CN113262462A - Billiard cue real-time identification and projection method, system, terminal and storage medium - Google Patents
Billiard cue real-time identification and projection method, system, terminal and storage medium Download PDFInfo
- Publication number
- CN113262462A CN113262462A CN202110546238.4A CN202110546238A CN113262462A CN 113262462 A CN113262462 A CN 113262462A CN 202110546238 A CN202110546238 A CN 202110546238A CN 113262462 A CN113262462 A CN 113262462A
- Authority
- CN
- China
- Prior art keywords
- real
- time
- cue
- billiard
- projection
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000003860 storage Methods 0.000 title claims abstract description 10
- 238000001914 filtration Methods 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 9
- 238000000926 separation method Methods 0.000 claims description 8
- 238000004891 communication Methods 0.000 claims description 7
- 230000000877 morphologic effect Effects 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 5
- 238000003708 edge detection Methods 0.000 claims description 4
- 230000011218 segmentation Effects 0.000 claims description 4
- 230000008030 elimination Effects 0.000 claims description 3
- 238000003379 elimination reaction Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000003628 erosive effect Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000010339 dilation Effects 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000011524 similarity measure Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63D—BOWLING GAMES, e.g. SKITTLES, BOCCE OR BOWLS; INSTALLATIONS THEREFOR; BAGATELLE OR SIMILAR GAMES; BILLIARDS
- A63D15/00—Billiards, e.g. carom billiards or pocket billiards; Billiard tables
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63D—BOWLING GAMES, e.g. SKITTLES, BOCCE OR BOWLS; INSTALLATIONS THEREFOR; BAGATELLE OR SIMILAR GAMES; BILLIARDS
- A63D15/00—Billiards, e.g. carom billiards or pocket billiards; Billiard tables
- A63D15/006—Training or aiming arrangements on billiard tables
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63D—BOWLING GAMES, e.g. SKITTLES, BOCCE OR BOWLS; INSTALLATIONS THEREFOR; BAGATELLE OR SIMILAR GAMES; BILLIARDS
- A63D15/00—Billiards, e.g. carom billiards or pocket billiards; Billiard tables
- A63D2015/001—Billiards, e.g. carom billiards or pocket billiards; Billiard tables with inclination indicating means
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a method, a system, a terminal and a storage medium for real-time identification and projection of a billiard cue, wherein the method comprises the following steps: capturing real-time pictures of the table top of the billiard table in real time through a camera above the billiard table; identifying billiards and ball clubs in the real-time picture according to a preset identification network model; determining coordinate points of a tip and a tail of a ball rod in a preset coordinate system based on the table top; connecting the coordinate point of the club tip with the coordinate point of the club tail to obtain the motion track of the club; the movement track of the ball arm is projected on the preset position of the table surface through the projection component. The method provided by the invention has the advantages of lower equipment cost, more accurate identification precision and higher speed of the billiards and the cue, and basically no delay in the dynamic generation of the auxiliary line.
Description
[ technical field ] A method for producing a semiconductor device
The invention relates to the technical field of billiard ball assistance, in particular to a billiard ball rod real-time identification and projection method, a billiard ball rod real-time identification and projection system, a billiard ball rod real-time identification and projection terminal and a storage medium.
[ background of the invention ]
Billiards is a fun indoor sport, but it is difficult for a novice to enter a ball, and it is easy to strike the enthusiasm of the novice for practice. Therefore, the motion track after the ball hitting can be displayed on the table during the ball hitting, the track is updated in real time along with the aiming direction of the ball rod, namely, a dynamic auxiliary line is arranged during the ball hitting, and the ball-entering rate of a novice can be greatly improved. The existing billiard auxiliary system is to capture the positions of the ball and the rod by a pre-selected camera, analyze the data by an internal computer and display the movement track of the ball on the table surface by a projection method. However, the above prior art is generally completed by using an industrial camera and an infrared camera, which is high in cost and limited in use scene.
Accordingly, there is a need to provide a method, a system, a terminal and a storage medium for real-time identification and projection of a billiard cue, which overcome the above-mentioned drawbacks.
[ summary of the invention ]
The invention aims to provide a billiard cue real-time identification and projection method, a billiard cue real-time identification and projection system, a billiard cue real-time identification and projection terminal and a storage medium, and aims to solve the problems that an existing billiard cue auxiliary system is high in cost and limited in use scene.
In order to achieve the above object, a first aspect of the present invention provides a billiard cue real-time identification and projection method, including the following steps:
capturing real-time pictures of the table top of the billiard table in real time through a camera above the billiard table;
identifying the billiards and the cue in the real-time picture according to a preset identification network model;
determining coordinate points of the tip and the tail of the ball rod in a preset coordinate system based on the table top;
connecting the coordinate point of the club tip with the coordinate point of the club tail to obtain the motion track of the club;
and projecting the motion trail of the ball rod on a preset position of the table top through a projection component.
In a preferred embodiment, the step of capturing a real-time picture of the playing surface in real time by a camera directly above the billiard table comprises the following steps:
and carrying out Gaussian filtering denoising processing on the real-time picture.
In a preferred embodiment, after the gaussian filtering denoising processing is performed on the real-time picture, the method further comprises the following steps:
and performing RGB channel separation on the real-time picture, and performing thresholding segmentation according to a preset characteristic threshold value to generate a new real-time picture.
In a preferred embodiment, after generating the new real-time picture, the method further comprises the following steps:
and connecting broken rods in the new real-time picture through morphological closing operation.
In a preferred embodiment, the step of determining the coordinate points of the tip and the tail of the club in a predetermined table-based coordinate system comprises the steps of:
converting the RGB color space of the real-time picture into HSV space, and carrying out color channel separation on the HSV space to obtain an H channel, an S channel and a V channel;
calculating a histogram of the image on the H channel;
acquiring a chromatic value of green stage mud in the histogram; wherein the chromatic value of the green stage mud is the maximum value in the histogram;
green removal is carried out on the green table mud area of the table surface in the real-time picture;
filtering out the communication area of the non-ball rod through morphological operation;
counting the connected areas, calculating the minimum external rectangle, and searching the connected area with the maximum aspect ratio, namely the ball bar area;
and confirming the tip coordinates and the tail coordinates of the club through the club area.
In a preferred embodiment, after green elimination of the green area of the playing surface in the real-time picture, the method further comprises the following steps:
and edge detection is carried out on the table mud area of the table top through a preset gradient amplitude threshold value, and the edge interference of the table mud table top is filtered.
In a preferred embodiment, after counting the connected regions, calculating the minimum bounding rectangle, and finding the connected region with the largest aspect ratio, namely the club region, the method further comprises the following steps:
filtering a communication area bonded with the cue by drawing cue lines, and extracting a complete cue area again;
and calculating the minimum circumscribed rectangle of the complete ball bar area, and setting the minimum threshold value of the ball bar length.
The invention provides a billiard cue real-time identification and projection system, which comprises:
the camera is arranged right above the billiard table and used for capturing real-time pictures of the billiard table surface in real time;
the cue recognition model is used for recognizing the billiards and the cue in the real-time picture according to a preset recognition network model;
the coordinate determination module is used for determining coordinate points of the tip and the tail of the ball rod in a preset table-board-based coordinate system;
the track generation module is used for connecting the coordinate point of the rod tip with the coordinate point of the rod tail to obtain the motion track of the ball rod;
the projection assembly is used for projecting the motion trail of the ball rod at a preset position of the table top.
A third aspect of the present invention provides a terminal comprising a memory, a processor and a real-time billiard cue identifying and projecting program stored in the memory and executable on the processor, wherein the real-time billiard cue identifying and projecting program, when executed by the processor, implements the steps of the real-time billiard cue identifying and projecting method according to any one of the above embodiments.
A fourth aspect of the present invention provides a computer-readable storage medium storing a real-time billiard cue identification and projection program, which when executed by a processor, implements the steps of the real-time billiard cue identification and projection method according to any one of the above embodiments.
The invention provides a real-time identification and projection method of a billiard cue, which is characterized in that a camera is adopted to capture each frame of picture on a table surface, then identification of the billiard cue and the billiard cue is carried out in an identification network model, two coordinate points of a cue tip and a cue tail are determined, the two coordinate points are projected on the table surface and converted into coordinate points on the table surface, then a line formed by connecting the two coordinate points is a motion track, finally the motion track is projected on the table surface through a projection assembly, and the motion track is updated in real time when a user moves the direction of a cue. The method provided by the invention has the advantages of lower equipment cost, more accurate identification precision and higher speed of the billiards and the cue, and basically no delay in the dynamic generation of the auxiliary line.
[ description of the drawings ]
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
FIG. 1 is a flow chart of a method for identifying and projecting a billiard cue in real time according to the present invention;
FIG. 2 is a flow chart illustrating a sub-step of step S13 in the real-time billiard cue identification and projection method of FIG. 1;
FIG. 3 is a frame diagram of a billiard cue real-time identification and projection system provided by the present invention.
[ detailed description ] embodiments
In order to make the objects, technical solutions and advantageous effects of the present invention more clearly apparent, the present invention is further described in detail below with reference to the accompanying drawings and the detailed description. It should be understood that the detailed description and specific examples, while indicating the preferred embodiment of the invention, are intended for purposes of illustration only and are not intended to limit the scope of the invention.
It is also to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the specification of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.
In an embodiment of the invention, a first aspect provides a real-time identification and projection method for a billiard cue, which is used for projecting a motion track of the billiard cue in real time when a user hits a ball on a table, so as to achieve an effect of aiming assistance.
As shown in FIG. 1, the real-time identification and projection method of the billiard cue comprises the following steps S11-S15.
And step S11, capturing real-time pictures of the table top in real time through a camera directly above the billiard table.
In this step, the camera is disposed right above the billiard table, so that real-time image information of each frame of the billiard table surface (i.e. the side of the billiard table away from the ground) can be captured at a vertical angle from the normal direction of the billiard table surface. The camera needs to be calibrated in advance to correct the picture. The real-time picture information includes the position of the hole (i.e., the pocket), the distribution of the billiards, and the placement of the cue.
Specifically, before the subsequent identification step is performed on the real-time picture captured by the camera, the method further includes the following preprocessing steps: and carrying out Gaussian filtering denoising processing on the real-time picture. The method is characterized in that the method is a process of weighted average of the whole real-time picture, and the value of each pixel point is obtained by weighted average of the pixel point and other pixel values in the neighborhood, so that the image information is smoothed, noise is eliminated, and an image with high signal-to-noise ratio is obtained.
Further, RGB channel separation is carried out on the real-time picture after Gaussian filtering processing, and then thresholding segmentation is carried out according to a preset characteristic threshold value to generate a new real-time picture. Specifically, after the RBG channel separation is performed on the real-time picture, three pictures, one red, one green, and one blue are generated. Then, the feature threshold may be preset, so that the real-time image of each color channel is segmented according to the similarity measure, and binary segmented images (i.e. new real-time pictures) are respectively generated, thereby facilitating subsequent identification and processing.
Further, since the club is often held by the hand of the user, the club may be in a broken state (the hollow portion is the hand-held portion) after the color channel separation is performed due to the different colors of the club and the hand. Therefore, the broken bar in the new real-time screen can be connected through the morphological closing operation. Specifically, the mathematical morphology operations can be divided into binary morphology and gray scale morphology, and include two basic operations, namely erosion and dilation, where the closed operation is first dilation and then erosion. The expansion can make the range of the target area become larger, background points contacted with the target area are combined into the target object, the boundary of the target object is expanded outwards, and the function is to fill some holes in the target area and eliminate small particle noise contained in the target area, namely to fill the holes of the club. Erosion can "narrow" the target area, which essentially causes the image boundaries to shrink, and can be used to eliminate small and meaningless objects.
And continuing to execute the step S12, and identifying the billiards and the cue in the real-time picture according to the preset identification network model. The recognition network model is constructed based on a deep neural network and is trained in advance through a training set containing a plurality of billiard and cue pictures to obtain the trained recognition network model. The billiards and the cue in the real-time picture are identified through the identification network model, so that the identification precision is more accurate and the speed is higher.
And step S13, determining coordinate points of the tip and the tail of the club in a preset table-based coordinate system.
Specifically, as shown in fig. 2, step S13 includes the following steps S131 to S137.
Step S131, converting the RGB color space of the real-time picture into HSV space, and performing color channel separation on the HSV space to obtain an H channel, an S channel and a V channel. Wherein, H value represents hue, S value represents saturation, and V value represents brightness.
In step S132, a histogram of the image is calculated on the H channel. Where represented on the histogram of the cone, the angle represents the hue H, the saturation S is represented as the distance of the point to the central vertical line, and the brightness value V is represented by the central vertical line.
Step S133, acquiring a chromatic value of green stage mud in the histogram; and the chromatic value of the green stage mud is the maximum value in the histogram. Wherein, because the table surface is basically green, the green table mud must be the maximum value in the histogram of the statistical number.
Step S134, green elimination is performed on the green table mud area of the table surface in the real-time picture. Namely, the background color of the cue is eliminated, thereby facilitating the subsequent image processing. In the process of filtering green stage mud, the broken rod is easily caused, so that the broken rod can be connected by morphological closing operation again.
In step S135, the connected region other than the club is filtered out by morphological operations. For the extraction step and the filtering step of the connected region in the binary segmentation image, reference may be made to the prior art, and this embodiment is not limited herein.
Further, as shown in fig. 2, after step S135, step S130 is further included, edge detection is performed on the table mud area of the table top through a preset gradient amplitude threshold, so as to filter out the interference of the table mud table top edge. It can be appreciated that the playing surface includes a green table mud portion and a table top border portion that encloses the green table mud portion. By carrying out edge detection on the table mud area of the table top, the data volume is greatly reduced, information which can be considered irrelevant is removed, and important structural attributes of the image are reserved.
And S136, counting the connected areas, calculating the minimum external rectangle, and searching the connected area with the maximum aspect ratio, namely the ball bar area.
Further, as shown in FIG. 2, steps S138-S139 are included after step S136.
Step S138, filtering a communication area bonded with the ball rod by drawing ball rod lines, and extracting a complete ball rod area again; and step S139, calculating the minimum circumscribed rectangle of the complete ball bar area, and setting the minimum threshold value of the ball bar length.
Continuing to step S137, the tip coordinates and the butt coordinates of the club are confirmed through the club region.
And step S14, connecting the coordinate point of the club tip with the coordinate point of the club tail to obtain the motion track of the club. The two coordinate points are projected on the table top and converted into coordinate points on the table top, and then a line formed by connecting the coordinate points is the motion track. It will be appreciated that the cue strikes the ball by moving back and forth, and therefore the direction of movement of the cue must be in the direction of the cue itself.
And step S15, projecting the movement track of the ball arm on the preset position of the table surface through the projection component.
Specifically, two projectors can be placed on the upper portion of the center of the table, and then a preset projection fusion program is used for fusing the projectors into a projection effect, so that forward projection is achieved, the picture is corrected, and the real scene of the room is completely adapted. The club recognition is always in work after the system is started, so that the motion track is updated in real time when the user moves the direction of the club.
It should be noted that, in an implementation mode, since the top of a common billiard table is provided with a lamp, the position for placing the lamp is replaced by a billiard dynamic auxiliary system, and the main components of the system comprise: two headlights on two sides, a camera in the middle, two projectors, a computer, a power supply and a remote controller. The remote controller is provided with corresponding buttons which can control the computer, the lamp, the projection switch and the like.
In summary, according to the real-time identification and projection method for the billiard cue provided by the invention, each frame of picture on the table top is captured by the camera, then identification of the billiard cue and the billiard cue is carried out in the identification network model, two coordinate points of the cue tip and the cue tail are determined, the two coordinate points are projected on the table top and converted into coordinate points on the table top, then a line formed by connecting the two coordinate points is a motion track, finally the motion track is projected on the table top through the projection assembly, and the motion track is updated in real time when the user moves the direction of the cue. The method provided by the invention has the advantages of lower equipment cost, more accurate identification precision and higher speed of the billiards and the cue, and basically no delay in the dynamic generation of the auxiliary line.
The invention provides a real-time identification and projection system 100 for a billiard cue, which is used for projecting the motion track of the billiard cue in real time when a user hits a ball on a table, so as to achieve the effect of aiming assistance. It should be noted that the implementation principle and the implementation mode of the billiard cue real-time identification and projection system 100 are consistent with the billiard cue real-time identification and projection method described above, and therefore, the following description is omitted.
As shown in fig. 3, the billiard cue real-time identification and projection system 100 includes:
the camera 10 is arranged right above the billiard table and used for capturing real-time pictures of the billiard table surface in real time;
the cue recognition model 20 is used for recognizing the billiards and the cue in the real-time picture according to a preset recognition network model;
the coordinate determination module 30 is used for determining coordinate points of the tip and the tail of the ball rod in a preset table-board-based coordinate system;
the track generation module 40 is used for connecting the coordinate point of the club tip with the coordinate point of the club tail to obtain the motion track of the club;
and the projection assembly 50 is used for projecting the motion trail of the ball rod at the preset position of the table surface.
A third aspect of the present invention provides a terminal (not shown in the drawings), which includes a memory, a processor and a real-time billiard cue identifying and projecting program stored in the memory and capable of running on the processor, wherein the real-time billiard cue identifying and projecting program, when executed by the processor, implements the steps of the real-time billiard cue identifying and projecting method according to any one of the embodiments described above.
A fourth aspect of the present invention provides a computer-readable storage medium (not shown in the drawings), wherein a real-time billiard cue identifying and projecting program is stored in the computer-readable storage medium, and when the real-time billiard cue identifying and projecting program is executed by a processor, the real-time billiard cue identifying and projecting program implements the steps of the real-time billiard cue identifying and projecting method according to any one of the above embodiments.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working processes of the units and modules in the system may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.
Those of ordinary skill in the art will appreciate that the various illustrative elements and method steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the embodiments provided in the present invention, it should be understood that the disclosed system or apparatus/terminal device and method can be implemented in other ways. For example, the above-described system or apparatus/terminal device embodiments are merely illustrative, and for example, the division of the modules or units is only one logical division, and there may be other divisions when actually implemented, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The invention is not limited solely to that described in the specification and embodiments, and additional advantages and modifications will readily occur to those skilled in the art, so that the invention is not limited to the specific details, representative apparatus, and illustrative examples shown and described herein, without departing from the spirit and scope of the general concept as defined by the appended claims and their equivalents.
Claims (10)
1. A real-time identification and projection method of a billiard cue is characterized by comprising the following steps:
capturing real-time pictures of the table top of the billiard table in real time through a camera above the billiard table;
identifying the billiards and the cue in the real-time picture according to a preset identification network model;
determining coordinate points of the tip and the tail of the ball rod in a preset coordinate system based on the table top;
connecting the coordinate point of the club tip with the coordinate point of the club tail to obtain the motion track of the club;
and projecting the motion trail of the ball rod on a preset position of the table top through a projection component.
2. A billiard cue real-time identification and projection method as recited in claim 1, wherein after the step of capturing real-time images of the playing surface in real-time with a camera directly above the billiard table, the method includes the steps of:
and carrying out Gaussian filtering denoising processing on the real-time picture.
3. The billiard cue real-time identification and projection method of claim 2, wherein after the gaussian filtering denoising process is performed on the real-time image, the method further comprises the steps of:
and performing RGB channel separation on the real-time picture, and performing thresholding segmentation according to a preset characteristic threshold value to generate a new real-time picture.
4. A billiard cue real-time identification and projection method of claim 3, further including the step of, after generating a new real-time image:
and connecting broken rods in the new real-time picture through morphological closing operation.
5. A method of identifying and projecting a billiard cue as claimed in claim 1, wherein the step of determining the coordinate points of the tip and tail of the cue in a predetermined table-based coordinate system includes the steps of:
converting the RGB color space of the real-time picture into HSV space, and carrying out color channel separation on the HSV space to obtain an H channel, an S channel and a V channel;
calculating a histogram of the image on the H channel;
acquiring a chromatic value of green stage mud in the histogram; wherein the chromatic value of the green stage mud is the maximum value in the histogram;
green removal is carried out on the green table mud area of the table surface in the real-time picture;
filtering out the communication area of the non-ball rod through morphological operation;
counting the connected areas, calculating the minimum external rectangle, and searching the connected area with the maximum aspect ratio, namely the ball bar area;
and confirming the tip coordinates and the tail coordinates of the club through the club area.
6. The billiard cue real-time identification and projection method of claim 5, wherein after green elimination of the green area of the playing surface in the real-time frame, further comprising the steps of:
and edge detection is carried out on the table mud area of the table top through a preset gradient amplitude threshold value, and the edge interference of the table mud table top is filtered.
7. A billiard cue real-time identification and projection method as claimed in claim 5, wherein after counting said connected regions, calculating the smallest bounding rectangle, and finding the connected region with the largest aspect ratio, that is, the cue region, further comprising the steps of:
filtering a communication area bonded with the cue by drawing cue lines, and extracting a complete cue area again;
and calculating the minimum circumscribed rectangle of the complete ball bar area, and setting the minimum threshold value of the ball bar length.
8. A billiard cue real-time identification and projection system is characterized by comprising:
the camera is arranged right above the billiard table and used for capturing real-time pictures of the billiard table surface in real time;
the cue recognition model is used for recognizing the billiards and the cue in the real-time picture according to a preset recognition network model;
the coordinate determination module is used for determining coordinate points of the tip and the tail of the ball rod in a preset table-board-based coordinate system;
the track generation module is used for connecting the coordinate point of the rod tip with the coordinate point of the rod tail to obtain the motion track of the ball rod;
the projection assembly is used for projecting the motion trail of the ball rod at a preset position of the table top.
9. A terminal comprising a memory, a processor, and a real-time billiard cue identification and projection program stored in the memory and executable on the processor, wherein the real-time billiard cue identification and projection program, when executed by the processor, implements the steps of the method of any one of claims 1-7.
10. A computer-readable storage medium storing a real-time billiard cue recognition and projection program, wherein the real-time billiard cue recognition and projection program, when executed by a processor, implements the steps of the real-time billiard cue recognition and projection method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110546238.4A CN113262462A (en) | 2021-05-19 | 2021-05-19 | Billiard cue real-time identification and projection method, system, terminal and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110546238.4A CN113262462A (en) | 2021-05-19 | 2021-05-19 | Billiard cue real-time identification and projection method, system, terminal and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113262462A true CN113262462A (en) | 2021-08-17 |
Family
ID=77232126
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110546238.4A Pending CN113262462A (en) | 2021-05-19 | 2021-05-19 | Billiard cue real-time identification and projection method, system, terminal and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113262462A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113836800A (en) * | 2021-09-10 | 2021-12-24 | 山东新一代信息产业技术研究院有限公司 | Billiard cue positioning method, device, equipment and medium integrating artificial intelligence |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102327697A (en) * | 2011-10-14 | 2012-01-25 | 李姣昂 | Projection-type billiard training system and implementation method thereof |
| CN103170126A (en) * | 2011-12-20 | 2013-06-26 | 西安天动数字科技有限公司 | Interactive billiard table system |
| CN104117201A (en) * | 2014-07-02 | 2014-10-29 | 乔冰 | Projection type billiard system gesture/billiard rod control system and implement method of projection type billiard system gesture/billiard rod control system |
| CN104117202A (en) * | 2014-07-02 | 2014-10-29 | 乔冰 | Projection type billiard hitting intelligent auxiliary system and method |
| CN106853290A (en) * | 2015-12-09 | 2017-06-16 | 西安沃贝农业科技有限公司 | A kind of billiards supplemental training device |
| CN112597929A (en) * | 2020-12-28 | 2021-04-02 | 深圳市普汇智联科技有限公司 | Billiard position determining method and system |
-
2021
- 2021-05-19 CN CN202110546238.4A patent/CN113262462A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102327697A (en) * | 2011-10-14 | 2012-01-25 | 李姣昂 | Projection-type billiard training system and implementation method thereof |
| CN103170126A (en) * | 2011-12-20 | 2013-06-26 | 西安天动数字科技有限公司 | Interactive billiard table system |
| CN104117201A (en) * | 2014-07-02 | 2014-10-29 | 乔冰 | Projection type billiard system gesture/billiard rod control system and implement method of projection type billiard system gesture/billiard rod control system |
| CN104117202A (en) * | 2014-07-02 | 2014-10-29 | 乔冰 | Projection type billiard hitting intelligent auxiliary system and method |
| CN106853290A (en) * | 2015-12-09 | 2017-06-16 | 西安沃贝农业科技有限公司 | A kind of billiards supplemental training device |
| CN112597929A (en) * | 2020-12-28 | 2021-04-02 | 深圳市普汇智联科技有限公司 | Billiard position determining method and system |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113836800A (en) * | 2021-09-10 | 2021-12-24 | 山东新一代信息产业技术研究院有限公司 | Billiard cue positioning method, device, equipment and medium integrating artificial intelligence |
| CN113836800B (en) * | 2021-09-10 | 2024-03-26 | 山东新一代信息产业技术研究院有限公司 | Billiard cue positioning method, device, equipment and medium integrating artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110232311B (en) | Method and device for segmenting hand image and computer equipment | |
| CN106924961B (en) | Intelligent chess playing control method and system | |
| CN100357959C (en) | Facial parts position detection device, method for detecting facial parts position, and program for detecting facial parts position | |
| TW201814435A (en) | Method and system for gesture-based interactions | |
| CN109271937A (en) | Athletic ground Marker Identity method and system based on image procossing | |
| CN105844242A (en) | Method for detecting skin color in image | |
| CN104517101A (en) | Game poker card recognition method based on pixel square difference matching | |
| CN112287867B (en) | Multi-camera human body action recognition method and device | |
| US20190311186A1 (en) | Face recognition method | |
| CN110032932B (en) | Human body posture identification method based on video processing and decision tree set threshold | |
| CN109117753A (en) | Position recognition methods, device, terminal and storage medium | |
| US8817125B2 (en) | Gesture recognition using chroma-keying | |
| US9947106B2 (en) | Method and electronic device for object tracking in a light-field capture | |
| CN113837065A (en) | Image processing method and device | |
| CN113262462A (en) | Billiard cue real-time identification and projection method, system, terminal and storage medium | |
| JP2004248725A (en) | Analysis device and method of shot ball | |
| CN111738264A (en) | Intelligent acquisition method for data of display panel of machine room equipment | |
| JP5016012B2 (en) | Silhouette extraction method | |
| CN114332629B (en) | Method for measuring multi-pesticide fogdrop impact leaf surface delay based on high-speed visual coupling contour feature extraction | |
| JP4181313B2 (en) | Scene content information adding device and scene content information adding program | |
| CN111046834B (en) | Monitoring video figure proportion correction method based on automatic learning analysis | |
| CN108121963B (en) | Video data processing method and device and computing equipment | |
| US20180211397A1 (en) | Object extraction from video images system and method | |
| CN114387354B (en) | Ping-pong ball drop point detection method and system based on improved color gamut recognition technology | |
| CN103533242B (en) | The method and system with tracking cursor point are extracted in video out of focus |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210817 |
|
| RJ01 | Rejection of invention patent application after publication |