CN112581532B - System and method for capturing position of moving object - Google Patents
System and method for capturing position of moving object Download PDFInfo
- Publication number
- CN112581532B CN112581532B CN202011455386.7A CN202011455386A CN112581532B CN 112581532 B CN112581532 B CN 112581532B CN 202011455386 A CN202011455386 A CN 202011455386A CN 112581532 B CN112581532 B CN 112581532B
- Authority
- CN
- China
- Prior art keywords
- moving object
- plane
- parameter
- determining
- position relation
- 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
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K17/00—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/66—Analysis of geometric attributes of image moments or centre of gravity
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30221—Sports video; Sports image
- G06T2207/30224—Ball; Puck
Abstract
The invention provides a system and a method for capturing the position of a moving object, wherein the system comprises: the markers are uniformly arranged on the outer surface of the moving object; the camera shooting unit is used for shooting an image of a moving object; and the processing unit is connected with the camera shooting unit and used for analyzing the image and determining the position of the moving object relative to the moving plane based on the marker. The moving object position capturing system has the advantages that the markers are arranged on the moving object in advance, the image of the billiards moving on the billiard table is shot through the shooting unit, the positions of the moving object and the moving plane are determined by taking the markers as reference points in the shot image, the probability of calculation errors is reduced compared with the situation that a reference object is adopted, and the accuracy of the position capturing of the billiards is improved.
Description
Technical Field
The invention relates to the technical field of position capture, in particular to a position capture system and method of a moving object.
Background
At present, billiards attract fans of all levels due to simple playing methods and various changes. With the development of science and technology, various systems for assisting billiard training or entertainment have appeared, and in order to realize accurate assistance, the accuracy of capturing the position of a billiard in motion is particularly important.
Disclosure of Invention
One of the objects of the present invention is to provide a position capturing system for a moving object, in which markers are previously set on the moving object (for example, billiards), an image of the billiards moving on a billiard table is captured by an imaging unit, and the positions of the moving object and a moving plane (for example, the surface of the billiards table) are determined from the captured image using a plurality of markers as reference points, so that the probability of calculation errors is reduced and the accuracy of capturing the billiard position is improved compared with the case of using one reference object.
The embodiment of the invention provides a position capturing system of a moving object, which comprises:
the markers are uniformly arranged on the outer surface of the moving object;
the camera shooting unit is used for shooting an image of a moving object;
and the processing unit is connected with the camera shooting unit and used for analyzing the image and determining the position of the moving object relative to the moving plane based on the marker.
Preferably, the processor performs the following operations:
acquiring size parameters of a moving object;
acquiring a first position relation parameter of a moving object moving plane and a camera unit;
constructing a position plane of the moving object and determining a second position relation parameter between the position plane and the camera unit based on the size parameter and the first position relation parameter;
dividing the position plane into four areas by two straight lines which are vertical and pass through the projection of the camera unit on the position plane;
analyzing the image to obtain display parameters of the marker on the image; the display parameters include: the shape, area and relative positional relationship with the projection position of the image pickup unit within the image;
determining the area of the moving object in the position plane based on the relative position relation;
determining a position relation library of the moving object and a position plane based on the position of the region formed by the markers in the image;
determining a third position relation parameter of the moving object and the camera unit based on the size parameter and the display parameter of the moving object;
determining a fourth position relation between the moving object and the position plane from the position relation library based on the second position relation parameter and the third position relation parameter;
and determining the position of the moving object and the movement plane based on the fourth position relation and the third position relation.
Preferably, the marker is arranged on the surface of the moving object in the following way:
when the moving object is manufactured, firstly, a colorless fluorescent material is coated on the surface of the moving object to form a mark, and finally, a non-fluorescent material is coated on a preset surface pattern of the moving object to cover the fluorescent material;
or the like, or, alternatively,
when the moving object is manufactured and the surface of the moving object is coated, splitting a preset surface pattern into a mark coating pattern and a filling pattern; first, according to the mark coating pattern, a fluorescent material of a corresponding color is coated based on the color on the mark coating pattern, and then a non-fluorescent material is coated according to the filling pattern.
Preferably, the determining the position relation library of the moving object and the position plane based on the position of the region composed of the markers in the image includes:
extracting outlines of all markers in a region formed by the markers to obtain a plurality of marker contour lines;
sampling and extracting the markers positioned on the outermost side of the region consisting of the markers to obtain a plurality of sampling points;
fitting the sampling points to obtain the contour of the moving object;
determining the center of the moving object based on the corresponding relation between the preset contour and the center;
determining the relative position relation between the center and the projection position of the camera unit in the image;
and calling a preset position relation library corresponding to the first relative position relation based on the preset first relative position relation and the list of the corresponding association of the first relative position and the position relation library.
Preferably, the fourth position relation of the moving object in the position plane is determined from the position relation library based on the second position relation parameter and the third position relation parameter; the method comprises the following steps:
constructing a reference vector based on the second position relation parameter and the third position relation parameter, calculating the similarity between the reference vector and the calling vector in the position relation library, and calling a fourth position relation corresponding to the calling vector with the maximum similarity;
the similarity calculation formula of the reference vector and the calling vector is as follows:
wherein Q is the similarity of the reference vector and the calling vector; n is in the reference vector and the call vectorThe number of data; x is the number ofiIs the ith data value of the reference vector; y isiIs the ith data value of the call vector.
Preferably, the position capturing system of the moving object further includes:
the wireless pressure sensing units are uniformly arranged on the outer surface of the moving object, are in wireless communication connection with the processing unit respectively and are used for detecting the pressure value applied to the surface of the moving object;
the processor performs the following operations:
acquiring a pressure value detected by a wireless pressure sensor unit;
judging whether the moving object moves on the moving plane or not based on the pressure value;
when the moving object moves on the motion plane, acquiring the size parameter of the moving object;
acquiring a first position relation parameter of a motion plane of a moving object and a camera unit;
constructing a position plane of the moving object and determining a second position relation parameter between the position plane and the camera unit based on the size parameter and the first position relation parameter;
dividing the position plane into four areas by two straight lines which are vertical and pass through the projection of the camera unit on the position plane;
analyzing the image to obtain display parameters of the marker on the image; the display parameters include: the shape, area and relative positional relationship with the projection position of the image pickup unit within the image;
determining the area of the moving object in the position plane based on the relative position relation;
determining the position of the moving object on a position plane based on the size parameter and the display parameter of the moving object;
and determining the position of the moving object relative to the movement plane based on the position of the moving object on the position plane and the position relation between the position plane and the movement plane.
Preferably, the position capturing system of the moving object further includes:
at least one group of RFID labels are arranged in the moving object, each group of RFID labels are symmetrically arranged at the center of the moving object,
the RFID card readers are uniformly arranged below the motion plane, are in wireless communication connection with the processing unit respectively and are used for reading RFID labels;
the processor performs the following operations:
reading the RFID label through an RFID card reader;
judging whether the moving object moves on the moving plane or not based on the RFID tag reading condition;
when the moving object moves on the motion plane, acquiring the size parameter of the moving object;
acquiring a first position relation parameter of a motion plane of a moving object and a camera unit;
constructing a position plane of the moving object and determining a second position relation parameter between the position plane and the camera unit based on the size parameter and the first position relation parameter;
dividing the position plane into four areas by two straight lines which are vertical and pass through the projection of the camera unit on the position plane;
analyzing the image to obtain display parameters of the marker on the image; the display parameters include: the shape, area and relative positional relationship with the projection position of the image pickup unit within the image;
determining the area of the moving object in the position plane based on the relative position relation;
determining the position of the moving object on a position plane based on the size parameter and the display parameter of the moving object;
and determining the position of the moving object relative to the movement plane based on the position of the moving object on the position plane and the position relation between the position plane and the movement plane.
Preferably, the position capturing system of the moving object further includes:
and the at least one group of correlation gratings are arranged on two sides of the motion plane, are electrically connected with the processing unit and are used for determining whether the moving object moves on the motion plane according to the shielding condition of the moving object on the light rays of the correlation gratings.
The invention also provides a position capturing method of the moving object, which comprises the following steps:
shooting an image of a moving object through a shooting unit; uniformly arranging a plurality of markers on the outer surface of a moving object in advance;
the images are analyzed and the position of the moving object relative to the plane of motion is determined based on the markers.
Preferably, analyzing the image and determining the position of the moving object relative to the plane of motion based on the markers comprises:
acquiring size parameters of a moving object;
acquiring a first position relation parameter of a moving object moving plane and a camera unit;
constructing a position plane of the moving object and determining a second position relation parameter between the position plane and the camera unit based on the size parameter and the first position relation parameter;
dividing the position plane into four areas by two straight lines which are vertical and pass through the projection of the camera unit on the position plane;
analyzing the image to obtain display parameters of the marker on the image; the display parameters include: the shape, area and relative positional relationship with the projection position of the image pickup unit within the image;
determining the area of the moving object in the position plane based on the relative position relation;
determining a position relation library of the moving object and a position plane based on the position of the region formed by the markers in the image;
determining a third position relation parameter of the moving object and the camera unit based on the size parameter and the display parameter of the moving object;
determining a fourth position relation between the moving object and the position plane from the position relation library based on the second position relation parameter and the third position relation parameter;
and determining the position of the moving object and the movement plane based on the fourth position relation and the third position relation.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a diagram of a system for capturing a position of a moving object according to an embodiment of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
An embodiment of the present invention provides a system for capturing a position of a moving object, as shown in fig. 1, including:
a plurality of markers 11 uniformly arranged on the outer surface of the moving object;
an image pickup unit 12 for picking up an image of a moving object;
and the processing unit 13 is connected with the camera unit 12 and used for analyzing the image and determining the position of the moving object relative to the moving plane based on the marker 11.
The working principle and the beneficial effects of the technical scheme are as follows:
when the moving object is taken as a reference during image analysis, accidental errors exist on the basis of factors such as the shape of the moving object, the accuracy of contour extraction and the like because only one reference point (namely the moving object) exists, and the accuracy of final position confirmation is influenced; the position of the moving object relative to the motion plane is determined by using the plurality of markers as reference points, so that accidental errors can be effectively avoided, the position of the moving object can be more accurately captured during motion, and an accurate data basis is further provided for a billiard auxiliary training system; in addition, a plurality of markers are uniformly distributed, so that the camera unit can be ensured to shoot enough markers as reference points no matter how a moving object rolls during movement; taking a billiard as an example, the marker is uniformly distributed on the surface of the billiard, and can be in a regular shape such as a circle, a triangle, a square and the like, or in an irregular shape such as a crescent, a tripod and the like; furthermore, moving objects can be distinguished through the shape of the markers, for example, the markers are arranged on the No. 1 ball of the billiard ball to be round, and the markers are arranged on the No. 2 ball to be triangular … …, so that the billiard balls are distinguished.
The moving object position capturing system of the invention is characterized in that the markers are arranged on the moving object (such as billiards) in advance, the image of the billiards moving on the billiard table is shot through the shooting unit, the positions of the moving object and the moving plane (such as the billiard table surface) are determined by taking the multiple markers as reference points in the shot image, and compared with the situation that one reference object is adopted, the probability of calculation errors is reduced, and the accuracy of the position capturing of the billiards is improved.
In one embodiment, a processor performs the following operations:
acquiring size parameters of a moving object;
acquiring a first position relation parameter of a moving object moving plane and a camera unit;
constructing a position plane of the moving object and determining a second position relation parameter between the position plane and the camera unit based on the size parameter and the first position relation parameter;
dividing the position plane into four areas by two straight lines which are vertical and pass through the projection of the camera unit on the position plane;
analyzing the image to obtain display parameters of the marker on the image; the display parameters include: the shape, area and relative positional relationship with the projection position of the image pickup unit within the image;
determining the area of the moving object in the position plane based on the relative position relation;
determining a position relation library of the moving object and a position plane based on the position of the region formed by the markers in the image;
determining a third position relation parameter of the moving object and the camera unit based on the size parameter and the display parameter of the moving object;
determining a fourth position relation between the moving object and the position plane from the position relation library based on the second position relation parameter and the third position relation parameter;
and determining the position of the moving object and the movement plane based on the fourth position relation and the third position relation.
The working principle and the beneficial effects of the technical scheme are as follows:
when the camera unit is installed, testing first position relation parameters of the motion plane and the camera unit, wherein the first position relation parameters comprise the shortest distance of the camera unit on the test motion plane, the projection position of the camera unit on the test motion plane and the like; because the moving object moves on the motion plane, the position plane formed by the center of the moving object can be determined when the moving object is at each position of the motion plane based on the size parameters of the moving object and the test plane; each point of a motion plane on the image is in one-to-one correspondence with the pixel points of the image, the region where the moving object is located can be determined firstly according to region division, images in other regions can be not processed, and the data amount of processing is reduced; when the billiards are trained or entertained, the billiards can jump on the billiard table, so that the positions of the areas formed by the markers in the images, which are mapped to the connecting lines between the points on the moving platform and the camera unit, are all the positions where the moving object can exist, namely, a set of the moving object, namely a position relation library, can be determined according to the positions of the areas formed by the markers in the images; then determining a third position relation parameter of the moving object and the camera unit according to the size parameter and the display parameter of the moving object, matching the position of the moving object from the position relation library based on the third position relation parameter, and further confirming the position of the moving object and the movement plane; and the third position relation parameter comprises the distance from the moving object to the camera shooting unit.
In one embodiment, the markers are disposed on the surface of the moving object in the following manner:
when the moving object is manufactured, firstly, a colorless fluorescent material is coated on the surface of the moving object to form a mark, and finally, a non-fluorescent material is coated on a preset surface pattern of the moving object to cover the fluorescent material;
or the like, or, alternatively,
when the moving object is manufactured and the surface of the moving object is coated, splitting a preset surface pattern into a mark coating pattern and a filling pattern; first, according to the mark coating pattern, a fluorescent material of a corresponding color is coated based on the color on the mark coating pattern, and then a non-fluorescent material is coated according to the filling pattern.
The working principle and the beneficial effects of the technical scheme are as follows:
the addition of the marker without affecting the appearance of the billiard is achieved by means of a fluorescent material, in which case the camera unit comprises a fluorescent camera.
In one embodiment, determining a position relation library of the moving object and the position plane based on the position of the region composed of the markers in the image comprises:
extracting outlines of all markers in a region formed by the markers to obtain a plurality of marker contour lines;
sampling and extracting the markers positioned on the outermost side of the region consisting of the markers to obtain a plurality of sampling points;
fitting the sampling points to obtain the contour of the moving object;
determining the center of the moving object based on the corresponding relation between the preset contour and the center;
determining the relative position relation between the center and the projection position of the camera unit in the image;
and calling a preset position relation library corresponding to the first relative position relation based on the preset first relative position relation and the list of the corresponding association of the first relative position and the position relation library.
The working principle and the beneficial effects of the technical scheme are as follows:
determining the contour of the moving object through contour extraction, sampling and fitting, and determining the center of the moving object based on the preset corresponding relation between the contour and the center; for example, the outline is that the center of a circle is at the center of the circle; partial work of data calculation is completed in advance through a position relation library established in advance, so that the online data processing amount is reduced, and the position capturing speed is improved. Furthermore, the outlines of all the markers are sampled to obtain a plurality of feature points, the positions of the feature points in the images are used as parameters to be input into a preset neural network model, a calling factor is determined, and a corresponding stored position relation library is called according to the calling factor.
In one embodiment, a fourth position relation of the moving object in the position plane is determined from the position relation library based on the second position relation parameter and the third position relation parameter; the method comprises the following steps:
constructing a reference vector based on the second position relation parameter and the third position relation parameter, calculating the similarity between the reference vector and the calling vector in the position relation library, and calling a fourth position relation corresponding to the calling vector with the maximum similarity;
the similarity calculation formula of the reference vector and the calling vector is as follows:
wherein Q is the similarity of the reference vector and the calling vector; n is the number of data in the reference vector and the calling vector; x is the number ofiIs the ith data value of the reference vector; y isiIs the ith data value of the call vector.
The working principle and the beneficial effects of the technical scheme are as follows:
and calculating the similarity between the calling vector correspondingly stored in the fourth position relation in the position relation library and the reference vector determined by the second position relation parameter and the third position relation parameter through a similarity calculation formula, and determining the called fourth position relation so as to capture the position of the moving object.
In one embodiment, the position capture system of a moving object further comprises:
the wireless pressure sensing units are uniformly arranged on the outer surface of the moving object, are in wireless communication connection with the processing unit respectively and are used for detecting the pressure value applied to the surface of the moving object;
the processor performs the following operations:
acquiring a pressure value detected by a wireless pressure sensor unit;
judging whether the moving object moves on the moving plane or not based on the pressure value;
when the moving object moves on the motion plane, acquiring the size parameter of the moving object;
acquiring a first position relation parameter of a motion plane of a moving object and a camera unit;
constructing a position plane of the moving object and determining a second position relation parameter between the position plane and the camera unit based on the size parameter and the first position relation parameter;
dividing the position plane into four areas by two straight lines which are vertical and pass through the projection of the camera unit on the position plane;
analyzing the image to obtain display parameters of the marker on the image; the display parameters include: the shape, area and relative positional relationship with the projection position of the image pickup unit within the image;
determining the area of the moving object in the position plane based on the relative position relation;
determining the position of the moving object on a position plane based on the size parameter and the display parameter of the moving object;
and determining the position of the moving object relative to the movement plane based on the position of the moving object on the position plane and the position relation between the position plane and the movement plane.
The working principle and the beneficial effects of the technical scheme are as follows:
the wireless pressure sensing unit determines that the moving object does not move on the moving plane, and the influence of the jumping of the moving object on position determination is not required to be considered in the moving plane, so that the calculation of data is reduced, and the speed of position capture is increased.
In one embodiment, the position capture system of a moving object further comprises:
at least one group of RFID labels are arranged in the moving object, each group of RFID labels are symmetrically arranged at the center of the moving object,
the RFID card readers are uniformly arranged below the motion plane, are in wireless communication connection with the processing unit respectively and are used for reading RFID labels;
the processor performs the following operations:
reading the RFID label through an RFID card reader;
judging whether the moving object moves on the moving plane or not based on the RFID tag reading condition;
when the moving object moves on the motion plane, acquiring the size parameter of the moving object;
acquiring a first position relation parameter of a motion plane of a moving object and a camera unit;
constructing a position plane of the moving object and determining a second position relation parameter between the position plane and the camera unit based on the size parameter and the first position relation parameter;
dividing the position plane into four areas by two straight lines which are vertical and pass through the projection of the camera unit on the position plane;
analyzing the image to obtain display parameters of the marker on the image; the display parameters include: the shape, area and relative positional relationship with the projection position of the image pickup unit within the image;
determining the area of the moving object in the position plane based on the relative position relation;
determining the position of the moving object on a position plane based on the size parameter and the display parameter of the moving object;
and determining the position of the moving object relative to the movement plane based on the position of the moving object on the position plane and the position relation between the position plane and the movement plane.
The working principle and the beneficial effects of the technical scheme are as follows:
the RFID positioning function is used for determining that the moving object does not move on the moving plane, and the influence of the jumping of the moving object on position determination is not required to be considered in the moving plane, so that the calculation of data is reduced, and the speed of position capture is increased. Furthermore, the last determined location can be verified by means of the RFID location function.
In one embodiment, the position capture system of a moving object further comprises:
and the at least one group of correlation gratings are arranged on two sides of the motion plane, are electrically connected with the processing unit and are used for determining whether the moving object moves on the motion plane according to the shielding condition of the moving object on the light rays of the correlation gratings.
The working principle and the beneficial effects of the technical scheme are as follows:
the moving object is determined to move on a plane of motion through the correlation grating, and the influence of the jumping of the moving object on the position determination is not required to be considered in the plane of motion, so that the data calculation is reduced, and the speed of position capture is increased. And furthermore, arranging at least one group of correlation gratings at two sides of the motion platform, arranging at least one group of correlation gratings at the other two sides of the motion platform, forming a correlation grating grid on the motion platform, and capturing the position of the moving object on the motion platform based on the shielding condition of the grating of the moving object.
The invention also provides a position capturing method of the moving object, which comprises the following steps:
shooting an image of a moving object through a shooting unit; uniformly arranging a plurality of markers on the outer surface of a moving object in advance;
the images are analyzed and the position of the moving object relative to the plane of motion is determined based on the markers.
The working principle and the beneficial effects of the technical scheme are as follows:
when the moving object is taken as a reference during image analysis, accidental errors exist on the basis of factors such as the shape of the moving object, the accuracy of contour extraction and the like because only one reference point (namely the moving object) exists, and the accuracy of final position confirmation is influenced; the position of the moving object relative to the motion plane is determined by using the plurality of markers as reference points, so that accidental errors can be effectively avoided, the position of the moving object can be more accurately captured during motion, and an accurate data basis is further provided for a billiard auxiliary training system; in addition, a plurality of markers are uniformly distributed, so that the camera unit can be ensured to shoot enough markers as reference points no matter how a moving object rolls during movement; taking a billiard as an example, the marker is uniformly distributed on the surface of the billiard, and can be in a regular shape such as a circle, a triangle, a square and the like, or in an irregular shape such as a crescent, a tripod and the like; furthermore, moving objects can be distinguished through the shape of the markers, for example, the markers are arranged on the No. 1 ball of the billiard ball to be round, and the markers are arranged on the No. 2 ball to be triangular … …, so that the billiard balls are distinguished.
The moving object position capturing system of the invention is characterized in that the markers are arranged on the moving object (such as billiards) in advance, the image of the billiards moving on the billiard table is shot through the shooting unit, the positions of the moving object and the moving plane (such as the billiard table surface) are determined by taking the multiple markers as reference points in the shot image, and compared with the situation that one reference object is adopted, the probability of calculation errors is reduced, and the accuracy of the position capturing of the billiards is improved.
In one embodiment, analyzing the image, determining the position of the moving object relative to the plane of motion based on the markers comprises:
acquiring size parameters of a moving object;
acquiring a first position relation parameter of a moving object moving plane and a camera unit;
constructing a position plane of the moving object and determining a second position relation parameter between the position plane and the camera unit based on the size parameter and the first position relation parameter;
dividing the position plane into four areas by two straight lines which are vertical and pass through the projection of the camera unit on the position plane;
analyzing the image to obtain display parameters of the marker on the image; the display parameters include: the shape, area and relative positional relationship with the projection position of the image pickup unit within the image;
determining the area of the moving object in the position plane based on the relative position relation;
determining a position relation library of the moving object and a position plane based on the position of the region formed by the markers in the image;
determining a third position relation parameter of the moving object and the camera unit based on the size parameter and the display parameter of the moving object;
determining a fourth position relation between the moving object and the position plane from the position relation library based on the second position relation parameter and the third position relation parameter;
and determining the position of the moving object and the movement plane based on the fourth position relation and the third position relation.
The working principle and the beneficial effects of the technical scheme are as follows:
when the camera unit is installed, testing first position relation parameters of the motion plane and the camera unit, wherein the first position relation parameters comprise the shortest distance of the camera unit on the test motion plane, the projection position of the camera unit on the test motion plane and the like; because the moving object moves on the motion plane, the position plane formed by the center of the moving object can be determined when the moving object is at each position of the motion plane based on the size parameters of the moving object and the test plane; each point of a motion plane on the image is in one-to-one correspondence with the pixel points of the image, the region where the moving object is located can be determined firstly according to region division, images in other regions can be not processed, and the data amount of processing is reduced; when the billiards are trained or entertained, the billiards can jump on the billiard table, so that the positions of the areas formed by the markers in the images, which are mapped to the connecting lines between the points on the moving platform and the camera unit, are all the positions where the moving object can exist, namely, a set of the moving object, namely a position relation library, can be determined according to the positions of the areas formed by the markers in the images; then determining a third position relation parameter of the moving object and the camera unit according to the size parameter and the display parameter of the moving object, matching the position of the moving object from the position relation library based on the third position relation parameter, and further confirming the position of the moving object and the movement plane; and the third position relation parameter comprises the distance from the moving object to the camera shooting unit.
In one embodiment, the markers are disposed on the surface of the moving object in the following manner:
when the moving object is manufactured, firstly, a colorless fluorescent material is coated on the surface of the moving object to form a mark, and finally, a non-fluorescent material is coated on a preset surface pattern of the moving object to cover the fluorescent material;
or the like, or, alternatively,
when the moving object is manufactured and the surface of the moving object is coated, splitting a preset surface pattern into a mark coating pattern and a filling pattern; first, according to the mark coating pattern, a fluorescent material of a corresponding color is coated based on the color on the mark coating pattern, and then a non-fluorescent material is coated according to the filling pattern.
The working principle and the beneficial effects of the technical scheme are as follows:
the addition of the marker without affecting the appearance of the billiard is achieved by means of a fluorescent material, in which case the camera unit comprises a fluorescent camera.
In one embodiment, determining a position relation library of the moving object and the position plane based on the position of the region composed of the markers in the image comprises:
extracting outlines of all markers in a region formed by the markers to obtain a plurality of marker contour lines;
sampling and extracting the markers positioned on the outermost side of the region consisting of the markers to obtain a plurality of sampling points;
fitting the sampling points to obtain the contour of the moving object;
determining the center of the moving object based on the corresponding relation between the preset contour and the center;
determining the relative position relation between the center and the projection position of the camera unit in the image;
and calling a preset position relation library corresponding to the first relative position relation based on the preset first relative position relation and the list of the corresponding association of the first relative position and the position relation library.
The working principle and the beneficial effects of the technical scheme are as follows:
determining the contour of the moving object through contour extraction, sampling and fitting, and determining the center of the moving object based on the preset corresponding relation between the contour and the center; for example, the outline is that the center of a circle is at the center of the circle; partial work of data calculation is completed in advance through a position relation library established in advance, so that the online data processing amount is reduced, and the position capturing speed is improved. Furthermore, the outlines of all the markers are sampled to obtain a plurality of feature points, the positions of the feature points in the images are used as parameters to be input into a preset neural network model, a calling factor is determined, and a corresponding stored position relation library is called according to the calling factor.
In one embodiment, a fourth position relation of the moving object in the position plane is determined from the position relation library based on the second position relation parameter and the third position relation parameter; the method comprises the following steps:
constructing a reference vector based on the second position relation parameter and the third position relation parameter, calculating the similarity between the reference vector and the calling vector in the position relation library, and calling a fourth position relation corresponding to the calling vector with the maximum similarity;
the similarity calculation formula of the reference vector and the calling vector is as follows:
wherein Q is the similarity of the reference vector and the calling vector; n is the number of data in the reference vector and the calling vector; x is the number ofiIs the ith data value of the reference vector; y isiIs the ith data value of the call vector.
The working principle and the beneficial effects of the technical scheme are as follows:
and calculating the similarity between the calling vector correspondingly stored in the fourth position relation in the position relation library and the reference vector determined by the second position relation parameter and the third position relation parameter through a similarity calculation formula, and determining the called fourth position relation so as to capture the position of the moving object.
In one embodiment, the method for capturing the position of a moving object further comprises:
acquiring pressure values detected by a plurality of wireless pressure sensor units; the wireless pressure sensing units are uniformly arranged on the outer surface of the moving object, are in wireless communication connection with the processing unit respectively and are used for detecting the pressure value applied to the surface of the moving object;
judging whether the moving object moves on the moving plane or not based on the pressure value;
when the moving object moves on the motion plane, acquiring the size parameter of the moving object;
acquiring a first position relation parameter of a motion plane of a moving object and a camera unit;
constructing a position plane of the moving object and determining a second position relation parameter between the position plane and the camera unit based on the size parameter and the first position relation parameter;
dividing the position plane into four areas by two straight lines which are vertical and pass through the projection of the camera unit on the position plane;
analyzing the image to obtain display parameters of the marker on the image; the display parameters include: the shape, area and relative positional relationship with the projection position of the image pickup unit within the image;
determining the area of the moving object in the position plane based on the relative position relation;
determining the position of the moving object on a position plane based on the size parameter and the display parameter of the moving object;
and determining the position of the moving object relative to the movement plane based on the position of the moving object on the position plane and the position relation between the position plane and the movement plane.
The working principle and the beneficial effects of the technical scheme are as follows:
the wireless pressure sensing unit determines that the moving object does not move on the moving plane, and the influence of the jumping of the moving object on position determination is not required to be considered in the moving plane, so that the calculation of data is reduced, and the speed of position capture is increased.
In one embodiment, the method for capturing the position of a moving object further comprises:
reading at least one group of RFID labels through a plurality of RFID card readers; the RFID readers are uniformly arranged below the motion plane, are in wireless communication connection with the processing unit respectively and are used for reading the RFID tags;
judging whether the moving object moves on the moving plane or not based on the RFID tag reading condition;
when the moving object moves on the motion plane, acquiring the size parameter of the moving object;
acquiring a first position relation parameter of a motion plane of a moving object and a camera unit;
constructing a position plane of the moving object and determining a second position relation parameter between the position plane and the camera unit based on the size parameter and the first position relation parameter;
dividing the position plane into four areas by two straight lines which are vertical and pass through the projection of the camera unit on the position plane;
analyzing the image to obtain display parameters of the marker on the image; the display parameters include: the shape, area and relative positional relationship with the projection position of the image pickup unit within the image;
determining the area of the moving object in the position plane based on the relative position relation;
determining the position of the moving object on a position plane based on the size parameter and the display parameter of the moving object;
and determining the position of the moving object relative to the movement plane based on the position of the moving object on the position plane and the position relation between the position plane and the movement plane.
The working principle and the beneficial effects of the technical scheme are as follows:
the RFID positioning function is used for determining that the moving object does not move on the moving plane, and the influence of the jumping of the moving object on position determination is not required to be considered in the moving plane, so that the calculation of data is reduced, and the speed of position capture is increased. Furthermore, the last determined location can be verified by means of the RFID location function.
In one embodiment, the position capture system of a moving object further comprises:
determining whether the moving object moves on the moving plane according to the shielding condition of the moving object on the light rays of at least one group of correlation gratings; and at least one group of correlation gratings are arranged on two sides of the motion plane and electrically connected with the processing unit.
The working principle and the beneficial effects of the technical scheme are as follows:
the moving object is determined to move on a plane of motion through the correlation grating, and the influence of the jumping of the moving object on the position determination is not required to be considered in the plane of motion, so that the data calculation is reduced, and the speed of position capture is increased. And furthermore, arranging at least one group of correlation gratings at two sides of the motion platform, arranging at least one group of correlation gratings at the other two sides of the motion platform, forming a correlation grating grid on the motion platform, and capturing the position of the moving object on the motion platform based on the shielding condition of the grating of the moving object.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (8)
1. A position capture system for a moving object, comprising:
the markers are uniformly arranged on the outer surface of the moving object;
the camera shooting unit is used for shooting the image of the moving object;
the processing unit is connected with the camera shooting unit and used for analyzing the image and determining the position of the moving object relative to a moving plane based on the marker;
the processing unit performs the following operations:
acquiring the size parameter of the moving object;
acquiring a first position relation parameter between the moving plane of the moving object and the camera shooting unit;
constructing a position plane of the moving object and determining a second position relation parameter between the position plane and the camera unit based on the size parameter and the first position relation parameter;
dividing the position plane into four areas by two straight lines which are vertical and pass through the projection of the camera unit on the position plane;
analyzing the image to obtain display parameters of the marker on the image; the display parameters include: a relative positional relationship of a shape, an area, and a projection position of the imaging unit within the image;
determining a region of the moving object located in the position plane based on the relative positional relationship;
determining a position relation library of the moving object and the position plane based on the position of the region composed of the markers in the image;
determining a third position relation parameter of the moving object and the camera unit based on the size parameter and the display parameter of the moving object;
determining a fourth position relation between the moving object and the position plane from the position relation library based on the second position relation parameter and the third position relation parameter;
and determining the position of the moving object and the moving plane based on the fourth position relation and the third position relation.
2. The system for capturing the position of a moving object according to claim 1, wherein the markers are provided on the surface of the moving object by:
when the moving object is manufactured, firstly, a colorless fluorescent material is coated on the surface of the moving object to form a mark, and finally, a non-fluorescent material is coated on a preset surface pattern of the moving object to cover the fluorescent material;
or the like, or, alternatively,
when the moving object is manufactured and the surface of the moving object is coated, splitting a preset surface pattern into a mark coating pattern and a filling pattern; according to the mark coating pattern, firstly, the fluorescent material with the corresponding color is coated by taking the color on the mark coating pattern as the reference, and then the non-fluorescent material is coated according to the filling pattern.
3. The system of claim 1, wherein the determining the library of positional relationships of the moving object to the location plane based on the locations of the regions of marker composition in the image comprises:
extracting contours of all the markers in the region formed by the markers to obtain a plurality of marker contour lines;
sampling and extracting the markers positioned on the outermost side of the region consisting of the markers to obtain a plurality of sampling points;
fitting the sampling points to obtain the contour of the moving object;
determining the center of the moving object based on the corresponding relation between the preset outline and the center;
determining a relative positional relationship between the center and a projection position of the image pickup unit in the image;
and calling a preset position relation library corresponding to the first relative position relation based on a preset first relative position relation and a list of corresponding associations of the first relative position and the position relation library.
4. The system for capturing the position of the moving object according to claim 1, wherein the fourth positional relationship of the moving object in the position plane is determined from the positional relationship library based on the second positional relationship parameter and the third positional relationship parameter; the method comprises the following steps:
constructing a reference vector based on the second position relation parameter and the third position relation parameter, calculating the similarity between the reference vector and a calling vector in the position relation library, and calling the fourth position relation corresponding to the calling vector with the maximum similarity;
wherein, the similarity calculation formula of the reference vector and the calling vector is as follows:
wherein Q is the similarity between the reference vector and the calling vector; n is the number of data in the reference vector and the calling vector; x is the number ofiIs the ith data value of the reference vector; y isiIs the ith data value of the call vector.
5. The motion object position capture system of claim 1, further comprising:
the wireless pressure sensing units are uniformly arranged on the outer surface of the moving object, are in wireless communication connection with the processing unit respectively, and are used for detecting the pressure value applied to the surface of the moving object;
the processing unit performs the following operations:
acquiring a pressure value detected by the wireless pressure sensor unit;
judging whether the moving object moves on a moving plane or not based on the pressure value;
when the moving object moves on a moving plane, acquiring the size parameter of the moving object;
acquiring a first position relation parameter between a motion plane of the moving object and the camera shooting unit;
constructing a position plane of the moving object and determining a second position relation parameter between the position plane and the camera unit based on the size parameter and the first position relation parameter;
dividing the position plane into four areas by two straight lines which are vertical and pass through the projection of the camera unit on the position plane;
analyzing the image to obtain display parameters of the marker on the image; the display parameters include: a relative positional relationship of a shape, an area, and a projection position of the imaging unit within the image;
determining a region of the moving object located in the position plane based on the relative positional relationship;
determining the position of the moving object on the position plane based on the size parameter and the display parameter of the moving object;
and determining the position of the moving object relative to the movement plane based on the position of the moving object in the position plane and the position relation between the position plane and the movement plane.
6. The motion object position capture system of claim 1, further comprising:
at least one group of RFID tags arranged inside the moving object, wherein each group of RFID tags are symmetrically arranged at the center of the moving object,
the RFID card readers are uniformly arranged below the motion plane, are in wireless communication connection with the processing unit respectively and are used for reading the RFID tags;
the processing unit performs the following operations:
reading the RFID tag through an RFID card reader;
judging whether the moving object moves on a moving plane or not based on the RFID label reading condition;
when the moving object moves on a moving plane, acquiring the size parameter of the moving object;
acquiring a first position relation parameter between a motion plane of the moving object and the camera shooting unit;
constructing a position plane of the moving object and determining a second position relation parameter between the position plane and the camera unit based on the size parameter and the first position relation parameter;
dividing the position plane into four areas by two straight lines which are vertical and pass through the projection of the camera unit on the position plane;
analyzing the image to obtain display parameters of the marker on the image; the display parameters include: a relative positional relationship of a shape, an area, and a projection position of the imaging unit within the image;
determining a region of the moving object located in the position plane based on the relative positional relationship;
determining the position of the moving object on the position plane based on the size parameter and the display parameter of the moving object;
and determining the position of the moving object relative to the movement plane based on the position of the moving object in the position plane and the position relation between the position plane and the movement plane.
7. The motion object position capture system of claim 1, further comprising:
and the at least one group of correlation gratings are arranged on two sides of the motion plane, are electrically connected with the processing unit and are used for determining whether the moving object moves on the motion plane according to the shielding condition of the moving object on the light rays of the correlation gratings.
8. A method for capturing a position of a moving object, comprising:
shooting an image of the moving object through a shooting unit; uniformly arranging a plurality of markers on the outer surface of the moving object in advance;
analyzing the image, determining a position of the moving object relative to a plane of motion based on the markers;
the analyzing the image, determining a position of the moving object relative to a plane of motion based on the markers comprises:
acquiring the size parameter of the moving object;
acquiring a first position relation parameter between the moving plane of the moving object and the camera shooting unit;
constructing a position plane of the moving object and determining a second position relation parameter between the position plane and the camera unit based on the size parameter and the first position relation parameter;
dividing the position plane into four areas by two straight lines which are vertical and pass through the projection of the camera unit on the position plane;
analyzing the image to obtain display parameters of the marker on the image; the display parameters include: a relative positional relationship of a shape, an area, and a projection position of the imaging unit within the image;
determining a region of the moving object located in the position plane based on the relative positional relationship;
determining a position relation library of the moving object and the position plane based on the position of the region composed of the markers in the image;
determining a third position relation parameter of the moving object and the camera unit based on the size parameter and the display parameter of the moving object;
determining a fourth position relation between the moving object and the position plane from the position relation library based on the second position relation parameter and the third position relation parameter;
and determining the position of the moving object and the moving plane based on the fourth position relation and the third position relation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011455386.7A CN112581532B (en) | 2020-12-10 | 2020-12-10 | System and method for capturing position of moving object |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011455386.7A CN112581532B (en) | 2020-12-10 | 2020-12-10 | System and method for capturing position of moving object |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112581532A CN112581532A (en) | 2021-03-30 |
| CN112581532B true CN112581532B (en) | 2021-07-13 |
Family
ID=75131529
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011455386.7A Active CN112581532B (en) | 2020-12-10 | 2020-12-10 | System and method for capturing position of moving object |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112581532B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114549442B (en) * | 2022-02-14 | 2022-09-20 | 常州市新创智能科技有限公司 | Real-time monitoring method, device and equipment for moving object and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001330411A (en) * | 2000-05-23 | 2001-11-30 | Fuji Electric Co Ltd | Position detecting method of moving object |
| CN101359051A (en) * | 2008-08-15 | 2009-02-04 | 中兴智能交通系统（北京）有限公司 | Method, system and apparatus for positioning objects |
| CN105809689A (en) * | 2016-03-09 | 2016-07-27 | 哈尔滨工程大学 | Machine vision-based ship hull six-degree-of-freedom measurement method |
| CN106851567A (en) * | 2017-01-16 | 2017-06-13 | 深圳拓邦股份有限公司 | A kind of localization method, apparatus and system |
| CN108846864A (en) * | 2018-05-29 | 2018-11-20 | 珠海全志科技股份有限公司 | A kind of position capture system, the method and device of moving object |
| EP3405927A1 (en) * | 2016-01-20 | 2018-11-28 | Carrier Corporation | A building management system using object detection and tracking in a large space with a low resolution sensor |
-
2020
- 2020-12-10 CN CN202011455386.7A patent/CN112581532B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001330411A (en) * | 2000-05-23 | 2001-11-30 | Fuji Electric Co Ltd | Position detecting method of moving object |
| CN101359051A (en) * | 2008-08-15 | 2009-02-04 | 中兴智能交通系统（北京）有限公司 | Method, system and apparatus for positioning objects |
| EP3405927A1 (en) * | 2016-01-20 | 2018-11-28 | Carrier Corporation | A building management system using object detection and tracking in a large space with a low resolution sensor |
| CN105809689A (en) * | 2016-03-09 | 2016-07-27 | 哈尔滨工程大学 | Machine vision-based ship hull six-degree-of-freedom measurement method |
| CN106851567A (en) * | 2017-01-16 | 2017-06-13 | 深圳拓邦股份有限公司 | A kind of localization method, apparatus and system |
| CN108846864A (en) * | 2018-05-29 | 2018-11-20 | 珠海全志科技股份有限公司 | A kind of position capture system, the method and device of moving object |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112581532A (en) | 2021-03-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103189827B (en) | Object display apparatus and object displaying method | |
| JP2020536324A (en) | Systems and methods for machine learning driven object detection | |
| CN111476827B (en) | Target tracking method, system, electronic device and storage medium | |
| JP4885867B2 (en) | POSITION INFORMATION DETECTING DEVICE, POSITION INFORMATION DETECTING METHOD, AND POSITION INFORMATION DETECTING PROGRAM | |
| CN109990662B (en) | Automatic target scoring method, device, equipment and computer readable storage medium | |
| CN109271937A (en) | Athletic ground Marker Identity method and system based on image procossing | |
| US20090084855A1 (en) | Methods and Apparatus for Directing Bar Code Positioning for Imaging Scanning | |
| CN109919157A (en) | A kind of vision positioning method and device | |
| CN112581532B (en) | System and method for capturing position of moving object | |
| CN111565293A (en) | Device, method, and program for analyzing state of manual work by operator | |
| CN110163916B (en) | Rolling target-based surrounding type circular mark point matching method | |
| CN115717867A (en) | Bridge deformation measurement method based on airborne double cameras and target tracking | |
| CN109948630B (en) | Target paper image identification method, device and system and storage medium | |
| CN111160280A (en) | RGBD camera-based target object identification and positioning method and mobile robot | |
| CN113515143A (en) | Robot navigation method, robot and computer readable storage medium | |
| CN108388854A (en) | A kind of localization method based on improvement FAST-SURF algorithms | |
| CN108550168A (en) | The multiple target quick high accuracy of Intelligentized mechanical arm view-based access control model identifies and localization method | |
| CN115187769A (en) | Positioning method and device | |
| CN113837044A (en) | Organ positioning method based on ambient brightness and related equipment | |
| CN115120950B (en) | Training assistance system, projection method, projection device and computer readable storage medium | |
| CN113082680A (en) | Automatic judgment system for ball out of bound of ball game based on machine vision | |
| CN112597929A (en) | Billiard position determining method and system | |
| CN111260309A (en) | Attendance checking method for automatic attendance checking | |
| CN112465873B (en) | Method and system for determining position of moving object in machine vision | |
| CN113011273B (en) | Intelligent visual detection method and system for billiard cue |
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 | ||
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address |
Address after: 518000 Room 201, building 4, software industry base, No. 19, 17 and 18, Haitian 1st Road, Binhai community, Yuehai street, Nanshan District, Shenzhen, Guangdong Patentee after: Shenzhen qidebao Technology Co.,Ltd. Address before: 518000 1705, satellite building, 61 Gaoxin South 9th Road, Gaoxin high tech Zone community, Yuehai street, Nanshan District, Shenzhen City, Guangdong Province Patentee before: Shenzhen Puhui Zhilian Technology Co.,Ltd. |