CN108195381B - Indoor robot vision positioning system - Google Patents

Indoor robot vision positioning system Download PDF

Info

Publication number
CN108195381B
CN108195381B CN201711437012.0A CN201711437012A CN108195381B CN 108195381 B CN108195381 B CN 108195381B CN 201711437012 A CN201711437012 A CN 201711437012A CN 108195381 B CN108195381 B CN 108195381B
Authority
CN
China
Prior art keywords
passive
landmark
road sign
optimal
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.)
Active
Application number
CN201711437012.0A
Other languages
Chinese (zh)
Other versions
CN108195381A (en
Inventor
辛喆
杨一平
张吉祥
王彦情
崔晓光
徐看
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Luoyang Zhongke Electric Measurement Robot Technology Co ltd
Institute of Automation of Chinese Academy of Science
Original Assignee
Luoyang Zhongke Electric Measurement Robot Technology Co ltd
Institute of Automation of Chinese Academy of Science
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Luoyang Zhongke Electric Measurement Robot Technology Co ltd, Institute of Automation of Chinese Academy of Science filed Critical Luoyang Zhongke Electric Measurement Robot Technology Co ltd
Priority to CN201711437012.0A priority Critical patent/CN108195381B/en
Publication of CN108195381A publication Critical patent/CN108195381A/en
Application granted granted Critical
Publication of CN108195381B publication Critical patent/CN108195381B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/20—Instruments for performing navigational calculations
    • G01C21/206—Instruments for performing navigational calculations specially adapted for indoor navigation

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Automation & Control Theory (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Image Processing (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)

Abstract

The invention relates to the field of robot navigation, and particularly provides an indoor robot vision positioning system, aiming at solving the technical problem of accurately positioning an indoor robot. For this purpose, the indoor robot vision positioning system comprises a road sign device, an image acquisition device and a server; the road sign device comprises a plurality of passive road signs, wherein the passive road signs comprise a plurality of mark positions for setting mark points; the image acquisition device is used for acquiring an original image and transmitting the original image to the server; the server comprises a first judging module for judging whether the original image has the passive road sign, a second judging module for acquiring the ID code of the optimal passive road sign, judging whether the optimal passive road sign exists in a preset database and acquiring the pixel coordinate of the center of each mark point when the optimal passive road sign is in a horizontal state, an optimal passive road sign acquiring module for acquiring the optimal passive road sign and a robot coordinate acquiring module for acquiring the coordinate of the robot in a world coordinate system.

Description

Indoor robot vision positioning system
Technical Field
The invention relates to the field of robot navigation, in particular to a visual positioning system of an indoor robot.
Background
Indoor robot positioning is an important guarantee for completing tasks such as navigation, and accurate robot posture information can be obtained according to current observation data and by combining prior map information.
Currently, robot visual positioning can be divided into natural landmark positioning and artificial landmark positioning according to landmark types. The natural landmark positioning refers to positioning by using existing features in the environment, and the environment does not need to be arranged, but the positioning algorithm is complex and has poor robustness. The artificial road sign positioning refers to the positioning by installing artificially designed characteristic signs in the environment, and the method has the advantages of small calculated amount, high precision and strong robustness.
Specifically, the artificial road signs mainly include natural light road signs and infrared road signs. The natural light road sign can work under a common vision sensor, but needs sufficient indoor illumination. The infrared road signs comprise active infrared road signs and passive infrared road signs. The active infrared road sign realizes the positioning of the road sign by actively emitting infrared rays. The passive infrared road sign is formed by coating an infrared reflecting material on a road sign and realizing road sign positioning by combining an infrared filter and an infrared light source, and can adapt to any illumination environment. Although the infrared road sign overcomes the limitation of the illumination condition, the infrared road sign has the following defects: 1. each road sign of the active infrared road sign needs to be independently powered and is complex to install. 2. When a positioning method based on the vertical relationship between the marking points is adopted, if the robot shakes or the road surface is uneven, the positioning accuracy will be greatly reduced. 3. A passive infrared landmark comprised of a circular arrangement of landmark points lacks robustness to noise, for example, when placed around a fluorescent lamp, a landmark-like noisy region may be created, resulting in a misidentification condition. 4. In the positioning process, when the direction of the road sign is judged according to the size of the mark point, the mark point can be adhered due to the expansion phenomenon caused by the reflection of light of the mark point, so that the positioning effect is influenced.
Disclosure of Invention
In order to solve the above problems in the prior art, that is, to solve the technical problem of how to accurately and robustly position an indoor robot, the invention provides a visual positioning system for an indoor robot.
The indoor robot vision positioning system comprises a road sign device, an image acquisition device and a server; the landmark device comprises a plurality of passive landmarks, and the passive landmarks are arranged at preset positions in a preset space, wherein the passive landmarks comprise a plurality of landmark positions which are used for setting landmark points; the server comprises a first judging module, a second judging module, an optimal passive road sign acquiring module and a robot coordinate acquiring module;
the image acquisition device is configured to acquire an original image of the preset space and transmit the acquired original image to the server;
the first judging module is configured to judge whether the original image received by the server has a passive road sign;
the optimal passive landmark obtaining module is configured to obtain an optimal passive landmark in the original image when the first judging module judges that the passive landmark exists in the original image;
the second judging module is configured to acquire the ID code of the optimal passive landmark acquired by the optimal passive landmark acquiring module, judge whether the ID code of the optimal passive landmark exists in a preset database, and acquire the pixel coordinate of the center of each landmark point when the optimal passive landmark is in a horizontal state; the preset database comprises ID codes of passive road signs, coordinates of the centers of all the mark points of the passive road signs in a horizontal state in a world coordinate system, and coordinates of the centers of all the mark points in a first coordinate system; the first coordinate system is a three-dimensional coordinate system which takes the center of the mark bit positioned at the first row and first column position of the passive road sign as an original point, the straight line of the perpendicular bisector in the horizontal direction of the center of the mark bit positioned at the first row and first column position of the passive road sign as an X coordinate axis, and the straight line of the perpendicular bisector in the vertical direction of the center of the mark bit positioned at the first row and first column position of the passive road sign as a Y coordinate axis in the horizontal state of the passive road sign;
the robot coordinate obtaining module is configured to obtain coordinates of the robot in the world coordinate system according to the ID code of the optimal passive landmark obtained by the second judging module, the pixel coordinates of the center of each landmark point when the optimal passive landmark is in the horizontal state, and the preset database, when the second judging module judges that the ID code of the optimal passive landmark exists in preset data.
Preferably, the flag bits are arrays of A × A, the flag bits are distributed in a grid manner at equal intervals to form a coding block, and the flag bit at the center of the coding block is provided with a flag point, wherein A is an odd number;
the passive road sign further comprises a rectangular strip; the rectangular strip and the coding blocks are arranged side by side, the middle points of the longer opposite sides of the rectangular strip and the centers of the coding blocks are on the same straight line, and the coding blocks are fixedly arranged on the preset sides of the rectangular strip;
the coding block is used for determining the ID number of the passive road sign;
the rectangular bar is used to determine the position of the passive landmark in the original image.
Preferably, the first judging module includes a contour extracting unit, an aspect ratio calculating unit, a position obtaining unit, a light emitting judging unit and an aspect ratio judging unit;
the contour extraction unit is configured to perform binarization processing on the original image received by the server and extract the contour of the image after the binarization processing;
the aspect ratio calculation unit is configured to calculate an aspect ratio of the contour extracted by the contour extraction unit, select a contour meeting a preset first aspect ratio to obtain a candidate rectangular bar contour, and select a contour meeting a preset second aspect ratio to obtain a candidate encoding block contour;
the position obtaining unit is configured to calculate an inclination angle of the candidate rectangular bar outline selected by the aspect ratio calculating unit, find out a perpendicular bisector between a center of the candidate rectangular bar outline and two opposite sides of the candidate rectangular bar outline in a horizontal state, and obtain candidate light emitting positions located on the perpendicular bisector of the candidate rectangular bar outline, wherein the distance between each candidate light emitting position and the center of the candidate rectangular bar is equal to the distance between the center of the rectangular bar in the passive road sign and the center of the coding block;
the light-emitting judging unit is configured to judge whether the candidate light-emitting position acquired by the position acquiring unit only has one light-emitting position;
the aspect ratio judging unit is configured to judge whether the aspect ratio of the outline of the light-emitting position is 1 or not when the light-emitting judging unit judges that only one light-emitting position exists, if so, a passive road sign exists in the original image, and if not, the passive road sign does not exist in the original image.
Preferably, the optimal passive landmark acquisition module comprises a distance calculation unit and an optimal passive landmark selection unit;
the distance calculation unit is configured to calculate the distance from the center of the rectangular bar to the center of the original image when the first judgment module judges that the passive road sign exists in the original image;
the optimal passive landmark selecting unit is configured to select a minimum distance from the distances obtained by the distance calculating unit, and take the passive landmark corresponding to the minimum distance as the optimal passive landmark.
Preferably, the second judging module includes a horizontal rotation unit and an ID code acquiring unit;
the horizontal rotation unit is configured to rotate the optimal passive landmark acquired by the optimal passive landmark acquisition module clockwise β degrees to a horizontal state according to a method shown in the following formula and a second coordinate system:
Figure BDA0001525995360000041
the second coordinate system is a two-dimensional coordinate system which is constructed by taking the center of the rectangular bar as an origin O ', taking the horizontal direction as an X' coordinate axis and taking the vertical direction as a Y 'coordinate axis, wherein β is the clockwise rotation angle of the optimal passive road sign, C is the center of a coding block of the optimal passive road sign, α is a radial O' C which takes the origin O 'as an end point and passes through the center of the coding block of the optimal passive road sign, and forms an included angle with the positive direction of the X' coordinate axis;
the ID code acquisition unit is configured to detect the marking point of the optimal passive landmark in the horizontal state acquired by the horizontal rotation unit, acquire the ID code of the optimal passive landmark, and acquire the pixel coordinates of the center of each marking point when the optimal passive landmark is in the horizontal state.
Preferably, the ID code obtaining unit includes a detecting subunit configured to perform the following operations:
for the optimal passive road sign in the horizontal state acquired by the horizontal rotation unit, starting from the center of a coding block of the optimal passive road sign, searching light-emitting points in the east, south, west and north directions according to grid intervals, and searching light-emitting points in the southeast, northeast, southwest and northwest directions according to preset intervals; defining the positive direction of the Y coordinate axis of the first coordinate system as north;
judging whether the length-width ratio of the outline of the luminous point is 1, if so, recording the number corresponding to the position of the luminous point as 1, and otherwise, recording the number corresponding to the position of the luminous point as 0;
and acquiring the ID code of the optimal passive road sign according to the numbers corresponding to the positions of all the luminous points.
Preferably, the robot coordinate acquiring module comprises a pixel coordinate acquiring unit, a first coordinate system coordinate acquiring unit, a first robot coordinate system coordinate acquiring unit and a robot world coordinate system coordinate acquiring unit;
the pixel coordinate acquisition unit is configured to rotate the pixel coordinates of the centers of the marker points anticlockwise by β degrees when the optimal passive road sign acquired by the ID code acquisition unit is in a horizontal state, so as to acquire the pixel coordinates of the centers of the marker points;
the first coordinate system coordinate obtaining unit is configured to obtain the coordinate of the optimal passive landmark in the first coordinate system according to the preset database and the ID code of the optimal passive landmark obtained by the ID code obtaining unit;
the robot first coordinate system coordinate acquisition unit is configured to acquire coordinates of the first coordinate system relative to the robot through a PnP method according to the pixel coordinates of the centers of the mark points acquired by the pixel coordinate acquisition unit and the coordinates of the optimal passive landmark acquired by the first coordinate system coordinate acquisition unit under the first coordinate system, and acquire the coordinates of the robot under the first coordinate system through direction transformation;
the robot world coordinate system coordinate acquisition unit is configured to acquire coordinates of the robot in a world coordinate system according to the ID code of the optimal passive landmark acquired by the ID code acquisition unit, the coordinates of the robot in the first coordinate system acquired by the robot first coordinate system coordinate acquisition unit, and the preset database.
Preferably, the road marking devices are configured to obtain the number of passive road markings and the distance between the passive road markings according to the length of a preset space, the focal distance of the camera, the length of the target surface size and the vertical distance between the robot and the ceiling, and construct the road marking devices according to the number of passive road markings and the distance between the passive road markings;
obtaining the number of passive signposts in the signpost device according to the following formula:
Figure BDA0001525995360000051
and obtaining the distance between the passive road signs according to the following method:
Figure BDA0001525995360000052
wherein f is a focal length of a camera, WD is a vertical distance between the robot and the road sign device, and SShLength of said target surface dimension, WhThe length of the preset space is n, the number of passive road signs in the road sign device is n, and d is the distance between the passive road signs 11.
Preferably, the optimal passive landmark obtaining module is configured to obtain the original image of the preset space and transmit the obtained original image to the server when the first judging module judges that the passive landmark does not exist in the original image.
Preferably, the robot coordinate acquiring module is configured to acquire an original image of the preset space and transmit the acquired original image to the server, when the second judging module judges that the ID code of the optimal passive landmark does not exist in a preset database.
Compared with the closest prior art, the technical scheme at least has the following beneficial effects:
1. in the indoor robot visual positioning system, by designing a road sign device, an image acquisition device, a server, a first judgment module, a second judgment module, an optimal passive road sign acquisition module and a robot coordinate acquisition module which are contained in the server, a passive road sign closest to an original image in the original image is selected as an optimal road sign to identify an ID code, and the coordinates of the robot in a world coordinate system are finally obtained through conversion between coordinate systems according to the ID code of the passive road sign and information in preset data. The road sign device in the system does not need to be supplied with power independently, is simple to install and low in cost, and in addition, the system overcomes the interference of the surrounding environment on positioning, and has accurate positioning result and strong robustness.
2. In the indoor robot vision positioning system, the passive road sign comprises the rectangular strip and the coding block, the rectangular strip is used for the position of the passive road sign in the original image, the coding block is used for determining the ID number of the passive road sign, and the condition of error identification is avoided by comparing the identified ID number with the ID number of the passive road sign stored in the preset data.
3. In the indoor robot vision positioning system, the mark points of the passive road signs are square, so that when a large number of noise areas are arranged around the passive road signs, the condition of error identification is avoided, and the robustness of the passive road signs to noise is enhanced.
Drawings
FIG. 1 is a schematic diagram of a main framework of an indoor robot vision positioning system according to an embodiment of the present invention;
FIG. 2 is a schematic structural diagram of a passive road sign in an indoor robot vision positioning system according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of an exemplary indoor robot vision positioning system operating environment;
FIG. 4 is a schematic diagram of a first coordinate system according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of the four possible directions of a passive road sign on an original image according to an embodiment of the present invention;
FIG. 6 is a schematic view of the main workflow of an indoor robot vision positioning system according to an embodiment of the present invention;
in the drawings are labeled: the system comprises a 1-road sign device, 11-passive road signs, 111-rectangular bars, 112 coding blocks, 1121 zone bits, 1122-zone points, 2-image acquisition devices, a 3-server, 31-a first judgment module, 32-an optimal passive road sign acquisition module, 33-a second judgment module, 34-a robot coordinate acquisition module and 4-a robot.
Detailed Description
Preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only for explaining the technical principle of the present invention, and are not intended to limit the scope of the present invention.
The following describes an indoor robot vision positioning system in an embodiment of the present invention with reference to the accompanying drawings.
Referring to fig. 1, fig. 1 schematically illustrates a main framework of an indoor robot vision positioning system according to an embodiment of the present invention. As shown in fig. 1, the indoor robot vision positioning system in this embodiment includes: a road sign device 1, an image acquisition device 2 and a server 3; the road sign device 1 comprises a plurality of passive road signs 11, and the plurality of passive road signs 11 are arranged at preset positions in a preset space, wherein the passive road signs 11 comprise a plurality of mark bits 1121, and the mark bits 1121 are used for setting mark points 1122; the server 3 includes a first judging module 31, a second judging module 33, an optimal passive landmark obtaining module 32, and a robot coordinate obtaining module 34.
Specifically, in order to position the robot 4 in the indoor robot vision recognition system, a working environment of the indoor robot vision recognition system is preferably constructed, which mainly includes constructing the road sign device 1 and arranging an infrared light source around the system.
The signpost device 1 comprises a plurality of passive signposts 11, the passive signposts 11 comprise rectangular bars 111 and coding blocks 112, the rectangular bars 111 and the coding blocks 112 are arranged side by side, two middle points of longer opposite sides of the rectangular bars 111 are in the same straight line with the centers of the coding blocks 112, the coding blocks 112 are fixedly arranged on the preset sides of the rectangular bars 111, referring to the attached drawing 2, fig. 2 exemplarily shows the structure of the passive signposts 11 in the indoor robot vision positioning system of the embodiment of the invention, referring to the layout of the rectangular bars 111 and the coding blocks 112 in fig. 2, the coding blocks 112 can be fixedly arranged on the left side or the right side of the rectangular bars 111, the coding blocks 112 are used for determining the ID numbers of the passive signposts 11, the rectangular bars 111 are used for determining the positions of the passive signposts 11 in an original image, the coding blocks 112 are composed of a plurality of marker bits 1121 which are distributed in an equidistant grid, the marker bits 1121 is used for setting the marker points 1121, the marker points 1121 are an array of A × A, the marker points 1122 are arranged on the marker points 1121 on the central positions of the coding blocks 112, wherein A is odd and A is not less than 3, the positioning algorithm, and the marker points 1121
Figure BDA0001525995360000071
And (4) a combination mode.
A preferred embodiment of the present invention will be described with reference to the accompanying drawings.
Referring to fig. 2, fig. 2 schematically illustrates a structure of a passive road sign 11 in an indoor robot vision positioning system according to an embodiment of the present invention, as shown in fig. 2, a coding block 112 is located on the right side of a rectangular bar 111, the rectangular bar 111 is spaced from the center of the coding block 112 by a distance of 2 grids, a flag 1121 in the coding block 112 is a matrix of 3 × 3, the flag 1121 is a square, and a flag point 1122 is coated with an infrared reflective material, fig. 2 is only a case of the passive road sign 11, and images of the passive road sign 11 are different according to the position of the flag point 1122.
In addition, referring to fig. 2, the coding blocks 112 may also be disposed on the left side of the rectangular bar 111, and the flag bits 1121 in the coding blocks 112 may also be a matrix of 5 × 5, a matrix of 7 × 7, a matrix of 9 × 9, and the like.
After the design of the passive road signs 11 is completed, the number of passive road signs 11 required in the working environment and the distance between the passive road signs 11 need to be calculated according to the working environment of the system, so as to construct the road marking device 1.
Specifically, referring to fig. 3, fig. 3 schematically illustrates an operating environment of an indoor robot vision positioning system according to an embodiment of the present invention, and as shown in fig. 3, in the operating environment of an indoor robot vision positioning system according to this embodiment, a road marking device 1 includes a plurality of passive road markings 11 coated with an infrared reflective material and is attached to a ceiling of the operating environment. A visible camera with an 850nm filter was placed on top of the robot 4, taking images vertically upwards. Wherein, the focal length of camera is 4mm, and infrared light source is collocated around in this operational environment. The road marking units 1 are configured to acquire the number of passive road markings 11 and the distance between the passive road markings 11 according to the length or width of a preset space, the focal distance of a camera, the length or width of a target surface size, and the vertical distance of the robot 4 from the ceiling, and to construct road marking units according to the number of passive road markings 11 and the distance between the passive road markings 11. The preset space in this embodiment is a ceiling. The road marking unit 1 is constructed according to the field of view and ensures that at least one passive road marking 11 can be seen at any position. Wherein, taking the length of the preset space and the length of the target surface size as an example, the number of the passive road signs 11 in the road sign device 1 can be obtained according to the following method (1):
Figure BDA0001525995360000081
the distance between the passive road markings 11 in the road marking device 1 can be obtained according to the following method (2):
Figure BDA0001525995360000082
wherein f is the focal length of the camera, WD is the vertical distance from the robot 4 to the road sign device 1, SShLength of target surface size, WhTo preset the length of the space, n is the number of passive road signs 11 in the road sign device 1, and d is the distance between the passive road signs 11.
After the passive road sign 11, the road sign device 1 and the arrangement of the passive road sign device are completed, the following describes the main working process of the indoor robot vision positioning system in the present invention with reference to fig. 1. Fig. 1 schematically shows a main framework of an indoor robot vision positioning system according to an embodiment of the present invention.
The image acquisition device 2 may be configured to acquire an original image of a preset space and transmit the acquired original image to the server 3.
Specifically, the image capturing device 2 in the present embodiment may include the above camera, and the preset space is the working environment of the system.
The first judging module 31 may be configured to judge whether the original image received by the server 3 has the passive road sign 11.
Further, the first determination module 31 in the present embodiment may include an outline extraction unit, an aspect ratio calculation unit, a position acquisition unit, a light emission determination unit, and an aspect ratio determination unit.
The contour extraction unit may be configured to perform binarization processing on the original image received by the server 3 and extract the contour of the binarized image.
The aspect ratio calculation unit may be configured to calculate an aspect ratio of the contour extracted by the contour extraction unit, select a contour satisfying a preset first aspect ratio to obtain a candidate rectangular bar contour, and select a contour satisfying a preset second aspect ratio to obtain a candidate coded block contour.
Specifically, in this embodiment, the preset first aspect ratio is an aspect ratio of a rectangular bar in the passive road sign, and the preset second aspect ratio is an aspect ratio of a coding block in the passive road sign.
The position acquisition unit may be configured to calculate an inclination angle of the candidate rectangular bar outline selected by the aspect ratio calculation unit, and find a perpendicular bisector between a center of the candidate rectangular bar outline and two opposite sides of the candidate rectangular bar outline in the horizontal state, and acquire candidate light-emitting positions located on the perpendicular bisector of the candidate rectangular bar outline, and each candidate light-emitting position is equal to a distance between a center of the rectangular bar in the passive landmark 11 and a center of the coding block.
Specifically, the horizontal state in the present embodiment means that the midperpendicular of the longer opposite side of the rectangular bar 111 is parallel to the horizontal line.
The light emission judging unit may be configured to judge whether or not the candidate light emission position acquired by the position acquiring unit has only one light emission.
Specifically, in the present embodiment, when the light emission judging unit judges that the candidate light emission position acquired by the position acquiring unit does not have only one light emission or no one light emission, the passive road sign 11 does not exist in the original image.
The aspect ratio determination unit may be configured to determine whether an aspect ratio of the outline of the light-emitting position is 1 if the light-emitting determination unit determines that there is only one light-emitting position, if so, the passive road sign 11 exists in the original image, otherwise, the passive road sign 11 does not exist in the original image.
The optimal passive landmark obtaining module 32 may be configured to obtain an optimal passive landmark in the original image if the first determining module 31 determines that the passive landmark 11 exists in the original image.
Further, the optimal passive landmark obtaining module 32 in this embodiment may include a distance calculating unit and an optimal passive landmark selecting unit.
The distance calculation unit may be configured to calculate the distance from the center of the rectangular bar 111 to the center of the original image in a case where the first judgment module 31 judges that the passive road sign 11 exists in the original image.
The optimal passive landmark selecting unit may be configured to select a minimum distance from the distances obtained by the distance calculating unit, and use the passive landmark 11 corresponding to the minimum distance as the optimal passive landmark.
Specifically, in this embodiment, when there are a plurality of passive road signs 11 in the original image, the optimal passive road sign selecting unit selects the passive road sign 11 corresponding to the minimum distance obtained by the distance calculating unit as the optimal passive road sign; when only one passive road sign exists in the original image, the optimal passive road sign selection unit selects the passive road sign as the optimal passive road sign.
Further, in this embodiment, the optimal passive landmark obtaining module 32 may be further configured to obtain an original image of a preset space and transmit the obtained original image to the server 3, in a case that the first judging module 31 judges that the passive landmarks 11 are not present in the original image.
The second determining module 33 may be configured to obtain the ID code of the optimal passive landmark obtained by the optimal passive landmark obtaining module 32, determine whether the ID code of the optimal passive landmark exists in a preset database, and obtain the pixel coordinate of the center of each landmark point when the optimal passive landmark is in a horizontal state; the preset database comprises ID codes of the passive road signs 11, coordinates of the centers of all the mark points of the passive road signs 11 in a horizontal state in a world coordinate system, and coordinates of the centers of all the mark points in a first coordinate system; the first coordinate system is a three-dimensional coordinate system in which, in a horizontal state, the passive road sign 11 uses the center of the mark 1121 located at the first row and first column of the passive road sign 11 as an origin, uses a straight line of a perpendicular bisector in the horizontal direction of the center of the mark 1121 located at the first row and first column of the passive road sign 11 as an X coordinate axis, and uses a straight line of a perpendicular bisector in the vertical direction of the center of the mark 1121 located at the first row and first column of the passive road sign 11 as a Y coordinate axis.
Specifically, the pixel coordinates in this embodiment are specific positions of the centers of the respective marker points in the original image. Referring to fig. 4, fig. 4 schematically illustrates a first coordinate system in an embodiment of the present invention.
Further, the second determination module 33 in the present embodiment includes a horizontal rotation unit and an ID code acquisition unit.
In particular, referring to fig. 5, fig. 5 illustrates schematically the four possible directions of the passive road markings 11 on the original image according to an embodiment of the present invention. The coordinate system in fig. 5 is a second coordinate system, and the second coordinate system is a two-dimensional coordinate system.
The horizontal rotation unit may be configured to rotate the optimal passive landmark acquired by the optimal passive landmark acquisition module 32 clockwise β degrees to a horizontal state according to a method and a second coordinate system shown in the following formula:
Figure BDA0001525995360000111
’
the second coordinate system is a two-dimensional coordinate system which is constructed by taking the center of the rectangular bar 111 as an origin O, taking the horizontal direction as an X ' coordinate axis and taking the vertical direction as a Y ' coordinate axis, β is the angle of clockwise rotation of the optimal passive road sign, C is the center of the coding block of the optimal passive road sign, α is an included angle formed by a ray O ' C which takes the origin O ' as an end point and passes through the center of the coding block of the optimal passive road sign and the positive direction of the X ' coordinate axis.
Specifically, in the present embodiment, as shown in fig. 5(a), the center of the coding block of the optimal passive road sign is located in the first quadrant, as shown in fig. 5(b), the center of the coding block of the optimal passive road sign is located in the fourth quadrant, as shown in fig. 5(C), the center of the coding block of the optimal passive road sign is located in the third quadrant, as shown in fig. 5(d), the center of the coding block of the optimal passive road sign is located in the second quadrant, and the positions of the ray O' C and the included angle α are shown in fig. 5.
The ID code acquiring unit may be configured to detect the landmark point of the optimal passive landmark in the horizontal state acquired by the horizontal rotating unit, acquire the ID code of the optimal passive landmark, and acquire the pixel coordinates of the center of each landmark point when the optimal passive landmark is in the horizontal state.
Further, the ID code acquiring unit in this embodiment may further include a detecting subunit; the detection subunit may be configured to perform the following operations:
for the optimal passive road sign in the horizontal state acquired by the horizontal rotation unit, starting from the center of a coding block of the optimal passive road sign, searching light-emitting points in the east, south, west and north directions according to the grid intervals, and searching light-emitting points in the southeast, northeast, southwest and northwest directions according to preset intervals; the positive direction of the Y coordinate axis of the first coordinate system is defined as north.
Specifically, the predetermined distance in this embodiment is
Figure BDA0001525995360000121
Multiple grid spacing.
And judging whether the length-width ratio of the outline of the luminous point is 1, if so, recording the number corresponding to the position of the luminous point as 1, and otherwise, recording the number corresponding to the position of the luminous point as 0.
Specifically, the order of the detection mark point 1122 in this embodiment is identical to the order of the number records corresponding to the position of the light emitting point. If the flag 1121 of the passive road sign 11 is square, the aspect ratio of the contour of the flag is 1, so that it is required to detect whether the contour of the light emitting point meets the aspect ratio of the flag 1121. Referring to fig. 2, the ID code 110111010 of the passive landmark 11 of fig. 2 may be derived according to the above-described operation. In order to prevent the misrecognition phenomenon, the ID code of the detected optimal passive landmark may be compared with the ID code in the preset database, and when the detected ID code of the optimal passive landmark is inconsistent with the ID code in the preset database, the original image in the original preset space is obtained again, and the original image is transmitted to the server 3.
And acquiring the ID code of the optimal passive road sign according to the numbers corresponding to the positions of all the luminous points.
The robot coordinate obtaining module 34 may be configured to, when the second determining module 33 determines that the ID code of the optimal passive landmark exists in the preset data, obtain the coordinate of the robot 4 in the world coordinate system according to the ID code of the optimal passive landmark obtained by the second determining module 33, the pixel coordinate of each landmark center when the optimal passive landmark is in the horizontal state, and the preset database.
Further, the robot coordinate acquisition module 34 in the present embodiment includes a pixel coordinate acquisition unit, a first coordinate system coordinate acquisition unit, a robot first coordinate system coordinate acquisition unit, and a robot world coordinate system coordinate acquisition unit.
The pixel coordinate acquiring unit may be configured to rotate the pixel coordinate of the center of each landmark point counterclockwise by β degrees when the optimal passive landmark acquired by the ID code acquiring unit is in the horizontal state, and acquire the pixel coordinate of the center of each landmark point.
The first coordinate system coordinate obtaining unit may be configured to obtain coordinates of the optimal passive landmark in the first coordinate system according to the preset database and the ID code of the optimal passive landmark obtained by the ID code obtaining unit.
Specifically, in this embodiment, the first coordinate system coordinate obtaining unit may be configured to obtain the coordinates of the optimal passive landmark under the first coordinate system according to the coordinates of the centers of the landmark points in the preset data under the first coordinate system and the ID code of the optimal passive landmark obtained by the ID code obtaining unit.
With continued reference to fig. 4, when the grid interval is d, the coordinates of the centers of the marker points of the passive marker 11 shown in fig. 4 are (0, 0, 0), (d, 0, 0), (0, -d, 0), (d, -d, 0), (2d, -d, 0), (d, -2d, 0), respectively, in the order from left to right and from top to bottom.
The robot first coordinate system coordinate obtaining unit may be configured to obtain coordinates of the first coordinate system relative to the robot 4 by a PnP method according to the pixel coordinates of the centers of the marker points obtained by the pixel coordinate obtaining unit and the coordinates of the optimal passive landmark under the first coordinate system obtained by the first coordinate system coordinate obtaining unit, and obtain the coordinates of the robot 4 under the first coordinate system by direction transformation.
The robot world coordinate system coordinate obtaining unit may be configured to obtain the coordinates of the robot 4 in the world coordinate system according to the ID code of the optimal passive landmark obtained by the ID code obtaining unit, the coordinates of the robot 4 in the first coordinate system obtained by the robot first coordinate system coordinate obtaining unit, and the preset database.
Specifically, in the embodiment, the coordinate obtaining unit of the world coordinate system of the robot is specifically based on coordinates of centers of each landmark point of the passive landmark 11 in a horizontal state in the world coordinate system in the preset data.
Further, the robot coordinate acquiring module 34 in the present embodiment may be configured to acquire an original image of a preset space and transmit the acquired original image to the server 3 in a case where the second judging module 33 judges that the ID code of the optimal passive landmark does not exist in the preset database.
The working process of the indoor robot vision positioning system is specifically described below with reference to the accompanying drawings.
Referring to fig. 6, fig. 6 schematically illustrates a main workflow of the indoor robot vision positioning system. The working flow of the indoor robot vision positioning system shown in fig. 6 mainly includes step S100, step S200, step S300, step S400 and step S500.
In step S100, the original image is acquired by the image acquisition device 2 and transmitted to the server 3.
In step S200, the first determining module 31 is used to determine whether the passive road sign 11 exists in the original image.
Specifically, in this embodiment, when the first determining module 31 determines that the passive road sign 11 exists in the original image, step S300 is executed, and when the passive road sign 11 does not exist in the original image, step S100 is executed.
In step S300, the optimal passive landmark obtaining module 32 obtains an optimal passive landmark.
In step S400, the second determining module 33 is used to obtain the pixel coordinates of the center of each landmark point when the optimal passive landmark is in the horizontal state, obtain the ID code of the optimal passive landmark, and determine whether the ID code exists in the preset database.
Specifically, in the present embodiment, when the ID code of the optimal passive landmark exists in the preset data, the robot coordinate acquiring module 34 is used to acquire the coordinates of the robot in the world coordinate system, otherwise, step S100 is performed.
In step S500, the coordinates of the robot in the world coordinate system are acquired by the robot coordinate acquisition module 34.
Those skilled in the art will appreciate that the above-described indoor robot visual positioning system also includes some other well-known structures, such as processors, controllers, memories, etc., wherein the memories include, but are not limited to, random access memory, flash memory, read only memory, programmable read only memory, volatile memory, non-volatile memory, serial memory, parallel memory or registers, etc., and the processors include, but are not limited to, CPLD/FPGA, DSP, ARM processor, MIPS processor, etc., and these well-known structures are not shown in order to unnecessarily obscure embodiments of the present disclosure.
Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
The various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functionality of some or all of the components in a server, client, or the like, according to embodiments of the present invention. The present invention may also be embodied as an apparatus or device program (e.g., PC program and PC program product) for carrying out a portion or all of the methods described herein. Such a program implementing the invention may be stored on a PC readable medium or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.
Furthermore, those skilled in the art will appreciate that while some embodiments described herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the claims of the present invention, any of the claimed embodiments may be used in any combination.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed PC. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.
So far, the technical solutions of the present invention have been described in connection with the preferred embodiments shown in the drawings, but it is easily understood by those skilled in the art that the scope of the present invention is obviously not limited to these specific embodiments. Equivalent changes or substitutions of related technical features can be made by those skilled in the art without departing from the principle of the invention, and the technical scheme after the changes or substitutions can fall into the protection scope of the invention.

Claims (9)

1. An indoor robot vision positioning system is characterized by comprising a road sign device, an image acquisition device and a server; the landmark device comprises a plurality of passive landmarks, and the passive landmarks are arranged at preset positions in a preset space, wherein the passive landmarks comprise a plurality of landmark positions which are used for setting landmark points; the server comprises a first judging module, a second judging module, an optimal passive road sign acquiring module and a robot coordinate acquiring module;
the image acquisition device is configured to acquire an original image of the preset space and transmit the acquired original image to the server;
the first judging module is configured to judge whether the original image received by the server has a passive road sign;
the optimal passive landmark obtaining module is configured to obtain an optimal passive landmark in the original image when the first judging module judges that the passive landmark exists in the original image;
the second judging module is configured to acquire the ID code of the optimal passive landmark acquired by the optimal passive landmark acquiring module, judge whether the ID code of the optimal passive landmark exists in a preset database, and acquire the pixel coordinate of the center of each landmark point when the optimal passive landmark is in a horizontal state; the preset database comprises ID codes of passive road signs, coordinates of the centers of all the mark points of the passive road signs in a horizontal state in a world coordinate system, and coordinates of the centers of all the mark points in a first coordinate system; the first coordinate system is a three-dimensional coordinate system which takes the center of the mark bit positioned at the first row and first column position of the passive road sign as an original point, the straight line of the perpendicular bisector in the horizontal direction of the center of the mark bit positioned at the first row and first column position of the passive road sign as an X coordinate axis, and the straight line of the perpendicular bisector in the vertical direction of the center of the mark bit positioned at the first row and first column position of the passive road sign as a Y coordinate axis in the horizontal state of the passive road sign;
the robot coordinate acquiring module is configured to acquire coordinates of the robot in the world coordinate system according to the ID code of the optimal passive landmark acquired by the second judging module, the pixel coordinates of the center of each landmark point when the optimal passive landmark is in the horizontal state, and the preset database, when the second judging module judges that the ID code of the optimal passive landmark exists in preset data;
the plurality of flag bits are arrays of A × A, the flag bits are distributed in a grid mode at equal intervals to form a coding block, the flag bit located at the center of the coding block is provided with a flag point, and the flag bits are squares, wherein A is an odd number;
the passive road sign further comprises a rectangular strip; the rectangular strip and the coding blocks are arranged side by side, the middle points of the longer opposite sides of the rectangular strip and the centers of the coding blocks are on the same straight line, and the coding blocks are fixedly arranged on the preset sides of the rectangular strip;
the coding block is used for determining the ID number of the passive road sign;
the rectangular bar is used to determine the position of the passive landmark in the original image.
2. The indoor robot vision positioning system of claim 1, wherein the first determination module comprises a contour extraction unit, an aspect ratio calculation unit, a position acquisition unit, a light emission determination unit, and an aspect ratio determination unit;
the contour extraction unit is configured to perform binarization processing on the original image received by the server and extract the contour of the image after the binarization processing;
the aspect ratio calculation unit is configured to calculate an aspect ratio of the contour extracted by the contour extraction unit, select a contour meeting a preset first aspect ratio to obtain a candidate rectangular bar contour, and select a contour meeting a preset second aspect ratio to obtain a candidate encoding block contour;
the position obtaining unit is configured to calculate an inclination angle of the candidate rectangular bar outline selected by the aspect ratio calculating unit, find out a perpendicular bisector between a center of the candidate rectangular bar outline and two opposite sides of the candidate rectangular bar outline in a horizontal state, and obtain candidate light emitting positions located on the perpendicular bisector of the candidate rectangular bar outline, wherein the distance between each candidate light emitting position and the center of the candidate rectangular bar is equal to the distance between the center of the rectangular bar in the passive road sign and the center of the coding block;
the light-emitting judging unit is configured to judge whether the candidate light-emitting position acquired by the position acquiring unit only has one light-emitting position;
the aspect ratio judging unit is configured to judge whether the aspect ratio of the outline of the light-emitting position is 1 or not when the light-emitting judging unit judges that only one light-emitting position exists, if so, a passive road sign exists in the original image, and if not, the passive road sign does not exist in the original image.
3. The indoor robot vision positioning system of claim 1, wherein the optimal passive landmark acquisition module comprises a distance calculation unit and an optimal passive landmark selection unit;
the distance calculation unit is configured to calculate the distance from the center of the rectangular bar to the center of the original image when the first judgment module judges that the passive road sign exists in the original image;
the optimal passive landmark selecting unit is configured to select a minimum distance from the distances obtained by the distance calculating unit, and take the passive landmark corresponding to the minimum distance as the optimal passive landmark.
4. The indoor robot vision positioning system of claim 1, wherein the second determination module comprises a horizontal rotation unit and an ID code acquisition unit;
the horizontal rotation unit is configured to rotate the optimal passive landmark acquired by the optimal passive landmark acquisition module clockwise β degrees to a horizontal state according to a method shown in the following formula and a second coordinate system:
Figure FDA0002478856040000031
the second coordinate system is a two-dimensional coordinate system which is constructed by taking the center of the rectangular bar as an origin O ', taking the horizontal direction as an X' coordinate axis and taking the vertical direction as a Y 'coordinate axis, wherein β is the clockwise rotation angle of the optimal passive road sign, C is the center of a coding block of the optimal passive road sign, α is a radial O' C which takes the origin O 'as an end point and passes through the center of the coding block of the optimal passive road sign, and forms an included angle with the positive direction of the X' coordinate axis;
the ID code acquisition unit is configured to detect the marking point of the optimal passive landmark in the horizontal state acquired by the horizontal rotation unit, acquire the ID code of the optimal passive landmark, and acquire the pixel coordinates of the center of each marking point when the optimal passive landmark is in the horizontal state.
5. The indoor robot visual positioning system of claim 4, wherein the ID code acquisition unit comprises a detection subunit configured to:
for the optimal passive road sign in the horizontal state acquired by the horizontal rotation unit, starting from the center of a coding block of the optimal passive road sign, searching light-emitting points in the east, south, west and north directions according to grid intervals, and searching light-emitting points in the southeast, northeast, southwest and northwest directions according to preset intervals; defining the positive direction of the Y coordinate axis of the first coordinate system as north;
judging whether the length-width ratio of the outline of the luminous point is 1, if so, recording the number corresponding to the position of the luminous point as 1, and otherwise, recording the number corresponding to the position of the luminous point as 0;
and acquiring the ID code of the optimal passive road sign according to the numbers corresponding to the positions of all the luminous points.
6. The indoor robot visual positioning system of claim 4, wherein the robot coordinate acquisition module comprises a pixel coordinate acquisition unit, a first coordinate system coordinate acquisition unit, a robot first coordinate system coordinate acquisition unit, and a robot world coordinate system coordinate acquisition unit;
the pixel coordinate acquisition unit is configured to rotate the pixel coordinates of the centers of the marker points anticlockwise by β degrees when the optimal passive road sign acquired by the ID code acquisition unit is in a horizontal state, so as to acquire the pixel coordinates of the centers of the marker points;
the first coordinate system coordinate obtaining unit is configured to obtain the coordinate of the optimal passive landmark in the first coordinate system according to the preset database and the ID code of the optimal passive landmark obtained by the ID code obtaining unit;
the robot first coordinate system coordinate acquisition unit is configured to acquire coordinates of the first coordinate system relative to the robot through a PnP method according to the pixel coordinates of the centers of the mark points acquired by the pixel coordinate acquisition unit and the coordinates of the optimal passive landmark acquired by the first coordinate system coordinate acquisition unit under the first coordinate system, and acquire the coordinates of the robot under the first coordinate system through direction transformation;
the robot world coordinate system coordinate acquisition unit is configured to acquire coordinates of the robot in a world coordinate system according to the ID code of the optimal passive landmark acquired by the ID code acquisition unit, the coordinates of the robot in the first coordinate system acquired by the robot first coordinate system coordinate acquisition unit, and the preset database.
7. The indoor robot vision positioning system of claim 1, wherein the road marking devices are configured to obtain the number of passive road markings and the distance between the passive road markings according to the length of a preset space, the focal distance of the camera, the length of the target surface size and the vertical distance of the robot from the ceiling, and to construct road marking devices according to the number of passive road markings and the distance between the passive road markings;
acquiring the number of passive road signs in the road sign device according to the following method:
Figure FDA0002478856040000041
and obtaining the distance between the passive road signs according to the following method:
Figure FDA0002478856040000042
wherein f is a focal length of a camera, WD is a vertical distance between the robot and the road sign device, and SShLength of said target surface dimension, WhAnd the length of the preset space is n, the number of the passive road signs in the road sign device is n, and the distance between the passive road signs is d.
8. The indoor robot vision positioning system of any one of claims 1 to 7, wherein the optimal passive landmark obtaining module is configured to obtain an original image of the preset space and transmit the obtained original image to the server if the first determining module determines that no passive landmarks exist in the original image.
9. The indoor robot vision positioning system of any one of claims 1 to 7, wherein the robot coordinate acquiring module is configured to acquire an original image of the preset space and transmit the acquired original image to the server, in a case where the second judging module judges that the ID code of the optimal passive landmark does not exist in a preset database.
CN201711437012.0A 2017-12-26 2017-12-26 Indoor robot vision positioning system Active CN108195381B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201711437012.0A CN108195381B (en) 2017-12-26 2017-12-26 Indoor robot vision positioning system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201711437012.0A CN108195381B (en) 2017-12-26 2017-12-26 Indoor robot vision positioning system

Publications (2)

Publication Number Publication Date
CN108195381A CN108195381A (en) 2018-06-22
CN108195381B true CN108195381B (en) 2020-06-30

Family

ID=62584466

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201711437012.0A Active CN108195381B (en) 2017-12-26 2017-12-26 Indoor robot vision positioning system

Country Status (1)

Country Link
CN (1) CN108195381B (en)

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110244263B (en) * 2019-06-06 2021-05-18 华中科技大学 Robot passive positioning method, system and equipment
CN112013858B (en) * 2020-10-16 2021-07-02 北京猎户星空科技有限公司 Positioning method, positioning device, self-moving equipment and storage medium
CN112265463B (en) * 2020-10-16 2022-07-26 北京猎户星空科技有限公司 Control method and device of self-moving equipment, self-moving equipment and medium
CN112013850B (en) * 2020-10-16 2021-11-19 北京猎户星空科技有限公司 Positioning method, positioning device, self-moving equipment and storage medium
CN113095103A (en) * 2021-04-15 2021-07-09 京东数科海益信息科技有限公司 Intelligent equipment positioning method, device, equipment and storage medium
CN113219972A (en) * 2021-05-08 2021-08-06 西安达升科技股份有限公司 Method and device for accurately positioning AGV (automatic guided vehicle) and storage medium
CN114234979B (en) * 2021-12-16 2024-04-26 上海擎朗智能科技有限公司 Robot indoor positioning method and device, medium and electronic equipment
CN115810117B (en) * 2022-12-19 2023-06-23 广东建石科技有限公司 Robot brick laying condition detection method and device, electronic equipment and storage medium

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR100698535B1 (en) * 2005-11-04 2007-03-22 재단법인 포항산업과학연구원 Position recognition device and method of mobile robot with tilt correction function
CN102135429A (en) * 2010-12-29 2011-07-27 东南大学 Robot indoor positioning and navigating method based on vision
CN102773862A (en) * 2012-07-31 2012-11-14 山东大学 Quick and accurate locating system used for indoor mobile robot and working method thereof
CN103824298A (en) * 2014-03-10 2014-05-28 北京理工大学 Intelligent body visual and three-dimensional positioning method based on double cameras and intelligent body visual and three-dimensional positioning device based on double cameras
CN104236540A (en) * 2014-06-24 2014-12-24 上海大学 Indoor passive navigation and positioning system and indoor passive navigation and positioning method
CN106526580A (en) * 2016-10-26 2017-03-22 哈工大机器人集团上海有限公司 Road sign, apparatus, and method for determining robot position

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR100698535B1 (en) * 2005-11-04 2007-03-22 재단법인 포항산업과학연구원 Position recognition device and method of mobile robot with tilt correction function
CN102135429A (en) * 2010-12-29 2011-07-27 东南大学 Robot indoor positioning and navigating method based on vision
CN102773862A (en) * 2012-07-31 2012-11-14 山东大学 Quick and accurate locating system used for indoor mobile robot and working method thereof
CN103824298A (en) * 2014-03-10 2014-05-28 北京理工大学 Intelligent body visual and three-dimensional positioning method based on double cameras and intelligent body visual and three-dimensional positioning device based on double cameras
CN104236540A (en) * 2014-06-24 2014-12-24 上海大学 Indoor passive navigation and positioning system and indoor passive navigation and positioning method
CN106526580A (en) * 2016-10-26 2017-03-22 哈工大机器人集团上海有限公司 Road sign, apparatus, and method for determining robot position

Also Published As

Publication number Publication date
CN108195381A (en) 2018-06-22

Similar Documents

Publication Publication Date Title
CN108195381B (en) Indoor robot vision positioning system
JP7165484B2 (en) High precision calibration system and method
ES2708274T3 (en) System and approach method of stadium lighting
CN101821580B (en) System and method for the three-dimensional measurement of shape of material objects
US8224024B2 (en) Tracking objects with markers
Robertson et al. An Image-Based System for Urban Navigation.
US7650013B2 (en) System and method for map and position-determination enhancement
ES2313036T3 (en) PROCEDURE AND SYSTEM FOR THE RECONSTRUCTION OF THE THREE-DIMENSIONAL SURFACE OF AN OBJECT.
JP6667065B2 (en) Position estimation device and position estimation method
Krajník et al. External localization system for mobile robotics
JP6910511B2 (en) Laser measurement method, laser measurement sign, and coordinate calculation program
CN112240205B (en) System for controlling a mining machine, method and medium for navigating by a mining vehicle
CN112492292B (en) Intelligent visual 3D information acquisition equipment of free gesture
US8548221B2 (en) Microbead automatic recognition method and microbead
CN110763204A (en) Planar coding target and pose measurement method thereof
CN113984039A (en) Method, device and system for correcting motion trail and storage medium
Sadeghi et al. 2DTriPnP: A robust two-dimensional method for fine visual localization using Google streetview database
CN106526580A (en) Road sign, apparatus, and method for determining robot position
CN109737962B (en) Machine vision autonomous positioning method and system based on special circular ring coding
CN112254638B (en) Intelligent visual 3D information acquisition equipment that every single move was adjusted
CN112074706A (en) Accurate positioning system
US10796183B2 (en) Fiducial marker, method for forming the fiducial marker, and system for sensing thereof
JP4918830B2 (en) Position measurement system
CN112254677B (en) Multi-position combined 3D acquisition system and method based on handheld device
CN111179347B (en) Positioning method, positioning equipment and storage medium based on regional characteristics

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