centroid q has relative to the central point p of equivalent straight line
Biggish offset, and the frame number that the Euclidean distance that straight line positions in Fig. 7 is greater than 2 pixels is that straight line mark have passed through image window
The turning b (x, y), the Euclidean distance of remaining frame number is in 2 pixels hereinafter, precision is higher.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all in essence of the invention
Made any modifications, equivalent replacements, and improvements etc., should all be included in the protection scope of the present invention within mind and principle.
Claims (3)
1. a kind of simple straight line automatic positioning method towards vision line walking, which comprises the following steps:
Step 1: video is obtained, according to the initial position and gradient of the straight line mark of required positioning in video, initialization segmentation
The central point P of line equationex, slope kexWith parameter paramex, obtain cut-off rule equation；
Step 2: first frame image f is read from videot(x,y)；
Step 3: to first frame image ft(x, y) carries out threshold process, obtains bianry image b (x, y)；
Step 4: in bianry image b (x, y), obtaining with point PexFor the center of circle, RminFor the cut zone C (P of radiusex,Rmin)；
Step 5: according to cut-off rule equation, cut-off rule is obtained, using cut-off rule by cut zone C (Pex,Rmin) it is divided into C1And C2
Two regions, judge that straight line is identified whether in C1And C2In two regions, if so, 6 are thened follow the steps, it is no to then follow the steps 2,
Handle the next frame in video；
Step 6: respectively in C1And C2Inside find out centroid P1And P2, according to centroid P1And P2Calculate the central point of equivalent straight line equation
Ptmp, slope KDWith parameter paramD, equivalent straight line equation is obtained, wherein when parameter paramD is 0, indicate that equivalent straight line is vertical
In x-axis, and when paramD is 1, indicate that equivalent straight line is not orthogonal to x-axis；
Step 7: judging whether video terminates, if terminated, equivalent straight line is obtained according to equivalent straight line equation, equivalent straight line is tired out
Secondary positioning result is stored in text file, otherwise, calculates the midpoint P of equivalent straight line and bianry image b (x, y) intersection pointc, update
The central point P of cut-off ruleexFor Pc, update the slope k of cut-off ruleexWith parameter paramex, updated cut-off rule equation is obtained,
Step 2 is executed, the next frame in video is handled；
In the step 1, the formula of cut-off rule equation is as follows:
Lex(Pex(xex,yex),kex,paramex)=paramex(y-yex)-kex(x-xex)=0；
Wherein, LexIndicate cut-off rule, PexIndicate the central point of cut-off rule, xex,yexRespectively indicate PexCross, ordinate, x, y point
Not Biao Shi on cut-off rule any point cross, ordinate, kexIndicate the slope of cut-off rule, paramexIndicate whether cut-off rule hangs down
Directly in x-axis；
In the step 6, centroid P1And P2Calculation formula it is as follows:
Wherein, X and Y is respectively centroid P1And P2Cross, ordinate, xiAnd yjRespectively straight line mark is in C1And C2Interior pixel
Horizontal, ordinate, N indicate region C1Or C2Interior pixel sum；
The central point P of equivalent straight line equationtmpCalculation formula it is as follows:
Wherein, xtmp、ytmpCentered on point PtmpCross, ordinate, x1、x2Respectively centroid P1And P2Abscissa, y1And y2For shape
Heart P1And P2Ordinate；
Work as x1=x2, it enables:
ParamD=0, kD=1；
Work as x1≠x2, it enables:
ParamD=1,
Obtain expression formula of the equivalent straight line in rectangular coordinate system xoy are as follows:
LD(Ptmp(xtmp,ytmp),kD, paramD) and=paramD (y-ytmp)-kD(x-xtmp)=0,
Wherein, LDIndicate equivalent straight line, kDIndicate that equivalent straight line slope, paramD indicate equivalent straight line whether perpendicular to x-axis.
2. a kind of simple straight line automatic positioning method towards vision line walking according to claim 1, it is characterised in that: institute
It states in step 4, cut zone C (Pex,Rmin) radius RminCalculation formula is as follows:
Rmin=min (Wide/2-xex,Wide/2+xex,Height/2-yex,Height/2+yex)；
Wherein, Wide is the width of bianry image b (x, y), and Height is the height of bianry image b (x, y).
3. a kind of simple straight line automatic positioning method towards vision line walking according to claim 1, which is characterized in that institute
It states in step 7, the slope k of cut-off ruleexWith parameter paramexUpdate it is specific as follows:
Work as paramD=0, enable:
paramex=1, kex=0；
Work as kD=0, it enables:
paramex=0, kex=1；
As paramD ≠ 0 and kD≠ 0, it enables:
paramex=1,
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710178728.7A CN106934832B (en) | 2017-03-23 | 2017-03-23 | A kind of simple straight line automatic positioning method towards vision line walking |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710178728.7A CN106934832B (en) | 2017-03-23 | 2017-03-23 | A kind of simple straight line automatic positioning method towards vision line walking |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106934832A CN106934832A (en) | 2017-07-07 |
| CN106934832B true CN106934832B (en) | 2019-07-09 |
Family
ID=59425135
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710178728.7A Active CN106934832B (en) | 2017-03-23 | 2017-03-23 | A kind of simple straight line automatic positioning method towards vision line walking |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106934832B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113840360A (en) | 2017-08-07 | 2021-12-24 | 杭州青奇科技有限公司 | Bicycle lock communication system and bicycle lock communication method for sharing bicycles |
| CN111208785B (en) * | 2020-04-20 | 2020-07-14 | 浙江欣奕华智能科技有限公司 | Motion control method and device |
| CN113222838A (en) * | 2021-05-07 | 2021-08-06 | 国网山西省电力公司吕梁供电公司 | Unmanned aerial vehicle autonomous line patrol method based on visual positioning |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101470807A (en) * | 2007-12-26 | 2009-07-01 | 河海大学常州校区 | Accurate detection method for highroad lane marker line |
| CN104766337A (en) * | 2015-04-27 | 2015-07-08 | 西北工业大学 | Aircraft landing vision enhancement method based on runway boundary enhancement |
| CN106371453A (en) * | 2016-05-27 | 2017-02-01 | 上海铸天智能科技有限公司 | Visual servo method for use in the automatic line inspection by multi-rotor unmanned plane |
-
2017
- 2017-03-23 CN CN201710178728.7A patent/CN106934832B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101470807A (en) * | 2007-12-26 | 2009-07-01 | 河海大学常州校区 | Accurate detection method for highroad lane marker line |
| CN104766337A (en) * | 2015-04-27 | 2015-07-08 | 西北工业大学 | Aircraft landing vision enhancement method based on runway boundary enhancement |
| CN106371453A (en) * | 2016-05-27 | 2017-02-01 | 上海铸天智能科技有限公司 | Visual servo method for use in the automatic line inspection by multi-rotor unmanned plane |
Non-Patent Citations (2)
| Title |
|---|
| 一种基于Hough 变换的新直线段检测算法;朱娟 等;《微电子学与计算机》;20081231;第25卷(第12期);第60-63页 * |
| 大幅面扫描图纸直线跟踪的矢量化新方法;陈镇龙 等;《电子设计工程》;20131130;第21卷(第21期);第178-180页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106934832A (en) | 2017-07-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6347827B2 (en) | Method, apparatus and device for detecting lane boundaries | |
| CN104197899B (en) | Method for positioning mobile robot and system | |
| CN101216895B (en) | An automatic extracting method for ellipse image features in complex background images | |
| Yuan et al. | Robust lane detection for complicated road environment based on normal map | |
| CN109506658A (en) | Robot autonomous localization method and system | |
| CN108597009B (en) | Method for detecting three-dimensional target based on direction angle information | |
| Yang et al. | Fast and accurate vanishing point detection and its application in inverse perspective mapping of structured road | |
| JP5385105B2 (en) | Image search method and system | |
| CN106934832B (en) | A kind of simple straight line automatic positioning method towards vision line walking | |
| CN110021029B (en) | Real-time dynamic registration method and storage medium suitable for RGBD-SLAM | |
| CN102721364A (en) | Positioning method and positioning device for workpiece | |
| CN107748855B (en) | Detection method for two-dimensional code image finding graph | |
| CN109285163B (en) | Laser point cloud based lane line left and right contour line interactive extraction method | |
| CN103768792B (en) | Partitioning and recognition method applied to wide-range video space object positioning system | |
| CN111680699B (en) | Air-ground infrared time-sensitive weak small target detection method based on background suppression | |
| Sehgal et al. | Real-time scale invariant 3D range point cloud registration | |
| CN111598952A (en) | Multi-scale cooperative target design and online detection and identification method and system | |
| CN113393524A (en) | Target pose estimation method combining deep learning and contour point cloud reconstruction | |
| CN107463939B (en) | Image key straight line detection method | |
| CN107895166B (en) | Method for realizing target robust recognition based on feature descriptor by geometric hash method | |
| CN111160280A (en) | RGBD camera-based target object identification and positioning method and mobile robot | |
| CN104992431A (en) | Method and device for multispectral image registration | |
| CN110675442A (en) | Local stereo matching method and system combined with target identification technology | |
| Jiang et al. | Mobile robot gas source localization via top-down visual attention mechanism and shape analysis | |
| CN104680152B (en) | A kind of cylinder brand recognition method and 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 |