CN106651990B - Indoor map construction method and indoor positioning method based on indoor map - Google Patents
Indoor map construction method and indoor positioning method based on indoor map Download PDFInfo
- Publication number
- CN106651990B CN106651990B CN201611208814.XA CN201611208814A CN106651990B CN 106651990 B CN106651990 B CN 106651990B CN 201611208814 A CN201611208814 A CN 201611208814A CN 106651990 B CN106651990 B CN 106651990B
- Authority
- CN
- China
- Prior art keywords
- road
- distance
- coordinate system
- image
- camera
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/20—Drawing from basic elements, e.g. lines or circles
- G06T11/206—Drawing of charts or graphs
-
- 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
Abstract
The invention is suitable for the technical field of visual positioning, and provides an indoor map construction method and an indoor positioning method based on an indoor map, wherein the indoor positioning method comprises the following steps: extracting a road sign in the current shot image, and judging whether the road sign is a known road sign or not; if the judgment result is yes, calculating the vertical distance from the camera to the ceiling according to the distance of the road mark points in the road marks on the image and the actual distance between the road mark points; calculating a second affine transformation matrix according to the vertical distance, the internal reference matrix, the coordinates of the landmark points in the image and the plane coordinates in the map coordinate system; and calculating plane coordinates of the center of the camera in the map coordinate system according to the rotation matrix and the translation vector of the camera in the affine change matrix II relative to the map coordinate system. According to the technical scheme, the position of the center of the camera can be calculated according to the road sign images shot by the camera, and the positioning method is simple to operate and relatively low in cost.
Description
Technical Field
The invention belongs to the technical field of visual positioning, and particularly relates to an indoor map construction method and an indoor positioning method based on an indoor map.
Background
In recent years, many researchers at home and abroad use various sensors and methods to deeply research the positioning of a mobile robot, and the sensors commonly used for the mobile robot include a camera, a laser radar, ultrasonic waves, infrared rays, a gyroscope, a speed or an accelerometer, and the like. Among them, the precision of ultrasonic wave and infrared ray is poor, and they are generally only used for emergency obstacle avoidance. The laser radar has high cost, and is not beneficial to the wide-range popularization and promotion of the mobile robot. Gyroscopes, compasses, velocities or accelerometers, etc. are generally used only as auxiliary sensors. Compared with other sensors, the camera can provide the most abundant information, and the hardware cost and the positioning precision of the camera are low. In indoor positioning, a vision-based positioning method is widely used.
The vision-based indoor positioning method firstly constructs an accurate indoor map for calculating the camera attitude under an absolute coordinate system and planning the moving path of the robot. The map can be constructed by utilizing environmental landmarks or artificial road signs, but the method based on the environmental landmarks has better universality, does not need to manually lay additional signs, but has complex calculation and poorer practicability, most of the existing methods based on the artificial road signs realize indoor positioning through a perspective projection matrix, before positioning, a two-axis inclinometer is required to be arranged on a sensor to calculate the inclination angles on two axes, and then the error between the two-axis inclinometer and a camera plane is required to be calibrated, therefore, the indoor positioning realized through the perspective projection matrix not only has complex operation, but also has relatively higher cost.
Disclosure of Invention
The embodiment of the invention provides an indoor positioning method based on an indoor map, and aims to solve the problems that the indoor positioning is realized through a perspective projection matrix, the operation is complex, and the cost is relatively high.
The invention is realized in such a way that an indoor map construction method comprises the following steps:
s1, extracting road signs in a current shot image, wherein the road signs comprise known road signs and unknown road signs;
s2, calculating a vertical distance H from the camera to a ceiling according to the distance of the road mark points in the known road marks or the unknown road marks on the image and the actual distance between the road mark points;
s3, according to the vertical distance H between the camera and the ceiling and the internal reference matrix MatcamAnd pixel locations of waypoints of known landmarksCalculating a first affine transformation matrix according to the homogeneous coordinate of the target and the homogeneous coordinate of the world coordinate in a map coordinate system;
s4, calculating the coordinates of the road sign points of the unknown road signs in a map coordinate system according to the affine transformation matrix I and the pixel coordinates of the road sign points of the unknown road signs;
the known landmark is a landmark which is already included in a map coordinate system, and the unknown landmark is a landmark which is not included in the map coordinate system.
The embodiment of the invention provides another indoor positioning method based on an indoor map, which comprises the following steps:
s5, extracting a road sign in the current shot image, and judging whether the road sign is a known road sign or not;
s6, if the judgment result is yes, calculating the vertical distance H from the camera to the ceiling according to the distance of the road mark points in the road marks on the image and the actual distance between the road mark points;
s7, according to the vertical distance H and the internal reference matrix MatcamCalculating a second affine transformation matrix according to the coordinates of the road mark points in the image and the plane coordinates in the map coordinate system;
s8, according to a rotation matrix Mat of the camera in the affine change matrix II relative to the map coordinate systemrotatAnd translation vector MattCalculating the plane coordinate X of the camera center in the map coordinate systemcam。
The embodiment of the invention realizes indoor positioning based on the constructed indoor map, calculates the vertical distance H from the camera to the ceiling according to the distance of the landmark point in the first landmark on the image and the actual distance between the landmark points by extracting the landmarks in the image, and further determines the position of the center of the camera in the map coordinate system by using the affine transformation matrix.
Drawings
Fig. 1 is a flowchart of an indoor map construction method according to an embodiment of the present invention;
fig. 2 is a flowchart of an indoor positioning method based on an indoor map according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Fig. 1 is a flowchart of an indoor map construction method according to an embodiment of the present invention, where the method includes the following steps:
s1, extracting road signs in a current shot image, wherein the road signs comprise known road signs and unknown road signs;
in the embodiment of the invention, a map coordinate system refers to that all indoor road sign systems are incorporated into a uniform coordinate system, which is called as a map coordinate system, known road signs refer to road signs incorporated into the map coordinate system, unknown road signs refer to road signs not incorporated into the map coordinate system, the road signs in the embodiment of the invention refer to dot matrix infrared road signs, the road sign points are arranged according to a predetermined rule, the road signs are attached to an indoor ceiling, the size of the road signs changes according to the distance from a camera to the ceiling, and because the visual angle of a camera is limited and cannot cover the whole ceiling, a plurality of road sign labels are required to be arranged to carry out relay positioning, so that in order to identify and distinguish different road signs, different distributed road sign points are mapped into a unique ID number, and the road signs are identified and distinguished through the ID numbers.
In the embodiment of the present invention, the method for extracting the road sign in the current shot image specifically includes the following steps:
s11, carrying out distortion correction on the shot image according to the calibrated camera distortion parameters;
in the embodiment of the invention, the camera needs to be calibrated before use to obtain the distortion parameter of the camera, and the distortion correction is carried out on the acquired image according to the distortion parameter, so that the point location extraction precision is improved.
S12, calculating the average gray value of the image after the distortion correction
To be provided with
As a threshold value for binarization, the image is binarized.
In the embodiment of the invention, the image after distortion correction is subjected to gray processing, and the average gray value is calculated
Since the average value is generally small and the noise is much during the binarization, the average gray value is used
Multiplying by a coefficient k (k > 1) as a threshold value, and carrying out binarization on the image to reduce the occurrence of noise points.
And S13, extracting the landmark points by using the shape of the pixel points and the distance constraint between the pixel points.
In the embodiment of the present invention, the step of extracting the landmark points by using the shape of the pixel points and the distance constraint between the pixel points specifically includes:
s131, carrying out ellipse fitting on the white pixel block in the binarized image;
s132, acquiring that the area of the ellipse is smaller than an area threshold value, and the ratio of the long axis to the short axis of the fitting ellipse is located in the center of the ellipse in a set interval;
in the embodiment of the invention, a plurality of pixel blocks exist in the binarized image, ellipse fitting is carried out on the pixel blocks, if the ellipse area after fitting is larger than the area threshold value, the pixel block is noise, and the pixel block needs to be discarded; the area threshold is set according to the resolution of the camera, the intensity of the light source, the angle of field of the lens, and the like, and the ratio of the minor axis to the major axis of the ellipse after fitting is in a set section, and the range of the section is greater than 0.5 and smaller than 1.
S133, calculating the number n (n is a positive integer) of the central points of the ellipses with the mutual distances smaller than the distance threshold, wherein when the number n is more than 3 and less than m2(m is more than or equal to 3), the mutual distance is less thanAnd taking the central point of the ellipse of the distance threshold as a landmark point of the landmark.
In the embodiment of the invention, the number n of points with mutual distances smaller than a distance threshold in the ellipse is larger than 3, at least 3 points are used for positioning the coordinate system, and the number n is smaller than m2And (m is more than or equal to 3) the landmark points need to meet the requirement of a rotational asymmetric structure, and are convenient to identify and position. The infrared road signs are illustrated in a 3 × 3 dot matrix form, and the numerical range of the number n is 3 < n < 9.
In the embodiment of the present invention, the map coordinate system is specified as a landmark coordinate system corresponding to a first landmark, and the step of establishing the landmark coordinate system specifically includes:
acquiring two landmark points A, B farthest from each other in the landmarks and a landmark point O farthest from the straight line AB;
judging whether an included angle between the lines OA and OB is located in an included angle designated area;
if the judgment result is yes, the landmark point A, B is used as a point on the coordinate axis, and O is used as a coordinate origin to establish a landmark coordinate system, and if the judgment result is no, the image corresponding to the landmark is discarded.
In the embodiment of the present invention, the designated interval of the included angle is generally 85 to 95 degrees. The infrared road sign is usually in a 3 x 3 lattice type and a 4 x 4 lattice type, two end points A, B of a diagonal line are taken as points on coordinate axes, the other end point O of the other diagonal line is taken as an origin, an OAB rectangular coordinate system is formed, an included angle between an OA axis and an OB axis is generally 90 degrees, the image inclination can be obtained according to the included angle between the two coordinate axes of the road sign coordinate system, the image inclination is overlarge, a large positioning error can be caused, the image needs to be discarded, the inclination degree of the image can be obtained by calculating the included angle between the two coordinate axes, the inclination degree of the camera can be obtained through the inclination degree of the image as the camera is approximately parallel to a ceiling, and the inclination angle of the camera is measured without an additional inclination angle sensor.
S2, calculating a vertical distance H from the camera to a ceiling according to the distance of the road mark points in the known road marks or the unknown road marks on the image and the actual distance between the road mark points;
in the embodiment of the present invention, the vertical distance from the camera to the ceiling may be calculated by using landmark points in the known landmark or the unknown landmark, the actual distance between the landmark points is already set when the landmark is disposed on the ceiling, and the distance of the known landmark or the unknown landmark on the image may be obtained according to the landmark extracted in step S1.
In this embodiment of the present invention, step S2 specifically includes:
s21, optionally selecting two landmark points M in the known landmark or the unknown landmark in the current image1、M2；
S22, matching the internal reference matrix MatcamInverse matrix of
Multiplying by the waypoint M1、M2Corresponding image point m1、m2Homogeneous coordinate of
Namely, it is
Obtaining coordinates ui1、ui2；
In the embodiment of the invention, the camera needs to be calibrated before use to obtain the internal reference matrix of the camera, wherein the internal reference matrix refers to the transformation parameters from the camera coordinate system to the image plane coordinate system.
S23, according to the coordinate ui1、ui2A distance S betweeniAnd a road marking point M1、M2Actual distance S betweenWCalculating the distance from the camera to the ceiling as
S3, according to the vertical distance H between the camera and the ceiling and the internal reference matrix MatcamCalculating a first affine transformation matrix according to the homogeneous coordinate of the pixel coordinates of the road mark points of the known road marks and the homogeneous coordinate of the world coordinates in a map coordinate system;
in the embodiment of the invention, the formula is used
Homogeneous coordinates, which are the pixel coordinates of known landmark points, H is the distance from the ceiling to the camera,
which is the inverse of the camera's internal reference matrix, u1 is also a homogeneous coordinate,
the homogeneous coordinate of the world coordinate of the known landmark point in the map coordinate system is calculated according to a formula
Can obtain an affine transformation matrix one
And S4, calculating the coordinates of the road sign points of the unknown road signs in a map coordinate system according to the affine transformation matrix I and the pixel coordinates of the road sign points of the unknown road signs.
In the embodiment of the invention, the formula is used
Can calculate XwIs the coordinate of the unknown road mark point in the map coordinate system, u is the pixel coordinate of the unknown road mark point, McamThe camera internal parameter s is a photographing depth factor (namely the distance H from the camera to the ceiling),
Is an affine transformation matrix.
According to the embodiment of the invention, the known road signs and the unknown road signs in the shot images are extracted, the vertical distance H from the camera to the ceiling is calculated according to the distance of the road sign points in the known road signs or the unknown road signs on the images and the actual distance between the road sign points, and then the coordinates of the road sign points of the unknown road signs in a map coordinate system are calculated through an affine transformation matrix I, so that the construction of an indoor map is realized, and the indoor map is provided for realizing indoor positioning.
The indoor positioning method in the embodiment of the invention is based on the indoor map constructed by the indoor map construction method for positioning, so the indoor positioning method further comprises the construction of the indoor map before the indoor positioning is carried out, and the construction method of the indoor map is as described above.
Fig. 2 is a flowchart of an indoor positioning method based on indoor map provided by an embodiment of the present invention, the method includes the following steps:
s5, extracting a road sign in the shot image, and judging whether the road sign is a known road sign or not;
in the embodiment of the present invention, when the photographed landmark is used for indoor positioning, a known landmark needs to exist in the current image, and in order to prevent the landmark from not being included in the map coordinate system when an indoor map is constructed and thus indoor positioning cannot be performed, the ID of the landmark in the photographed image is obtained, whether the ID of the landmark in the photographed image and the ID number of the landmark included in the map coordinate system are detected is detected, if the detection result is yes, step S6 is executed, and if the detection result is no, the photographed image corresponding to the landmark is discarded.
S6, if the judgment result is yes, calculating the vertical distance H from the camera to the ceiling according to the distance of the road mark points in the road marks on the image and the actual distance between the road mark points;
in the embodiment of the present invention, the actual distance between the landmark points is already set when the landmark is disposed on the ceiling, and the distance of the landmark on the image can be obtained based on the landmark extracted in step S5.
In this embodiment of the present invention, step S6 specifically includes:
s61, selecting two optional road mark points M in the current image1、M2；
S62, matching the internal reference matrix MatcamInverse matrix of
Multiplying by the waypoint M1、M2Corresponding image point m1、m2Homogeneous coordinate of
Namely, it is
Obtaining coordinates ui1、ui2；
S63, according to the coordinate ui1、ui2A distance S betweeniAnd a road marking point M1、M2Actual distance S betweenWCalculating the distance from the camera to the ceiling as
S7, according to the vertical distance H and the internal reference matrix MatcamCalculating a second affine transformation matrix according to the coordinates of the road mark points in the image and the plane coordinates in the map coordinate system;
in the embodiment of the invention, the image point coordinates u and the camera internal parameters M of the landmark points are extractedcamAnd the vertical distance H from the camera to the ceiling, according to the formula
Calculating coordinate X of the road mark point in the camera coordinate systemCAnd then the coordinate X of the landmark point in the camera coordinate system is utilizedCAnd plane coordinate X in the landmark point map coordinate systemWAccording to the formula XC＝Mataff*XWCalculating an affine transformation matrix two Mataff。
S8, according to a rotation matrix Mat of the camera in the affine change matrix II relative to a map coordinate systemrotatAnd translation vector MattCalculating the plane coordinate X of the camera center in the map coordinate systemcam。
In an embodiment of the invention, the plane coordinate X of the camera center in the map coordinate systemcamThe calculation formula is as follows:
wherein, MatrotatMat being a rotation matrix of the camera relative to the map coordinate systemtTo translate the vector of the camera relative to the map coordinate system.
The embodiment of the invention realizes indoor positioning based on the constructed indoor map, calculates the vertical distance H from the camera to the ceiling according to the distance of the landmark point in the first landmark on the image and the actual distance between the landmark points by extracting the landmarks in the image, and further determines the position of the center of the camera in the map coordinate system by using the affine transformation matrix.
In the embodiment of the present invention, the method for extracting a landmark from a captured image specifically includes the following steps:
s51, carrying out distortion correction on the shot image according to the calibrated camera distortion parameters;
in the embodiment of the invention, the camera needs to be calibrated before use to obtain the distortion parameter of the camera, and the distortion correction is carried out on the acquired image according to the distortion parameter, so that the point location extraction precision is improved.
S52, calculating the average gray value of the image after the distortion correction
To be provided with
As a threshold value for binarization, the image is binarized.
In the embodiment of the invention, the image after distortion correction is subjected to gray processing, and the average gray value is calculated
Since the average value is generally small and the noise is much during the binarization, the average gray value is used
Multiplying by a coefficient k (k > 1) as a threshold value, forThe image is binarized to reduce the occurrence of noise points.
And S53, extracting the landmark points by using the shape of the pixel points and the distance constraint between the pixel points.
In the embodiment of the present invention, the step of extracting the landmark points by using the shape of the pixel points and the distance constraint between the pixel points specifically includes:
s531, carrying out ellipse fitting on the white pixel block in the binarized image;
s532, acquiring the ellipse with the area smaller than an area threshold value and the ratio of the long axis to the short axis of the fitting ellipse positioned in the center of the ellipse in the set interval;
in the embodiment of the invention, a plurality of pixel blocks exist in the binarized image, ellipse fitting is carried out on the pixel blocks, if the ellipse area after fitting is larger than the area threshold value, the pixel block is noise, and the pixel block needs to be discarded; the area threshold is set according to the resolution of the camera, the intensity of the light source, the angle of field of the lens, and the like, and the ratio of the minor axis to the major axis of the ellipse after fitting is in a set section, and the range of the section is greater than 0.5 and smaller than 1.
S533, calculating the number n (n is a positive integer) of the central points of the ellipses with the mutual distance smaller than the distance threshold, and when the number satisfies 3 < n < m2And (m is more than or equal to 3), taking the central points of the ellipses with the mutual distances smaller than the distance threshold value as the landmark points of the landmark.
In the embodiment of the invention, the number n of points with mutual distances smaller than a distance threshold in the ellipse is larger than 3, at least 3 points are used for positioning the coordinate system, and the number n is smaller than m2And (m is more than or equal to 3) the landmark points need to meet the requirement of a rotational asymmetric structure, and are convenient to identify and position. The infrared road signs are illustrated in a 3 × 3 dot matrix form, and the numerical range of the number n is 3 < n < 9.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (7)
1. An indoor map construction method is characterized by comprising the following steps:
s1, extracting road signs in a current shot image, wherein the road signs comprise known road signs and unknown road signs;
s2, calculating a vertical distance H from the camera to a ceiling according to the distance of the road mark points in the known road marks or the unknown road marks on the image and the actual distance between the road mark points;
s3, according to the vertical distance H between the camera and the ceiling and the internal reference matrix MatcamCalculating a first affine transformation matrix according to the homogeneous coordinate of the pixel coordinates of the road mark points of the known road marks and the homogeneous coordinate of the world coordinates in a map coordinate system;
s4, calculating the coordinates of the road sign points of the unknown road signs in a map coordinate system according to the affine transformation matrix I and the pixel coordinates of the road sign points of the unknown road signs;
the known road signs and the unknown road signs are arranged on the indoor ceiling, the known road signs are road signs already brought into a map coordinate system, the unknown road signs are road signs not brought into the map coordinate system, the map coordinate system is that all the indoor road signs are brought into a unified coordinate system, and the coordinate system is the map coordinate system;
the step S2 specifically includes:
s21, selecting two optional road mark points M in the road marks1、M2；
S22, matching the internal reference matrix MatcamInverse matrix of
Multiplied by the waypoint M1、M2Corresponding image point m1、m2Homogeneous coordinate of
Namely, it is
Obtaining coordinates ui1、ui2；
S23, according to the coordinates ui1、ui2In betweenDistance SiAnd the waypoint M1、M2Actual distance S betweenWAnd calculating the distance H from the camera to the ceiling, wherein the calculation formula is as follows:
the internal reference matrix MatcamRefers to the transformation parameters from the camera coordinate system to the image plane coordinate system.
2. The indoor map construction method of claim 1, wherein the step of extracting the landmark in the currently captured image specifically comprises:
s11, carrying out distortion correction on the shot image according to the calibrated camera distortion parameters;
s12, calculating the average gray value of the image after the distortion correction
To be provided with
Performing binarization on the image as a binarization threshold, wherein k is more than 1;
and S13, extracting the landmark points by using the shape of the pixel points and the distance constraint between the pixel points.
3. An indoor map construction method according to claim 2, wherein the step S13 specifically includes:
s131, carrying out ellipse fitting on the white pixel block in the binarized image;
s132, acquiring the ellipse center of which the ellipse area is smaller than an area threshold value and the ratio of the major axis to the minor axis of the fitting ellipse is positioned in a set interval;
s133, calculating the number n of the ellipse centers with the mutual distance smaller than the distance threshold, wherein when the number n is more than 3 and less than m2When the distance between the two ellipse centers is smaller than the distance threshold value, the center of the ellipse with the distance smaller than the distance threshold value is used as a landmark point in a single landmark, wherein m is larger than or equal to3。
4. The indoor map building method according to claim 3, wherein the map coordinate system is specified as a landmark coordinate system corresponding to a first landmark, and the landmark coordinate system is established by steps including:
acquiring two landmark points A, B with the farthest distance in the landmarks and a landmark point O with the farthest distance from the straight line AB;
judging whether the included angle between the straight lines OA and OB is positioned in the included angle designated interval or not;
if the judgment result is yes, A, B is used as a point on a coordinate axis, and O is used as a coordinate origin to establish a landmark coordinate system; and if the judgment result is negative, discarding the image corresponding to the road sign.
5. An indoor positioning method based on the indoor mapping method according to any one of claims 1 to 4, wherein the method comprises the following steps:
s5, extracting a road sign in the current shot image, and judging whether the road sign is a known road sign or not;
s6, if the judgment result is yes, calculating the vertical distance H from the camera to the ceiling according to the distance of the road mark points in the road marks on the image and the actual distance between the road mark points;
s7, according to the vertical distance H and the internal reference matrix MatcamCalculating a second affine transformation matrix according to the coordinates of the road mark points in the image and the plane coordinates in the map coordinate system;
s8, according to a rotation matrix Mat of the camera in the affine change matrix II relative to the map coordinate systemrotatAnd translation vector MattCalculating the plane coordinate X of the camera center in the map coordinate systemcam；
The step S6 specifically includes:
s61, selecting two optional road mark points M in the road marks1、M2；
S62, matching the internal reference matrix MatcamInverse matrix of
Multiplied by the waypoint M1、M2Corresponding image point m1、m2Homogeneous coordinate of
Namely, it is
Obtaining coordinates ui1、ui2；
S63, according to the coordinates ui1、ui2A distance S betweeniAnd the waypoint M1、M2Actual distance S betweenWAnd calculating the distance H from the camera to the ceiling, wherein the calculation formula is as follows:
the internal reference matrix MatcamRefers to the transformation parameters from the camera coordinate system to the image plane coordinate system.
6. The indoor positioning method of the indoor map construction method according to claim 5, wherein the step of extracting the landmark in the currently captured image specifically includes:
s51, carrying out distortion correction on the shot image according to the calibrated camera distortion parameters;
s52, calculating the average gray value of the image after the distortion correction
To be provided with
Performing binarization on the image as a binarization threshold, wherein k is more than 1;
and S53, extracting the landmark points by using the shape of the pixel points and the distance constraint between the pixel points.
7. The indoor positioning method of the indoor map construction method according to claim 6, wherein the step S53 specifically includes:
s531, carrying out ellipse fitting on the white pixel block in the binarized image;
s532, acquiring the ellipse center of which the ellipse area is smaller than an area threshold and the ratio of the long axis to the short axis of the fitting ellipse is positioned in a set interval;
s533, calculating the number n of the ellipse centers with the mutual distance smaller than the distance threshold, wherein when the number satisfies 3 < n < m2And taking the centers of the ellipses with the mutual distances smaller than the distance threshold value as landmark points in a single landmark, wherein m is more than or equal to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611208814.XA CN106651990B (en) | 2016-12-23 | 2016-12-23 | Indoor map construction method and indoor positioning method based on indoor map |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611208814.XA CN106651990B (en) | 2016-12-23 | 2016-12-23 | Indoor map construction method and indoor positioning method based on indoor map |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106651990A CN106651990A (en) | 2017-05-10 |
| CN106651990B true CN106651990B (en) | 2020-08-11 |
Family
ID=58827033
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611208814.XA Active CN106651990B (en) | 2016-12-23 | 2016-12-23 | Indoor map construction method and indoor positioning method based on indoor map |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106651990B (en) |
Families Citing this family (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107403151B (en) * | 2017-07-18 | 2020-11-24 | 广州贰拾肆机器人科技有限公司 | Method, device, equipment and readable medium for positioning through indoor ceiling |
| JP6761786B2 (en) * | 2017-08-10 | 2020-09-30 | 本田技研工業株式会社 | Ceiling map creation method, ceiling map creation device and ceiling map creation program |
| CN107436422B (en) * | 2017-08-22 | 2019-09-03 | 杭州慧仓信息科技有限公司 | A kind of robot localization method based on infrared lamp solid array |
| CN108225327B (en) * | 2017-12-31 | 2021-05-14 | 芜湖哈特机器人产业技术研究院有限公司 | Construction and positioning method of top mark map |
| CN108180917B (en) * | 2017-12-31 | 2021-05-14 | 芜湖哈特机器人产业技术研究院有限公司 | Top map construction method based on pose graph optimization |
| CN109269477A (en) * | 2018-10-08 | 2019-01-25 | 塔米智能科技（北京）有限公司 | A kind of vision positioning method, device, equipment and storage medium |
| CN109483507B (en) * | 2018-12-04 | 2021-06-29 | 北京壹氢科技有限公司 | Indoor visual positioning method for walking of multiple wheeled robots |
| CN109613547B (en) * | 2018-12-28 | 2022-05-27 | 芜湖哈特机器人产业技术研究院有限公司 | Method for constructing occupied grid map based on reflector |
| CN110031817B (en) * | 2018-12-28 | 2022-05-27 | 芜湖哈特机器人产业技术研究院有限公司 | Rapid matching method for laser radar reflector |
| CN109612468A (en) * | 2018-12-28 | 2019-04-12 | 芜湖哈特机器人产业技术研究院有限公司 | A kind of top mark map structuring and robot localization method |
| CN109613550B (en) * | 2018-12-28 | 2023-04-07 | 芜湖哈特机器人产业技术研究院有限公司 | Laser radar map construction and positioning method based on reflector |
| CN110175540A (en) * | 2019-05-11 | 2019-08-27 | 深圳市普渡科技有限公司 | Road sign map structuring system and robot |
| CN111024062B (en) * | 2019-12-31 | 2022-03-29 | 芜湖哈特机器人产业技术研究院有限公司 | Drawing system based on pseudo GNSS and INS |
| WO2022021132A1 (en) * | 2020-07-29 | 2022-02-03 | 上海高仙自动化科技发展有限公司 | Computer device positioning method and apparatus, computer device, and storage medium |
| CN114115212A (en) * | 2020-08-26 | 2022-03-01 | 宁波方太厨具有限公司 | Cleaning robot positioning method and cleaning robot adopting same |
| CN116197889A (en) * | 2021-11-30 | 2023-06-02 | 珠海一微半导体股份有限公司 | Positioning method of ceiling vision robot |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102135429A (en) * | 2010-12-29 | 2011-07-27 | 东南大学 | Robot indoor positioning and navigating method based on vision |
| CN102419178A (en) * | 2011-09-05 | 2012-04-18 | 中国科学院自动化研究所 | Mobile robot positioning system and method based on infrared road sign |
| WO2012116350A3 (en) * | 2011-02-24 | 2013-04-04 | Purdue Research Foundation | Figure-ground organization of 3-d scenes |
| CN105841687A (en) * | 2015-01-14 | 2016-08-10 | 上海智乘网络科技有限公司 | Indoor location method and indoor location system |
| CN106092090A (en) * | 2016-08-06 | 2016-11-09 | 中科院合肥技术创新工程院 | A kind of infrared road sign for indoor mobile robot location and using method thereof |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101906329B1 (en) * | 2010-12-15 | 2018-12-07 | 한국전자통신연구원 | Apparatus and method for indoor localization based on camera |
-
2016
- 2016-12-23 CN CN201611208814.XA patent/CN106651990B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102135429A (en) * | 2010-12-29 | 2011-07-27 | 东南大学 | Robot indoor positioning and navigating method based on vision |
| WO2012116350A3 (en) * | 2011-02-24 | 2013-04-04 | Purdue Research Foundation | Figure-ground organization of 3-d scenes |
| CN102419178A (en) * | 2011-09-05 | 2012-04-18 | 中国科学院自动化研究所 | Mobile robot positioning system and method based on infrared road sign |
| CN105841687A (en) * | 2015-01-14 | 2016-08-10 | 上海智乘网络科技有限公司 | Indoor location method and indoor location system |
| CN106092090A (en) * | 2016-08-06 | 2016-11-09 | 中科院合肥技术创新工程院 | A kind of infrared road sign for indoor mobile robot location and using method thereof |
Non-Patent Citations (2)
| Title |
|---|
| 《基于天花板的移动机器人视觉定位方法的研究》;朱莹莹;《现代电子技术》;20161201;第129-132页 * |
| 《基于被动式红外路标的移动机器人室内定位技术研究与嵌入式实现》;刘晓龙;《中国优秀硕士学位论文全文数据库》;20130115;第35-48页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106651990A (en) | 2017-05-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106651990B (en) | Indoor map construction method and indoor positioning method based on indoor map | |
| CN108571971B (en) | AGV visual positioning system and method | |
| CN108868268B (en) | Unmanned parking space posture estimation method based on point-to-surface distance and cross-correlation entropy registration | |
| EP3371671B1 (en) | Method, device and assembly for map generation | |
| WO2021026850A1 (en) | Qr code-based navigation attitude determining and positioning method and system | |
| CN104848858B (en) | Quick Response Code and be used for robotic vision-inertia combined navigation system and method | |
| CN106548173B (en) | A kind of improvement no-manned plane three-dimensional information acquisition method based on classification matching strategy | |
| JP5588812B2 (en) | Image processing apparatus and imaging apparatus using the same | |
| CN106908040B (en) | A kind of binocular panorama visual robot autonomous localization method based on SURF algorithm | |
| CN107436422B (en) | A kind of robot localization method based on infrared lamp solid array | |
| CN109446973B (en) | Vehicle positioning method based on deep neural network image recognition | |
| CN104200086A (en) | Wide-baseline visible light camera pose estimation method | |
| JP2014098683A (en) | Method for remotely measuring crack | |
| JP2009053059A (en) | Object specifying device, object specifying method, and object specifying program | |
| WO2015019526A1 (en) | Image processing device and markers | |
| CN110595476A (en) | Unmanned aerial vehicle landing navigation method and device based on GPS and image visual fusion | |
| WO2022078513A1 (en) | Positioning method and apparatus, self-moving device, and storage medium | |
| US10482615B2 (en) | Image processing device and image processing method | |
| CN109685855A (en) | A kind of camera calibration optimization method under road cloud monitor supervision platform | |
| CN110009682A (en) | A kind of object recognition and detection method based on monocular vision | |
| WO2019136613A1 (en) | Indoor locating method and device for robot | |
| CN106370160A (en) | Robot indoor positioning system and method | |
| WO2022078488A1 (en) | Positioning method and apparatus, self-moving device, and storage medium | |
| Ruotsalainen et al. | Heading change detection for indoor navigation with a smartphone camera | |
| CN112129263B (en) | Distance measurement method of separated mobile stereo distance measurement camera |
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 |