CN109685845A - A kind of realtime graphic splicing processing method based on POS system for FOD detection robot - Google Patents
A kind of realtime graphic splicing processing method based on POS system for FOD detection robot Download PDFInfo
- Publication number
- CN109685845A CN109685845A CN201811420436.0A CN201811420436A CN109685845A CN 109685845 A CN109685845 A CN 109685845A CN 201811420436 A CN201811420436 A CN 201811420436A CN 109685845 A CN109685845 A CN 109685845A
- Authority
- CN
- China
- Prior art keywords
- image
- distortion
- frame image
- robot
- detection robot
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 25
- 238000003672 processing method Methods 0.000 title claims abstract description 7
- 238000000034 method Methods 0.000 claims abstract description 18
- 238000012937 correction Methods 0.000 claims description 19
- 238000013507 mapping Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000006073 displacement reaction Methods 0.000 claims description 3
- 238000013178 mathematical model Methods 0.000 claims description 3
- 230000001360 synchronised effect Effects 0.000 claims description 3
- 238000013519 translation Methods 0.000 claims description 3
- 241000208340 Araliaceae Species 0.000 claims 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims 1
- 235000003140 Panax quinquefolius Nutrition 0.000 claims 1
- 235000008434 ginseng Nutrition 0.000 claims 1
- 230000005283 ground state Effects 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration by the use of more than one image, e.g. averaging, subtraction
-
- G06T5/80—
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/80—Camera processing pipelines; Components thereof
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/80—Camera processing pipelines; Components thereof
- H04N23/81—Camera processing pipelines; Components thereof for suppressing or minimising disturbance in the image signal generation
Abstract
A kind of realtime graphic splicing processing method based on POS system for FOD detection robot, treats position and posture information, interpolation reconstruction, image rectification, the image mosaic that geodetic face was shot, detected robot including line-scan digital camera;This method combines image with real time position and posture, can effectively solve the problems, such as that movement velocity and direction are inconsistent and cause linear array camera image splicing effect poor during the motion for FOD detection robot.
Description
(1) technical field:
The present invention relates to technical field of image processing, it is especially a kind of for FOD (Foreign Object Debris, outside
Object damage) detection robot based on POS (Positioning and Orientation System, positioning and orientation system) system
The realtime graphic splicing processing method of system.
(2) background technique:
The big visual field, high frame amplitude-frequency and high accurancy and precision are needed when FOD detection robot detection road surface exotic, so needing
Image Acquisition is carried out using line-scan digital camera, but usually only several pixels of the width direction of line-scan digital camera need to shoot
The splicing that multiple image carries out width direction could obtain the two dimensional image of big width.The image mosaic side of current line-scan digital camera
Method is usually to be spliced in the fixed environments such as lathe using the equipment record position information such as grating, but FDO detects machine
The usage scenario of people is more open, has high-freedom degree, is not available existing joining method.
POS positioning and orientation system can obtain the information such as high precision position, navigation, posture and the speed of load in real time,
FDO detects robot field, especially image procossing direction, and there are no be widely used.
(3) summary of the invention:
It is an object of that present invention to provide a kind of realtime graphic stitching portions based on POS system for FOD detection robot
Reason method, this method can make up the deficiencies in the prior art, are a kind of simple and easy image processing methods, are able to solve FOD
Detect robot during the motion as speed change, turn to or pavement roughness and caused by the collected figure of line-scan digital camera
As the problem of can not normally splice.
A kind of technical solution of the present invention: realtime graphic splicing based on POS system for FOD detection robot
Method, it is characterised in that it the following steps are included:
(1) rotary encoder being mounted on FOD detection robot hub for vehicle wheel triggers linear array phase according to the rotation of wheel
Machine is treated geodetic face and is shot;
(2) position that current time FOD detects robot is obtained by GPS signal by POS system while shooting ground
And posture information, make each frame image keep data synchronous with the position of FOD detection robot and posture information;
(3) it is directed to the distortion situation of line-scan digital camera camera lens, linear array phase is obtained by the method for shooting fixed range sampled point
The distortion parameter of machine, establishes distortion correction function, adopts each pixel of image to camera to line-scan digital camera acquired image
Point is calculated with distortion correction function, the position after its correction can be obtained, then again according to the correction position of each pixel
It is combined into new image, correction image can be obtained;
(4) it does not adjust to the first frame image taken, as initial position;Remaining each frame image is according to the image
Correspondence moment when storage detects position and the posture information of robot, to be adjusted to the frame image, compares the frame image
Position and posture information with its previous frame image detect travel speed and the direction of robot according to FOD, if two field pictures
Offset on position and posture angle of arrival or position then carries out corresponding rotation and translation to the frame image, for keeping figure
As consistent with the driving direction and displacement of detection robot;
(5) it is matched according to the gray scale of present frame and its previous frame image, texture, finds and be overlapped in this two field pictures
Two field pictures are obtained the position of two field pictures by ground location image if there is intersection according to the overlapping positions point being matched to
Mapping relations are set, the pixel of the frame image and previous frame image are spliced according to mapping relations, delete duplicate figure
As data, piece image is merged into;According to position and attitude acquisition of information position mapping relations if two field pictures are without intersection,
The frame image is spliced with previous frame image, the image slices vegetarian refreshments closed on according to gap is to the space part in two field pictures
Divide and carry out bilinear interpolation processing, fills up complete;
The frame image is deleted without intersection and if being overlapped occurs in location information if two field pictures;
(6) when the frame number of image mosaic reaches setting value, the image that completion is spliced in output at this time is final image.
Distortion parameter in the step (3) is the parameter for including radial distortion, tangential distortion and non-flat area distortion.
Distortion function in the step (3) is established as follows:
X '=x-x0
Y '=y-y0
R=x ' * x '+y ' * y '
X "=x '+k1x′r2+k2x′r4+k3x′r6+p1(r+2x′x′)+2p2x′y′+ap1x′+ap2*y′
Y "=y '+k1y′r2+k3y′r6+p1(r+2y′y′)+2p2x′y′
In formula, x ", y " is the image slices vegetarian refreshments coordinate after correction, and x, y are original image pixels point coordinate, x0、y0For principal point
Coordinate, k1、k2、k3The respectively first three items of the taylor series expansion of camera lens radial distortion mathematical model, p1、p2For camera
The tangential distortion parameter of camera lens, ap1、ap2For non-planar distortion parameter.
The calculation method of bilinear interpolation in the step (5) are as follows:
Wherein, (x, y), (x1, y1)、(x2, y2)、(x1, y2)、(x2, y1) it is respectively 5 coordinates, x, x on two dimensional image1、
x2For image level direction coordinate value, y, y1、y2For image vertical direction coordinate value, coordinate is (x, y) in f (x, y) representative image
Point pixel value, wherein (x, y) point pixel value it is unknown, remaining 4 points for (x, y) point around closest to four pixel values
Pixel coordinate.
The working principle of the invention:
1.POS system: using GPS relative positioning method, and using two GPS signal receivers, a receiver setting exists
In airport in a fixed observer station, another receiver being placed in FOD detection robot with fixed observer station is carried out together
Step observation, to determine the instantaneous position of the relatively fixed observation station of FOD detection robot.Using survey phase pseudorange dynamic relative positioning
Method carries out Dynamic High-accuracy relative positioning based on dynamically settling accounts carrier phase integral cycle unknown.And machine is detected with FOD
The three-dimensional velocity information of the receiver output disposed on people settles accounts its posture, thus can get position and the appearance of FOD robot
State information.Line-scan digital camera and receiver are in identical platform simultaneously, pass through the available stringent geometry between them of calibration
Relationship.
2. image rectification and splicing: the reason of image geometry deformation mainly includes two parts: lens distortion and FOD robot
Deviate picture position caused by traveling offset and attitudes vibration.For the distortion situation of line-scan digital camera camera lens, by spatially
Equally spaced placement sampled point keeps x-axis coordinate constant, and 1 group mark point of equally spaced extraction, moves a certain distance on the y axis
Continue sampling site in an identical manner afterwards and taken pictures to obtain corresponding pixel points with camera, respectively obtains reality using Cross ration invariability
The double ratio value of border sampled point and the double ratio value of corresponding pixel points, obtain corresponding double ratio relationship, while establishing the abnormal of line-scan digital camera
Varying function is brought into obtained double ratio relationship, establishes lens distortion calibration function, is mended to camera lens distortion error
Repay correction.
For the traveling offset of FOD robot and attitudes vibration, need by the real time position and appearance obtained by POS system
The geometrical relationship of state information and the good line-scan digital camera of calibration and POS system receiver obtains the outer of line-scan digital camera scanning moment
The element of orientation can then calculate position of the every one scan line image of line-scan digital camera in earth axes.According to every one scan line
Image corresponding to the progress of current scan line image can be rotated with the relative positional relationship of preceding one scan line image, be translated
Correct operation is finally matched and is spliced with previous row image.
Superiority of the invention: the image mosaic processing method based on POS system is by image and real time position and posture phase
In conjunction with can effectively solving FOD detection robot, movement velocity and direction are inconsistent and lead to line-scan digital camera during the motion
The problem of image mosaic effect difference.
(4) Detailed description of the invention:
Fig. 1 is a kind of realtime graphic splicing side based on POS system that robot is detected for FOD involved by the present invention
The flow diagram of method.
Fig. 2 is a kind of realtime graphic splicing side based on POS system that robot is detected for FOD involved by the present invention
The parameters relationship schematic diagram of bilinear interpolation in method.
(5) specific embodiment:
Embodiment: a kind of realtime graphic splicing processing method based on POS system for FOD detection robot, such as Fig. 1
It is shown, it is characterised in that it the following steps are included:
(1) rotary encoder being mounted on FOD detection robot hub for vehicle wheel triggers linear array phase according to the rotation of wheel
Machine is treated geodetic face and is shot;
(2) position that current time FOD detects robot is obtained by GPS signal by POS system while shooting ground
And posture information, make each frame image keep data synchronous with the position of FOD detection robot and posture information;
(3) it is directed to the distortion situation of line-scan digital camera camera lens, linear array phase is obtained by the method for shooting fixed range sampled point
The distortion parameter of machine, the parameter including radial distortion, tangential distortion and non-flat area distortion, establishes distortion correction function, to linear array
Each pixel that camera acquired image adopts image to camera is calculated with distortion correction function, after its correction can be obtained
Position, be then reassembled into according to the correction position of each pixel as new image, correction image can be obtained;
Wherein, distortion function is established as follows:
X '=x-x0
Y '=y-y0
R=x ' * x '+y ' * y '
X "=x '+k1x′r2+k2x′r4+k3x′r6+p1(r+2x′x′)+2p2x′y′+ap1x′+ap2*y′
Y "=y '+k1y′r2+k3y′r6+p1(r+2y′y′)+2p2x′y′
In formula, x ", y " is the image slices vegetarian refreshments coordinate after correction, and x, y are original image pixels point coordinate, x0、y0For principal point
Coordinate, k1、k2、k3The respectively first three items of the taylor series expansion of camera lens radial distortion mathematical model, p1、p2For camera
The tangential distortion parameter of camera lens, ap1、ap2For non-planar distortion parameter.
(4) it does not adjust to the first frame image taken, as initial position;Remaining each frame image is according to the image
Correspondence moment when storage detects position and the posture information of robot, to be adjusted to the frame image, compares the frame image
Position and posture information with its previous frame image detect travel speed and the direction of robot according to FOD, if two field pictures
Offset on position and posture angle of arrival or position then carries out corresponding rotation and translation to the frame image, for keeping figure
As consistent with the driving direction and displacement of detection robot;
(5) it is matched according to the gray scale of present frame and its previous frame image, texture, finds and be overlapped in this two field pictures
Two field pictures are obtained the position of two field pictures by ground location image if there is intersection according to the overlapping positions point being matched to
Mapping relations are set, the pixel of the frame image and previous frame image are spliced according to mapping relations, delete duplicate figure
As data, piece image is merged into;According to position and attitude acquisition of information position mapping relations if two field pictures are without intersection,
The frame image is spliced with previous frame image, the image slices vegetarian refreshments closed on according to gap is to the space part in two field pictures
Divide and carry out bilinear interpolation processing, fills up complete;
The calculation method of bilinear interpolation are as follows:
Wherein, (x, y), (x1, y1)、(x2, y2)、(x1, y2)、(x2, y1) it is respectively 5 coordinates, x, x on two dimensional image1、
x2For image level direction coordinate value, y, y1、y2For image vertical direction coordinate value, coordinate is (x, y) in f (x, y) representative image
Point pixel value, wherein (x, y) point pixel value it is unknown, remaining 4 points for (x, y) point around closest to four pixel values
Pixel coordinate, as shown in Figure 2:
Fig. 2 is image coordinate system schematic diagram, and transverse and longitudinal coordinate is represented as number of lines of pixels and columns, and wherein P point is unknown pixel
The pixel of value, coordinate are (x, y);Q11、Q12、Q21、Q22For the pixel for four known pixel values that P point closes on, coordinate
Respectively (x1,y1)、(x1,y2)、(x2,y1)、(x2,y2), then the pixel value of P point can be according to above-mentioned bilinear interpolation formula meter
It obtains;
The frame image is deleted without intersection and if being overlapped occurs in location information if two field pictures;
(6) when the frame number of image mosaic reaches setting value, the image that completion is spliced in output at this time is final image.
Claims (4)
1. a kind of realtime graphic splicing processing method based on POS system for FOD detection robot, it is characterised in that it is wrapped
Include following steps:
(1) rotary encoder being mounted on FOD detection robot hub for vehicle wheel triggers line-scan digital camera pair according to the rotation of wheel
Ground to be measured is shot;
(2) position and the appearance that current time FOD detects robot are obtained by GPS signal by POS system while shooting ground
State information makes each frame image keep data synchronous with the position of FOD detection robot and posture information;
(3) it is directed to the distortion situation of line-scan digital camera camera lens, line-scan digital camera is obtained by the method for shooting fixed range sampled point
Distortion parameter establishes distortion correction function, and each pixel for adopting image to camera to line-scan digital camera acquired image is used
Distortion correction function calculates, then the position after its correction can be obtained is reconfigured according to the correction position of each pixel
As new image, correction image can be obtained;
(4) it does not adjust to the first frame image taken, as initial position;Remaining each frame image is stored according to the image
When the correspondence moment, detect position and the posture information of robot, to be adjusted to the frame image, compare the frame image and its
The position of previous frame image and posture information detect travel speed and the direction of robot according to FOD, if the position of two field pictures
With the offset on posture angle of arrival or position, then corresponding rotation and translation is carried out to the frame image, for keep image with
The driving direction for detecting robot is consistent with displacement;
(5) it is matched according to the gray scale of present frame and its previous frame image, texture, finds the ground being overlapped in this two field pictures
Location drawing picture reflects two field pictures according to the position that the overlapping positions point being matched to obtains two field pictures if there is intersection
Relationship is penetrated, the pixel of the frame image and previous frame image are spliced according to mapping relations, delete duplicate picture number
According to merging into piece image;According to position and attitude acquisition of information position mapping relations if two field pictures are without intersection, by this
Frame image is spliced with previous frame image, the image slices vegetarian refreshments closed on according to gap to the gap section in two field pictures into
The processing of row bilinear interpolation, fills up complete;
The frame image is deleted without intersection and if being overlapped occurs in location information if two field pictures;
(6) when the frame number of image mosaic reaches setting value, the image that completion is spliced in output at this time is final image.
2. a kind of realtime graphic splicing side based on POS system for FOD detection robot according to claim 1
Method, it is characterised in that the distortion parameter in the step (3) is the ginseng for including radial distortion, tangential distortion and non-flat area distortion
Number.
3. a kind of realtime graphic splicing side based on POS system for FOD detection robot according to claim 1
Method, it is characterised in that the distortion function in the step (3) is established as follows:
X '=x-x0
Y '=y-y0
R=x ' * x '+y ' * y '
X "=x '+k1x′r2+k2x′r4+k3x′r6+p1(r+2x′x′)+2p2x′y′+ap1x′+ap2*y′
Y "=y '+k1y′r2+k3y′r6+p1(r+2y′y′)+2p2x′y′
In formula, x ", y " is the image slices vegetarian refreshments coordinate after correction, and x, y are original image pixels point coordinate, x0、y0For principal point seat
Mark, k1、k2、k3The respectively first three items of the taylor series expansion of camera lens radial distortion mathematical model, p1、p2For camera mirror
The tangential distortion parameter of head, ap1、ap2For non-planar distortion parameter.
4. a kind of realtime graphic splicing side based on POS system for FOD detection robot according to claim 1
Method, it is characterised in that the calculation method of the bilinear interpolation in the step (5) are as follows:
Wherein, (x, y), (x1, y1)、(x2, y2)、(x1, y2)、(x2, y1) it is respectively 5 coordinates, x, x on two dimensional image1、x2For
Image level direction coordinate value, y, y1、y2For image vertical direction coordinate value, coordinate is the point of (x, y) in f (x, y) representative image
Pixel value, wherein (x, y) point pixel value it is unknown, remaining 4 points for (x, y) point around closest to four pixel values picture
The coordinate of vegetarian refreshments.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811420436.0A CN109685845B (en) | 2018-11-26 | 2018-11-26 | POS system-based real-time image splicing processing method for FOD detection robot |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811420436.0A CN109685845B (en) | 2018-11-26 | 2018-11-26 | POS system-based real-time image splicing processing method for FOD detection robot |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109685845A true CN109685845A (en) | 2019-04-26 |
CN109685845B CN109685845B (en) | 2023-04-07 |
Family
ID=66184970
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811420436.0A Active CN109685845B (en) | 2018-11-26 | 2018-11-26 | POS system-based real-time image splicing processing method for FOD detection robot |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109685845B (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110310248A (en) * | 2019-08-27 | 2019-10-08 | 成都数之联科技有限公司 | A kind of real-time joining method of unmanned aerial vehicle remote sensing images and system |
CN111179176A (en) * | 2019-12-30 | 2020-05-19 | 北京东宇宏达科技有限公司 | Automatic splicing calibration method for infrared panoramic imaging |
CN112200126A (en) * | 2020-10-26 | 2021-01-08 | 上海盛奕数字科技有限公司 | Method for identifying limb shielding gesture based on artificial intelligence running |
CN112215892A (en) * | 2020-10-22 | 2021-01-12 | 常州大学 | Method for monitoring position and motion path of site robot |
CN112950493A (en) * | 2021-02-01 | 2021-06-11 | 中车青岛四方车辆研究所有限公司 | Method and device for correcting image distortion of linear array camera of rail train |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2008152740A1 (en) * | 2007-06-13 | 2008-12-18 | Information & Science Techno-System Co., Ltd. | Digital aerial photographing three-dimensional measurement system |
CN101505433A (en) * | 2009-03-13 | 2009-08-12 | 四川大学 | Real acquisition real display multi-lens digital stereo system |
CN102829763A (en) * | 2012-07-30 | 2012-12-19 | 中国人民解放军国防科学技术大学 | Pavement image collecting method and system based on monocular vision location |
CN104077760A (en) * | 2014-03-19 | 2014-10-01 | 中科宇图天下科技有限公司 | Rapid splicing system for aerial photogrammetry and implementing method thereof |
CN104506828A (en) * | 2015-01-13 | 2015-04-08 | 中南大学 | Halogen-free low-smoke low-toxic flame-resistant epoxy resin system |
CN105335931A (en) * | 2015-11-09 | 2016-02-17 | 广州视源电子科技股份有限公司 | Board card image stitching method, processing device and system |
CN106447602A (en) * | 2016-08-31 | 2017-02-22 | 浙江大华技术股份有限公司 | Image mosaic method and device |
CN107111864A (en) * | 2014-12-23 | 2017-08-29 | 华为技术有限公司 | The computational polyphaser adjustment for switching for smooth view and scaling |
CN108257090A (en) * | 2018-01-12 | 2018-07-06 | 北京航空航天大学 | A kind of high-dynamics image joining method that camera is swept towards airborne row |
US20180315221A1 (en) * | 2017-05-01 | 2018-11-01 | Lockheed Martin Corporation | Real-time camera position estimation with drift mitigation in incremental structure from motion |
-
2018
- 2018-11-26 CN CN201811420436.0A patent/CN109685845B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2008152740A1 (en) * | 2007-06-13 | 2008-12-18 | Information & Science Techno-System Co., Ltd. | Digital aerial photographing three-dimensional measurement system |
CN101505433A (en) * | 2009-03-13 | 2009-08-12 | 四川大学 | Real acquisition real display multi-lens digital stereo system |
CN102829763A (en) * | 2012-07-30 | 2012-12-19 | 中国人民解放军国防科学技术大学 | Pavement image collecting method and system based on monocular vision location |
CN104077760A (en) * | 2014-03-19 | 2014-10-01 | 中科宇图天下科技有限公司 | Rapid splicing system for aerial photogrammetry and implementing method thereof |
CN107111864A (en) * | 2014-12-23 | 2017-08-29 | 华为技术有限公司 | The computational polyphaser adjustment for switching for smooth view and scaling |
CN104506828A (en) * | 2015-01-13 | 2015-04-08 | 中南大学 | Halogen-free low-smoke low-toxic flame-resistant epoxy resin system |
CN105335931A (en) * | 2015-11-09 | 2016-02-17 | 广州视源电子科技股份有限公司 | Board card image stitching method, processing device and system |
CN106447602A (en) * | 2016-08-31 | 2017-02-22 | 浙江大华技术股份有限公司 | Image mosaic method and device |
US20180315221A1 (en) * | 2017-05-01 | 2018-11-01 | Lockheed Martin Corporation | Real-time camera position estimation with drift mitigation in incremental structure from motion |
CN108257090A (en) * | 2018-01-12 | 2018-07-06 | 北京航空航天大学 | A kind of high-dynamics image joining method that camera is swept towards airborne row |
Non-Patent Citations (2)
Title |
---|
冯其强,李宗春,李广云: ""基于有限元模型的数字工业摄影测量相机二次检校"", 《测绘通报》 * |
张敏,金龙旭,李国宁等: ""基于直线特征的摄像机镜头畸变标定方法"", 《光学学报》 * |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110310248A (en) * | 2019-08-27 | 2019-10-08 | 成都数之联科技有限公司 | A kind of real-time joining method of unmanned aerial vehicle remote sensing images and system |
CN110310248B (en) * | 2019-08-27 | 2019-11-26 | 成都数之联科技有限公司 | A kind of real-time joining method of unmanned aerial vehicle remote sensing images and system |
CN111179176A (en) * | 2019-12-30 | 2020-05-19 | 北京东宇宏达科技有限公司 | Automatic splicing calibration method for infrared panoramic imaging |
CN112215892A (en) * | 2020-10-22 | 2021-01-12 | 常州大学 | Method for monitoring position and motion path of site robot |
CN112215892B (en) * | 2020-10-22 | 2024-03-12 | 常州大学 | Method for monitoring position and motion path of site robot |
CN112200126A (en) * | 2020-10-26 | 2021-01-08 | 上海盛奕数字科技有限公司 | Method for identifying limb shielding gesture based on artificial intelligence running |
CN112950493A (en) * | 2021-02-01 | 2021-06-11 | 中车青岛四方车辆研究所有限公司 | Method and device for correcting image distortion of linear array camera of rail train |
CN112950493B (en) * | 2021-02-01 | 2022-11-01 | 中车青岛四方车辆研究所有限公司 | Method and device for correcting image distortion of linear array camera of rail train |
Also Published As
Publication number | Publication date |
---|---|
CN109685845B (en) | 2023-04-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109685845A (en) | A kind of realtime graphic splicing processing method based on POS system for FOD detection robot | |
KR100728377B1 (en) | Method for real-time updating gis of changed region vis laser scanning and mobile internet | |
Li | Mobile mapping: An emerging technology for spatial data acquisition | |
CN110412616A (en) | A kind of mining area underground mining stope acceptance method and device | |
CN109341535B (en) | High-efficiency high-precision large satellite antenna assembly measurement system | |
CN107101582A (en) | Axial workpiece run-out error On-line Measuring Method based on structure light vision | |
CN108733039A (en) | The method and apparatus of navigator fix in a kind of robot chamber | |
JPWO2004113836A1 (en) | Shooting image display method | |
CN103411587B (en) | Positioning and orientation method and system | |
CN114693754B (en) | Unmanned aerial vehicle autonomous positioning method and system based on monocular vision inertial navigation fusion | |
KR20110119589A (en) | System for determining 3-dimensional coordinates of objects using overlapping omni-directional images and method thereof | |
Ahmed et al. | Pothole 3D reconstruction with a novel imaging system and structure from motion techniques | |
Scaioni et al. | Image-based deformation measurement | |
DE102009040468A1 (en) | Portable mobile detection device for three-dimensional geometric detection of environment, has receiving device attached to sensor device, where sensor device has inertial measurement system and laser scanner | |
CN110986888A (en) | Aerial photography integrated method | |
El-Hakim et al. | A mobile system for indoors 3-D mapping and positioning | |
CN102620745B (en) | Airborne inertial measurement unite (IMU) collimation axis error calibration method | |
Canaz | Planar and linear feature-based registration of terrestrial laser scans with minimum overlap using photogrammetric data | |
Habib | Integration of lidar and photogrammetric data: triangulation and orthorectification | |
Grammatikopoulos et al. | Geometric information from single uncalibrated images of roads | |
Cannelle et al. | Off-line vs. on-line calibration of a panoramic-based mobile mapping system | |
Lee et al. | Automatic building reconstruction with satellite images and digital maps | |
Fryskowska | Accuracy Assessment of Point Clouds Geo-Referencing in Surveying and Documentation of Historical Complexes | |
Yotumata et al. | INVESTIGATION FOR MAPPING ACCURAACY OF THE AIRBORNE DIGITAL SENSOR-ADS40 | |
Odaka et al. | Localization in tunnels using feature-based scan matching |
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 |