CN108168431A - A kind of tennis robot positioning system of view-based access control model identification and method - Google Patents
A kind of tennis robot positioning system of view-based access control model identification and method Download PDFInfo
- Publication number
- CN108168431A CN108168431A CN201711482458.5A CN201711482458A CN108168431A CN 108168431 A CN108168431 A CN 108168431A CN 201711482458 A CN201711482458 A CN 201711482458A CN 108168431 A CN108168431 A CN 108168431A
- Authority
- CN
- China
- Prior art keywords
- image
- column
- robot
- tennis
- coordinate
- 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
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/002—Measuring arrangements characterised by the use of optical techniques for measuring two or more coordinates
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
- Manipulator (AREA)
Abstract
The invention discloses a kind of tennis robot positioning systems of view-based access control model identification, it is characterised in that system includes:It is sequentially connected extracting the mark unit used when the image extraction unit of image information in place, the image processing unit for receiving image information and being handled to image information and calculating robot position as object of reference;Described image processing unit include to remove the filtering module of picture noise point, filtered image carried out to threshold process and conversion modular converter, delimit the search module of place range and locating module for locking robot location.The present invention is using visual recognition positioning principle, and the distance based on binocular vision calculating robot to several markers realizes the positioning of robot, and without setting up base station, device structure is simple, of low cost, and disclosure satisfy that system accuracy requirement.
Description
Technical field
The present invention relates to computer technology and image processing techniques, in particular relate to a kind of tennis machine of view-based access control model identification
Device people alignment system and method.
Background technology
In recent years, tennis is rapidly developed in China, and tennis population increases sharply.Tennis pick-up in tennis venue
Tool is also increasingly fast-selling.It arrives with the intelligent epoch, the Intellectualized Tendency of tennis pickup instrument is increasingly apparent, especially with tennis server
The development of intelligent positioning technology of the device people on tennis court is the most prominent.
Reckoning (Dead-Reckoning abbreviation DR) is a kind of most popular positioning means.It does not need to be outer
The estimation to vehicle location and direction can be realized in portion's sensor information, and is capable of providing very high short-term positioning accuracy.Boat
The key of mark reckoning positioning technology is to measure the distance that mobile robot unit interval is passed by.And at this section
The variation in interior mobile robot course.According to the difference of sensor, mainly there is the reckoning positioning based on inertial sensor
Method and the reckoning localization method based on code-disc.Specific rotation and acceleration are measured respectively using gyro and accelerometer
Rate is integrated to measurement result, so as to solve the variation of the distance of mobile robot movement and course, further according to boat
The rudimentary algorithm that mark calculates acquires the position and posture of mobile robot, but has drift at any time using technique, integrates
Later, any small constant error can all increase without limitation.Therefore the specific objective positioning field not being suitable in finite region.
UWB (Ultra Wide Band, ultra wide band) is a kind of nothing with extremely low power high speed transmission data in short distance
Line communication technology, it is all that UWB has that strong anti-interference performance, transmission rate are high, very bandwidth is wide, consumption electric energy is small, transmission power is small etc.
More advantages are mainly used in the fields such as indoor communications, home network, position finding, detections of radar.The big transmission power of power system capacity
It is very small, the influence of Electromagnetic Wave Radiation on Human also can very little, application surface is with regard to wide.But it is needed on the scene with expensive
The shortcomings of ground sets up base station, and installation and debugging are relatively complicated.
In conclusion lacking effective tennis robot localization technology in the prior art, largely constrain
Tennis develops to intelligent direction.
Invention content
In view of the deficiencies in the prior art, the present invention proposes a kind of tennis robot positioning system of visual recognition, this is
System can accurately measure distance of the tennis service robot with respect to marker, utilize tennis service robot and known coordinate position
The relative position relation of marker judge half-court residing for robot, and then realize that tennis robot determines in the tennis court whole audience
Position.
A kind of tennis robot positioning system of view-based access control model identification, it is characterised in that system includes:It extracts in place and schemes
It image extraction unit as information, the image processing unit for receiving image information and being handled to image information and calculates
The mark unit used during robot location as object of reference;
Described image processing unit includes removing the filtering module of picture noise point, filtered image being carried out threshold value
The modular converter of processing and conversion, the search module for delimiting place range and the locating module for locking robot location.
Further, described image extraction unit further includes 2 CMOS cameras being set up in parallel, drives camera rotation
Steering engine and control steering engine rotation Arduino control panels, the two CMOS camera spacing 300mm, and respectively capture take the photograph
As the image in front of head in 120 degree of orientation.
Further, the mark unit, which includes being attached to tennis court two, blocks different colours marker on column, to distinguish
Half-court where robot.
Further, the filtering module sends out image extraction unit using the following formula according to bilateral filtering processing mode
The image information sent is handled:
Wherein, (i, j) is the pixel coordinate of current pixel point, and (k, l) is that the pixel of current pixel point surrounding pixel point is sat
Mark, f (i, j) and f (k, l) represent the pixel value at image coordinate (i, j) and (k, l), f respectively1(i, j) is sat for image after processing
The pixel value at (i, j) is marked, w (i, j, k, l) represents weighted value, σdIt is the standard deviation of spatial domain, σrIt is the standard deviation in gray scale domain.
Further, image is converted into HSV coded images and is identified according to mark cell colors by the modular converter
Image is converted into bianry image by HSV parameters.
Further, described search module adjusts the extraction scope of image extraction unit according to bianry image, it is ensured that tennis
Two of field block the visual field that column appears in two CMOS cameras of left and right simultaneously, otherwise send signal to Arduino control panels to adjust
Whole steering engine rotation.
Further, the locating module obtains the position that robot blocks column relative to tennis court, specifically includes:
After steering engine stops rotating, column profile is blocked using minimum area-encasing rectangle algorithm pickup tennis court, to determine tennis court
Block pixel coordinate x of the column center line in left imagelAnd the pixel coordinate x in right imager;
The distance L that robot blocks column to two is acquired according to the following formula1And L2:
Wherein, wherein Z represents that vertical plane where two cameras blocks the distance of column to object, and f is represented with pixel
Camera focal length, T are the spacing between two camera optical axises, xlIt is that column center line is blocked in left camera shooting image in tennis court
On image coordinate, xrIt is that image coordinate of the column center line on right camera shooting image is blocked in tennis court;
According to L1And L2Acquire robot coordinate:
X=± L2*cosA
Y=L3+L2*sinA
Wherein A is robot and blocks line and the angle of X-axis between column 2, and
L3Column is blocked to the distance of tennis court outer boundaries for tennis court;
The relative position relation for blocking column different colours marker according in image two judges that robot coordinate x's is positive and negative, if
It blocks column 1 and is blocking 2 left side of column, then x takes positive sign, and otherwise then x takes negative sign.
The present invention also provides a kind of tennis localization method based on system described in claim 1, including:
Step 1 starts CMOS camera, and two cameras acquire floor area image and image is sent to calculating simultaneously
Machine;
Step 2, computer disposal image, adjustment steering engine rotation, specifically include:
Bilateral filtering processing is carried out to the image of camera acquisition;
Described image is converted into HSV forms, and binary conversion treatment is carried out in marker color gamut;
Steering engine rotation is adjusted according to bianry image until two block column and appear in simultaneously in two camera views;
Column profile is blocked using smallest enclosing circle algorithm pickup tennis court, determines that column center line is blocked in left and right camera shooting in tennis court
Pixel coordinate x in head shooting imagelAnd xr;
Step 3, the relative position relation for blocking column different colours marker according to the basic principle of binocular vision and two are asked
Solve tennis robot coordinate.
Further, the method further includes foundation and column line is blocked using tennis court outer boundaries as X-axis, using two as Y-axis
The step of coordinate system.
Further, the method further includes the step of being demarcated to camera.
Through the above technical solutions, the present invention, using visual recognition positioning principle, based on binocular vision, calculating robot arrives
The distance of several markers realizes the positioning of robot, and without setting up base station, device structure is simple, of low cost, and can
Meet system accuracy requirement.
Description of the drawings
For the clearer technical solution for illustrating the embodiment of the present invention or the prior art, to embodiment or will show below
Have technology describe needed in attached drawing do one and simply introduce, it should be apparent that, the accompanying drawings in the following description is only
Some embodiments of the present invention for those of ordinary skill in the art, without creative efforts, may be used also
To obtain other attached drawings according to these attached drawings.
Fig. 1 is present system structure diagram;
Fig. 2 is present system image extraction unit structure diagram;
Fig. 3 is present system work flow diagram;
Fig. 4 is positioning principle schematic diagram of the present invention.
Drawing reference numeral explanation:
1st, COMS cameras, 2, steering engine, 3, stent, 4, Arduino control panels.
Specific embodiment
Purpose, technical scheme and advantage to make the embodiment of the present invention are clearer, with reference to the embodiment of the present invention
In attached drawing, the technical solution in the embodiment of the present invention is clearly completely described:
As shown in Figure 1, the invention discloses a kind of tennis robot positioning system of view-based access control model identification, system includes:
The image extraction unit of image information, reception image information and the image procossing list handled image information in extraction place
The mark unit used when member and calculating robot position as object of reference;Described image processing unit includes removing
The filtering module of picture noise point, delimit place range at the modular converter that filtered image is carried out to threshold process and conversion
Search module and the locating module for locking robot location.As shown in Fig. 2, image extraction unit further includes 2 side by side
The CMOS camera 1 of setting, the steering engine 2 for driving camera rotation, camera bracket 3 and the Arduino of control steering engine rotation
Control panel 4, wherein CMOS camera 1 are fixed on camera bracket 3, and camera bracket is fixed on steering engine 2, can be by steering engine band
Dynamic rotation.More particularly, selected two CMOS cameras spacing 300mm and be small distortion camera, can capture camera
Image in the orientation of 120 degree of front.Further, the mark unit, which includes being attached to tennis court two, blocks different colours mark on column
Object is known, to distinguish half-court where robot.
After alignment system electrifying startup, CMOS camera obtains picture, is transferred in computer through USB port and does further place
Reason since the image of acquisition can inevitably adulterate noise, influences the subsequent processing to image, therefore first the image collected is used
Bilateral filtering processing, to remove the reservation more clearly object edge simultaneously of the noise spot in image.In particular, filtering module
It is handled according to bilateral filtering processing mode using the image information that the following formula sends image extraction unit:
Wherein, (i, j) is the pixel coordinate of current pixel point, and (k, l) is that the pixel of current pixel point surrounding pixel point is sat
Mark, f (i, j) and f (k, l) represent the pixel value at image coordinate (i, j) and (k, l), f respectively1(i, j) is sat for image after processing
The pixel value at (i, j) is marked, w (i, j, k, l) represents weighted value, σdIt is the standard deviation of spatial domain, σrIt is the standard deviation in gray scale domain.
In view of the image of HSV forms can be better against the variation of intensity of illumination in image identification, therefore the present invention utilizes
Picture format after bilateral filtering is converted into HSV by modular converter by RGB, and specific conversion process is:
If (r, g, b) is the red, green and blue coordinate of a color respectively, their value is the real number between 0 to 1.If
Max is equivalent to r, and the maximum in g and b, min is equal to the reckling in these values.It is found in HSL spaces according to the following formula
In corresponding (h, s, l) value,
V=max
Wherein h ∈ [0,360) represent the hue angle of angle, and s, l ∈ [0,1] represent saturation degree and brightness.
Further, modular converter blocks the HSV parameters of column colour code according to known tennis court, and image is converted into two
Value figure, wherein, the pixel value in marker color gamut is set to 1, remaining is set to 0.
Further, described search module adjusts the extraction scope of image extraction unit according to bianry image, it is ensured that tennis
Two of field block the visual field that column appears in two CMOS cameras of left and right simultaneously, otherwise send signal to Arduino control panels to adjust
Whole steering engine rotation.Specifically, judged according to bianry image, if two of tennis court are blocked column and appear in regarding for left and right camera simultaneously
Yezhong then enters in next step.Otherwise, computer sends signal by way of serial communication to Arduino control panels,
Arduino control panels then control steering engine to rotate.At the same time, camera judges tennis still constantly to computer output image
Field blocks whether column is appeared in the visual field, if so, steering engine stops rotating;Otherwise steering engine continues to rotate.
Further, the locating module obtains the position that robot blocks column relative to tennis court, specifically includes:
After steering engine stops rotating, column profile is blocked using minimum area-encasing rectangle algorithm pickup tennis court, to determine tennis court
Block pixel coordinate x of the column center line in left imagelAnd the pixel coordinate x in right imager;
The distance L that robot blocks column to two is acquired according to the following formula1And L2:
Wherein, wherein Z represents that vertical plane where two cameras blocks the distance of column to object, and f is represented with pixel
Camera focal length, T are the spacing between two camera optical axises, xlIt is that column center line is blocked in left camera shooting image in tennis court
On image coordinate, xrIt is that image coordinate of the column center line on right camera shooting image is blocked in tennis court;
As shown in figure 4, according to L1And L2Acquire robot coordinate:
X=± L2*cosA
Y=L3+L2*sinA
Wherein A is robot and blocks line and the angle of X-axis between column 2, and L3Column is blocked to the distance of tennis court outer boundaries for tennis court;
The relative position relation for blocking column different colours marker according in image two judges that robot coordinate x's is positive and negative, if
It blocks column 1 and is blocking 2 left side of column, then x takes positive sign, and otherwise then x takes negative sign.
The present invention also provides a kind of tennis localization method based on system described in claim 1, as shown in figure 3, it is wrapped
It includes:
Step 1 starts CMOS camera, and two cameras acquire floor area image and image is sent to calculating simultaneously
Machine;
Step 2, computer disposal image, adjustment steering engine rotation, specifically include:
Bilateral filtering processing is carried out to the image of camera acquisition;
Described image is converted into HSV forms, and binary conversion treatment is carried out in marker color gamut;
Steering engine rotation is adjusted according to bianry image until two block column and appear in simultaneously in two camera views;
Column profile is blocked using smallest enclosing circle algorithm pickup tennis court, determines that column center line is blocked in left and right camera shooting in tennis court
Pixel coordinate x in head shooting imagelAnd xr。
It is further comprising the steps of that column is blocked in identification:
The morphology cellular construction for constructing rectangular configuration carries out bilateral filtering operation to described image, makes an uproar in image is filtered out
While point, preferably retaining color marker destination edge.
Described image is converted into the image of HSV codings;
Using known ground colour code object HSV parameters carry out thresholding processing to image, obtain corresponding binary map.
The center line and its coordinate for blocking column in tennis court must be arrived using minimum area-encasing rectangle algorithm.
Step 3, the relative position relation for blocking column different colours marker according to the basic principle of binocular vision and two are asked
Solve tennis robot coordinate:
X=± L2*cosA
Y=L3+L2*sinA
Wherein A is robot and blocks line and the angle of X-axis between column 2, and L2For robot to the distance for blocking column 2, L3Column is blocked to the distance of tennis court outer boundaries for tennis court;
The relative position relation for blocking column different colours marker according in image two judges that robot coordinate x's is positive and negative, if
It blocks column 1 and is blocking 2 left side of column, then x takes positive sign, and otherwise then x takes negative sign.
The relative position relation for blocking column different colours marker according in image two judges that robot coordinate x's is positive and negative, if
It blocks column 1 and is blocking 2 left side of column, then x takes positive sign, and otherwise then x takes negative sign.
Further, system further includes the step of carrying out parameter correction to camera before extracting image from CMOS camera.
Further, the method further includes foundation and column line is blocked using tennis court outer boundaries as X-axis, using two as Y-axis
The step of coordinate system.
The present invention is using visual recognition positioning principle, the distance based on binocular vision calculating robot to several markers
Realize the positioning of robot, without setting up base station, device structure is simple, of low cost, and disclosure satisfy that system accuracy requirement.
The foregoing is only a preferred embodiment of the present invention, but protection scope of the present invention be not limited thereto,
Any one skilled in the art in the technical scope disclosed by the present invention, according to the technique and scheme of the present invention and its
Inventive concept is subject to equivalent substitution or change, should be covered by the protection scope of the present invention.
Claims (10)
1. a kind of tennis robot positioning system of view-based access control model identification, it is characterised in that system includes:Extract image in place
The image extraction unit of information receives image information and the image processing unit and computer that are handled image information
The mark unit used during device people position as object of reference;
Described image processing unit includes removing the filtering module of picture noise point, filtered image being carried out threshold process
The search module of modular converter, delimitation place range with conversion and the locating module for locking robot location.
2. tennis robot positioning system according to claim 1, it is characterised in that described image extraction unit further includes 2
The Arduino control panels of a CMOS camera being set up in parallel, the steering engine for driving camera rotation and control steering engine rotation, two
The CMOS camera spacing 300mm, and the image in front of capture camera in 120 degree of orientation respectively.
3. tennis robot positioning system according to claim 1, it is characterised in that the mark unit includes being attached to net
The different colours marker on column is blocked in court two, to distinguish half-court where robot.
4. tennis robot positioning system according to claim 1, it is characterised in that the filtering module is according to bilateral filter
Wave processing mode is handled using the image information that the following formula sends image extraction unit:
Wherein, (i, j) is the pixel coordinate of current pixel point, and (k, l) is the pixel coordinate of current pixel point surrounding pixel point, f
(i, j) and f (k, l) represent the pixel value at image coordinate (i, j) and (k, l), f respectively1(i, j) is image coordinate after processing
Pixel value at (i, j), w (i, j, k, l) represent weighted value, σdIt is the standard deviation of spatial domain, σrIt is the standard deviation in gray scale domain.
5. tennis robot positioning system according to claim 4, it is characterised in that the modular converter converts image
Image is converted into bianry image for HSV coded images and according to the HSV parameters that mark cell colors identify.
6. tennis robot positioning system according to claim 5, it is characterised in that described search module is according to binary map
As the extraction scope of adjustment image extraction unit, it is ensured that two of tennis court block column and appear in two CMOS cameras of left and right simultaneously
Otherwise the visual field sends signal to adjust steering engine rotation to Arduino control panels.
7. tennis robot positioning system according to claim 6, it is characterised in that the locating module obtains robot
The position of column is blocked relative to tennis court, is specifically included:
After steering engine stops rotating, column profile is blocked using minimum area-encasing rectangle algorithm pickup tennis court, to determine that column is blocked in tennis court
Pixel coordinate x of the center line in left imagelAnd the pixel coordinate x in right imager;
The distance L that robot blocks column to two is acquired according to the following formula1And L2:
Wherein, wherein Z represents that vertical plane where two cameras blocks the distance of column to object, and f is the camera shooting represented with pixel
Head focal length, T is the spacing between two camera optical axises, xlIt is that column center line is blocked on left camera shooting image in tennis court
Image coordinate, xrIt is that image coordinate of the column center line on right camera shooting image is blocked in tennis court;
According to L1And L2Acquire robot coordinate:
X=± L2*cosA
Y=L3+L2*sinA
Wherein A is robot and blocks line and the angle of X-axis between column 2, and
L3Column is blocked to the distance of tennis court outer boundaries for tennis court;
The relative position relation for blocking column different colours marker according in image two judges that robot coordinate x's is positive and negative, if blocking column 1
2 left side of column is being blocked, then x takes positive sign, and otherwise then x takes negative sign.
8. a kind of localization method of above-mentioned tennis robot positioning system, it is characterised in that including:
Step 1 starts CMOS camera, and two cameras acquire floor area image and image is sent to computer simultaneously;
Step 2, computer disposal image, adjustment steering engine rotation, specifically include:
Bilateral filtering processing is carried out to the image of camera acquisition;
Described image is converted into HSV forms, and binary conversion treatment is carried out in marker color gamut;
Steering engine rotation is adjusted according to bianry image until two block column and appear in simultaneously in two camera views;
Column profile is blocked using smallest enclosing circle algorithm pickup tennis court, determines that tennis court is blocked column center line and clapped in left and right camera
Take the photograph the pixel coordinate x in imagelAnd xr;
Step 3, the relative position relation for blocking column different colours marker according to the basic principle of binocular vision and two solve
Tennis robot coordinate.
9. tennis robot localization method according to claim 8, it is characterised in that further include foundation on the outside of tennis court
Boundary is X-axis, the step of coordinate system of the column line as Y-axis is blocked using two.
10. tennis robot localization method according to claim 8, it is characterised in that further include and demarcated to camera
The step of.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711482458.5A CN108168431A (en) | 2017-12-29 | 2017-12-29 | A kind of tennis robot positioning system of view-based access control model identification and method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711482458.5A CN108168431A (en) | 2017-12-29 | 2017-12-29 | A kind of tennis robot positioning system of view-based access control model identification and method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108168431A true CN108168431A (en) | 2018-06-15 |
Family
ID=62516557
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711482458.5A Pending CN108168431A (en) | 2017-12-29 | 2017-12-29 | A kind of tennis robot positioning system of view-based access control model identification and method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108168431A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109146973A (en) * | 2018-09-05 | 2019-01-04 | 鲁东大学 | Robot Site characteristic identifies and positions method, apparatus, equipment and storage medium |
CN109490858A (en) * | 2018-11-06 | 2019-03-19 | 浙江大华技术股份有限公司 | A kind of thunder ball sizing system and method |
CN110322508A (en) * | 2019-06-19 | 2019-10-11 | 四川阿泰因机器人智能装备有限公司 | A kind of assisted location method based on computer vision |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102679960A (en) * | 2012-05-10 | 2012-09-19 | 清华大学 | Robot vision locating method based on round road sign imaging analysis |
CN103365292A (en) * | 2013-07-15 | 2013-10-23 | 兰州理工大学 | Ball picking method based on visual identification and multi-sensor data fusion |
CN106338287A (en) * | 2016-08-24 | 2017-01-18 | 杭州国辰牵星科技有限公司 | Ceiling-based indoor moving robot vision positioning method |
CN106709436A (en) * | 2016-12-08 | 2017-05-24 | 华中师范大学 | Cross-camera suspicious pedestrian target tracking system for rail transit panoramic monitoring |
CN107137895A (en) * | 2017-06-05 | 2017-09-08 | 王舒婷 | A kind of dual-purpose supplemental training robot of new Wire driven robot tennis shuttlecock |
-
2017
- 2017-12-29 CN CN201711482458.5A patent/CN108168431A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102679960A (en) * | 2012-05-10 | 2012-09-19 | 清华大学 | Robot vision locating method based on round road sign imaging analysis |
CN103365292A (en) * | 2013-07-15 | 2013-10-23 | 兰州理工大学 | Ball picking method based on visual identification and multi-sensor data fusion |
CN106338287A (en) * | 2016-08-24 | 2017-01-18 | 杭州国辰牵星科技有限公司 | Ceiling-based indoor moving robot vision positioning method |
CN106709436A (en) * | 2016-12-08 | 2017-05-24 | 华中师范大学 | Cross-camera suspicious pedestrian target tracking system for rail transit panoramic monitoring |
CN107137895A (en) * | 2017-06-05 | 2017-09-08 | 王舒婷 | A kind of dual-purpose supplemental training robot of new Wire driven robot tennis shuttlecock |
Non-Patent Citations (5)
Title |
---|
卢洪军: "基于双目视觉机器人自定位与动态目标定位", 《沈阳大学学报》 * |
崔宝侠 等: "基于全景视觉机器人定位的路标提取方法*", 《沈阳工业大学学报》 * |
林广茂 等: "基于视觉识别的全自动网球拾取机器人设计", 《机电工程技术》 * |
隋裕召 等: "基于视觉识别的智能网球拾取机器人的设计", 《科技创新导报》 * |
齐庆磊: "基于双目立体视觉的三维定位技术研究与实现", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109146973A (en) * | 2018-09-05 | 2019-01-04 | 鲁东大学 | Robot Site characteristic identifies and positions method, apparatus, equipment and storage medium |
CN109146973B (en) * | 2018-09-05 | 2022-03-04 | 鲁东大学 | Robot site feature recognition and positioning method, device, equipment and storage medium |
CN109490858A (en) * | 2018-11-06 | 2019-03-19 | 浙江大华技术股份有限公司 | A kind of thunder ball sizing system and method |
CN110322508A (en) * | 2019-06-19 | 2019-10-11 | 四川阿泰因机器人智能装备有限公司 | A kind of assisted location method based on computer vision |
CN110322508B (en) * | 2019-06-19 | 2023-05-05 | 四川阿泰因机器人智能装备有限公司 | Auxiliary positioning method based on computer vision |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20200272803A1 (en) | Systems and methods for detecting and tracking movable objects | |
CN110297498B (en) | Track inspection method and system based on wireless charging unmanned aerial vehicle | |
US11019322B2 (en) | Estimation system and automobile | |
CN108873917A (en) | A kind of unmanned plane independent landing control system and method towards mobile platform | |
CN105512628B (en) | Vehicle environmental sensory perceptual system based on unmanned plane and method | |
CN108255198B (en) | Shooting cradle head control system and control method under unmanned aerial vehicle flight state | |
CN110928301B (en) | Method, device and medium for detecting tiny obstacle | |
CN106338712A (en) | Visible light indoor positioning method and system based on camera communication | |
CN108168431A (en) | A kind of tennis robot positioning system of view-based access control model identification and method | |
CN105279372A (en) | Building height computing method and apparatus | |
CN106019264A (en) | Binocular vision based UAV (Unmanned Aerial Vehicle) danger vehicle distance identifying system and method | |
CN112364707B (en) | System and method for performing beyond-the-horizon perception on complex road conditions by intelligent vehicle | |
CN107453811B (en) | A method of the unmanned plane based on photopic vision communication cooperates with SLAM | |
CN110456330A (en) | Method and system for automatically calibrating external parameter without target between camera and laser radar | |
CN110858414A (en) | Image processing method and device, readable storage medium and augmented reality system | |
CN107403450A (en) | A kind of method and device of unmanned plane pinpoint landing | |
CN107221006A (en) | A kind of communication single pipe tower slant detection method based on unmanned plane imaging platform | |
CN109483507B (en) | Indoor visual positioning method for walking of multiple wheeled robots | |
CN109883433A (en) | Vehicle positioning method in structured environment based on 360 degree of panoramic views | |
CN110046584A (en) | A kind of road crack detection device and detection method based on unmanned plane inspection | |
CN105427284A (en) | Fixed target marking method based on airborne android platform | |
CN109076167A (en) | Image processor, photographic device and image processing system | |
CN108303029B (en) | High real-time analysis platform based on image analysis | |
CN108074265A (en) | A kind of tennis alignment system, the method and device of view-based access control model identification | |
CN108036786A (en) | Position and posture detection method, device and computer-readable recording medium based on auxiliary line |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
TA01 | Transfer of patent application right | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20201229 Address after: 350001 No.260, Wusi Road, Gulou District, Fuzhou City, Fujian Province Applicant after: Dong Mingwu Address before: Room 303, building 1, courtyard 13, cuihu'nan Ring Road, Sujiatuo Town, Haidian District, Beijing Applicant before: SIBO SAIRUI (BEIJING) TECHNOLOGY Co.,Ltd. |
|
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180615 |