CN215954346U - Video shooting device for automatically generating point maps of athletes in basketball game - Google Patents
Video shooting device for automatically generating point maps of athletes in basketball game Download PDFInfo
- Publication number
- CN215954346U CN215954346U CN202121868598.8U CN202121868598U CN215954346U CN 215954346 U CN215954346 U CN 215954346U CN 202121868598 U CN202121868598 U CN 202121868598U CN 215954346 U CN215954346 U CN 215954346U
- Authority
- CN
- China
- Prior art keywords
- basketball
- automatically generating
- camera
- video
- dot
- 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
- 230000002093 peripheral effect Effects 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 3
- 230000005611 electricity Effects 0.000 claims 1
- 239000011159 matrix material Substances 0.000 abstract description 31
- 230000009466 transformation Effects 0.000 abstract description 10
- 230000011218 segmentation Effects 0.000 abstract description 9
- 238000004458 analytical method Methods 0.000 abstract description 4
- 238000013507 mapping Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 15
- 238000000034 method Methods 0.000 description 9
- 238000001514 detection method Methods 0.000 description 8
- 238000009434 installation Methods 0.000 description 3
- 230000036544 posture Effects 0.000 description 3
- 238000012937 correction Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000008094 contradictory effect Effects 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Images
Landscapes
- Studio Devices (AREA)
Abstract
The utility model relates to the technical field of video recording of sports events, and discloses a video shooting device for automatically generating a dot matrix of a basketball game, calculating homography matrix of current picture and basketball court plane picture by using calibrated parameter matrix of wide-angle camera and corner information of two-value segmentation picture of basketball court, the homography or perspective transformation is carried out on the image through the homography matrix, the mapping of the positions of the athletes to the plane graph of the basketball court is completed, the generated point bitmap is fused into the original video image for output, therefore, the positions of the players are displayed while the video images of the basketball game are shot and recorded, the dot maps of the players in the basketball court in the plane positions of the basketball court can be automatically generated in real time, tactical analysis and planning can be conveniently carried out during or after the basketball game, and the efficiency and the intelligent degree of dot map drawing are greatly improved.
Description
Technical Field
The utility model relates to the technical field of video recording of sports events, in particular to a video shooting device for automatically generating a dot matrix of an athlete in a basketball game.
Background
At present, the plan position schematic diagram (dot diagram) of athletes in the existing basketball game is mostly drawn manually, after the game is finished, the game video is watched by professionals, the positions of the athletes in the game video are drawn into the dot diagram correspondingly, the dot diagram of the athletes is drawn manually, time and labor are wasted, the efficiency is low, although some software can enable the work of drawing tracks to be easier, the software needs to be used after the game, and the dot diagram cannot be generated when the game video is shot and recorded.
SUMMERY OF THE UTILITY MODEL
The utility model mainly aims to provide a video shooting device for automatically generating a dot bitmap of an athlete in a basketball game, which aims to generate a plane position schematic diagram (dot bitmap) of the athlete while shooting and recording a video of the basketball game for tactical analysis and planning in or after the basketball game.
In order to achieve the purpose, the video shooting device for automatically generating the dot chart of the athlete in the basketball game comprises a camera body, a supporting rod and a tripod, wherein the upper end part of the supporting rod is detachably and fixedly connected with the lower end wall of the camera body, the lower end part of the supporting rod is connected with the upper end part of the tripod in a vertically sliding and horizontally rotating manner, a wide-angle camera and a microphone are arranged at the front end part of the camera body, a viewfinder eyepiece is arranged at the upper end part of the camera body, and a main control chip, a CMOS image sensor and an image signal processing unit are arranged in the camera body and are respectively and electrically connected with the main control chip.
Furthermore, the upper end of the supporting rod is provided with a threaded hole, the lower end wall of the camera body is convexly provided with a screw rod, and the screw rod is detachably screwed in the threaded hole.
Further, the tripod comprises fastening screws, an installation sleeve is arranged at the upper end of the tripod, the lower end of the supporting rod is embedded in the installation sleeve in a vertically sliding and horizontally rotating mode, the fastening screws are respectively screwed on the peripheral wall of the upper end of the installation sleeve, and the front end of each fastening screw can be abutted to the peripheral wall of the corresponding supporting rod.
Furthermore, a handle is arranged at the upper end part of the camera body.
Further, the resolution of the wide-angle camera is 2K or 4K.
Furthermore, the master control chip adopts an ASC8850 microprocessor chip of NXP,
further, the CMOS image sensor adopts an ICX445CMOS image sensor of SONY.
By adopting the technical scheme of the utility model, the utility model has the following beneficial effects: according to the technical scheme, the homography matrix of the current picture and the plane diagram of the basketball court is calculated through the calibrated parameter matrix of the wide-angle camera and the corner information of the two-value segmentation diagram of the basketball court, the homography transformation or perspective transformation is carried out on the image through the homography matrix, the positions of players are mapped to the plane diagram of the basketball court, and the generated dot-matrix diagram is fused into the original video image for output, so that the positions of the players are displayed while the video image of the basketball game is shot and recorded, the dot-matrix diagrams of the players in the plane position of the basketball court of both players can be automatically generated in real time, the tactical analysis and planning during or after the basketball game are facilitated, and the efficiency and the intelligent degree of dot-matrix drawing are greatly improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the structures shown in the drawings without creative efforts.
FIG. 1 is a flowchart illustrating the overall process steps of a method for automatically generating a point map of an athlete during a basketball game in accordance with the present invention;
FIG. 2 is a flowchart of the steps of boundary detection and binary segmentation of images of a basketball court in a method for automatically generating a dot map of a player in a basketball game according to the present invention;
FIG. 3 is an architectural diagram of an Encoder and a Decode according to a method for automatically generating a point map of an athlete in a basketball game according to the present invention;
FIG. 4 is a schematic flow chart of the detection and player tracking of the method for automatically generating the point map of the player in the basketball game according to the present invention;
FIG. 5 is a general block diagram of a video camera for automatically generating a point map of a player for a basketball game according to the present invention;
fig. 6 is an overall view of another view angle of the video camera for automatically generating the point map of the player in the basketball game according to the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that all the directional indicators (such as up, down, left, right, front, and rear … …) in the embodiment of the present invention are only used to explain the relative position relationship between the components, the movement situation, etc. in a specific posture (as shown in the drawing), and if the specific posture is changed, the directional indicator is changed accordingly.
In addition, technical solutions between various embodiments may be combined with each other, but must be realized by a person skilled in the art, and when the technical solutions are contradictory or cannot be realized, such a combination should not be considered to exist, and is not within the protection scope of the present invention.
The utility model provides a video shooting device for automatically generating a dot diagram of an athlete in a basketball game.
As shown in fig. 5 and 6, the video camera device for automatically generating a dot chart of an athlete in a basketball game according to the present invention includes a camera body 101, a support rod 102 and a tripod 103, an upper end of the support rod 102 is detachably and fixedly connected to a lower end wall of the camera body 101, a lower end of the support rod 102 is connected to an upper end of the tripod 103 in a vertically slidable and laterally rotatable manner, a wide-angle camera 1011 and a microphone (not shown) are disposed at a front end of the camera body 101, a viewfinder eyepiece 1012 is disposed at an upper end of the camera body 101, and a main control chip (not shown) and a CMOS image sensor (not shown) and an image signal processing unit (not shown) electrically connected to the main control chip are disposed in the camera body 101.
Optionally, a threaded hole is formed in the upper end of the support rod 102, a screw rod is convexly arranged on the lower end wall of the camera body 101, and the screw rod is detachably screwed in the threaded hole.
Optionally, the tripod 103 further comprises fastening screws (not shown), an upper end portion of the tripod 103 is provided with a mounting sleeve 1031, a lower end portion of the support rod 102 is embedded in the mounting sleeve 1031 in a manner of being capable of sliding up and down and rotating left and right, the fastening screws are respectively screwed on the peripheral wall of the upper end portion of the mounting sleeve 1031, and front end portions of the fastening screws are respectively capable of abutting against the peripheral wall of the support rod 102.
Optionally, a handle 1013 is provided at an upper end portion of the camera body 101.
Optionally, the resolution of the wide-angle camera 1011 is 2K or 4K.
Optionally, the main control chip is an ASC8850 microprocessor chip of NXP, and the CMOS image sensor is an ICX445CMOS image sensor of SONY.
As shown in fig. 1 to 4, the present invention also provides a method for automatically generating a point map of a player in a basketball game, comprising the steps of:
s1: selecting the position of a wide-angle camera, and shooting a full-field picture of a basketball game through the wide-angle camera;
s2: calibrating the wide-angle camera and correcting the distortion of the image, and correcting the distortion of the image of the wide-angle camera by changing the parameter matrix;
s3: basketball court boundary detection and image segmentation, namely completing the basketball court boundary detection and the image binary segmentation through a coding-decoding model, wherein a flow step diagram is shown in figure 2, and architectures of an Encoder and a Decoder are shown in figure 3;
s4: athlete detection and athlete tracking, wherein staff tracking information is generated through a multi-target detection and tracking model, and the players on the field are judged and tracked in real time through a filter by combining boundary detection of a basketball court and binary segmentation information of an image, the team and referee of the players on both sides of a game are distinguished through a color filter, and the flow steps are shown in figure 4;
s5: mapping the positions of the athletes, calculating a homography matrix of a current picture and a plane drawing of the basketball court according to a calibrated parameter matrix of the wide-angle camera and the corner information of the two-value segmentation drawing of the basketball court, and performing homography transformation or perspective transformation on the images according to the homography matrix to map the positions of the athletes to the plane drawing of the basketball court;
s6: and automatically generating a video image with a dot pattern, and fusing the dot pattern generated in the step S5 into the original video image for output, wherein the positions of all players are displayed in the video image, and the positions of the dot pattern of all players are determined by the lowest points of the center lines of the frames traced by the players in the step S4.
Optionally, a specific method for performing distortion correction on the wide-angle camera image by changing the parameter matrix in step S2 is as follows:
step S2.1: the wide-angle camera shoots 10-20 calibration images on the calibration board printed with the black and white chessmen at different positions, different angles and different postures;
step S2.2: extracting vertex position information of each corner on each calibration image, wherein a corner detector adopts Harris or Shi-Tomasi;
step S2.3: calculating a translation vector and a rotation vector through optimization iteration;
step S2.4: calculating a parameter matrix KK of the wide-angle camera;
step S2.5: and performing geometric transformation on the image by using the obtained parameter matrix KK so as to finish the distortion correction of the wide-angle camera image.
The relationship between the pixel positions xp and yp of the calibrated image and the pixel positions xd (1) and xd (2) of the pre-calibrated image is as follows:
KK is a camera parameter matrix, and by using the matrix and the formula, corresponding position transformation can be carried out on points on the distorted image, so that the image is corrected. The possible parameters in the KK camera parameter matrix are described as follows:
wherein,
fc (1) and fc (2) are focal lengths of the camera in each direction in units of pixels;
cc (1) and cc (2) are camera principal point coordinates in units of pixels;
alpha _ c is a skew coefficient;
kc is a distortion parameter of the image, including radial distortion and tangential distortion;
the above parameters are all calculated by the camera parameter calculation step.
Optionally, in step S4, the working method of the filter is specifically as follows:
step S4.1: calculating the coordinate position of the midpoint at the bottom of the square frame according to the personnel detection and the finally provided square frame;
step S4.2: judging whether the point position in the previous frame is in a white area or not according to the binarization segmentation information;
step S4.3: if the midpoint location is within the white area, retaining the box; otherwise, the block is discarded.
Optionally, in step S5, the method for solving and transforming the homography matrix is specifically as follows:
step S5.1: obtaining coordinates x (i) and y (i) of 4 corner points according to corner point information of a spherical field binary segmentation image in a video, wherein i is 1-4;
step S5.2: the height-width ratio of the basketball court is a fixed value, coordinates of 4 angular points, x ^ (i) and y ^ i are set according to the height-width ratio, wherein i ^ 1-4, and the numerical value is about the same magnitude as the number in the first step;
step S5.3: the two sets of coordinates satisfy the following relationship:
and substituting the coordinates of each point to expand to obtain:
step S5.4: h is to be33Setting the homography matrix to be 1, and solving by Least square estimation (Least square estimation) to obtain a homography matrix H;
step S5.5: by means of the H matrix, video coordinates x of each player2And y2Information transformation is carried out to generate point location coordinates x1And y1The conversion formula is as follows:
specifically, the homography matrix of the current picture and the plane graph of the basketball court is calculated through the calibrated parameter matrix of the wide-angle camera and the corner information of the two-value segmentation graph of the basketball court, the homography matrix is used for carrying out homography transformation or perspective transformation on the image, the positions of players are mapped to the plane graph of the basketball court, and the generated dot-matrix is fused into the original video image for output, so that the positions of the players are displayed while the video image of the basketball game is shot and recorded, the dot-matrix of the planar positions of the players in the basketball court of both players can be automatically generated in real time, tactical analysis and planning can be conveniently carried out during or after the basketball game, and the drawing efficiency and the intelligent degree of the dot-matrix are greatly improved.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications and equivalents of the technical solutions of the present invention, which are made by using the contents of the present specification and the accompanying drawings, or directly/indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (7)
1. The utility model provides a basketball match automatic generation sportsman's point bitmap's video shooting device, a serial communication port, including camera body, bracing piece and tripod, the upper end of bracing piece with fixed connection can be dismantled to the lower terminal wall of camera body, the lower tip of bracing piece with the upper end of tripod can slide from top to bottom and control the rotation and connect, the preceding tip of camera body is equipped with a wide-angle camera and microphone, the upper end of camera body is equipped with a view finder eyepiece, this internal main control chip that is equipped with of camera and respectively with CMOS image sensor and the image signal processing unit that the main control chip electricity is connected.
2. The video shooting device for automatically generating the dot charts of the athletes in the basketball game as claimed in claim 1, wherein a threaded hole is formed in the upper end of the supporting rod, a screw rod is convexly arranged on the lower end wall of the camera body, and the screw rod is detachably screwed in the threaded hole.
3. The video shooting device for automatically generating the dot charts of the athletes in the basketball game as claimed in claim 1, further comprising fastening screws, wherein a mounting sleeve is provided at the upper end of the tripod, the lower end of the support rod is embedded in the mounting sleeve in a manner of sliding up and down and rotating left and right, the fastening screws are respectively screwed on the peripheral wall of the upper end of the mounting sleeve, and the front ends of the fastening screws are respectively arranged in a manner of being abutted against the peripheral wall of the support rod.
4. The video camera for automatically generating the dot charts of the players in the basketball game as claimed in claim 1, wherein a handle is provided at the upper end of the camera body.
5. The video camera for automatically generating player point maps for basketball games as in claim 1, wherein said wide angle camera has a resolution of 2K or 4K.
6. The video shooting device for automatically generating the dot patterns of the players in the basketball game as claimed in claim 1, wherein the main control chip adopts an ASC8850 microprocessor chip of NXP.
7. The video camera for automatically generating player point maps for basketball games as in claim 1, wherein said CMOS image sensor is a SONY ICX445CMOS image sensor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202121868598.8U CN215954346U (en) | 2021-08-10 | 2021-08-10 | Video shooting device for automatically generating point maps of athletes in basketball game |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202121868598.8U CN215954346U (en) | 2021-08-10 | 2021-08-10 | Video shooting device for automatically generating point maps of athletes in basketball game |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN215954346U true CN215954346U (en) | 2022-03-04 |
Family
ID=80435585
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202121868598.8U Active CN215954346U (en) | 2021-08-10 | 2021-08-10 | Video shooting device for automatically generating point maps of athletes in basketball game |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN215954346U (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113506210A (en) * | 2021-08-10 | 2021-10-15 | 深圳市前海动竞体育科技有限公司 | Method for automatically generating point maps of athletes in basketball game and video shooting device |
-
2021
- 2021-08-10 CN CN202121868598.8U patent/CN215954346U/en active Active
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113506210A (en) * | 2021-08-10 | 2021-10-15 | 深圳市前海动竞体育科技有限公司 | Method for automatically generating point maps of athletes in basketball game and video shooting device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107766855B (en) | Chessman positioning method and system based on machine vision, storage medium and robot | |
| CN113506210A (en) | Method for automatically generating point maps of athletes in basketball game and video shooting device | |
| KR20140086938A (en) | Method and system for photographing object in movement with fixed camera, and based on taken images therefor, obtaining projection image of actual movement trace of same object | |
| CN109934878A (en) | A kind of linear calibration's system and method based on camera coordinates system | |
| CN108629756A (en) | A kind of Kinect v2 depth images Null Spot restorative procedure | |
| CN110490943B (en) | Rapid and accurate calibration method and system of 4D holographic capture system and storage medium | |
| CN106886976B (en) | Image generation method for correcting fisheye camera based on internal parameters | |
| CN101628174B (en) | Automatic distortion correction extraction method of coordinates of Snooker tabletop | |
| CN215954346U (en) | Video shooting device for automatically generating point maps of athletes in basketball game | |
| CN108257186A (en) | Method and device for determining calibration image, camera and storage medium | |
| CN112184807A (en) | Floor type detection method and system for golf balls and storage medium | |
| CN109883433A (en) | Vehicle positioning method in structured environment based on 360 degree of panoramic views | |
| WO2020105697A1 (en) | Motion capture camera system and calibration method | |
| CN105513074A (en) | Badminton robot camera calibration method | |
| CN107734223B (en) | Positioning device based on image identification | |
| CN114037923A (en) | Target activity hotspot graph drawing method, system, equipment and storage medium | |
| CN116449387B (en) | Multi-dimensional environment information acquisition platform and calibration method thereof | |
| CN117115273A (en) | Camera self-calibration method and system based on badminton court sideline detection | |
| CN107087219B (en) | Human posture's identification device | |
| CN107094264A (en) | Intelligent network player | |
| CN107770586A (en) | cloud computer device | |
| KR102603819B1 (en) | Golf ball landing type detection method, system and storage medium | |
| CN114612522B (en) | Table tennis sport parameter detection method and device and table tennis training auxiliary system | |
| TWI775637B (en) | Golf swing analysis system, golf swing analysis method and information memory medium | |
| TWI775636B (en) | Golf swing analysis system, golf swing analysis method and information memory medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant |